diff options
Diffstat (limited to 'arch/powerpc')
76 files changed, 751 insertions, 535 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 652c25260838..2d0be82c3061 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -125,6 +125,7 @@ config PPC # # Please keep this list sorted alphabetically. # + select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE @@ -175,6 +176,7 @@ config PPC select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT + select HAVE_ARCH_NVRAM_OPS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_CBPF_JIT if !PPC64 @@ -230,7 +232,6 @@ config PPC select NEED_SG_DMA_LENGTH select OF select OF_EARLY_FLATTREE - select OF_RESERVED_MEM select OLD_SIGACTION if PPC32 select OLD_SIGSUSPEND select PCI_DOMAINS if PCI @@ -269,11 +270,6 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y -# All PPC32s use generic nvram driver through ppc_md -config GENERIC_NVRAM - bool - default y if PPC32 - config SCHED_OMIT_FRAME_POINTER bool default y diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 0e8dadd011bc..73d1f3562978 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -218,7 +218,7 @@ quiet_cmd_bootas = BOOTAS $@ cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< quiet_cmd_bootar = BOOTAR $@ - cmd_bootar = $(BOOTAR) $(BOOTARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ + cmd_bootar = $(BOOTAR) $(BOOTARFLAGS) $@.$$$$ $(real-prereqs); mv $@.$$$$ $@ $(obj-libfdt): $(obj)/%.o: $(srctree)/scripts/dtc/libfdt/%.c FORCE $(call if_changed_dep,bootcc) diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index c2b1c4404683..e4bfb1101c0e 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -120,6 +120,5 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 53687c3a70c4..7c6baf6df139 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -1123,7 +1123,6 @@ CONFIG_NLS_ISO8859_15=m CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_DEBUG_INFO=y -# CONFIG_ENABLE_WARN_DEPRECATED is not set CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 46130ef4941c..ec2a55a553c7 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte); + static inline int hstate_get_psize(struct hstate *hstate) { unsigned long shift; @@ -50,4 +54,12 @@ static inline bool gigantic_page_supported(void) /* hugepd entry valid bit */ #define HUGEPD_VAL_BITS (0x8000000000000000UL) +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); #endif diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 49c2c2888274..581f91be9dd4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1292,6 +1292,24 @@ static inline int pud_pfn(pud_t pud) BUILD_BUG(); return 0; } +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); +void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, + pte_t *, pte_t, pte_t); + +/* + * Returns true for a R -> RW upgrade of pte + */ +static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val) +{ + if (!(old_val & _PAGE_READ)) + return false; + + if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE)) + return true; + + return false; +} #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 7d1a3d1543fc..5ab134eeed20 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -127,6 +127,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep pte_t entry, unsigned long address, int psize); +extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte); + static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, unsigned long set) { diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 7f19fbd3ba55..4b73847e9b95 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -783,8 +783,10 @@ extern void __iounmap_at(void *ea, unsigned long size); #define mmio_read16be(addr) readw_be(addr) #define mmio_read32be(addr) readl_be(addr) +#define mmio_read64be(addr) readq_be(addr) #define mmio_write16be(val, addr) writew_be(val, addr) #define mmio_write32be(val, addr) writel_be(val, addr) +#define mmio_write64be(val, addr) writeq_be(val, addr) #define mmio_insb(addr, dst, count) readsb(addr, dst, count) #define mmio_insw(addr, dst, count) readsw(addr, dst, count) #define mmio_insl(addr, dst, count) readsl(addr, dst, count) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 0f98f00da2ea..e6b5bb012ccb 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -99,6 +99,8 @@ struct kvm_nested_guest; struct kvm_vm_stat { ulong remote_tlb_flush; + ulong num_2M_pages; + ulong num_1G_pages; }; struct kvm_vcpu_stat { @@ -377,6 +379,7 @@ struct kvmppc_mmu { void (*slbmte)(struct kvm_vcpu *vcpu, u64 rb, u64 rs); u64 (*slbmfee)(struct kvm_vcpu *vcpu, u64 slb_nr); u64 (*slbmfev)(struct kvm_vcpu *vcpu, u64 slb_nr); + int (*slbfee)(struct kvm_vcpu *vcpu, gva_t eaddr, ulong *ret_slb); void (*slbie)(struct kvm_vcpu *vcpu, u64 slb_nr); void (*slbia)(struct kvm_vcpu *vcpu); /* book3s */ @@ -837,7 +840,7 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index a6c8548ed9fa..ac22b28ae78d 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -36,6 +36,8 @@ #endif #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #include <asm/paca.h> +#include <asm/xive.h> +#include <asm/cpu_has_feature.h> #endif /* @@ -617,6 +619,18 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } #endif /* CONFIG_KVM_XIVE */ +#if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER) +static inline bool xics_on_xive(void) +{ + return xive_enabled() && cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool xics_on_xive(void) +{ + return false; +} +#endif + /* * Prototypes for functions called only from assembler code. * Having prototypes reduces sparse errors. diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index 09a518bb7c03..629a5cdcc865 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -78,9 +78,6 @@ extern int pmac_get_partition(int partition); extern u8 pmac_xpram_read(int xpaddr); extern void pmac_xpram_write(int xpaddr, u8 data); -/* Synchronize NVRAM */ -extern void nvram_sync(void); - /* Initialize NVRAM OS partition */ extern int __init nvram_init_os_partition(struct nvram_os_partition *part); @@ -98,10 +95,4 @@ extern int nvram_write_os_partition(struct nvram_os_partition *part, unsigned int err_type, unsigned int error_log_cnt); -/* Determine NVRAM size */ -extern ssize_t nvram_get_size(void); - -/* Normal access to NVRAM */ -extern unsigned char nvram_read_byte(int i); -extern void nvram_write_byte(unsigned char c, int i); #endif /* _ASM_POWERPC_NVRAM_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 6c0039f3a3a6..fc188e0e9179 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -10,6 +10,7 @@ #include <linux/pci.h> #include <linux/list.h> #include <linux/ioport.h> +#include <linux/numa.h> struct device_node; @@ -264,7 +265,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus); #ifdef CONFIG_NUMA #define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE)) #else -#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1) +#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE) #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 2bc949414669..c5698a523bb1 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -341,6 +341,7 @@ #define PPC_INST_DIVWU 0x7c000396 #define PPC_INST_DIVD 0x7c0003d2 #define PPC_INST_RLWINM 0x54000000 +#define PPC_INST_RLWINM_DOT 0x54000001 #define PPC_INST_RLWIMI 0x50000000 #define PPC_INST_RLDICL 0x78000000 #define PPC_INST_RLDICR 0x78000004 diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index e3a731793ea2..4d6d905e9138 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -28,7 +28,6 @@ #define USER_DS MAKE_MM_SEG(TASK_SIZE - 1) #endif -#define get_ds() (KERNEL_DS) #define get_fs() (current->thread.addr_limit) static inline void set_fs(mm_segment_t fs) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index a3c35e6d6ffb..f44dbc65e38e 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -29,8 +29,8 @@ #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SIGNAL -#define __ARCH_WANT_SYS_TIME -#define __ARCH_WANT_SYS_UTIME +#define __ARCH_WANT_SYS_TIME32 +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_WAITPID #define __ARCH_WANT_SYS_SOCKETCALL #define __ARCH_WANT_SYS_FADVISE64 @@ -45,8 +45,8 @@ #define __ARCH_WANT_OLD_STAT #endif #ifdef CONFIG_PPC64 -#define __ARCH_WANT_COMPAT_SYS_TIME -#define __ARCH_WANT_SYS_UTIME32 +#define __ARCH_WANT_SYS_TIME +#define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_NEWFSTATAT #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 8c876c166ef2..26ca425f4c2c 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char { #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) +#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) +#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 94de465e0920..12aa0c43e775 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -11,8 +11,8 @@ #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 -#define SO_RCVTIMEO 18 -#define SO_SNDTIMEO 19 +#define SO_RCVTIMEO_OLD 18 +#define SO_SNDTIMEO_OLD 19 #define SO_PASSCRED 20 #define SO_PEERCRED 21 diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index e49bd5efcfe6..c66fd3ce6478 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -810,7 +810,6 @@ static int __init process_cpufeatures_node(unsigned long node, int len; f = &dt_cpu_features[i]; - memset(f, 0, sizeof(struct dt_cpu_feature)); f->node = node; @@ -1005,7 +1004,12 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char /* Count and allocate space for cpu features */ of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes, &nr_dt_cpu_features); - dt_cpu_features = __va(memblock_phys_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE)); + dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE); + if (!dt_cpu_features) + panic("%s: Failed to allocate %zu bytes align=0x%lx\n", + __func__, + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, + PAGE_SIZE); cpufeatures_setup_start(isa); diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 38b03a330cd2..244d2462e781 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -7,12 +7,6 @@ * 2 of the License, or (at your option) any later version. * * /dev/nvram driver for PPC64 - * - * This perhaps should live in drivers/char - * - * TODO: Split the /dev/nvram part (that one can use - * drivers/char/generic_nvram.c) from the arch & partition - * parsing code. */ #include <linux/types.h> @@ -714,137 +708,6 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, spin_unlock_irqrestore(&lock, flags); } -static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) -{ - if (ppc_md.nvram_size == NULL) - return -ENODEV; - return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, - ppc_md.nvram_size()); -} - - -static ssize_t dev_nvram_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - ssize_t ret; - char *tmp = NULL; - ssize_t size; - - if (!ppc_md.nvram_size) { - ret = -ENODEV; - goto out; - } - - size = ppc_md.nvram_size(); - if (size < 0) { - ret = size; - goto out; - } - - if (*ppos >= size) { - ret = 0; - goto out; - } - - count = min_t(size_t, count, size - *ppos); - count = min(count, PAGE_SIZE); - - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto out; - } - - ret = ppc_md.nvram_read(tmp, count, ppos); - if (ret <= 0) - goto out; - - if (copy_to_user(buf, tmp, ret)) - ret = -EFAULT; - -out: - kfree(tmp); - return ret; - -} - -static ssize_t dev_nvram_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - ssize_t ret; - char *tmp = NULL; - ssize_t size; - - ret = -ENODEV; - if (!ppc_md.nvram_size) - goto out; - - ret = 0; - size = ppc_md.nvram_size(); - if (*ppos >= size || size < 0) - goto out; - - count = min_t(size_t, count, size - *ppos); - count = min(count, PAGE_SIZE); - - tmp = memdup_user(buf, count); - if (IS_ERR(tmp)) { - ret = PTR_ERR(tmp); - goto out; - } - - ret = ppc_md.nvram_write(tmp, count, ppos); - - kfree(tmp); -out: - return ret; -} - -static long dev_nvram_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - switch(cmd) { -#ifdef CONFIG_PPC_PMAC - case OBSOLETE_PMAC_NVRAM_GET_OFFSET: - printk(KERN_WARNING "nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); - /* fall through */ - case IOC_NVRAM_GET_OFFSET: { - int part, offset; - - if (!machine_is(powermac)) - return -EINVAL; - if (copy_from_user(&part, (void __user*)arg, sizeof(part)) != 0) - return -EFAULT; - if (part < pmac_nvram_OF || part > pmac_nvram_NR) - return -EINVAL; - offset = pmac_get_partition(part); - if (offset < 0) - return offset; - if (copy_to_user((void __user*)arg, &offset, sizeof(offset)) != 0) - return -EFAULT; - return 0; - } -#endif /* CONFIG_PPC_PMAC */ - default: - return -EINVAL; - } -} - -static const struct file_operations nvram_fops = { - .owner = THIS_MODULE, - .llseek = dev_nvram_llseek, - .read = dev_nvram_read, - .write = dev_nvram_write, - .unlocked_ioctl = dev_nvram_ioctl, -}; - -static struct miscdevice nvram_dev = { - NVRAM_MINOR, - "nvram", - &nvram_fops -}; - - #ifdef DEBUG_NVRAM static void __init nvram_print_partitions(char * label) { @@ -992,6 +855,8 @@ loff_t __init nvram_create_partition(const char *name, int sig, long size = 0; int rc; + BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16); + /* Convert sizes from bytes to blocks */ req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN; min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN; @@ -1192,22 +1057,3 @@ int __init nvram_scan_partitions(void) kfree(header); return err; } - -static int __init nvram_init(void) -{ - int rc; - - BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16); - - if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0) - return -ENODEV; - - rc = misc_register(&nvram_dev); - if (rc != 0) { - printk(KERN_ERR "nvram_init: failed to register device\n"); - return rc; - } - - return rc; -} -device_initcall(nvram_init); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 913bfca09c4f..e7382abee868 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/memblock.h> #include <linux/sched/task.h> +#include <linux/numa.h> #include <asm/lppaca.h> #include <asm/paca.h> @@ -27,7 +28,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, unsigned long limit, int cpu) { - unsigned long pa; + void *ptr; int nid; /* @@ -36,23 +37,21 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, * which will put its paca in the right place. */ if (cpu == boot_cpuid) { - nid = -1; + nid = NUMA_NO_NODE; memblock_set_bottom_up(true); } else { nid = early_cpu_to_node(cpu); } - pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE); - if (!pa) { - pa = memblock_alloc_base(size, align, limit); - if (!pa) - panic("cannot allocate paca data"); - } + ptr = memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + limit, nid); + if (!ptr) + panic("cannot allocate paca data"); if (cpu == boot_cpuid) memblock_set_bottom_up(false); - return __va(pa); + return ptr; } #ifdef CONFIG_PPC_PSERIES @@ -118,7 +117,6 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) } s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu); - memset(s, 0, sizeof(*s)); s->persistent = cpu_to_be32(SLB_NUM_BOLTED); s->buffer_length = cpu_to_be32(sizeof(*s)); @@ -198,7 +196,11 @@ void __init allocate_paca_ptrs(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; - paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, SMP_CACHE_BYTES)); + paca_ptrs = memblock_alloc_raw(paca_ptrs_size, SMP_CACHE_BYTES); + if (!paca_ptrs) + panic("Failed to allocate %d bytes for paca pointers\n", + paca_ptrs_size); + memset(paca_ptrs, 0x88, paca_ptrs_size); } @@ -222,7 +224,6 @@ void __init allocate_paca(int cpu) paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES, limit, cpu); paca_ptrs[cpu] = paca; - memset(paca, 0, sizeof(struct paca_struct)); initialise_paca(paca, cpu); #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 60f20c2e559a..ff4b7539cbdf 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -32,6 +32,7 @@ #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/vgaarb.h> +#include <linux/numa.h> #include <asm/processor.h> #include <asm/io.h> @@ -126,7 +127,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) int nid = of_node_to_nid(dev); if (nid < 0 || !node_online(nid)) - nid = -1; + nid = NUMA_NO_NODE; PHB_SET_NODE(phb, nid); } diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index d3f04f2d8249..0417fda13636 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -205,6 +205,9 @@ pci_create_OF_bus_map(void) of_prop = memblock_alloc(sizeof(struct property) + 256, SMP_CACHE_BYTES); + if (!of_prop) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct property) + 256); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 4181ec715f88..4221527b082f 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -126,7 +126,10 @@ static void __init move_device_tree(void) if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || !memblock_is_memory(start + size - 1) || overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { - p = __va(memblock_phys_alloc(size, PAGE_SIZE)); + p = memblock_alloc_raw(size, PAGE_SIZE); + if (!p) + panic("Failed to allocate %lu bytes to move device tree\n", + size); memcpy(p, initial_boot_params, size); initial_boot_params = p; DBG("Moved device tree to 0x%px\n", p); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index de35bd8f047f..fbc676160adf 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1187,7 +1187,11 @@ void __init rtas_initialize(void) ibm_suspend_me_token = rtas_token("ibm,suspend-me"); } #endif - rtas_rmo_buf = memblock_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); + rtas_rmo_buf = memblock_phys_alloc_range(RTAS_RMOBUF_MAX, PAGE_SIZE, + 0, rtas_region); + if (!rtas_rmo_buf) + panic("ERROR: RTAS: Failed to allocate %lx bytes below %pa\n", + PAGE_SIZE, &rtas_region); #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index e7534f306c8e..2e5dfb6e0823 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -459,8 +459,11 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - cpu_to_phys_id = __va(memblock_phys_alloc(nr_cpu_ids * sizeof(u32), __alignof__(u32))); - memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32)); + cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32), + __alignof__(u32)); + if (!cpu_to_phys_id) + panic("%s: Failed to allocate %zu bytes align=0x%zx\n", + __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32)); for_each_node_by_type(dn, "cpu") { const __be32 *intserv; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1f0b7629c1a6..4a65e08a6042 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -17,6 +17,7 @@ #include <linux/console.h> #include <linux/memblock.h> #include <linux/export.h> +#include <linux/nvram.h> #include <asm/io.h> #include <asm/prom.h> @@ -147,41 +148,6 @@ static int __init ppc_setup_l3cr(char *str) } __setup("l3cr=", ppc_setup_l3cr); -#ifdef CONFIG_GENERIC_NVRAM - -/* Generic nvram hooks used by drivers/char/gen_nvram.c */ -unsigned char nvram_read_byte(int addr) -{ - if (ppc_md.nvram_read_val) - return ppc_md.nvram_read_val(addr); - return 0xff; -} -EXPORT_SYMBOL(nvram_read_byte); - -void nvram_write_byte(unsigned char val, int addr) -{ - if (ppc_md.nvram_write_val) - ppc_md.nvram_write_val(addr, val); -} -EXPORT_SYMBOL(nvram_write_byte); - -ssize_t nvram_get_size(void) -{ - if (ppc_md.nvram_size) - return ppc_md.nvram_size(); - return -1; -} -EXPORT_SYMBOL(nvram_get_size); - -void nvram_sync(void) -{ - if (ppc_md.nvram_sync) - ppc_md.nvram_sync(); -} -EXPORT_SYMBOL(nvram_sync); - -#endif /* CONFIG_NVRAM */ - static int __init ppc_init(void) { /* clear the progress line */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index daa361fc6a24..ba404dd9ce1d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -902,8 +902,13 @@ static void __ref init_fallback_flush(void) * hardware prefetch runoff. We don't have a recipe for load patterns to * reliably avoid the prefetcher. */ - l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit)); - memset(l1d_flush_fallback_area, 0, l1d_size * 2); + l1d_flush_fallback_area = memblock_alloc_try_nid(l1d_size * 2, + l1d_size, MEMBLOCK_LOW_LIMIT, + limit, NUMA_NO_NODE); + if (!l1d_flush_fallback_area) + panic("%s: Failed to allocate %llu bytes align=0x%llx max_addr=%pa\n", + __func__, l1d_size * 2, l1d_size, &limit); + for_each_possible_cpu(cpu) { struct paca_struct *paca = paca_ptrs[cpu]; diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index db3bbb8744af..b18abb0c3dae 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -20,7 +20,9 @@ 10 common unlink sys_unlink 11 nospu execve sys_execve compat_sys_execve 12 common chdir sys_chdir -13 common time sys_time compat_sys_time +13 32 time sys_time32 +13 64 time sys_time +13 spu time sys_time 14 common mknod sys_mknod 15 common chmod sys_chmod 16 common lchown sys_lchown @@ -36,14 +38,17 @@ 22 spu umount sys_ni_syscall 23 common setuid sys_setuid 24 common getuid sys_getuid -25 common stime sys_stime compat_sys_stime +25 32 stime sys_stime32 +25 64 stime sys_stime +25 spu stime sys_stime 26 nospu ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm 28 32 oldfstat sys_fstat sys_ni_syscall 28 64 oldfstat sys_ni_syscall 28 spu oldfstat sys_ni_syscall 29 nospu pause sys_pause -30 nospu utime sys_utime compat_sys_utime +30 32 utime sys_utime32 +30 64 utime sys_utime 31 common stty sys_ni_syscall 32 common gtty sys_ni_syscall 33 common access sys_access @@ -157,7 +162,9 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall -124 common adjtimex sys_adjtimex compat_sys_adjtimex +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex +124 spu adjtimex sys_adjtimex 125 common mprotect sys_mprotect 126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 126 64 sigprocmask sys_ni_syscall @@ -198,8 +205,12 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +161 spu sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep +162 spu nanosleep sys_nanosleep 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -213,7 +224,8 @@ 173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +176 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 common pread64 sys_pread64 compat_sys_pread64 @@ -260,7 +272,9 @@ 218 common removexattr sys_removexattr 219 common lremovexattr sys_lremovexattr 220 common fremovexattr sys_fremovexattr -221 common futex sys_futex compat_sys_futex +221 32 futex sys_futex_time32 +221 64 futex sys_futex +221 spu futex sys_futex 222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity # 224 unused @@ -268,7 +282,9 @@ 226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64 227 common io_setup sys_io_setup compat_sys_io_setup 228 common io_destroy sys_io_destroy -229 common io_getevents sys_io_getevents compat_sys_io_getevents +229 32 io_getevents sys_io_getevents_time32 +229 64 io_getevents sys_io_getevents +229 spu io_getevents sys_io_getevents 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address @@ -280,19 +296,33 @@ 238 common epoll_wait sys_epoll_wait 239 common remap_file_pages sys_remap_file_pages 240 common timer_create sys_timer_create compat_sys_timer_create -241 common timer_settime sys_timer_settime compat_sys_timer_settime -242 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +241 32 timer_settime sys_timer_settime32 +241 64 timer_settime sys_timer_settime +241 spu timer_settime sys_timer_settime +242 32 timer_gettime sys_timer_gettime32 +242 64 timer_gettime sys_timer_gettime +242 spu timer_gettime sys_timer_gettime 243 common timer_getoverrun sys_timer_getoverrun 244 common timer_delete sys_timer_delete -245 common clock_settime sys_clock_settime compat_sys_clock_settime -246 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -247 common clock_getres sys_clock_getres compat_sys_clock_getres -248 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +245 32 clock_settime sys_clock_settime32 +245 64 clock_settime sys_clock_settime +245 spu clock_settime sys_clock_settime +246 32 clock_gettime sys_clock_gettime32 +246 64 clock_gettime sys_clock_gettime +246 spu clock_gettime sys_clock_gettime +247 32 clock_getres sys_clock_getres_time32 +247 64 clock_getres sys_clock_getres +247 spu clock_getres sys_clock_getres +248 32 clock_nanosleep sys_clock_nanosleep_time32 +248 64 clock_nanosleep sys_clock_nanosleep +248 spu clock_nanosleep sys_clock_nanosleep 249 32 swapcontext ppc_swapcontext ppc32_swapcontext 249 64 swapcontext ppc64_swapcontext 249 spu swapcontext sys_ni_syscall 250 common tgkill sys_tgkill -251 common utimes sys_utimes compat_sys_utimes +251 32 utimes sys_utimes_time32 +251 64 utimes sys_utimes +251 spu utimes sys_utimes 252 common statfs64 sys_statfs64 compat_sys_statfs64 253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 254 32 fadvise64_64 ppc_fadvise64_64 @@ -308,8 +338,10 @@ 261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 262 nospu mq_open sys_mq_open compat_sys_mq_open 263 nospu mq_unlink sys_mq_unlink -264 nospu mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -265 nospu mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +264 32 mq_timedsend sys_mq_timedsend_time32 +264 64 mq_timedsend sys_mq_timedsend +265 32 mq_timedreceive sys_mq_timedreceive_time32 +265 64 mq_timedreceive sys_mq_timedreceive 266 nospu mq_notify sys_mq_notify compat_sys_mq_notify 267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 268 nospu kexec_load sys_kexec_load compat_sys_kexec_load @@ -324,8 +356,10 @@ 277 nospu inotify_rm_watch sys_inotify_rm_watch 278 nospu spu_run sys_spu_run 279 nospu spu_create sys_spu_create -280 nospu pselect6 sys_pselect6 compat_sys_pselect6 -281 nospu ppoll sys_ppoll compat_sys_ppoll +280 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +280 64 pselect6 sys_pselect6 +281 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +281 64 ppoll sys_ppoll 282 common unshare sys_unshare 283 common splice sys_splice 284 common tee sys_tee @@ -334,7 +368,9 @@ 287 common mkdirat sys_mkdirat 288 common mknodat sys_mknodat 289 common fchownat sys_fchownat -290 common futimesat sys_futimesat compat_sys_futimesat +290 32 futimesat sys_futimesat_time32 +290 64 futimesat sys_futimesat +290 spu utimesat sys_futimesat 291 32 fstatat64 sys_fstatat64 291 64 newfstatat sys_newfstatat 291 spu newfstatat sys_newfstatat @@ -350,15 +386,21 @@ 301 common move_pages sys_move_pages compat_sys_move_pages 302 common getcpu sys_getcpu 303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -304 common utimensat sys_utimensat compat_sys_utimensat +304 32 utimensat sys_utimensat_time32 +304 64 utimensat sys_utimensat +304 spu utimensat sys_utimensat 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd 308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 309 nospu fallocate sys_fallocate compat_sys_fallocate 310 nospu subpage_prot sys_subpage_prot -311 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -312 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +311 32 timerfd_settime sys_timerfd_settime32 +311 64 timerfd_settime sys_timerfd_settime +311 spu timerfd_settime sys_timerfd_settime +312 32 timerfd_gettime sys_timerfd_gettime32 +312 64 timerfd_gettime sys_timerfd_gettime +312 spu timerfd_gettime sys_timerfd_gettime 313 common signalfd4 sys_signalfd4 compat_sys_signalfd4 314 common eventfd2 sys_eventfd2 315 common epoll_create1 sys_epoll_create1 @@ -389,11 +431,15 @@ 340 common getsockopt sys_getsockopt compat_sys_getsockopt 341 common sendmsg sys_sendmsg compat_sys_sendmsg 342 common recvmsg sys_recvmsg compat_sys_recvmsg -343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +343 64 recvmmsg sys_recvmmsg +343 spu recvmmsg sys_recvmmsg 344 common accept4 sys_accept4 345 common name_to_handle_at sys_name_to_handle_at 346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -347 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +347 32 clock_adjtime sys_clock_adjtime32 +347 64 clock_adjtime sys_clock_adjtime +347 spu clock_adjtime sys_clock_adjtime 348 common syncfs sys_syncfs 349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 350 common setns sys_setns @@ -414,6 +460,7 @@ 363 spu switch_endian sys_ni_syscall 364 common userfaultfd sys_userfaultfd 365 common membarrier sys_membarrier +# 366-377 originally left for IPC, now unused 378 nospu mlock2 sys_mlock2 379 nospu copy_file_range sys_copy_file_range 380 common preadv2 sys_preadv2 compat_sys_preadv2 @@ -424,4 +471,37 @@ 385 nospu pkey_free sys_pkey_free 386 nospu pkey_mprotect sys_pkey_mprotect 387 nospu rseq sys_rseq -388 nospu io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +388 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +388 64 io_pgetevents sys_io_pgetevents +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 7725a9714736..a31b6234fcd7 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -798,7 +798,6 @@ static int __init vdso_init(void) BUG_ON(vdso32_pagelist == NULL); for (i = 0; i < vdso32_pages; i++) { struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); get_page(pg); vdso32_pagelist[i] = pg; } @@ -812,7 +811,6 @@ static int __init vdso_init(void) BUG_ON(vdso64_pagelist == NULL); for (i = 0; i < vdso64_pages; i++) { struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); get_page(pg); vdso64_pagelist[i] = pg; } diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 9a7dadbe1f17..10c5579d20ce 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -39,6 +39,7 @@ #include "book3s.h" #include "trace.h" +#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU /* #define EXIT_DEBUG */ @@ -71,6 +72,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "pthru_all", VCPU_STAT(pthru_all) }, { "pthru_host", VCPU_STAT(pthru_host) }, { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, + { "largepages_2M", VM_STAT(num_2M_pages) }, + { "largepages_1G", VM_STAT(num_1G_pages) }, { NULL } }; @@ -642,7 +645,7 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, r = -ENXIO; break; } - if (xive_enabled()) + if (xics_on_xive()) *val = get_reg_val(id, kvmppc_xive_get_icp(vcpu)); else *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu)); @@ -715,7 +718,7 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, r = -ENXIO; break; } - if (xive_enabled()) + if (xics_on_xive()) r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val)); else r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val)); @@ -991,7 +994,7 @@ int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall) int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { - if (xive_enabled()) + if (xics_on_xive()) return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level, line_status); else @@ -1044,7 +1047,7 @@ static int kvmppc_book3s_init(void) #ifdef CONFIG_KVM_XICS #ifdef CONFIG_KVM_XIVE - if (xive_enabled()) { + if (xics_on_xive()) { kvmppc_xive_init_module(); kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS); } else @@ -1057,7 +1060,7 @@ static int kvmppc_book3s_init(void) static void kvmppc_book3s_exit(void) { #ifdef CONFIG_KVM_XICS - if (xive_enabled()) + if (xics_on_xive()) kvmppc_xive_exit_module(); #endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 612169988a3d..6f789f674048 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -425,6 +425,7 @@ void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu) mmu->slbmte = NULL; mmu->slbmfee = NULL; mmu->slbmfev = NULL; + mmu->slbfee = NULL; mmu->slbie = NULL; mmu->slbia = NULL; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index c92dd25bed23..d4b967f0e8d4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -435,6 +435,19 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) kvmppc_mmu_map_segment(vcpu, esid << SID_SHIFT); } +static int kvmppc_mmu_book3s_64_slbfee(struct kvm_vcpu *vcpu, gva_t eaddr, + ulong *ret_slb) +{ + struct kvmppc_slb *slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr); + + if (slbe) { + *ret_slb = slbe->origv; + return 0; + } + *ret_slb = 0; + return -ENOENT; +} + static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr) { struct kvmppc_slb *slbe; @@ -670,6 +683,7 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu) mmu->slbmte = kvmppc_mmu_book3s_64_slbmte; mmu->slbmfee = kvmppc_mmu_book3s_64_slbmfee; mmu->slbmfev = kvmppc_mmu_book3s_64_slbmfev; + mmu->slbfee = kvmppc_mmu_book3s_64_slbfee; mmu->slbie = kvmppc_mmu_book3s_64_slbie; mmu->slbia = kvmppc_mmu_book3s_64_slbia; mmu->xlate = kvmppc_mmu_book3s_64_xlate; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index bd2dcfbf00cd..be7bc070eae5 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -442,6 +442,24 @@ int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, u32 last_inst; /* + * Fast path - check if the guest physical address corresponds to a + * device on the FAST_MMIO_BUS, if so we can avoid loading the + * instruction all together, then we can just handle it and return. + */ + if (is_store) { + int idx, ret; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, (gpa_t) gpa, 0, + NULL); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (!ret) { + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); + return RESUME_GUEST; + } + } + + /* * If we fail, we just return to the guest and try executing it again. */ if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) != diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 1b821c6efdef..f55ef071883f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -403,8 +403,13 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, if (!memslot) return; } - if (shift) + if (shift) { /* 1GB or 2MB page */ page_size = 1ul << shift; + if (shift == PMD_SHIFT) + kvm->stat.num_2M_pages--; + else if (shift == PUD_SHIFT) + kvm->stat.num_1G_pages--; + } gpa &= ~(page_size - 1); hpa = old & PTE_RPN_MASK; @@ -878,6 +883,14 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, put_page(page); } + /* Increment number of large pages if we (successfully) inserted one */ + if (!ret) { + if (level == 1) + kvm->stat.num_2M_pages++; + else if (level == 2) + kvm->stat.num_1G_pages++; + } + return ret; } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 532ab79734c7..f02b04973710 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -133,7 +133,6 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, continue; kref_put(&stit->kref, kvm_spapr_tce_liobn_put); - return; } } } @@ -338,14 +337,15 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, } } + kvm_get_kvm(kvm); if (!ret) ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, stt, O_RDWR | O_CLOEXEC); - if (ret >= 0) { + if (ret >= 0) list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); - kvm_get_kvm(kvm); - } + else + kvm_put_kvm(kvm); mutex_unlock(&kvm->lock); diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 8c7e933e942e..6ef7c5f00a49 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -47,6 +47,7 @@ #define OP_31_XOP_SLBMFEV 851 #define OP_31_XOP_EIOIO 854 #define OP_31_XOP_SLBMFEE 915 +#define OP_31_XOP_SLBFEE 979 #define OP_31_XOP_TBEGIN 654 #define OP_31_XOP_TABORT 910 @@ -416,6 +417,23 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.mmu.slbia(vcpu); break; + case OP_31_XOP_SLBFEE: + if (!(inst & 1) || !vcpu->arch.mmu.slbfee) { + return EMULATE_FAIL; + } else { + ulong b, t; + ulong cr = kvmppc_get_cr(vcpu) & ~CR0_MASK; + + b = kvmppc_get_gpr(vcpu, rb); + if (!vcpu->arch.mmu.slbfee(vcpu, b, &t)) + cr |= 2 << CR0_SHIFT; + kvmppc_set_gpr(vcpu, rt, t); + /* copy XER[SO] bit to CR0[SO] */ + cr |= (vcpu->arch.regs.xer & 0x80000000) >> + (31 - CR0_SHIFT); + kvmppc_set_cr(vcpu, cr); + } + break; case OP_31_XOP_SLBMFEE: if (!vcpu->arch.mmu.slbmfee) { emulated = EMULATE_FAIL; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index a3d5318f5d1e..06964350b97a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -922,7 +922,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) case H_IPOLL: case H_XIRR_X: if (kvmppc_xics_enabled(vcpu)) { - if (xive_enabled()) { + if (xics_on_xive()) { ret = H_NOT_AVAILABLE; return RESUME_GUEST; } @@ -937,6 +937,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) ret = kvmppc_h_set_xdabr(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5)); break; +#ifdef CONFIG_SPAPR_TCE_IOMMU case H_GET_TCE: ret = kvmppc_h_get_tce(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5)); @@ -966,6 +967,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) if (ret == H_TOO_HARD) return RESUME_HOST; break; +#endif case H_RANDOM: if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4])) ret = H_HARDWARE; @@ -1445,7 +1447,7 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) case BOOK3S_INTERRUPT_HV_RM_HARD: vcpu->arch.trap = 0; r = RESUME_GUEST; - if (!xive_enabled()) + if (!xics_on_xive()) kvmppc_xics_rm_complete(vcpu, 0); break; default: @@ -3648,11 +3650,12 @@ static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc, static void grow_halt_poll_ns(struct kvmppc_vcore *vc) { - /* 10us base */ - if (vc->halt_poll_ns == 0 && halt_poll_ns_grow) - vc->halt_poll_ns = 10000; - else - vc->halt_poll_ns *= halt_poll_ns_grow; + if (!halt_poll_ns_grow) + return; + + vc->halt_poll_ns *= halt_poll_ns_grow; + if (vc->halt_poll_ns < halt_poll_ns_grow_start) + vc->halt_poll_ns = halt_poll_ns_grow_start; } static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) @@ -3666,7 +3669,7 @@ static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) #ifdef CONFIG_KVM_XICS static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu) { - if (!xive_enabled()) + if (!xics_on_xive()) return false; return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr < vcpu->arch.xive_saved_state.cppr; @@ -4226,7 +4229,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); srcu_read_unlock(&kvm->srcu, srcu_idx); } else if (r == RESUME_PASSTHROUGH) { - if (WARN_ON(xive_enabled())) + if (WARN_ON(xics_on_xive())) r = H_SUCCESS; else r = kvmppc_xics_rm_complete(vcpu, 0); @@ -4750,7 +4753,7 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) * If xive is enabled, we route 0x500 interrupts directly * to the guest. */ - if (xive_enabled()) + if (xics_on_xive()) lpcr |= LPCR_LPES; } @@ -4986,7 +4989,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) if (i == pimap->n_mapped) pimap->n_mapped++; - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc); else kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq); @@ -5027,7 +5030,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) return -ENODEV; } - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc); else kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq); @@ -5359,13 +5362,11 @@ static int kvm_init_subcore_bitmap(void) continue; sibling_subcore_state = - kmalloc_node(sizeof(struct sibling_subcore_state), + kzalloc_node(sizeof(struct sibling_subcore_state), GFP_KERNEL, node); if (!sibling_subcore_state) return -ENOMEM; - memset(sibling_subcore_state, 0, - sizeof(struct sibling_subcore_state)); for (j = 0; j < threads_per_core; j++) { int cpu = first_cpu + j; @@ -5406,7 +5407,7 @@ static int kvmppc_book3s_init_hv(void) * indirectly, via OPAL. */ #ifdef CONFIG_SMP - if (!xive_enabled() && !kvmhv_on_pseries() && + if (!xics_on_xive() && !kvmhv_on_pseries() && !local_paca->kvm_hstate.xics_phys) { struct device_node *np; diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index a71e2fc00a4e..b0cf22477e87 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -257,7 +257,7 @@ void kvmhv_rm_send_ipi(int cpu) } /* We should never reach this */ - if (WARN_ON_ONCE(xive_enabled())) + if (WARN_ON_ONCE(xics_on_xive())) return; /* Else poke the target with an IPI */ @@ -577,7 +577,7 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_xirr(vcpu); if (unlikely(!__xive_vm_h_xirr)) @@ -592,7 +592,7 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu) if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; vcpu->arch.regs.gpr[5] = get_tb(); - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_xirr(vcpu); if (unlikely(!__xive_vm_h_xirr)) @@ -606,7 +606,7 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_ipoll(vcpu, server); if (unlikely(!__xive_vm_h_ipoll)) @@ -621,7 +621,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_ipi(vcpu, server, mfrr); if (unlikely(!__xive_vm_h_ipi)) @@ -635,7 +635,7 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_cppr(vcpu, cppr); if (unlikely(!__xive_vm_h_cppr)) @@ -649,7 +649,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_eoi(vcpu, xirr); if (unlikely(!__xive_vm_h_eoi)) diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index b3f5786b20dc..3b9662a4207e 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -144,6 +144,13 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, return; } + if (xive_enabled() && kvmhv_on_pseries()) { + /* No XICS access or hypercalls available, too hard */ + this_icp->rm_action |= XICS_RM_KICK_VCPU; + this_icp->rm_kick_target = vcpu; + return; + } + /* * Check if the core is loaded, * if not, find an available host core to post to wake the VCPU, diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 25043b50cb30..3a5e719ef032 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2272,8 +2272,13 @@ hcall_real_table: .long DOTSYM(kvmppc_h_clear_mod) - hcall_real_table .long DOTSYM(kvmppc_h_clear_ref) - hcall_real_table .long DOTSYM(kvmppc_h_protect) - hcall_real_table +#ifdef CONFIG_SPAPR_TCE_IOMMU .long DOTSYM(kvmppc_h_get_tce) - hcall_real_table .long DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table +#else + .long 0 /* 0x1c */ + .long 0 /* 0x20 */ +#endif .long 0 /* 0x24 - H_SET_SPRG0 */ .long DOTSYM(kvmppc_h_set_dabr) - hcall_real_table .long 0 /* 0x2c */ @@ -2351,8 +2356,13 @@ hcall_real_table: .long 0 /* 0x12c */ .long 0 /* 0x130 */ .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table +#ifdef CONFIG_SPAPR_TCE_IOMMU .long DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table .long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table +#else + .long 0 /* 0x138 */ + .long 0 /* 0x13c */ +#endif .long 0 /* 0x140 */ .long 0 /* 0x144 */ .long 0 /* 0x148 */ diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 2d3b2b1cc272..4e178c4c1ea5 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -33,7 +33,7 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) server = be32_to_cpu(args->args[1]); priority = be32_to_cpu(args->args[2]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority); else rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority); @@ -56,7 +56,7 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); server = priority = 0; - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority); else rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority); @@ -83,7 +83,7 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_int_off(vcpu->kvm, irq); else rc = kvmppc_xics_int_off(vcpu->kvm, irq); @@ -105,7 +105,7 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_int_on(vcpu->kvm, irq); else rc = kvmppc_xics_int_on(vcpu->kvm, irq); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b90a7d154180..8885377ec3e0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -748,7 +748,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu); break; case KVMPPC_IRQ_XICS: - if (xive_enabled()) + if (xics_on_xive()) kvmppc_xive_cleanup_vcpu(vcpu); else kvmppc_xics_free_icp(vcpu); @@ -1931,7 +1931,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EPERM; dev = kvm_device_from_filp(f.file); if (dev) { - if (xive_enabled()) + if (xics_on_xive()) r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]); else r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]); @@ -2189,10 +2189,12 @@ static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp) KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | KVM_PPC_CPU_CHAR_BR_HINT_HONOURED | KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF | - KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS | + KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | - KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR | + KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; } return 0; } @@ -2251,12 +2253,16 @@ static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) if (have_fw_feat(fw_features, "enabled", "fw-count-cache-disabled")) cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + if (have_fw_feat(fw_features, "enabled", + "fw-count-cache-flush-bcctr2,0,0")) + cp->character |= KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 | KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED | KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 | KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 | KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | - KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS | + KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; if (have_fw_feat(fw_features, "enabled", "speculation-policy-favor-security")) @@ -2267,9 +2273,13 @@ static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) if (!have_fw_feat(fw_features, "disabled", "needs-spec-barrier-for-bound-checks")) cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + if (have_fw_feat(fw_features, "enabled", + "needs-count-cache-flush-on-context-switch")) + cp->behaviour |= KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | - KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR | + KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; of_node_put(fw_features); } diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index dedf88a76f58..ce180870bd52 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -15,6 +15,9 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) p = kzalloc(size, mask); else { p = memblock_alloc(size, SMP_CACHE_BYTES); + if (!p) + panic("%s: Failed to allocate %zu bytes\n", __func__, + size); } return p; } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 4aa0797000f7..0a4f939a8161 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -882,8 +882,12 @@ static void __init htab_initialize(void) } #endif /* CONFIG_PPC_CELL */ - table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, - limit); + table = memblock_phys_alloc_range(htab_size_bytes, + htab_size_bytes, + 0, limit); + if (!table) + panic("ERROR: Failed to allocate %pa bytes below %pa\n", + &htab_size_bytes, &limit); DBG("Hash table allocated at %lx, size: %lx\n", table, htab_size_bytes); @@ -908,9 +912,12 @@ static void __init htab_initialize(void) #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled()) { linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT; - linear_map_hash_slots = __va(memblock_alloc_base( - linear_map_hash_count, 1, ppc64_rma_size)); - memset(linear_map_hash_slots, 0, linear_map_hash_count); + linear_map_hash_slots = memblock_alloc_try_nid( + linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT, + ppc64_rma_size, NUMA_NO_NODE); + if (!linear_map_hash_slots) + panic("%s: Failed to allocate %lu bytes max_addr=%pa\n", + __func__, linear_map_hash_count, &ppc64_rma_size); } #endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index f6b09edc5e6e..b0d9209d9a86 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -120,3 +120,28 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + unsigned long pte_val; + /* + * Clear the _PAGE_PRESENT so that no hardware parallel update is + * possible. Also keep the pte_present true so that we don't take + * wrong fault. + */ + pte_val = pte_update(vma->vm_mm, addr, ptep, + _PAGE_PRESENT, _PAGE_INVALID, 1); + + return __pte(pte_val); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + + if (radix_enabled()) + return radix__huge_ptep_modify_prot_commit(vma, addr, ptep, + old_pte, pte); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 97c7a39ebc00..cab06331c0c0 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -91,3 +91,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return vm_unmapped_area(&info); } + +void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + struct mm_struct *mm = vma->vm_mm; + + /* + * To avoid NMMU hang while relaxing access we need to flush the tlb before + * we set the new value. + */ + if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + (atomic_read(&mm->context.copros) > 0)) + radix__flush_hugetlb_page(vma, addr); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index a712a650a8b6..e7a9c4f6bfca 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -21,6 +21,7 @@ #include <linux/sizes.h> #include <asm/mmu_context.h> #include <asm/pte-walk.h> +#include <linux/mm_inline.h> static DEFINE_MUTEX(mem_list_mutex); @@ -34,8 +35,18 @@ struct mm_iommu_table_group_mem_t { atomic64_t mapped; unsigned int pageshift; u64 ua; /* userspace address */ - u64 entries; /* number of entries in hpas[] */ - u64 *hpas; /* vmalloc'ed */ + u64 entries; /* number of entries in hpas/hpages[] */ + /* + * in mm_iommu_get we temporarily use this to store + * struct page address. + * + * We need to convert ua to hpa in real mode. Make it + * simpler by storing physical address. + */ + union { + struct page **hpages; /* vmalloc'ed */ + phys_addr_t *hpas; + }; #define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1) u64 dev_hpa; /* Device memory base address */ }; @@ -80,64 +91,13 @@ bool mm_iommu_preregistered(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mm_iommu_preregistered); -/* - * Taken from alloc_migrate_target with changes to remove CMA allocations - */ -struct page *new_iommu_non_cma_page(struct page *page, unsigned long private) -{ - gfp_t gfp_mask = GFP_USER; - struct page *new_page; - - if (PageCompound(page)) - return NULL; - - if (PageHighMem(page)) - gfp_mask |= __GFP_HIGHMEM; - - /* - * We don't want the allocation to force an OOM if possibe - */ - new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN); - return new_page; -} - -static int mm_iommu_move_page_from_cma(struct page *page) -{ - int ret = 0; - LIST_HEAD(cma_migrate_pages); - - /* Ignore huge pages for now */ - if (PageCompound(page)) - return -EBUSY; - - lru_add_drain(); - ret = isolate_lru_page(page); - if (ret) - return ret; - - list_add(&page->lru, &cma_migrate_pages); - put_page(page); /* Drop the gup reference */ - - ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page, - NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE); - if (ret) { - if (!list_empty(&cma_migrate_pages)) - putback_movable_pages(&cma_migrate_pages); - } - - return 0; -} - static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, - unsigned long entries, unsigned long dev_hpa, - struct mm_iommu_table_group_mem_t **pmem) + unsigned long entries, unsigned long dev_hpa, + struct mm_iommu_table_group_mem_t **pmem) { struct mm_iommu_table_group_mem_t *mem; - long i, j, ret = 0, locked_entries = 0; + long i, ret, locked_entries = 0; unsigned int pageshift; - unsigned long flags; - unsigned long cur_ua; - struct page *page = NULL; mutex_lock(&mem_list_mutex); @@ -187,62 +147,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, goto unlock_exit; } + down_read(&mm->mmap_sem); + ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL); + up_read(&mm->mmap_sem); + if (ret != entries) { + /* free the reference taken */ + for (i = 0; i < ret; i++) + put_page(mem->hpages[i]); + + vfree(mem->hpas); + kfree(mem); + ret = -EFAULT; + goto unlock_exit; + } + + pageshift = PAGE_SHIFT; for (i = 0; i < entries; ++i) { - cur_ua = ua + (i << PAGE_SHIFT); - if (1 != get_user_pages_fast(cur_ua, - 1/* pages */, 1/* iswrite */, &page)) { - ret = -EFAULT; - for (j = 0; j < i; ++j) - put_page(pfn_to_page(mem->hpas[j] >> - PAGE_SHIFT)); - vfree(mem->hpas); - kfree(mem); - goto unlock_exit; - } + struct page *page = mem->hpages[i]; + /* - * If we get a page from the CMA zone, since we are going to - * be pinning these entries, we might as well move them out - * of the CMA zone if possible. NOTE: faulting in + migration - * can be expensive. Batching can be considered later + * Allow to use larger than 64k IOMMU pages. Only do that + * if we are backed by hugetlb. */ - if (is_migrate_cma_page(page)) { - if (mm_iommu_move_page_from_cma(page)) - goto populate; - if (1 != get_user_pages_fast(cur_ua, - 1/* pages */, 1/* iswrite */, - &page)) { - ret = -EFAULT; - for (j = 0; j < i; ++j) - put_page(pfn_to_page(mem->hpas[j] >> - PAGE_SHIFT)); - vfree(mem->hpas); - kfree(mem); - goto unlock_exit; - } - } -populate: - pageshift = PAGE_SHIFT; - if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) { - pte_t *pte; + if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) { struct page *head = compound_head(page); - unsigned int compshift = compound_order(head); - unsigned int pteshift; - - local_irq_save(flags); /* disables as well */ - pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift); - - /* Double check it is still the same pinned page */ - if (pte && pte_page(*pte) == head && - pteshift == compshift + PAGE_SHIFT) - pageshift = max_t(unsigned int, pteshift, - PAGE_SHIFT); - local_irq_restore(flags); + + pageshift = compound_order(head) + PAGE_SHIFT; } mem->pageshift = min(mem->pageshift, pageshift); + /* + * We don't need struct page reference any more, switch + * to physical address. + */ mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } good_exit: + ret = 0; atomic64_set(&mem->mapped, 1); mem->used = 1; mem->ua = ua; diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 22d71a58167f..1945c5f19f5e 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -461,10 +461,19 @@ void __init mmu_context_init(void) * Allocate the maps used by context management */ context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); + if (!context_map) + panic("%s: Failed to allocate %zu bytes\n", __func__, + CTX_MAP_SIZE); context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), SMP_CACHE_BYTES); + if (!context_mm) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(void *) * (LAST_CONTEXT + 1)); #ifdef CONFIG_SMP stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); + if (!stale_map[boot_cpuid]) + panic("%s: Failed to allocate %zu bytes\n", __func__, + CTX_MAP_SIZE); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b5d1c45c1475..f976676004ad 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -84,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void) alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); /* cpumask_of_node() will now work */ - dbg("Node to cpumask map for %d nodes\n", nr_node_ids); + dbg("Node to cpumask map for %u nodes\n", nr_node_ids); } static int __init fake_numa_create_new_node(unsigned long end_pfn, @@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid, */ static int associativity_to_nid(const __be32 *associativity) { - int nid = -1; + int nid = NUMA_NO_NODE; if (min_common_depth == -1) goto out; @@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity) /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= MAX_NUMNODES) - nid = -1; + nid = NUMA_NO_NODE; if (nid > 0 && of_read_number(associativity, 1) >= distance_ref_points_depth) { @@ -244,7 +244,7 @@ out: */ static int of_node_to_nid_single(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; const __be32 *tmp; tmp = of_get_associativity(device); @@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device) /* Walk the device tree upwards, looking for an associativity id */ int of_node_to_nid(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; of_node_get(device); while (device) { @@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb) */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = -1; + int nid = NUMA_NO_NODE; struct device_node *cpu; /* @@ -788,6 +788,10 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) int tnid; nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) + panic("Cannot allocate %zu bytes for node %d data\n", + nd_size, nid); + nd = __va(nd_pa); /* report and initialize */ @@ -930,7 +934,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) { struct drmem_lmb *lmb; unsigned long lmb_size; - int nid = -1; + int nid = NUMA_NO_NODE; lmb_size = drmem_lmb_size(); @@ -960,7 +964,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) static int hot_add_node_scn_to_nid(unsigned long scn_addr) { struct device_node *memory; - int nid = -1; + int nid = NUMA_NO_NODE; for_each_node_by_type(memory, "memory") { unsigned long start, size; diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/pgtable-book3e.c index e0ccf36714b2..1032ef7aaf62 100644 --- a/arch/powerpc/mm/pgtable-book3e.c +++ b/arch/powerpc/mm/pgtable-book3e.c @@ -57,12 +57,16 @@ void vmemmap_remove_mapping(unsigned long start, static __ref void *early_alloc_pgtable(unsigned long size) { - void *pt; + void *ptr; - pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); - memset(pt, 0, size); + ptr = memblock_alloc_try_nid(size, size, MEMBLOCK_LOW_LIMIT, + __pa(MAX_DMA_ADDRESS), NUMA_NO_NODE); - return pt; + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%lx\n", + __func__, size, size, __pa(MAX_DMA_ADDRESS)); + + return ptr; } /* diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index ecd31569a120..a4341aba0af4 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -195,11 +195,11 @@ void __init mmu_partition_table_init(void) unsigned long ptcr; BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large."); - partition_tb = __va(memblock_alloc_base(patb_size, patb_size, - MEMBLOCK_ALLOC_ANYWHERE)); - /* Initialize the Partition Table with no entries */ - memset((void *)partition_tb, 0, patb_size); + partition_tb = memblock_alloc(patb_size, patb_size); + if (!partition_tb) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, patb_size, patb_size); /* * update partition table control register, @@ -401,6 +401,31 @@ void arch_report_meminfo(struct seq_file *m) } #endif /* CONFIG_PROC_FS */ +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + unsigned long pte_val; + + /* + * Clear the _PAGE_PRESENT so that no hardware parallel update is + * possible. Also keep the pte_present true so that we don't take + * wrong fault. + */ + pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0); + + return __pte(pte_val); + +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + if (radix_enabled()) + return radix__ptep_modify_prot_commit(vma, addr, + ptep, old_pte, pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); +} + /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 931156069a81..154472a28c77 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -51,26 +51,22 @@ static int native_register_process_table(unsigned long base, unsigned long pg_sz static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) { - unsigned long pa = 0; - void *pt; + phys_addr_t min_addr = MEMBLOCK_LOW_LIMIT; + phys_addr_t max_addr = MEMBLOCK_ALLOC_ANYWHERE; + void *ptr; - if (region_start || region_end) /* has region hint */ - pa = memblock_alloc_range(size, size, region_start, region_end, - MEMBLOCK_NONE); - else if (nid != -1) /* has node hint */ - pa = memblock_alloc_base_nid(size, size, - MEMBLOCK_ALLOC_ANYWHERE, - nid, MEMBLOCK_NONE); + if (region_start) + min_addr = region_start; + if (region_end) + max_addr = region_end; - if (!pa) - pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE); + ptr = memblock_alloc_try_nid(size, size, min_addr, max_addr, nid); - BUG_ON(!pa); + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa max_addr=%pa\n", + __func__, size, size, nid, &min_addr, &max_addr); - pt = __va(pa); - memset(pt, 0, size); - - return pt; + return ptr; } static int early_map_kernel_page(unsigned long ea, unsigned long pa, @@ -1063,3 +1059,21 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, } /* See ptesync comment in radix__set_pte_at */ } + +void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + struct mm_struct *mm = vma->vm_mm; + + /* + * To avoid NMMU hang while relaxing access we need to flush the tlb before + * we set the new value. We need to do this only for radix, because hash + * translation does flush when updating the linux pte. + */ + if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + (atomic_read(&mm->context.copros) > 0)) + radix__flush_tlb_page(vma, addr); + + set_pte_at(mm, addr, ptep, pte); +} diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 2d5b0d50fb31..f29d2f118b44 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -339,8 +339,10 @@ void __init MMU_init_hw(void) * Find some memory for the hash table. */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); - Hash = __va(memblock_phys_alloc(Hash_size, Hash_size)); - memset(Hash, 0, Hash_size); + Hash = memblock_alloc(Hash_size, Hash_size); + if (!Hash) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, Hash_size, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size); diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index c2d5192ed64f..549e9490ff2a 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -165,6 +165,10 @@ #define PPC_RLWINM(d, a, i, mb, me) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \ ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RLWINM_DOT(d, a, i, mb, me) EMIT(PPC_INST_RLWINM_DOT | \ + ___PPC_RA(d) | ___PPC_RS(a) | \ + __PPC_SH(i) | __PPC_MB(mb) | \ + __PPC_ME(me)) #define PPC_RLWIMI(d, a, i, mb, me) EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \ ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(mb) | __PPC_ME(me)) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 7ce57657d3b8..4194d3cfb60c 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -768,36 +768,58 @@ emit_clear: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_X: true_cond = COND_GT; goto cond_branch; case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_X: true_cond = COND_LT; goto cond_branch; case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_X: true_cond = COND_GE; goto cond_branch; case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_X: true_cond = COND_LE; goto cond_branch; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_X: true_cond = COND_EQ; goto cond_branch; case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_X: true_cond = COND_NE; goto cond_branch; case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_X: true_cond = COND_NE; /* Fall through */ @@ -809,18 +831,44 @@ cond_branch: case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_X: /* unsigned comparison */ - PPC_CMPLD(dst_reg, src_reg); + if (BPF_CLASS(code) == BPF_JMP32) + PPC_CMPLW(dst_reg, src_reg); + else + PPC_CMPLD(dst_reg, src_reg); break; case BPF_JMP | BPF_JSGT | BPF_X: case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_X: /* signed comparison */ - PPC_CMPD(dst_reg, src_reg); + if (BPF_CLASS(code) == BPF_JMP32) + PPC_CMPW(dst_reg, src_reg); + else + PPC_CMPD(dst_reg, src_reg); break; case BPF_JMP | BPF_JSET | BPF_X: - PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg); + case BPF_JMP32 | BPF_JSET | BPF_X: + if (BPF_CLASS(code) == BPF_JMP) { + PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, + src_reg); + } else { + int tmp_reg = b2p[TMP_REG_1]; + + PPC_AND(tmp_reg, dst_reg, src_reg); + PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0, + 31); + } break; case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JEQ | BPF_K: @@ -828,43 +876,87 @@ cond_branch: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_K: + { + bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32; + /* * Need sign-extended load, so only positive * values can be used as imm in cmpldi */ - if (imm >= 0 && imm < 32768) - PPC_CMPLDI(dst_reg, imm); - else { + if (imm >= 0 && imm < 32768) { + if (is_jmp32) + PPC_CMPLWI(dst_reg, imm); + else + PPC_CMPLDI(dst_reg, imm); + } else { /* sign-extending load */ PPC_LI32(b2p[TMP_REG_1], imm); /* ... but unsigned comparison */ - PPC_CMPLD(dst_reg, b2p[TMP_REG_1]); + if (is_jmp32) + PPC_CMPLW(dst_reg, + b2p[TMP_REG_1]); + else + PPC_CMPLD(dst_reg, + b2p[TMP_REG_1]); } break; + } case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_K: + { + bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32; + /* * signed comparison, so any 16-bit value * can be used in cmpdi */ - if (imm >= -32768 && imm < 32768) - PPC_CMPDI(dst_reg, imm); - else { + if (imm >= -32768 && imm < 32768) { + if (is_jmp32) + PPC_CMPWI(dst_reg, imm); + else + PPC_CMPDI(dst_reg, imm); + } else { PPC_LI32(b2p[TMP_REG_1], imm); - PPC_CMPD(dst_reg, b2p[TMP_REG_1]); + if (is_jmp32) + PPC_CMPW(dst_reg, + b2p[TMP_REG_1]); + else + PPC_CMPD(dst_reg, + b2p[TMP_REG_1]); } break; + } case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_K: /* andi does not sign-extend the immediate */ if (imm >= 0 && imm < 32768) /* PPC_ANDI is _only/always_ dot-form */ PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm); else { - PPC_LI32(b2p[TMP_REG_1], imm); - PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, - b2p[TMP_REG_1]); + int tmp_reg = b2p[TMP_REG_1]; + + PPC_LI32(tmp_reg, imm); + if (BPF_CLASS(code) == BPF_JMP) { + PPC_AND_DOT(tmp_reg, dst_reg, + tmp_reg); + } else { + PPC_AND(tmp_reg, dst_reg, + tmp_reg); + PPC_RLWINM_DOT(tmp_reg, tmp_reg, + 0, 0, 31); + } } break; } @@ -1093,6 +1185,7 @@ skip_codegen_passes: bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE)); if (!fp->is_func || extra_pass) { + bpf_prog_fill_jited_linfo(fp, addrs); out_addrs: kfree(addrs); kfree(jit_data); diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 72238eedc360..d2b8e6061933 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1306,15 +1306,6 @@ static int h_24x7_event_init(struct perf_event *event) return -EINVAL; } - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest) - return -EINVAL; - /* no branch sampling */ if (has_branch_stack(event)) return -EOPNOTSUPP; @@ -1577,6 +1568,7 @@ static struct pmu h_24x7_pmu = { .start_txn = h_24x7_event_start_txn, .commit_txn = h_24x7_event_commit_txn, .cancel_txn = h_24x7_event_cancel_txn, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; static int hv_24x7_init(void) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 43fabb3cae0f..735e77b09cdb 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -232,15 +232,6 @@ static int h_gpci_event_init(struct perf_event *event) return -EINVAL; } - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest) - return -EINVAL; - /* no branch sampling */ if (has_branch_stack(event)) return -EOPNOTSUPP; @@ -285,6 +276,7 @@ static struct pmu h_gpci_pmu = { .start = h_gpci_event_start, .stop = h_gpci_event_stop, .read = h_gpci_event_update, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; static int hv_gpci_init(void) diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index f292a3f284f1..b1c37cc3fa98 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -473,15 +473,6 @@ static int nest_imc_event_init(struct perf_event *event) if (event->hw.sample_period) return -EINVAL; - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest) - return -EINVAL; - if (event->cpu < 0) return -EINVAL; @@ -748,15 +739,6 @@ static int core_imc_event_init(struct perf_event *event) if (event->hw.sample_period) return -EINVAL; - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest) - return -EINVAL; - if (event->cpu < 0) return -EINVAL; @@ -1069,6 +1051,7 @@ static int update_pmu_ops(struct imc_pmu *pmu) pmu->pmu.stop = imc_event_stop; pmu->pmu.read = imc_event_update; pmu->pmu.attr_groups = pmu->attr_groups; + pmu->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group; switch (pmu->domain) { diff --git a/arch/powerpc/platforms/chrp/Makefile b/arch/powerpc/platforms/chrp/Makefile index 4b3bfadc70fa..dc3465cc8bc6 100644 --- a/arch/powerpc/platforms/chrp/Makefile +++ b/arch/powerpc/platforms/chrp/Makefile @@ -1,3 +1,3 @@ obj-y += setup.o time.o pegasos_eth.o pci.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_NVRAM) += nvram.o +obj-$(CONFIG_NVRAM:m=y) += nvram.o diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c index 791b86398e1d..37ac20ccbb19 100644 --- a/arch/powerpc/platforms/chrp/nvram.c +++ b/arch/powerpc/platforms/chrp/nvram.c @@ -24,7 +24,7 @@ static unsigned int nvram_size; static unsigned char nvram_buf[4]; static DEFINE_SPINLOCK(nvram_lock); -static unsigned char chrp_nvram_read(int addr) +static unsigned char chrp_nvram_read_val(int addr) { unsigned int done; unsigned long flags; @@ -46,7 +46,7 @@ static unsigned char chrp_nvram_read(int addr) return ret; } -static void chrp_nvram_write(int addr, unsigned char val) +static void chrp_nvram_write_val(int addr, unsigned char val) { unsigned int done; unsigned long flags; @@ -64,6 +64,11 @@ static void chrp_nvram_write(int addr, unsigned char val) spin_unlock_irqrestore(&nvram_lock, flags); } +static ssize_t chrp_nvram_size(void) +{ + return nvram_size; +} + void __init chrp_nvram_init(void) { struct device_node *nvram; @@ -85,8 +90,9 @@ void __init chrp_nvram_init(void) printk(KERN_INFO "CHRP nvram contains %u bytes\n", nvram_size); of_node_put(nvram); - ppc_md.nvram_read_val = chrp_nvram_read; - ppc_md.nvram_write_val = chrp_nvram_write; + ppc_md.nvram_read_val = chrp_nvram_read_val; + ppc_md.nvram_write_val = chrp_nvram_write_val; + ppc_md.nvram_size = chrp_nvram_size; return; } diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index e66644e0fb40..fcf6f2342ef4 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -538,8 +538,7 @@ static void __init chrp_init_IRQ(void) /* see if there is a keyboard in the device tree with a parent of type "adb" */ for_each_node_by_name(kbd, "keyboard") - if (kbd->parent && kbd->parent->type - && strcmp(kbd->parent->type, "adb") == 0) + if (of_node_is_type(kbd->parent, "adb")) break; of_node_put(kbd); if (kbd) @@ -550,7 +549,7 @@ static void __init chrp_init_IRQ(void) static void __init chrp_init2(void) { -#ifdef CONFIG_NVRAM +#if IS_ENABLED(CONFIG_NVRAM) chrp_nvram_init(); #endif diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index bbeb6a1b0393..044c6089462c 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -208,7 +208,12 @@ static int __init iob_init(struct device_node *dn) pr_debug(" -> %s\n", __func__); /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */ - iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); + iob_l2_base = memblock_alloc_try_nid_raw(1UL << 21, 1UL << 21, + MEMBLOCK_LOW_LIMIT, 0x80000000, + NUMA_NO_NODE); + if (!iob_l2_base) + panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%x\n", + __func__, 1UL << 21, 1UL << 21, 0x80000000); pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base); @@ -269,4 +274,3 @@ void __init iommu_init_early_pasemi(void) pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi; set_pci_dma_ops(&dma_iommu_ops); } - diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index 923bfb340433..20ebf35d7913 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -15,7 +15,5 @@ obj-$(CONFIG_PMAC_BACKLIGHT) += backlight.o # need this to be a bool. Cheat here and pretend CONFIG_NVRAM=m is really # CONFIG_NVRAM=y obj-$(CONFIG_NVRAM:m=y) += nvram.o -# ppc64 pmac doesn't define CONFIG_NVRAM but needs nvram stuff -obj-$(CONFIG_PPC64) += nvram.o obj-$(CONFIG_PPC32) += bootx_init.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index ae54d7fe68f3..86989c5779c2 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -147,6 +147,11 @@ static ssize_t core99_nvram_size(void) static volatile unsigned char __iomem *nvram_addr; static int nvram_mult; +static ssize_t ppc32_nvram_size(void) +{ + return NVRAM_SIZE; +} + static unsigned char direct_nvram_read_byte(int addr) { return in_8(&nvram_data[(addr & (NVRAM_SIZE - 1)) * nvram_mult]); @@ -514,6 +519,9 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) return -EINVAL; } nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES); + if (!nvram_image) + panic("%s: Failed to allocate %u bytes\n", __func__, + NVRAM_SIZE); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ @@ -590,21 +598,25 @@ int __init pmac_nvram_init(void) nvram_mult = 1; ppc_md.nvram_read_val = direct_nvram_read_byte; ppc_md.nvram_write_val = direct_nvram_write_byte; + ppc_md.nvram_size = ppc32_nvram_size; } else if (nvram_naddrs == 1) { nvram_data = ioremap(r1.start, s1); nvram_mult = (s1 + NVRAM_SIZE - 1) / NVRAM_SIZE; ppc_md.nvram_read_val = direct_nvram_read_byte; ppc_md.nvram_write_val = direct_nvram_write_byte; + ppc_md.nvram_size = ppc32_nvram_size; } else if (nvram_naddrs == 2) { nvram_addr = ioremap(r1.start, s1); nvram_data = ioremap(r2.start, s2); ppc_md.nvram_read_val = indirect_nvram_read_byte; ppc_md.nvram_write_val = indirect_nvram_write_byte; + ppc_md.nvram_size = ppc32_nvram_size; } else if (nvram_naddrs == 0 && sys_ctrler == SYS_CTRLER_PMU) { #ifdef CONFIG_ADB_PMU nvram_naddrs = -1; ppc_md.nvram_read_val = pmu_nvram_read_byte; ppc_md.nvram_write_val = pmu_nvram_write_byte; + ppc_md.nvram_size = ppc32_nvram_size; #endif /* CONFIG_ADB_PMU */ } else { printk(KERN_ERR "Incompatible type of NVRAM\n"); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 2e8221e20ee8..b7efcf336589 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -316,8 +316,7 @@ static void __init pmac_setup_arch(void) find_via_pmu(); smu_init(); -#if defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) || \ - defined(CONFIG_PPC64) +#if IS_ENABLED(CONFIG_NVRAM) pmac_nvram_init(); #endif #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index f157e3d071f2..b36ddee17c87 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -68,7 +68,7 @@ long __init pmac_time_init(void) { s32 delta = 0; -#ifdef CONFIG_NVRAM +#if defined(CONFIG_NVRAM) && defined(CONFIG_PPC32) int dst; delta = ((s32)pmac_xpram_read(PMAC_XPRAM_MACHINE_LOC + 0x9)) << 16; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 84d038ed3882..248a38ad25c7 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/numa.h> #include <asm/machdep.h> #include <asm/debugfs.h> @@ -223,7 +224,7 @@ static int memtrace_online(void) ent = &memtrace_array[i]; /* We have onlined this chunk previously */ - if (ent->nid == -1) + if (ent->nid == NUMA_NO_NODE) continue; /* Remove from io mappings */ @@ -257,7 +258,7 @@ static int memtrace_online(void) */ debugfs_remove_recursive(ent->dir); pr_info("Added trace memory back to node %d\n", ent->nid); - ent->size = ent->start = ent->nid = -1; + ent->size = ent->start = ent->nid = NUMA_NO_NODE; } if (ret) return ret; diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 2ca3ba95f8aa..2b0eca104f86 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -170,8 +170,10 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, /* * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range =__va(memblock_phys_alloc(size, __alignof__(u64))); - memset(mc_recoverable_range, 0, size); + mc_recoverable_range = memblock_alloc(size, __alignof__(u64)); + if (!mc_recoverable_range) + panic("%s: Failed to allocate %u bytes align=0x%lx\n", + __func__, size, __alignof__(u64)); for (i = 0; i < mc_recoverable_range_len; i++) { mc_recoverable_range[i].start_addr = diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index f1ce39f64329..3ead4c237ed0 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1593,6 +1593,8 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pnv_pci_ioda2_setup_dma_pe(phb, pe); #ifdef CONFIG_IOMMU_API + iommu_register_group(&pe->table_group, + pe->phb->hose->global_number, pe->pe_number); pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL); #endif } @@ -3655,6 +3657,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, pr_debug(" PHB-ID : 0x%016llx\n", phb_id); phb = memblock_alloc(sizeof(*phb), SMP_CACHE_BYTES); + if (!phb) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*phb)); /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); @@ -3701,6 +3706,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE; phb->diag_data = memblock_alloc(phb->diag_data_size, SMP_CACHE_BYTES); + if (!phb->diag_data) + panic("%s: Failed to allocate %u bytes\n", __func__, + phb->diag_data_size); /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(hose, np, !hose->global_number); @@ -3760,6 +3768,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, pemap_off = size; size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe); aux = memblock_alloc(size, SMP_CACHE_BYTES); + if (!aux) + panic("%s: Failed to allocate %lu bytes\n", __func__, size); phb->ioda.pe_alloc = aux; phb->ioda.m64_segmap = aux + m64map_off; phb->ioda.m32_segmap = aux + m32map_off; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 45fb70b4bfa7..ef9448a907c6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1147,6 +1147,8 @@ static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, return 0; pe = &phb->ioda.pe_array[pdn->pe_number]; + if (!pe->table_group.group) + return 0; iommu_add_device(&pe->table_group, dev); return 0; case BUS_NOTIFY_DEL_DEVICE: diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 658bfab3350b..4ce5458eb0f8 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -127,6 +127,9 @@ static void __init prealloc(struct ps3_prealloc *p) return; p->address = memblock_alloc(p->size, p->align); + if (!p->address) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, p->size, p->align); printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size, p->address); diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 5b4a56131904..84e8ec4011ba 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -261,8 +261,7 @@ static char *ibmebus_chomp(const char *in, size_t count) return out; } -static ssize_t ibmebus_store_probe(struct bus_type *bus, - const char *buf, size_t count) +static ssize_t probe_store(struct bus_type *bus, const char *buf, size_t count) { struct device_node *dn = NULL; struct device *dev; @@ -298,10 +297,9 @@ out: return rc; return count; } -static BUS_ATTR(probe, 0200, NULL, ibmebus_store_probe); +static BUS_ATTR_WO(probe); -static ssize_t ibmebus_store_remove(struct bus_type *bus, - const char *buf, size_t count) +static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; char *path; @@ -325,7 +323,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus, return -ENODEV; } } -static BUS_ATTR(remove, 0200, NULL, ibmebus_store_remove); +static BUS_ATTR_WO(remove); static struct attribute *ibmbus_bus_attrs[] = { &bus_attr_probe.attr, diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 69cedc1b3b8a..1136a38ff039 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -7,8 +7,6 @@ * 2 of the License, or (at your option) any later version. * * /dev/nvram driver for PPC64 - * - * This perhaps should live in drivers/char */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 41f62ca27c63..e4f0dfd4ae33 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -130,8 +130,13 @@ static void __init fwnmi_init(void) * It will be used in real mode mce handler, hence it needs to be * below RMA. */ - mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus, - RTAS_ERROR_LOG_MAX, ppc64_rma_size)); + mce_data_buf = memblock_alloc_try_nid_raw(RTAS_ERROR_LOG_MAX * nr_cpus, + RTAS_ERROR_LOG_MAX, MEMBLOCK_LOW_LIMIT, + ppc64_rma_size, NUMA_NO_NODE); + if (!mce_data_buf) + panic("Failed to allocate %d bytes below %pa for MCE buffer\n", + RTAS_ERROR_LOG_MAX * nr_cpus, &ppc64_rma_size); + for_each_possible_cpu(i) { paca_ptrs[i]->mce_data_buf = mce_data_buf + (RTAS_ERROR_LOG_MAX * i); @@ -140,8 +145,13 @@ static void __init fwnmi_init(void) #ifdef CONFIG_PPC_BOOK3S_64 /* Allocate per cpu slb area to save old slb contents during MCE */ size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus; - slb_ptr = __va(memblock_alloc_base(size, sizeof(struct slb_entry), - ppc64_rma_size)); + slb_ptr = memblock_alloc_try_nid_raw(size, sizeof(struct slb_entry), + MEMBLOCK_LOW_LIMIT, ppc64_rma_size, + NUMA_NO_NODE); + if (!slb_ptr) + panic("Failed to allocate %zu bytes below %pa for slb area\n", + size, &ppc64_rma_size); + for_each_possible_cpu(i) paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i); #endif diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 809797dbe169..2a751795ec1e 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -251,8 +251,11 @@ static void allocate_dart(void) * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we * will blow up an entire large page anyway in the kernel mapping. */ - dart_tablebase = __va(memblock_alloc_base(1UL<<24, - 1UL<<24, 0x80000000L)); + dart_tablebase = memblock_alloc_try_nid_raw(SZ_16M, SZ_16M, + MEMBLOCK_LOW_LIMIT, SZ_2G, + NUMA_NO_NODE); + if (!dart_tablebase) + panic("Failed to allocate 16MB below 2GB for DART table\n"); /* There is no point scanning the DART space for leaks*/ kmemleak_no_scan((void *)dart_tablebase); @@ -262,6 +265,9 @@ static void allocate_dart(void) * prefetching into invalid pages and corrupting data */ tmp = memblock_phys_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); + if (!tmp) + panic("DART: table allocation failed\n"); + dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) & DARTMAP_RPNMASK); diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index d45450f6666a..51a679a1c403 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -129,6 +129,9 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, bmp->bitmap = kzalloc(size, GFP_KERNEL); else { bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES); + if (!bmp->bitmap) + panic("%s: Failed to allocate %u bytes\n", __func__, + size); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } |