diff options
Diffstat (limited to 'arch/powerpc')
| -rw-r--r-- | arch/powerpc/configs/cell_defconfig | 40 | ||||
| -rw-r--r-- | arch/powerpc/kernel/cputable.c | 16 | ||||
| -rw-r--r-- | arch/powerpc/kernel/kprobes.c | 14 | ||||
| -rw-r--r-- | arch/powerpc/kernel/module_64.c | 16 | ||||
| -rw-r--r-- | arch/powerpc/kernel/prom.c | 70 | ||||
| -rw-r--r-- | arch/powerpc/kernel/prom_init.c | 112 | ||||
| -rw-r--r-- | arch/powerpc/kernel/ptrace.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/kernel/setup-common.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/kernel/setup_64.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/kernel/sysfs.c | 18 | ||||
| -rw-r--r-- | arch/powerpc/kernel/systbl.S | 13 | ||||
| -rw-r--r-- | arch/powerpc/mm/hugetlbpage.c | 295 | ||||
| -rw-r--r-- | arch/powerpc/mm/init_64.c | 7 | ||||
| -rw-r--r-- | arch/powerpc/mm/numa.c | 32 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/Kconfig | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/setup.c | 78 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spu_base.c | 101 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spu_callbacks.c | 13 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powermac/pci.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh_event.c | 8 |
20 files changed, 674 insertions, 185 deletions
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index fe22e54ab2b..dbe421dc3c1 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -9,6 +9,7 @@ CONFIG_PPC_MERGE=y CONFIG_MMU=y CONFIG_GENERIC_HARDIRQS=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_PPC=y CONFIG_EARLY_PRINTK=y @@ -55,6 +56,7 @@ CONFIG_SYSCTL=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y # CONFIG_CPUSETS is not set +# CONFIG_RELAY is not set CONFIG_INITRAMFS_SOURCE="" CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_EMBEDDED is not set @@ -69,10 +71,6 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -84,7 +82,6 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_KMOD=y @@ -93,6 +90,7 @@ CONFIG_STOP_MACHINE=y # # Block layer # +# CONFIG_BLK_DEV_IO_TRACE is not set # # IO Schedulers @@ -126,6 +124,7 @@ CONFIG_RTAS_FLASH=y CONFIG_MMIO_NVRAM=y CONFIG_CELL_IIC=y # CONFIG_PPC_MPC106 is not set +# CONFIG_PPC_970_NAP is not set # CONFIG_CPU_FREQ is not set # CONFIG_WANT_EARLY_SERIAL is not set @@ -167,7 +166,6 @@ CONFIG_HAVE_MEMORY_PRESENT=y CONFIG_SPARSEMEM_EXTREME=y # CONFIG_MEMORY_HOTPLUG is not set CONFIG_SPLIT_PTLOCK_CPUS=4 -CONFIG_MIGRATION=y # CONFIG_PPC_64K_PAGES is not set CONFIG_SCHED_SMT=y CONFIG_PROC_DEVICETREE=y @@ -184,7 +182,6 @@ CONFIG_GENERIC_ISA_DMA=y # CONFIG_PPC_INDIRECT_PCI is not set CONFIG_PCI=y CONFIG_PCI_DOMAINS=y -CONFIG_PCI_LEGACY_PROC=y # CONFIG_PCI_DEBUG is not set # @@ -226,6 +223,7 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set CONFIG_INET_TUNNEL=y CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y @@ -242,6 +240,7 @@ CONFIG_IPV6=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_INET6_XFRM_TUNNEL=m CONFIG_INET6_TUNNEL=m CONFIG_IPV6_TUNNEL=m CONFIG_NETFILTER=y @@ -632,6 +631,7 @@ CONFIG_SERIAL_NONSTANDARD=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -717,7 +717,6 @@ CONFIG_I2C_ALGOBIT=y # CONFIG_I2C_PARPORT_LIGHT is not set # CONFIG_I2C_PROSAVAGE is not set # CONFIG_I2C_SAVAGE4 is not set -# CONFIG_SCx200_ACB is not set # CONFIG_I2C_SIS5595 is not set # CONFIG_I2C_SIS630 is not set # CONFIG_I2C_SIS96X is not set @@ -736,9 +735,7 @@ CONFIG_I2C_ALGOBIT=y # CONFIG_SENSORS_PCF8574 is not set # CONFIG_SENSORS_PCA9539 is not set # CONFIG_SENSORS_PCF8591 is not set -# CONFIG_SENSORS_RTC8564 is not set # CONFIG_SENSORS_MAX6875 is not set -# CONFIG_RTC_X1205_I2C is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set # CONFIG_I2C_DEBUG_BUS is not set @@ -766,10 +763,6 @@ CONFIG_I2C_ALGOBIT=y # # -# Multimedia Capabilities Port drivers -# - -# # Multimedia devices # # CONFIG_VIDEO_DEV is not set @@ -818,6 +811,19 @@ CONFIG_USB_ARCH_HAS_EHCI=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# +# LED drivers +# + +# +# LED Triggers +# + +# # InfiniBand support # CONFIG_INFINIBAND=y @@ -834,6 +840,11 @@ CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y # # +# Real Time Clock +# +# CONFIG_RTC_CLASS is not set + +# # File systems # CONFIG_EXT2_FS=y @@ -889,7 +900,6 @@ CONFIG_TMPFS=y CONFIG_HUGETLBFS=y CONFIG_HUGETLB_PAGE=y CONFIG_RAMFS=y -# CONFIG_RELAYFS_FS is not set # CONFIG_CONFIGFS_FS is not set # diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 39e348a3ade..3f7182db9ed 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -57,6 +57,8 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) #define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) @@ -263,6 +265,20 @@ struct cpu_spec cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .platform = "power5+", }, + { /* Power6 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003e0000, + .cpu_name = "POWER6", + .cpu_features = CPU_FTRS_POWER6, + .cpu_user_features = COMMON_USER_POWER6, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_power4, + .oprofile_cpu_type = "ppc64/power6", + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power6", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 856ef1a832b..f78866367b7 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -90,15 +90,15 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) { - kprobe_opcode_t insn = *p->ainsn.insn; - regs->msr |= MSR_SE; - /* single step inline if it is a trap variant */ - if (is_trap(insn)) - regs->nip = (unsigned long)p->addr; - else - regs->nip = (unsigned long)p->ainsn.insn; + /* + * On powerpc we should single step on the original + * instruction even if the probed insn is a trap + * variant as values in regs could play a part in + * if the trap is taken or not + */ + regs->nip = (unsigned long)p->ainsn.insn; } static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 928b8581fcb..ba34001fca8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -191,11 +191,19 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, (void *)hdr + sechdrs[sechdrs[i].sh_link].sh_offset); } - if (!me->arch.stubs_section || !me->arch.toc_section) { - printk("%s: doesn't contain .toc or .stubs.\n", me->name); + + if (!me->arch.stubs_section) { + printk("%s: doesn't contain .stubs.\n", me->name); return -ENOEXEC; } + /* If we don't have a .toc, just use .stubs. We need to set r2 + to some reasonable value in case the module calls out to + other functions via a stub, or if a function pointer escapes + the module by some means. */ + if (!me->arch.toc_section) + me->arch.toc_section = me->arch.stubs_section; + /* Override the stubs size */ sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs); return 0; @@ -342,7 +350,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_PPC64_TOC16: - /* Subtact TOC pointer */ + /* Subtract TOC pointer */ value -= my_r2(sechdrs, me); if (value + 0x8000 > 0xffff) { printk("%s: bad TOC16 relocation (%lu)\n", @@ -355,7 +363,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_PPC64_TOC16_DS: - /* Subtact TOC pointer */ + /* Subtract TOC pointer */ value -= my_r2(sechdrs, me); if ((value & 3) != 0 || value + 0x8000 > 0xffff) { printk("%s: bad TOC16_DS relocation (%lu)\n", diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 1cb69e8fb0b..9a07f97f071 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -885,6 +885,74 @@ void __init unflatten_device_tree(void) DBG(" <- unflatten_device_tree()\n"); } +/* + * ibm,pa-features is a per-cpu property that contains a string of + * attribute descriptors, each of which has a 2 byte header plus up + * to 254 bytes worth of processor attribute bits. First header + * byte specifies the number of bytes following the header. + * Second header byte is an "attribute-specifier" type, of which + * zero is the only currently-defined value. + * Implementation: Pass in the byte and bit offset for the feature + * that we are interested in. The function will return -1 if the + * pa-features property is missing, or a 1/0 to indicate if the feature + * is supported/not supported. Note that the bit numbers are + * big-endian to match the definition in PAPR. + */ +static struct ibm_pa_feature { + unsigned long cpu_features; /* CPU_FTR_xxx bit */ + unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned char pabyte; /* byte number in ibm,pa-features */ + unsigned char pabit; /* bit number (big-endian) */ + unsigned char invert; /* if 1, pa bit set => clear feature */ +} ibm_pa_features[] __initdata = { + {0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, + {0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, + {CPU_FTR_SLB, 0, 0, 2, 0}, + {CPU_FTR_CTRL, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 1, 1, 1}, + {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, +}; + +static void __init check_cpu_pa_features(unsigned long node) +{ + unsigned char *pa_ftrs; + unsigned long len, tablelen, i, bit; + + pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen); + if (pa_ftrs == NULL) + return; + + /* find descriptor with type == 0 */ + for (;;) { + if (tablelen < 3) + return; + len = 2 + pa_ftrs[0]; + if (tablelen < len) + return; /* descriptor 0 not found */ + if (pa_ftrs[1] == 0) + break; + tablelen -= len; + pa_ftrs += len; + } + + /* loop over bits we know about */ + for (i = 0; i < ARRAY_SIZE(ibm_pa_features); ++i) { + struct ibm_pa_feature *fp = &ibm_pa_features[i]; + + if (fp->pabyte >= pa_ftrs[0]) + continue; + bit = (pa_ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1; + if (bit ^ fp->invert) { + cur_cpu_spec->cpu_features |= fp->cpu_features; + cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + } else { + cur_cpu_spec->cpu_features &= ~fp->cpu_features; + cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + } + } +} + static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) @@ -969,6 +1037,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node, } #endif /* CONFIG_ALTIVEC */ + check_cpu_pa_features(node); + #ifdef CONFIG_PPC_PSERIES if (nthreads > 1) cur_cpu_spec->cpu_features |= CPU_FTR_SMT; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 7e4d54821a0..078fb553354 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -636,10 +636,96 @@ static void __init early_cmdline_parse(void) #ifdef CONFIG_PPC_PSERIES /* - * To tell the firmware what our capabilities are, we have to pass - * it a fake 32-bit ELF header containing a couple of PT_NOTE sections - * that contain structures that contain the actual values. + * There are two methods for telling firmware what our capabilities are. + * Newer machines have an "ibm,client-architecture-support" method on the + * root node. For older machines, we have to call the "process-elf-header" + * method in the /packages/elf-loader node, passing it a fake 32-bit + * ELF header containing a couple of PT_NOTE sections that contain + * structures that contain various information. */ + +/* + * New method - extensible architecture description vector. + * + * Because the description vector contains a mix of byte and word + * values, we declare it as an unsigned char array, and use this + * macro to put word values in. + */ +#define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \ + ((x) >> 8) & 0xff, (x) & 0xff + +/* Option vector bits - generic bits in byte 1 */ +#define OV_IGNORE 0x80 /* ignore this vector */ +#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/ + +/* Option vector 1: processor architectures supported */ +#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */ +#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */ +#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */ +#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */ +#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */ +#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */ + +/* Option vector 2: Open Firmware options supported */ +#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ + +/* Option vector 3: processor options supported */ +#define OV3_FP 0x80 /* floating point */ +#define OV3_VMX 0x40 /* VMX/Altivec */ + +/* Option vector 5: PAPR/OF options supported */ +#define OV5_LPAR 0x80 /* logical partitioning supported */ +#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */ +/* ibm,dynamic-reconfiguration-memory property supported */ +#define OV5_DRCONF_MEMORY 0x20 +#define OV5_LARGE_PAGES 0x10 /* large pages supported */ + +/* + * The architecture vector has an array of PVR mask/value pairs, + * followed by # option vectors - 1, followed by the option vectors. + */ +static unsigned char ibm_architecture_vec[] = { + W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */ + W(0xffff0000), W(0x003e0000), /* POWER6 */ + W(0xfffffffe), W(0x0f000001), /* all 2.04-compliant and earlier */ + 5 - 1, /* 5 option vectors */ + + /* option vector 1: processor architectures supported */ + 3 - 1, /* length */ + 0, /* don't ignore, don't halt */ + OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 | + OV1_PPC_2_04 | OV1_PPC_2_05, + + /* option vector 2: Open Firmware options supported */ + 34 - 1, /* length */ + OV2_REAL_MODE, + 0, 0, + W(0xffffffff), /* real_base */ + W(0xffffffff), /* real_size */ + W(0xffffffff), /* virt_base */ + W(0xffffffff), /* virt_size */ + W(0xffffffff), /* load_base */ + W(64), /* 128MB min RMA */ + W(0xffffffff), /* full client load */ + 0, /* min RMA percentage of total RAM */ + 48, /* max log_2(hash table size) */ + + /* option vector 3: processor options supported */ + 3 - 1, /* length */ + 0, /* don't ignore, don't halt */ + OV3_FP | OV3_VMX, + + /* option vector 4: IBM PAPR implementation */ + 2 - 1, /* length */ + 0, /* don't halt */ + + /* option vector 5: PAPR/OF options */ + 3 - 1, /* length */ + 0, /* don't ignore, don't halt */ + OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES, +}; + +/* Old method - ELF header with PT_NOTE sections */ static struct fake_elf { Elf32_Ehdr elfhdr; Elf32_Phdr phdr[2]; @@ -728,8 +814,26 @@ static struct fake_elf { static void __init prom_send_capabilities(void) { - ihandle elfloader; + ihandle elfloader, root; + prom_arg_t ret; + + root = call_prom("open", 1, 1, ADDR("/")); + if (root != 0) { + /* try calling the ibm,client-architecture-support method */ + if (call_prom_ret("call-method", 3, 2, &ret, + ADDR("ibm,client-architecture-support"), + ADDR(ibm_architecture_vec)) == 0) { + /* the call exists... */ + if (ret) + prom_printf("WARNING: ibm,client-architecture" + "-support call FAILED!\n"); + call_prom("close", 1, 0, root); + return; + } + call_prom("close", 1, 0, root); + } + /* no ibm,client-architecture-support call, try the old way */ elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader")); if (elfloader == 0) { prom_printf("couldn't open /packages/elf-loader\n"); diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index bcb83574335..4a677d1bd4e 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -538,7 +538,7 @@ void do_syscall_trace_enter(struct pt_regs *regs) do_syscall_trace(); if (unlikely(current->audit_context)) - audit_syscall_entry(current, + audit_syscall_entry( #ifdef CONFIG_PPC32 AUDIT_ARCH_PPC, #else @@ -556,8 +556,7 @@ void do_syscall_trace_leave(struct pt_regs *regs) #endif if (unlikely(current->audit_context)) - audit_syscall_exit(current, - (regs->ccr&0x1000)?AUDITSC_FAILURE:AUDITSC_SUCCESS, + audit_syscall_exit((regs->ccr&0x1000)?AUDITSC_FAILURE:AUDITSC_SUCCESS, regs->result); if ((test_thread_flag(TIF_SYSCALL_TRACE) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1d93e73a700..684ab1d49c6 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -516,3 +516,11 @@ void probe_machine(void) printk(KERN_INFO "Using %s machine description\n", ppc_md.name); } + +int check_legacy_ioport(unsigned long base_port) +{ + if (ppc_md.check_legacy_ioport == NULL) + return 0; + return ppc_md.check_legacy_ioport(base_port); +} +EXPORT_SYMBOL(check_legacy_ioport); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 13e91c4d70a..4467c49903b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -594,14 +594,6 @@ void ppc64_terminate_msg(unsigned int src, const char *msg) printk("[terminate]%04x %s\n", src, msg); } -int check_legacy_ioport(unsigned long base_port) -{ - if (ppc_md.check_legacy_ioport == NULL) - return 0; - return ppc_md.check_legacy_ioport(base_port); -} -EXPORT_SYMBOL(check_legacy_ioport); - void cpu_die(void) { if (ppc_md.cpu_die) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index ed737cacf92..5bc2585c803 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -322,13 +322,31 @@ static void register_nodes(void) } } } + +int sysfs_add_device_to_node(struct sys_device *dev, int nid) +{ + struct node *node = &node_devices[nid]; + return sysfs_create_link(&node->sysdev.kobj, &dev->kobj, + kobject_name(&dev->kobj)); +} + +void sysfs_remove_device_from_node(struct sys_device *dev, int nid) +{ + struct node *node = &node_devices[nid]; + sysfs_remove_link(&node->sysdev.kobj, kobject_name(&dev->kobj)); +} + #else static void register_nodes(void) { return; } + #endif +EXPORT_SYMBOL_GPL(sysfs_add_device_to_node); +EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node); + /* Only valid if CPU is present. */ static ssize_t show_physical_id(struct sys_device *dev, char *buf) { diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 0b98eea73c5..cf56a1d499f 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -325,6 +325,19 @@ SYSCALL(unshare) SYSCALL(splice) SYSCALL(tee) SYSCALL(vmsplice) +COMPAT_SYS(openat) +SYSCALL(mkdirat) +SYSCALL(mknodat) +SYSCALL(fchownat) +COMPAT_SYS(futimesat) +SYSX(sys_newfstatat, sys_fstatat64, sys_fstatat64) +SYSCALL(unlinkat) +SYSCALL(renameat) +SYSCALL(linkat) +SYSCALL(symlinkat) +SYSCALL(readlinkat) +SYSCALL(fchmodat) +SYSCALL(faccessat) /* * please add new calls to arch/powerpc/platforms/cell/spu_callbacks.c diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7370f9f33e2..266b8b2ceac 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -30,13 +30,66 @@ #define NUM_LOW_AREAS (0x100000000UL >> SID_SHIFT) #define NUM_HIGH_AREAS (PGTABLE_RANGE >> HTLB_AREA_SHIFT) +#ifdef CONFIG_PPC_64K_PAGES +#define HUGEPTE_INDEX_SIZE (PMD_SHIFT-HPAGE_SHIFT) +#else +#define HUGEPTE_INDEX_SIZE (PUD_SHIFT-HPAGE_SHIFT) +#endif +#define PTRS_PER_HUGEPTE (1 << HUGEPTE_INDEX_SIZE) +#define HUGEPTE_TABLE_SIZE (sizeof(pte_t) << HUGEPTE_INDEX_SIZE) + +#define HUGEPD_SHIFT (HPAGE_SHIFT + HUGEPTE_INDEX_SIZE) +#define HUGEPD_SIZE (1UL << HUGEPD_SHIFT) +#define HUGEPD_MASK (~(HUGEPD_SIZE-1)) + +#define huge_pgtable_cache (pgtable_cache[HUGEPTE_CACHE_NUM]) + +/* Flag to mark huge PD pointers. This means pmd_bad() and pud_bad() + * will choke on pointers to hugepte tables, which is handy for + * catching screwups early. */ +#define HUGEPD_OK 0x1 + +typedef struct { unsigned long pd; } hugepd_t; + +#define hugepd_none(hpd) ((hpd).pd == 0) + +static inline pte_t *hugepd_page(hugepd_t hpd) +{ + BUG_ON(!(hpd.pd & HUGEPD_OK)); + return (pte_t *)(hpd.pd & ~HUGEPD_OK); +} + +static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr) +{ + unsigned long idx = ((addr >> HPAGE_SHIFT) & (PTRS_PER_HUGEPTE-1)); + pte_t *dir = hugepd_page(*hpdp); + + return dir + idx; +} + +static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, + unsigned long address) +{ + pte_t *new = kmem_cache_alloc(huge_pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); + + if (! new) + return -ENOMEM; + + spin_lock(&mm->page_table_lock); + if (!hugepd_none(*hpdp)) + kmem_cache_free(huge_pgtable_cache, new); + else + hpdp->pd = (unsigned long)new | HUGEPD_OK; + spin_unlock(&mm->page_table_lock); + return 0; +} + /* Modelled after find_linux_pte() */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pg; pud_t *pu; - pmd_t *pm; - pte_t *pt; BUG_ON(! in_hugepage_area(mm->context, addr)); @@ -46,26 +99,14 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) if (!pgd_none(*pg)) { pu = pud_offset(pg, addr); if (!pud_none(*pu)) { - pm = pmd_offset(pu, addr); #ifdef CONFIG_PPC_64K_PAGES - /* Currently, we use the normal PTE offset within full - * size PTE pages, thus our huge PTEs are scattered in - * the PTE page and we do waste some. We may change - * that in the future, but the current mecanism keeps - * things much simpler - */ - if (!pmd_none(*pm)) { - /* Note: pte_offset_* are all equivalent on - * ppc64 as we don't have HIGHMEM - */ - pt = pte_offset_kernel(pm, addr); - return pt; - } -#else /* CONFIG_PPC_64K_PAGES */ - /* On 4k pages, we put huge PTEs in the PMD page */ - pt = (pte_t *)pm; - return pt; -#endif /* CONFIG_PPC_64K_PAGES */ + pmd_t *pm; + pm = pmd_offset(pu, addr); + if (!pmd_none(*pm)) + return hugepte_offset((hugepd_t *)pm, addr); +#else + return hugepte_offset((hugepd_t *)pu, addr); +#endif } } @@ -76,8 +117,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) { pgd_t *pg; pud_t *pu; - pmd_t *pm; - pte_t *pt; + hugepd_t *hpdp = NULL; BUG_ON(! in_hugepage_area(mm->context, addr)); @@ -87,23 +127,182 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) pu = pud_alloc(mm, pg, addr); if (pu) { +#ifdef CONFIG_PPC_64K_PAGES + pmd_t *pm; pm = pmd_alloc(mm, pu, addr); - if (pm) { + if (pm) + hpdp = (hugepd_t *)pm; +#else + hpdp = (hugepd_t *)pu; +#endif + } + + if (! hpdp) + return NULL; + + if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr)) + return NULL; + + return hugepte_offset(hpdp, addr); +} + +static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp) +{ + pte_t *hugepte = hugepd_page(*hpdp); + + hpdp->pd = 0; + tlb->need_flush = 1; + pgtable_free_tlb(tlb, pgtable_free_cache(hugepte, HUGEPTE_CACHE_NUM, + HUGEPTE_TABLE_SIZE-1)); +} + #ifdef CONFIG_PPC_64K_PAGES - /* See comment in huge_pte_offset. Note that if we ever - * want to put the page size in the PMD, we would have - * to open code our own pte_alloc* function in order - * to populate and set the size atomically - */ - pt = pte_alloc_map(mm, pm, addr); -#else /* CONFIG_PPC_64K_PAGES */ - pt = (pte_t *)pm; -#endif /* CONFIG_PPC_64K_PAGES */ - return pt; - } +static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pmd_t *pmd; + unsigned long next; + unsigned long start; + + start = addr; + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none(*pmd)) + continue; + free_hugepte_range(tlb, (hugepd_t *)pmd); + } while (pmd++, addr = next, addr != end); + + start &= PUD_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PUD_MASK; + if (!ceiling) + return; } + if (end - 1 > ceiling - 1) + return; - return NULL; + pmd = pmd_offset(pud, start); + pud_clear(pud); + pmd_free_tlb(tlb, pmd); +} +#endif + +static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pud_t *pud; + unsigned long next; + unsigned long start; + + start = addr; + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); +#ifdef CONFIG_PPC_64K_PAGES + if (pud_none_or_clear_bad(pud)) + continue; + hugetlb_free_pmd_range(tlb, pud, addr, next, floor, ceiling); +#else + if (pud_none(*pud)) + continue; + free_hugepte_range(tlb, (hugepd_t *)pud); +#endif + } while (pud++, addr = next, addr != end); + + start &= PGDIR_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PGDIR_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(pgd, start); + pgd_clear(pgd); + pud_free_tlb(tlb, pud); +} + +/* + * This function frees user-level page tables of a process. + * + * Must be called with pagetable lock held. + */ +void hugetlb_free_pgd_range(struct mmu_gather **tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pgd_t *pgd; + unsigned long next; + unsigned long start; + + /* + * Comments below take from the normal free_pgd_range(). They + * apply here too. The tests against HUGEPD_MASK below are + * essential, because we *don't* test for this at the bottom + * level. Without them we'll attempt to free a hugepte table + * when we unmap just part of it, even if there are other + * active mappings using it. + * + * The next few lines have given us lots of grief... + * + * Why are we testing HUGEPD* at this top level? Because + * often there will be no work to do at all, and we'd prefer + * not to go all the way down to the bottom just to discover + * that. + * + * Why all these "- 1"s? Because 0 represents both the bottom + * of the address space and the top of it (using -1 for the + * top wouldn't help much: the masks would do the wrong thing). + * The rule is that addr 0 and floor 0 refer to the bottom of + * the address space, but end 0 and ceiling 0 refer to the top + * Comparisons need to use "end - 1" and "ceiling - 1" (though + * that end 0 case should be mythical). + * + * Wherever addr is brought up or ceiling brought down, we + * must be careful to reject "the opposite 0" before it + * confuses the subsequent tests. But what about where end is + * brought down by HUGEPD_SIZE below? no, end can't go down to + * 0 there. + * + * Whereas we round start (addr) and ceiling down, by different + * masks at different levels, in order to test whether a table + * now has no other vmas using it, so can be freed, we don't + * bother to round floor or end up - the tests don't need that. + */ + + addr &= HUGEPD_MASK; + if (addr < floor) { + addr += HUGEPD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= HUGEPD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= HUGEPD_SIZE; + if (addr > end - 1) + return; + + start = addr; + pgd = pgd_offset((*tlb)->mm, addr); + do { + BUG_ON(! in_hugepage_area((*tlb)->mm->context, addr)); + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + hugetlb_free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + } while (pgd++, addr = next, addr != end); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, @@ -841,3 +1040,27 @@ repeat: out: return err; } + +static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags) +{ + memset(addr, 0, kmem_cache_size(cache)); +} + +static int __init hugetlbpage_init(void) +{ + if (!cpu_has_feature(CPU_FTR_16M_PAGE)) + return -ENODEV; + + huge_pgtable_cache = kmem_cache_create("hugepte_cache", + HUGEPTE_TABLE_SIZE, + HUGEPTE_TABLE_SIZE, + SLAB_HWCACHE_ALIGN | + SLAB_MUST_HWCACHE_ALIGN, + zero_ctor, NULL); + if (! huge_pgtable_cache) + panic("hugetlbpage_init(): could not create hugepte cache\n"); + + return 0; +} + +module_init(hugetlbpage_init); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index babebd15bdc..9e30f968c18 100644 --- a/arch/powerpc/mm/init_64.c +++ b/ |