diff options
Diffstat (limited to 'arch/powerpc/kernel')
90 files changed, 2626 insertions, 2011 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 803858e86160..8b133afbdc20 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -16,7 +16,7 @@ obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ signal_64.o ptrace32.o \ - paca.o cpu_setup_power4.o \ + paca.o cpu_setup_ppc970.o \ firmware.o sysfs.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o @@ -50,7 +50,8 @@ extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds -obj-y += time.o prom.o traps.o setup-common.o udbg.o +obj-y += time.o prom.o traps.o setup-common.o \ + udbg.o misc.o io.o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o misc_32.o obj-$(CONFIG_PPC64) += misc_64.o dma_64.o iommu.o obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o @@ -66,9 +67,11 @@ pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o pci_iommu.o \ pci_direct_iommu.o iomap.o pci32-$(CONFIG_PPC32) := pci_32.o obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) -kexec-$(CONFIG_PPC64) := machine_kexec_64.o crash.o +kexec-$(CONFIG_PPC64) := machine_kexec_64.o kexec-$(CONFIG_PPC32) := machine_kexec_32.o -obj-$(CONFIG_KEXEC) += machine_kexec.o $(kexec-y) +obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o $(kexec-y) +obj-$(CONFIG_AUDIT) += audit.o +obj64-$(CONFIG_AUDIT) += compat_audit.o ifeq ($(CONFIG_PPC_ISERIES),y) $(obj)/head_64.o: $(obj)/lparmap.s diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ff2940548929..d06f378597bb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -13,7 +13,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -41,9 +40,10 @@ #ifdef CONFIG_PPC64 #include <asm/paca.h> #include <asm/lppaca.h> -#include <asm/iseries/hv_lp_event.h> #include <asm/cache.h> #include <asm/compat.h> +#include <asm/mmu.h> +#include <asm/hvcall.h> #endif #define DEFINE(sym, val) \ @@ -137,11 +137,18 @@ int main(void) DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); + DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr)); + DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset)); + DEFINE(SLBSHADOW_STACKVSID, + offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid)); + DEFINE(SLBSHADOW_STACKESID, + offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid)); DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); + DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -160,6 +167,12 @@ int main(void) /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); + + /* hcall statistics */ + DEFINE(HCALL_STAT_SIZE, sizeof(struct hcall_stats)); + DEFINE(HCALL_STAT_CALLS, offsetof(struct hcall_stats, num_calls)); + DEFINE(HCALL_STAT_TB, offsetof(struct hcall_stats, tb_total)); + DEFINE(HCALL_STAT_PURR, offsetof(struct hcall_stats, purr_total)); #endif /* CONFIG_PPC64 */ DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0])); DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1])); @@ -241,6 +254,7 @@ int main(void) DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value)); DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features)); DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup)); + DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore)); #ifndef CONFIG_PPC64 DEFINE(pbe_address, offsetof(struct pbe, address)); diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c new file mode 100644 index 000000000000..7fe5e6300e9a --- /dev/null +++ b/arch/powerpc/kernel/audit.c @@ -0,0 +1,66 @@ +#include <linux/init.h> +#include <linux/types.h> +#include <linux/audit.h> +#include <asm/unistd.h> + +static unsigned dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +static unsigned read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +static unsigned write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +static unsigned chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +int audit_classify_syscall(int abi, unsigned syscall) +{ +#ifdef CONFIG_PPC64 + extern int ppc32_classify_syscall(unsigned); + if (abi == AUDIT_ARCH_PPC) + return ppc32_classify_syscall(syscall); +#endif + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_socketcall: + return 4; + case __NR_execve: + return 5; + default: + return 0; + } +} + +static int __init audit_classes_init(void) +{ +#ifdef CONFIG_PPC64 + extern __u32 ppc32_dir_class[]; + extern __u32 ppc32_write_class[]; + extern __u32 ppc32_read_class[]; + extern __u32 ppc32_chattr_class[]; + audit_register_class(AUDIT_CLASS_WRITE_32, ppc32_write_class); + audit_register_class(AUDIT_CLASS_READ_32, ppc32_read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE_32, ppc32_dir_class); + audit_register_class(AUDIT_CLASS_CHATTR_32, ppc32_chattr_class); +#endif + audit_register_class(AUDIT_CLASS_WRITE, write_class); + audit_register_class(AUDIT_CLASS_READ, read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); + audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); + return 0; +} + +__initcall(audit_classes_init); diff --git a/arch/powerpc/kernel/binfmt_elf32.c b/arch/powerpc/kernel/binfmt_elf32.c index 8ad6b0f33651..5cb58757e1b1 100644 --- a/arch/powerpc/kernel/binfmt_elf32.c +++ b/arch/powerpc/kernel/binfmt_elf32.c @@ -19,7 +19,6 @@ #include <asm/processor.h> #include <linux/module.h> -#include <linux/config.h> #include <linux/elfcore.h> #include <linux/compat.h> diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 6223d39177cb..995fcef156fd 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -3,7 +3,6 @@ * * Benjamin Herrenschmidt <benh@kernel.crashing.org> */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> @@ -112,7 +111,7 @@ void __init btext_setup_display(int width, int height, int depth, int pitch, logicalDisplayBase = (unsigned char *)address; dispDeviceBase = (unsigned char *)address; dispDeviceRowBytes = pitch; - dispDeviceDepth = depth; + dispDeviceDepth = depth == 15 ? 16 : depth; dispDeviceRect[0] = dispDeviceRect[1] = 0; dispDeviceRect[2] = width; dispDeviceRect[3] = height; @@ -159,27 +158,35 @@ int btext_initialize(struct device_node *np) { unsigned int width, height, depth, pitch; unsigned long address = 0; - u32 *prop; + const u32 *prop; - prop = (u32 *)get_property(np, "width", NULL); + prop = get_property(np, "linux,bootx-width", NULL); + if (prop == NULL) + prop = get_property(np, "width", NULL); if (prop == NULL) return -EINVAL; width = *prop; - prop = (u32 *)get_property(np, "height", NULL); + prop = get_property(np, "linux,bootx-height", NULL); + if (prop == NULL) + prop = get_property(np, "height", NULL); if (prop == NULL) return -EINVAL; height = *prop; - prop = (u32 *)get_property(np, "depth", NULL); + prop = get_property(np, "linux,bootx-depth", NULL); + if (prop == NULL) + prop = get_property(np, "depth", NULL); if (prop == NULL) return -EINVAL; depth = *prop; pitch = width * ((depth + 7) / 8); - prop = (u32 *)get_property(np, "linebytes", NULL); + prop = get_property(np, "linux,bootx-linebytes", NULL); + if (prop == NULL) + prop = get_property(np, "linebytes", NULL); if (prop) pitch = *prop; if (pitch == 1) pitch = 0x1000; - prop = (u32 *)get_property(np, "address", NULL); + prop = get_property(np, "address", NULL); if (prop) address = *prop; @@ -195,7 +202,7 @@ int btext_initialize(struct device_node *np) g_max_loc_Y = height / 16; dispDeviceBase = (unsigned char *)address; dispDeviceRowBytes = pitch; - dispDeviceDepth = depth; + dispDeviceDepth = depth == 15 ? 16 : depth; dispDeviceRect[0] = dispDeviceRect[1] = 0; dispDeviceRect[2] = width; dispDeviceRect[3] = height; @@ -207,11 +214,11 @@ int btext_initialize(struct device_node *np) int __init btext_find_display(int allow_nonstdout) { - char *name; + const char *name; struct device_node *np = NULL; int rc = -ENODEV; - name = (char *)get_property(of_chosen, "linux,stdout-path", NULL); + name = get_property(of_chosen, "linux,stdout-path", NULL); if (name != NULL) { np = of_find_node_by_path(name); if (np != NULL) { diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c new file mode 100644 index 000000000000..640d4bb29321 --- /dev/null +++ b/arch/powerpc/kernel/compat_audit.c @@ -0,0 +1,38 @@ +#undef __powerpc64__ +#include <asm/unistd.h> + +unsigned ppc32_dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +unsigned ppc32_chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +unsigned ppc32_write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +unsigned ppc32_read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +int ppc32_classify_syscall(unsigned syscall) +{ + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_socketcall: + return 4; + case __NR_execve: + return 5; + default: + return 1; + } +} diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index 365381fcb27c..8b4a4ee85eca 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -9,7 +9,6 @@ * */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/cputable.h> diff --git a/arch/powerpc/kernel/cpu_setup_power4.S b/arch/powerpc/kernel/cpu_setup_ppc970.S index 271418308d53..652594891d58 100644 --- a/arch/powerpc/kernel/cpu_setup_power4.S +++ b/arch/powerpc/kernel/cpu_setup_ppc970.S @@ -9,7 +9,6 @@ * */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/cputable.h> @@ -17,27 +16,12 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> -_GLOBAL(__970_cpu_preinit) - /* - * Do nothing if not running in HV mode - */ +_GLOBAL(__cpu_preinit_ppc970) + /* Do nothing if not running in HV mode */ mfmsr r0 rldicl. r0,r0,4,63 beqlr - /* - * Deal only with PPC970 and PPC970FX. - */ - mfspr r0,SPRN_PVR - srwi r0,r0,16 - cmpwi r0,0x39 - beq 1f - cmpwi r0,0x3c - beq 1f - cmpwi r0,0x44 - bnelr -1: - /* Make sure HID4:rm_ci is off before MMU is turned off, that large * pages are enabled with HID4:61 and clear HID5:DCBZ_size and * HID5:DCBZ32_ill @@ -73,21 +57,6 @@ _GLOBAL(__970_cpu_preinit) isync blr -_GLOBAL(__setup_cpu_ppc970) - mfspr r0,SPRN_HID0 - li r11,5 /* clear DOZE and SLEEP */ - rldimi r0,r11,52,8 /* set NAP and DPM */ - mtspr SPRN_HID0,r0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - sync - isync - blr - /* Definitions for the table use to save CPU states */ #define CS_HID0 0 #define CS_HID1 8 @@ -102,30 +71,32 @@ cpu_state_storage: .balign L1_CACHE_BYTES,0 .text -/* Called in normal context to backup CPU 0 state. This - * does not include cache settings. This function is also - * called for machine sleep. This does not include the MMU - * setup, BATs, etc... but rather the "special" registers - * like HID0, HID1, HID4, etc... - */ -_GLOBAL(__save_cpu_setup) - /* Some CR fields are volatile, we back it up all */ - mfcr r7 - /* Get storage ptr */ +_GLOBAL(__setup_cpu_ppc970) + /* Do nothing if not running in HV mode */ + mfmsr r0 + rldicl. r0,r0,4,63 + beqlr + + mfspr r0,SPRN_HID0 + li r11,5 /* clear DOZE and SLEEP */ + rldimi r0,r11,52,8 /* set NAP and DPM */ + li r11,0 + rldimi r0,r11,32,31 /* clear EN_ATTN */ + mtspr SPRN_HID0,r0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + sync + isync + + /* Save away cpu state */ LOAD_REG_IMMEDIATE(r5,cpu_state_storage) - /* We only deal with 970 for now */ - mfspr r0,SPRN_PVR - srwi r0,r0,16 - cmpwi r0,0x39 - beq 1f - cmpwi r0,0x3c - beq 1f - cmpwi r0,0x44 - bne 2f - -1: /* Save HID0,1,4 and 5 */ + /* Save HID0,1,4 and 5 */ mfspr r3,SPRN_HID0 std r3,CS_HID0(r5) mfspr r3,SPRN_HID1 @@ -135,31 +106,20 @@ _GLOBAL(__save_cpu_setup) mfspr r3,SPRN_HID5 std r3,CS_HID5(r5) -2: - mtcr r7 blr /* Called with no MMU context (typically MSR:IR/DR off) to * restore CPU state as backed up by the previous * function. This does not include cache setting */ -_GLOBAL(__restore_cpu_setup) - /* Get storage ptr (FIXME when using anton reloc as we - * are running with translation disabled here - */ - LOAD_REG_IMMEDIATE(r5,cpu_state_storage) +_GLOBAL(__restore_cpu_ppc970) + /* Do nothing if not running in HV mode */ + mfmsr r0 + rldicl. r0,r0,4,63 + beqlr - /* We only deal with 970 for now */ - mfspr r0,SPRN_PVR - srwi r0,r0,16 - cmpwi r0,0x39 - beq 1f - cmpwi r0,0x3c - beq 1f - cmpwi r0,0x44 - bnelr - -1: /* Before accessing memory, we make sure rm_ci is clear */ + LOAD_REG_IMMEDIATE(r5,cpu_state_storage) + /* Before accessing memory, we make sure rm_ci is clear */ li r0,0 mfspr r3,SPRN_HID4 rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 1c114880dc05..190a57e20765 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -10,7 +10,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/threads.h> @@ -40,7 +39,10 @@ extern void __setup_cpu_7400(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_7410(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); #endif /* CONFIG_PPC32 */ +#ifdef CONFIG_PPC64 extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); +extern void __restore_cpu_ppc970(void); +#endif /* CONFIG_PPC64 */ /* This table only contains "desktop" CPUs, it need to be filled with embedded * ones as well... @@ -56,6 +58,9 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); #define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ PPC_FEATURE_TRUE_LE) +#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_HAS_ALTIVEC_COMP) #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) @@ -185,6 +190,7 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", @@ -200,6 +206,7 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", @@ -215,6 +222,7 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", @@ -281,6 +289,17 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .platform = "ppc-cell-be", }, + { /* PA Semi PA6T */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00900000, + .cpu_name = "PA6T", + .cpu_features = CPU_FTRS_PA6T, + .cpu_user_features = COMMON_USER_PA6T, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 6, + .platform = "pa6t", + }, { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, @@ -722,18 +741,6 @@ struct cpu_spec cpu_specs[] = { .oprofile_type = PPC_OPROFILE_G4, .platform = "ppc7450", }, - { /* 8641 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80040010, - .cpu_name = "8641", - .cpu_features = CPU_FTRS_7447A, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .cpu_setup = __setup_cpu_745x - }, - { /* 82xx (8240, 8245, 8260 are all 603e cores) */ .pvr_mask = 0x7fff0000, .pvr_value = 0x00810000, @@ -942,6 +949,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* 405EP */ .pvr_mask = 0xffff0000, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index dbcb85994f46..1af41f7616dc 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -24,9 +24,11 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/types.h> +#include <linux/irq.h> #include <asm/processor.h> #include <asm/machdep.h> +#include <asm/kexec.h> #include <asm/kdump.h> #include <asm/lmb.h> #include <asm/firmware.h> @@ -41,6 +43,8 @@ /* This keeps a track of which one is crashing cpu. */ int crashing_cpu = -1; +static cpumask_t cpus_in_crash = CPU_MASK_NONE; +cpumask_t cpus_in_sr = CPU_MASK_NONE; static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data, size_t data_len) @@ -98,34 +102,72 @@ static void crash_save_this_cpu(struct pt_regs *regs, int cpu) } #ifdef CONFIG_SMP -static atomic_t waiting_for_crash_ipi; +static atomic_t enter_on_soft_reset = ATOMIC_INIT(0); void crash_ipi_callback(struct pt_regs *regs) { int cpu = smp_processor_id(); - if (cpu == crashing_cpu) - return; - if (!cpu_online(cpu)) return; + local_irq_disable(); + if (!cpu_isset(cpu, cpus_in_crash)) + crash_save_this_cpu(regs, cpu); + cpu_set(cpu, cpus_in_crash); + + /* + * Entered via soft-reset - could be the kdump + * process is invoked using soft-reset or user activated + * it if some CPU did not respond to an IPI. + * For soft-reset, the secondary CPU can enter this func + * twice. 1 - using IPI, and 2. soft-reset. + * Tell the kexec CPU that entered via soft-reset and ready + * to go down. + */ + if (cpu_isset(cpu, cpus_in_sr)) { + cpu_clear(cpu, cpus_in_sr); + atomic_inc(&enter_on_soft_reset); + } + + /* + * Starting the kdump boot. + * This barrier is needed to make sure that all CPUs are stopped. + * If not, soft-reset will be invoked to bring other CPUs. + */ + while (!cpu_isset(crashing_cpu, cpus_in_crash)) + cpu_relax(); + if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 1); - local_irq_disable(); - - crash_save_this_cpu(regs, cpu); - atomic_dec(&waiting_for_crash_ipi); +#ifdef CONFIG_PPC64 kexec_smp_wait(); +#else + for (;;); /* FIXME */ +#endif + /* NOTREACHED */ } -static void crash_kexec_prepare_cpus(void) +/* + * Wait until all CPUs are entered via soft-reset. + */ +static void crash_soft_reset_check(int cpu) +{ + unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ + + cpu_clear(cpu, cpus_in_sr); + while (atomic_read(&enter_on_soft_reset) != ncpus) + cpu_relax(); +} + + +static void crash_kexec_prepare_cpus(int cpu) { unsigned int msecs; - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ crash_send_ipi(crash_ipi_callback); smp_wmb(); @@ -133,14 +175,13 @@ static void crash_kexec_prepare_cpus(void) /* * FIXME: Until we will have the way to stop other CPUSs reliabally, * the crash CPU will send an IPI and wait for other CPUs to - * respond. If not, proceed the kexec boot even though we failed to - * capture other CPU states. + * respond. * Delay of at least 10 seconds. */ - printk(KERN_ALERT "Sending IPI to other cpus...\n"); + printk(KERN_EMERG "Sending IPI to other cpus...\n"); msecs = 10000; - while ((atomic_read(&waiting_for_crash_ipi) > 0) && (--msecs > 0)) { - barrier(); + while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) { + cpu_relax(); mdelay(1); } @@ -149,18 +190,71 @@ static void crash_kexec_prepare_cpus(void) /* * FIXME: In case if we do not get all CPUs, one possibility: ask the * user to do soft reset such that we get all. - * IPI handler is already set by the panic cpu initially. Therefore, - * all cpus could invoke this handler from die() and the panic CPU - * will call machine_kexec() directly from this handler to do - * kexec boot. + * Soft-reset will be used until better mechanism is implemented. + */ + if (cpus_weight(cpus_in_crash) < ncpus) { + printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n", + ncpus - cpus_weight(cpus_in_crash)); + printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n"); + cpus_in_sr = CPU_MASK_NONE; + atomic_set(&enter_on_soft_reset, 0); + while (cpus_weight(cpus_in_crash) < ncpus) + cpu_relax(); + } + /* + * Make sure all CPUs are entered via soft-reset if the kdump is + * invoked using soft-reset. */ - if (atomic_read(&waiting_for_crash_ipi)) - printk(KERN_ALERT "done waiting: %d cpus not responding\n", - atomic_read(&waiting_for_crash_ipi)); + if (cpu_isset(cpu, cpus_in_sr)) + crash_soft_reset_check(cpu); /* Leave the IPI callback set */ } + +/* + * This function will be called by secondary cpus or by kexec cpu + * if soft-reset is activated to stop some CPUs. + */ +void crash_kexec_secondary(struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + unsigned long flags; + int msecs = 5; + + local_irq_save(flags); + /* Wait 5ms if the kexec CPU is not entered yet. */ + while (crashing_cpu < 0) { + if (--msecs < 0) { + /* + * Either kdump image is not loaded or + * kdump process is not started - Probably xmon + * exited using 'x'(exit and recover) or + * kexec_should_crash() failed for all running tasks. + */ + cpu_clear(cpu, cpus_in_sr); + local_irq_restore(flags); + return; + } + mdelay(1); + cpu_relax(); + } + if (cpu == crashing_cpu) { + /* + * Panic CPU will enter this func only via soft-reset. + * Wait until all secondary CPUs entered and + * then start kexec boot. + */ + crash_soft_reset_check(cpu); + cpu_set(crashing_cpu, cpus_in_crash); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 0); + machine_kexec(kexec_crash_image); + /* NOTREACHED */ + } + crash_ipi_callback(regs); +} + #else -static void crash_kexec_prepare_cpus(void) +static void crash_kexec_prepare_cpus(int cpu) { /* * move the secondarys to us so that we can copy @@ -168,9 +262,17 @@ static void crash_kexec_prepare_cpus(void) * * do this if kexec in setup.c ? */ +#ifdef CONFIG_PPC64 smp_release_cpus(); +#else + /* FIXME */ +#endif } +void crash_kexec_secondary(struct pt_regs *regs) +{ + cpus_in_sr = CPU_MASK_NONE; +} #endif void default_machine_crash_shutdown(struct pt_regs *regs) @@ -179,7 +281,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) /* * This function is only called after the system - * has paniced or is otherwise in a critical state. + * has panicked or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. * @@ -190,23 +292,23 @@ void default_machine_crash_shutdown(struct pt_regs *regs) local_irq_disable(); for_each_irq(irq) { - struct irq_desc *desc = irq_descp(irq); + struct irq_desc *desc = irq_desc + irq; if (desc->status & IRQ_INPROGRESS) - desc->handler->end(irq); + desc->chip->eoi(irq); if (!(desc->status & IRQ_DISABLED)) - desc->handler->disable(irq); + desc->chip->disable(irq); } - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(1, 0); - /* * Make a note of crashing cpu. Will be used in machine_kexec * such that another IPI will not be sent. */ crashing_cpu = smp_processor_id(); - crash_kexec_prepare_cpus(); crash_save_this_cpu(regs, crashing_cpu); + crash_kexec_prepare_cpus(crashing_cpu); + cpu_set(crashing_cpu, cpus_in_crash); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 0); } diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 371973be8d71..2f6f5a7bc69e 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -80,7 +80,7 @@ static int __init parse_savemaxmem(char *p) } __setup("savemaxmem=", parse_savemaxmem); -/* +/** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied * @buf: target memory address for the copy; this can be in kernel address diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c index 36aaa7663f02..6c168f6ea142 100644 --- a/arch/powerpc/kernel/dma_64.c +++ b/arch/powerpc/kernel/dma_64.c @@ -35,10 +35,9 @@ int dma_supported(struct device *dev, u64 mask) { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - return dma_ops->dma_supported(dev, mask); - BUG(); - return 0; + BUG_ON(!dma_ops); + + return dma_ops->dma_supported(dev, mask); } EXPORT_SYMBOL(dma_supported); @@ -66,10 +65,9 @@ void *dma_alloc_coherent(struct device *dev, size_t size, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - return dma_ops->alloc_coherent(dev, size, dma_handle, flag); - BUG(); - return NULL; + BUG_ON(!dma_ops); + + return dma_ops->alloc_coherent(dev, size, dma_handle, flag); } EXPORT_SYMBOL(dma_alloc_coherent); @@ -78,10 +76,9 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); - else - BUG(); + BUG_ON(!dma_ops); + + dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); } EXPORT_SYMBOL(dma_free_coherent); @@ -90,10 +87,9 @@ dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - return dma_ops->map_single(dev, cpu_addr, size, direction); - BUG(); - return (dma_addr_t)0; + BUG_ON(!dma_ops); + + return dma_ops->map_single(dev, cpu_addr, size, direction); } EXPORT_SYMBOL(dma_map_single); @@ -102,10 +98,9 @@ void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - dma_ops->unmap_single(dev, dma_addr, size, direction); - else - BUG(); + BUG_ON(!dma_ops); + + dma_ops->unmap_single(dev, dma_addr, size, direction); } EXPORT_SYMBOL(dma_unmap_single); @@ -115,11 +110,10 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - return dma_ops->map_single(dev, - (page_address(page) + offset), size, direction); - BUG(); - return (dma_addr_t)0; + BUG_ON(!dma_ops); + + return dma_ops->map_single(dev, page_address(page) + offset, size, + direction); } EXPORT_SYMBOL(dma_map_page); @@ -128,10 +122,9 @@ void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - dma_ops->unmap_single(dev, dma_address, size, direction); - else - BUG(); + BUG_ON(!dma_ops); + + dma_ops->unmap_single(dev, dma_address, size, direction); } EXPORT_SYMBOL(dma_unmap_page); @@ -140,10 +133,9 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - return dma_ops->map_sg(dev, sg, nents, direction); - BUG(); - return 0; + BUG_ON(!dma_ops); + + return dma_ops->map_sg(dev, sg, nents, direction); } EXPORT_SYMBOL(dma_map_sg); @@ -152,9 +144,8 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, { struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - if (dma_ops) - dma_ops->unmap_sg(dev, sg, nhwentries, direction); - else - BUG(); + BUG_ON(!dma_ops); + + dma_ops->unmap_sg(dev, sg, nhwentries, direction); } EXPORT_SYMBOL(dma_unmap_sg); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 8866fd26c6b9..c03e829fee3c 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -19,7 +19,6 @@ * */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/sys.h> #include <linux/threads.h> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 221062c960c9..2cd872b5283b 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -18,7 +18,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/errno.h> #include <asm/unistd.h> #include <asm/processor.h> @@ -376,6 +375,14 @@ BEGIN_FTR_SECTION ld r7,KSP_VSID(r4) /* Get new stack's VSID */ oris r0,r6,(SLB_ESID_V)@h ori r0,r0,(SLB_NUM_BOLTED-1)@l + + /* Update the last bolted SLB */ + ld r9,PACA_SLBSHADOWPTR(r13) + li r12,0 + std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */ + std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */ + std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */ + slbie r6 slbie r6 /* Workaround POWER5 < DD2.1 issue */ slbmte r7,r0 diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index 0bfe9061720a..1679a70bbcad 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -13,7 +13,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/module.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 01f71200c603..821e152e093c 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -2,6 +2,11 @@ * FPU support code, moved here from head.S so that it can be used * by chips which use other head-whatever.S files. * + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Copyright (C) 1996 Paul Mackerras. + * Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -9,7 +14,6 @@ * */ -#include <linux/config.h> #include <asm/reg.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index b25b25902d15..d88e182e40b3 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -22,7 +22,6 @@ * */ -#include <linux/config.h> #include <asm/reg.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 47c7fa148c9a..accb39d49911 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -28,7 +28,6 @@ * option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_4xx.S b/arch/powerpc/kernel/head_4xx.S index 2590e97f5539..adc7f8097cd4 100644 --- a/arch/powerpc/kernel/head_4xx.S +++ b/arch/powerpc/kernel/head_4xx.S @@ -31,7 +31,6 @@ * */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 831acbdf2592..3065b472b95d 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -21,7 +21,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/threads.h> #include <asm/reg.h> #include <asm/page.h> @@ -85,34 +84,6 @@ END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ trap -#ifdef CONFIG_PPC_ISERIES - /* - * At offset 0x20, there is a pointer to iSeries LPAR data. - * This is required by the hypervisor - */ - . = 0x20 - .llong hvReleaseData-KERNELBASE - - /* - * At offset 0x28 and 0x30 are offsets to the mschunks_map - * array (used by the iSeries LPAR debugger to do translation - * between physical addresses and absolute addresses) and - * to the pidhash table (also used by the debugger) - */ - .llong mschunks_map-KERNELBASE - .llong 0 /* pidhash-KERNELBASE SFRXXX */ - - /* Offset 0x38 - Pointer to start of embedded System.map */ - .globl embedded_sysmap_start -embedded_sysmap_start: - .llong 0 - /* Offset 0x40 - Pointer to end of embedded System.map */ - .globl embedded_sysmap_end -embedded_sysmap_end: - .llong 0 - -#endif /* CONFIG_PPC_ISERIES */ - /* Secondary processors spin on this value until it goes to 1. */ .globl __secondary_hold_spinloop __secondary_hold_spinloop: @@ -124,6 +95,15 @@ __secondary_hold_spinloop: __secondary_hold_acknowledge: .llong 0x0 +#ifdef CONFIG_PPC_ISERIES + /* + * At offset 0x20, there is a pointer to iSeries LPAR data. + * This is required by the hypervisor + */ + . = 0x20 + .llong hvReleaseData-KERNELBASE +#endif /* CONFIG_PPC_ISERIES */ + . = 0x60 /* * The following code is used on pSeries to hold secondary processors @@ -152,7 +132,7 @@ _GLOBAL(__secondary_hold) bne 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) - LOAD_REG_IMMEDIATE(r4, .pSeries_secondary_smp_init) + LOAD_REG_IMMEDIATE(r4, .generic_secondary_smp_init) mtctr r4 mr r3,r24 bctr @@ -211,6 +191,37 @@ exception_marker: ori reg,reg,(label)@l; /* virt addr of handler ... */ #endif +/* + * Equal to EXCEPTION_PROLOG_PSERIES, except that it forces 64bit mode. + * The firmware calls the registered system_reset_fwnmi and + * machine_check_fwnmi handlers in 32bit mode if the cpu happens to run + * a 32bit application at the time of the event. + * This firmware bug is present on POWER4 and JS20. + */ +#define EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(area, label) \ + mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ + std r9,area+EX_R9(r13); /* save r9 - r12 */ \ + std r10,area+EX_R10(r13); \ + std r11,area+EX_R11(r13); \ + std r12,area+EX_R12(r13); \ + mfspr r9,SPRN_SPRG1; \ + std r9,area+EX_R13(r13); \ + mfcr r9; \ + clrrdi r12,r13,32; /* get high part of &label */ \ + mfmsr r10; \ + /* force 64bit mode */ \ + li r11,5; /* MSR_SF_LG|MSR_ISF_LG */ \ + rldimi r10,r11,61,0; /* insert into top 3 bits */ \ + /* done 64bit mode */ \ + mfspr r11,SPRN_SRR0; /* save SRR0 */ \ + LOAD_HANDLER(r12,label) \ + ori r10,r10,MSR_IR|MSR_DR|MSR_RI; \ + mtspr SPRN_SRR0,r12; \ + mfspr r12,SPRN_SRR1; /* and SRR1 */ \ + mtspr SPRN_SRR1,r10; \ + rfid; \ + b . /* prevent speculative execution */ + #define EXCEPTION_PROLOG_PSERIES(area, label) \ mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ std r9,area+EX_R9(r13); /* save r9 - r12 */ \ @@ -624,14 +635,14 @@ slb_miss_user_pseries: system_reset_fwnmi: HMT_MEDIUM mtspr SPRN_SPRG1,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXGEN, system_reset_common) .globl machine_check_fwnmi .align 7 machine_check_fwnmi: HMT_MEDIUM mtspr SPRN_SPRG1,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXMC, machine_check_common) #ifdef CONFIG_PPC_ISERIES /*** ISeries-LPAR interrupt handlers ***/ @@ -1473,19 +1484,17 @@ fwnmi_data_area: . = 0x8000 /* - * On pSeries, secondary processors spin in the following code. + * On pSeries and most other platforms, secondary processors spin + * in the following code. * At entry, r3 = this processor's number (physical cpu id) */ -_GLOBAL(pSeries_secondary_smp_init) +_GLOBAL(generic_secondary_smp_init) mr r24,r3 /* turn on 64-bit mode */ bl .enable_64b_mode isync - /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_setup - /* Set up a paca value for this processor. Since we have the * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. @@ -1511,15 +1520,28 @@ _GLOBAL(pSeries_secondary_smp_init) /* start. */ sync - /* Create a temp kernel stack for use before relocation is on. */ +#ifndef CONFIG_SMP + b 3b /* Never go on non-SMP */ +#else + cmpwi 0,r23,0 + beq 3b /* Loop until told to go */ + + /* See if we need to call a cpu state restore handler */ + LOAD_REG_IMMEDIATE(r23, cur_cpu_spec) + ld r23,0(r23) + ld r23,CPU_SPEC_RESTORE(r23) + cmpdi 0,r23,0 + beq 4f + ld r23,0(r23) + mtctr r23 + bctrl + +4: /* Create a temp kernel stack for use before relocation is on. */ ld r1,PACAEMERGSP(r13) subi r1,r1,STACK_FRAME_OVERHEAD - cmpwi 0,r23,0 -#ifdef CONFIG_SMP - bne .__secondary_start + b .__secondary_start #endif - b 3b /* Loop until told to go */ #ifdef CONFIG_PPC_ISERIES _STATIC(__start_initialization_iSeries) @@ -1600,10 +1622,16 @@ _GLOBAL(__start_initialization_multiplatform) bl .enable_64b_mode /* Setup some critical 970 SPRs before switching MMU off */ - bl .__970_cpu_preinit - - /* cpu # */ - li r24,0 + mfspr r0,SPRN_PVR + srwi r0,r0,16 + cmpwi r0,0x39 /* 970 */ + beq 1f + cmpwi r0,0x3c /* 970FX */ + beq 1f + cmpwi r0,0x44 /* 970MP */ + bne 2f +1: bl .__cpu_preinit_ppc970 +2: /* Switch off MMU if not already */ LOAD_REG_IMMEDIATE(r4, .__after_prom_start - KERNELBASE) @@ -1683,6 +1711,9 @@ _STATIC(__after_prom_start) /* i.e. where we are running */ /* the source addr */ + cmpdi r4,0 /* In some cases the loader may */ + beq .start_here_multiplatform /* have already put us at zero */ + /* so we can skip the copy. */ LOAD_REG_IMMEDIATE(r5,copy_to_here) /* # bytes of memory to copy */ sub r5,r5,r27 @@ -1717,7 +1748,7 @@ _STATIC(__after_prom_start) _GLOBAL(copy_and_flush) addi r5,r5,-8 addi r6,r6,-8 -4: li r0,16 /* Use the least common */ +4: li r0,8 /* Use the smallest common */ /* denominator cache line */ /* size. This results in */ /* extra cache line flushes */ @@ -1771,7 +1802,7 @@ _GLOBAL(pmac_secondary_start) isync /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_setup + bl .__restore_cpu_ppc970 /* pSeries do that early though I don't think we really need it */ mfmsr r3 @@ -1921,12 +1952,6 @@ _STATIC(start_here_multiplatform) mr r5,r26 bl .identify_cpu - /* Save some low level config HIDs of CPU0 to be copied to - * other CPUs later on, or used for suspend/resume - */ - bl .__save_cpu_setup - sync - /* Do very early kernel initializations, including initial hash table, * stab and slb setup before we turn on relocation. */ @@ -1962,14 +1987,6 @@ _STATIC(start_here_common) li r3,0 bl .do_cpu_ftr_fixups - LOAD_REG_IMMEDIATE(r26, boot_cpuid) - lwz r26,0(r26) - - LOAD_REG_IMMEDIATE(r24, paca) /* Get base vaddr of paca array */ - mulli r13,r26,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r13,r24 /* for this processor. */ - mtspr SPRN_SPRG3,r13 - /* ptr to current */ LOAD_REG_IMMEDIATE(r4, init_task) std r4,PACACURRENT(r13) @@ -1995,17 +2012,6 @@ _STATIC(start_here_common) /* Not reached */ BUG_OPCODE -/* Put the paca pointer into r13 and SPRG3 */ -_GLOBAL(setup_boot_paca) - LOAD_REG_IMMEDIATE(r3, boot_cpuid) - lwz r3,0(r3) - LOAD_REG_IMMEDIATE(r4, paca) /* Get base vaddr of paca array */ - mulli r3,r3,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r3,r4 /* for this processor. */ - mtspr SPRN_SPRG3,r13 - - blr - /* * We put a few things here that have to be page-aligned. * This stuff goes at the beginning of the bss, which is page-aligned. diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 28941f5ce673..901be47a02a9 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -19,7 +19,6 @@ * */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index dd86bbed7627..66877bdfe0b7 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -30,7 +30,6 @@ * option) any later version. */ -#include <linux/config.h> #include <linux/threads.h> #include <asm/processor.h> #include <asm/page.h> diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index e47d40ac6f39..124dbcba94a8 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -167,7 +167,7 @@ static DEVICE_ATTR(name, S_IRUSR | S_IRGRP | S_IROTH, ibmebusdev_show_name, NULL); static struct ibmebus_dev* __devinit ibmebus_register_device_common( - struct ibmebus_dev *dev, char *name) + struct ibmebus_dev *dev, const char *name) { int err = 0; @@ -194,10 +194,10 @@ static struct ibmebus_dev* __devinit ibmebus_register_device_node( struct device_node *dn) { struct ibmebus_dev *dev; - char *loc_code; + const char *loc_code; int length; - loc_code = (char *)get_property(dn, "ibm,loc-code", NULL); + loc_code = get_property(dn, "ibm,loc-code", NULL); if (!loc_code) { printk(KERN_WARNING "%s: node %s missing 'ibm,loc-code'\n", __FUNCTION__, dn->name ? dn->name : "<unknown>"); @@ -323,13 +323,11 @@ int ibmebus_request_irq(struct ibmebus_dev *dev, unsigned long irq_flags, const char * devname, void *dev_id) { - unsigned int irq = virt_irq_create_mapping(ist); + unsigned int irq = irq_create_mapping(NULL, ist); if (irq == NO_IRQ) return -EINVAL; - irq = irq_offset_up(irq); - return request_irq(irq, handler, irq_flags, devname, dev_id); } @@ -337,12 +335,9 @@ EXPORT_SYMBOL(ibmebus_request_irq); void ibmebus_free_irq(struct ibmebus_dev *dev, u32 ist, void *dev_id) { - unsigned int irq = virt_irq_create_mapping(ist); + unsigned int irq = irq_find_mapping(NULL, ist); - irq = irq_offset_up(irq); free_irq(irq, dev_id); - - return; } EXPORT_SYMBOL(ibmebus_free_irq); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index d491052c8e0c..4180c3998b39 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -19,7 +19,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/smp.h> diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index b45fa0e37212..01bcd52bbf8e 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -13,7 +13,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/threads.h> #include <asm/reg.h> #include <asm/page.h> diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index d85c7c938eed..30de81da7b40 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -7,7 +7,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/threads.h> #include <asm/processor.h> #include <asm/page.h> diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c new file mode 100644 index 000000000000..e98180686b35 --- /dev/null +++ b/arch/powerpc/kernel/io.c @@ -0,0 +1,131 @@ +/* + * I/O string operations + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Copyright (C) 2006 IBM Corporation + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * + * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + * + * Rewritten in C by Stephen Rothwell. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/module.h> + +#include <asm/io.h> +#include <asm/firmware.h> +#include <asm/bug.h> + +void _insb(volatile u8 __iomem *port, void *buf, long count) +{ + u8 *tbuf = buf; + u8 tmp; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + tmp = *port; + asm volatile("eieio"); + *tbuf++ = tmp; + } while (--count != 0); + asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); +} +EXPORT_SYMBOL(_insb); + +void _outsb(volatile u8 __iomem *port, const void *buf, long count) +{ + const u8 *tbuf = buf; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + *port = *tbuf++; + } while (--count != 0); + asm volatile("sync"); +} +EXPORT_SYMBOL(_outsb); + +void _insw_ns(volatile u16 __iomem *port, void *buf, long count) +{ + u16 *tbuf = buf; + u16 tmp; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + tmp = *port; + asm volatile("eieio"); + *tbuf++ = tmp; + } while (--count != 0); + asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); +} +EXPORT_SYMBOL(_insw_ns); + +void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count) +{ + const u16 *tbuf = buf; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + *port = *tbuf++; + } while (--count != 0); + asm volatile("sync"); +} +EXPORT_SYMBOL(_outsw_ns); + +void _insl_ns(volatile u32 __iomem *port, void *buf, long count) +{ + u32 *tbuf = buf; + u32 tmp; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + tmp = *port; + asm volatile("eieio"); + *tbuf++ = tmp; + } while (--count != 0); + asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); +} +EXPORT_SYMBOL(_insl_ns); + +void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count) +{ + const u32 *tbuf = buf; + + BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES)); + + if (unlikely(count <= 0)) + return; + asm volatile("sync"); + do { + *port = *tbuf++; + } while (--count != 0); + asm volatile("sync"); +} +EXPORT_SYMBOL(_outsl_ns); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 7cb77c20fc5d..ba0694071728 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -23,7 +23,6 @@ */ -#include <linux/config.h> #include <linux/init.h> #include <linux/types.h> #include <linux/slab.h> @@ -38,6 +37,7 @@ #include <asm/iommu.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/kdump.h> #define DBG(...) @@ -440,8 +440,37 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) tbl->it_largehint = tbl->it_halfpoint; spin_lock_init(&tbl->it_lock); +#ifdef CONFIG_CRASH_DUMP + if (ppc_md.tce_get) { + unsigned long index, tceval; + unsigned long tcecount = 0; + + /* + * Reserve the existing mappings left by the first kernel. + */ + for (index = 0; index < tbl->it_size; index++) { + tceval = ppc_md.tce_get(tbl, index + tbl->it_offset); + /* + * Freed TCE entry contains 0x7fffffffffffffff on JS20 + */ + if (tceval && (tceval != 0x7fffffffffffffffUL)) { + __set_bit(index, tbl->it_map); + tcecount++; + } + } + if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) { + printk(KERN_WARNING "TCE table is full; "); + printk(KERN_WARNING "freeing %d entries for the kdump boot\n", + KDUMP_MIN_TCE_ENTRIES); + for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES; + index < tbl->it_size; index++) + __clear_bit(index, tbl->it_map); + } + } +#else /* Clear the hardware table in case firmware left allocations in it */ ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); +#endif if (!welcomed) { printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 40d4c14fde8f..b4432332341f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -29,6 +29,8 @@ * to reduce code space and undefined function references. */ +#undef DEBUG + #include <linux/module.h> #include <linux/threads.h> #include <linux/kernel_stat.h> @@ -38,7 +40,6 @@ #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/timex.h> -#include <linux/config.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> @@ -47,6 +48,10 @@ #include <linux/cpumask.h> #include <linux/profile.h> #include <linux/bitops.h> +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/mutex.h> +#include <linux/bootmem.h> #include <linux/pci.h> #include <asm/uaccess.h> @@ -58,39 +63,38 @@ #include <asm/prom.h> #include <asm/ptrace.h> #include <asm/machdep.h> +#include <asm/udbg.h> #ifdef CONFIG_PPC_ISERIES #include <asm/paca.h> #endif int __irq_offset_value; -#ifdef CONFIG_PPC32 -EXPORT_SYMBOL(__irq_offset_value); -#endif - static int ppc_spurious_interrupts; #ifdef CONFIG_PPC32 -#define NR_MASK_WORDS ((NR_IRQS + 31) / 32) +EXPORT_SYMBOL(__irq_offset_value); +atomic_t ppc_n_lost_interrupts; +#ifndef CONFIG_PPC_MERGE +#define NR_MASK_WORDS ((NR_IRQS + 31) / 32) unsigned long ppc_cached_irq_mask[NR_MASK_WORDS]; -atomic_t ppc_n_lost_interrupts; +#endif #ifdef CONFIG_TAU_INT extern int tau_initialized; extern int tau_interrupts(int); #endif +#endif /* CONFIG_PPC32 */ #if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE) extern atomic_t ipi_recv; extern atomic_t ipi_sent; #endif -#endif /* CONFIG_PPC32 */ #ifdef CONFIG_PPC64 EXPORT_SYMBOL(irq_desc); int distribute_irqs = 1; -u64 ppc64_interrupt_controller; #endif /* CONFIG_PPC64 */ int show_interrupts(struct seq_file *p, void *v) @@ -120,8 +124,8 @@ int show_interrupts(struct seq_file *p, void *v) #else seq_printf(p, "%10u ", kstat_irqs(i)); #endif /* CONFIG_SMP */ - if (desc->handler) - seq_printf(p, " %s ", desc->handler->typename); + if (desc->chip) + seq_printf(p, " %s ", desc->chip->typename); else seq_puts(p, " None "); seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge "); @@ -164,13 +168,13 @@ void fixup_irqs(cpumask_t map) if (irq_desc[irq].status & IRQ_PER_CPU) continue; - cpus_and(mask, irq_affinity[irq], map); + cpus_and(mask, irq_desc[irq].affinity, map); if (any_online_cpu(mask) == NR_CPUS) { printk("Breaking affinity for irq %i\n", irq); mask = map; } - if (irq_desc[irq].handler->set_affinity) - irq_desc[irq].handler->set_affinity(irq, mask); + if (irq_desc[irq].chip->set_affinity) + irq_desc[irq].chip->set_affinity(irq, mask); else if (irq_desc[irq].action && !(warned++)) printk("Cannot set affinity for irq %i\n", irq); } @@ -183,7 +187,7 @@ void fixup_irqs(cpumask_t map) void do_IRQ(struct pt_regs *regs) { - int irq; + unsigned int irq; #ifdef CONFIG_IRQSTACKS struct thread_info *curtp, *irqtp; #endif @@ -214,22 +218,26 @@ void do_IRQ(struct pt_regs *regs) */ irq = ppc_md.get_irq(regs); - if (irq >= 0) { + if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { #ifdef CONFIG_IRQSTACKS /* Switch to the irq stack to handle this */ curtp = current_thread_info(); irqtp = hardirq_ctx[smp_processor_id()]; if (curtp != irqtp) { + struct irq_desc *desc = irq_desc + irq; + void *handler = desc->handle_irq; + if (handler == NULL) + handler = &__do_IRQ; irqtp->task = curtp->task; irqtp->flags = 0; - call___do_IRQ(irq, regs, irqtp); + call_handle_irq(irq, desc, regs, irqtp, handler); irqtp->task = NULL; if (irqtp->flags) set_bits(irqtp->flags, &curtp->flags); } else #endif - __do_IRQ(irq, regs); - } else if (irq != -2) + generic_handle_irq(irq, regs); + } else if (irq != NO_IRQ_IGNORE) /* That's not SMP safe ... but who cares ? */ ppc_spurious_interrupts++; @@ -246,196 +254,619 @@ void do_IRQ(struct pt_regs *regs) void __init init_IRQ(void) { + ppc_md.init_IRQ(); #ifdef CONFIG_PPC64 - static int once = 0; + irq_ctx_init(); +#endif +} + + +#ifdef CONFIG_IRQSTACKS +struct thread_info *softirq_ctx[NR_CPUS] __read_mostly; +struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly; + +void irq_ctx_init(void) +{ + struct thread_info *tp; + int i; + + for_each_possible_cpu(i) { + memset((void *)softirq_ctx[i], 0, THREAD_SIZE); + tp = softirq_ctx[i]; + tp->cpu = i; + tp->preempt_count = SOFTIRQ_OFFSET; + + memset((void *)hardirq_ctx[i], 0, THREAD_SIZE); + tp = hardirq_ctx[i]; + tp->cpu = i; + tp->preempt_count = HARDIRQ_OFFSET; + } +} + +static inline void do_softirq_onstack(void) +{ + struct thread_info *curtp, *irqtp; + + curtp = current_thread_info(); + irqtp = softirq_ctx[smp_processor_id()]; + irqtp->task = curtp->task; + call_do_softirq(irqtp); + irqtp->task = NULL; +} + +#else +#define do_softirq_onstack() __do_softirq() +#endif /* CONFIG_IRQSTACKS */ - if (once) +void do_softirq(void) +{ + unsigned long flags; + + if (in_interrupt()) return; - once++; + local_irq_save(flags); + + if (local_softirq_pending()) + do_softirq_onstack(); -#endif - ppc_md.init_IRQ(); -#ifdef CONFIG_PPC64 - irq_ctx_init(); -#endif + local_irq_restore(flags); } +EXPORT_SYMBOL(do_softirq); + -#ifdef CONFIG_PPC64 /* - * Virtual IRQ mapping code, used on systems with XICS interrupt controllers. + * IRQ controller and virtual interrupts */ -#define UNDEFINED_IRQ 0xffffffff -unsigned int virt_irq_to_real_map[NR_IRQS]; +#ifdef CONFIG_PPC_MERGE -/* - * Don't use virtual irqs 0, 1, 2 for devices. - * The pcnet32 driver considers interrupt numbers < 2 to be invalid, - * and 2 is the XICS IPI interrupt. - * We limit virtual irqs to __irq_offet_value less than virt_irq_max so - * that when we offset them we don't end up with an interrupt - * number >= virt_irq_max. - */ -#define MIN_VIRT_IRQ 3 +static LIST_HEAD(irq_hosts); +static spinlock_t irq_big_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_PER_CPU(unsigned int, irq_radix_reader); +static unsigned int irq_radix_writer; +struct irq_map_entry irq_map[NR_IRQS]; +static unsigned int irq_virq_count = NR_IRQS; +static struct irq_host *irq_default_host; + +struct irq_host *irq_alloc_host(unsigned int revmap_type, + unsigned int revmap_arg, + struct irq_host_ops *ops, + irq_hw_number_t inval_irq) +{ + struct irq_host *host; + unsigned int size = sizeof(struct irq_host); + unsigned int i; + unsigned int *rmap; + unsigned long flags; + + /* Allocate structure and revmap table if using linear mapping */ + if (revmap_type == IRQ_HOST_MAP_LINEAR) + size += revmap_arg * sizeof(unsigned int); + if (mem_init_done) + host = kzalloc(size, GFP_KERNEL); + else { + host = alloc_bootmem(size); + if (host) + memset(host, 0, size); + } + if (host == NULL) + return NULL; -unsigned int virt_irq_max; -static unsigned int max_virt_irq; -static unsigned int nr_virt_irqs; + /* Fill structure */ + host->revmap_type = revmap_type; + host->inval_irq = inval_irq; + host->ops = ops; -void -virt_irq_init(void) + spin_lock_irqsave(&irq_big_lock, flags); + + /* If it's a legacy controller, check for duplicates and + * mark it as allocated (we use irq 0 host pointer for that + */ + if (revmap_type == IRQ_HOST_MAP_LEGACY) { + if (irq_map[0].host != NULL) { + spin_unlock_irqrestore(&irq_big_lock, flags); + /* If we are early boot, we can't free the structure, + * too bad... + * this will be fixed once slab is made available early + * instead of the current cruft + */ + if (mem_init_done) + kfree(host); + return NULL; + } + irq_map[0].host = host; + } + + list_add(&host->link, &irq_hosts); + spin_unlock_irqrestore(&irq_big_lock, flags); + + /* Additional setups per revmap type */ + switch(revmap_type) { + case IRQ_HOST_MAP_LEGACY: + /* 0 is always the invalid number for legacy */ + host->inval_irq = 0; + /* setup us as the host for all legacy interrupts */ + for (i = 1; i < NUM_ISA_INTERRUPTS; i++) { + irq_map[i].hwirq = 0; + smp_wmb(); + irq_map[i].host = host; + smp_wmb(); + + /* Clear norequest flags */ + get_irq_desc(i)->status &= ~IRQ_NOREQUEST; + + /* Legacy flags are left to default at this point, + * one can then use irq_create_mapping() to + * explicitely change them + */ + ops->map(host, i, i); + } + break; + case IRQ_HOST_MAP_LINEAR: + rmap = (unsigned int *)(host + 1); + for (i = 0; i < revmap_arg; i++) + rmap[i] = IRQ_NONE; + host->revmap_data.linear.size = revmap_arg; + smp_wmb(); + host->revmap_data.linear.revmap = rmap; + break; + default: + break; + } + + pr_debug("irq: Allocated host of type %d @0x%p\n", revmap_type, host); + + return host; +} + +struct irq_host *irq_find_host(struct device_node *node) { - int i; + struct irq_host *h, *found = NULL; + unsigned long flags; - if ((virt_irq_max == 0) || (virt_irq_max > (NR_IRQS - 1))) - virt_irq_max = NR_IRQS - 1; - max_virt_irq = virt_irq_max - __irq_offset_value; - nr_virt_irqs = max_virt_irq - MIN_VIRT_IRQ + 1; + /* We might want to match the legacy controller last since + * it might potentially be set to match all interrupts in + * the absence of a device node. This isn't a problem so far + * yet though... + */ + spin_lock_irqsave(&irq_big_lock, flags); + list_for_each_entry(h, &irq_hosts, link) + if (h->ops->match == NULL || h->ops->match(h, node)) { + found = h; + break; + } + spin_unlock_irqrestore(&irq_big_lock, flags); + return found; +} +EXPORT_SYMBOL_GPL(irq_find_host); - for (i = 0; i < NR_IRQS; i++) - virt_irq_to_real_map[i] = UNDEFINED_IRQ; +void irq_set_default_host(struct irq_host *host) +{ + pr_debug("irq: Default host set to @0x%p\n", host); + + irq_default_host = host; } -/* Create a mapping for a real_irq if it doesn't already exist. - * Return the virtual irq as a convenience. +void irq_set_virq_count(unsigned int count) +{ + pr_debug("irq: Trying to set virq count to %d\n", count); + + BUG_ON(count < NUM_ISA_INTERRUPTS); + if (count < NR_IRQS) + irq_virq_count = count; +} + +/* radix tree not lockless safe ! we use a brlock-type mecanism + * for now, until we can use a lockless radix tree */ -int virt_irq_create_mapping(unsigned int real_irq) +static void irq_radix_wrlock(unsigned long *flags) { - unsigned int virq, first_virq; - static int warned; + unsigned int cpu, ok; - if (ppc64_interrupt_controller == IC_OPEN_PIC) - return real_irq; /* no mapping for openpic (for now) */ + spin_lock_irqsave(&irq_big_lock, *flags); + irq_radix_writer = 1; + smp_mb(); + do { + barrier(); + ok = 1; + for_each_possible_cpu(cpu) { + if (per_cpu(irq_radix_reader, cpu)) { + ok = 0; + break; + } + } + if (!ok) + cpu_relax(); + } while(!ok); +} - if (ppc64_interrupt_controller == IC_CELL_PIC) - return real_irq; /* no mapping for iic either */ +static void irq_radix_wrunlock(unsigned long flags) +{ + smp_wmb(); + irq_radix_writer = 0; + spin_unlock_irqrestore(&irq_big_lock, flags); +} - /* don't map interrupts < MIN_VIRT_IRQ */ - if (real_irq < MIN_VIRT_IRQ) { - virt_irq_to_real_map[real_irq] = real_irq; - return real_irq; +static void irq_radix_rdlock(unsigned long *flags) +{ + local_irq_save(*flags); + __get_cpu_var(irq_radix_reader) = 1; + smp_mb(); + if (likely(irq_radix_writer == 0)) + return; + __get_cpu_var(irq_radix_reader) = 0; + smp_wmb(); + spin_lock(&irq_big_lock); + __get_cpu_var(irq_radix_reader) = 1; + spin_unlock(&irq_big_lock); +} + +static void irq_radix_rdunlock(unsigned long flags) +{ + __get_cpu_var(irq_radix_reader) = 0; + local_irq_restore(flags); +} + + +unsigned int irq_create_mapping(struct irq_host *host, + irq_hw_number_t hwirq) +{ + unsigned int virq, hint; + + pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", host, hwirq); + + /* Look for default host if nececssary */ + if (host == NULL) + host = irq_default_host; + if (host == NULL) { + printk(KERN_WARNING "irq_create_mapping called for" + " NULL host, hwirq=%lx\n", hwirq); + WARN_ON(1); + return NO_IRQ; } + pr_debug("irq: -> using host @%p\n", host); - /* map to a number between MIN_VIRT_IRQ and max_virt_irq */ - virq = real_irq; - if (virq > max_virt_irq) - virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ; - - /* search for this number or a free slot */ - first_virq = virq; - while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) { - if (virt_irq_to_real_map[virq] == real_irq) - return virq; - if (++virq > max_virt_irq) - virq = MIN_VIRT_IRQ; - if (virq == first_virq) - goto nospace; /* oops, no free slots */ + /* Check if mapping already exist, if it does, call + * host->ops->map() to update the flags + */ + virq = irq_find_mapping(host, hwirq); + if (virq != IRQ_NONE) { + pr_debug("irq: -> existing mapping on virq %d\n", virq); + return virq; } - virt_irq_to_real_map[virq] = real_irq; + /* Get a virtual interrupt number */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) { + /* Handle legacy */ + virq = (unsigned int)hwirq; + if (virq == 0 || virq >= NUM_ISA_INTERRUPTS) + return NO_IRQ; + return virq; + } else { + /* Allocate a virtual interrupt number */ + hint = hwirq % irq_virq_count; + virq = irq_alloc_virt(host, 1, hint); + if (virq == NO_IRQ) { + pr_debug("irq: -> virq allocation failed\n"); + return NO_IRQ; + } + } + pr_debug("irq: -> obtained virq %d\n", virq); + + /* Clear IRQ_NOREQUEST flag */ + get_irq_desc(virq)->status &= ~IRQ_NOREQUEST; + + /* map it */ + smp_wmb(); + irq_map[virq].hwirq = hwirq; + smp_mb(); + if (host->ops->map(host, virq, hwirq)) { + pr_debug("irq: -> mapping failed, freeing\n"); + irq_free_virt(virq, 1); + return NO_IRQ; + } return virq; +} +EXPORT_SYMBOL_GPL(irq_create_mapping); - nospace: - if (!warned) { - printk(KERN_CRIT "Interrupt table is full\n"); - printk(KERN_CRIT "Increase virt_irq_max (currently %d) " - "in your kernel sources and rebuild.\n", virt_irq_max); - warned = 1; +extern unsigned int irq_create_of_mapping(struct device_node *controller, + u32 *intspec, unsigned int intsize) +{ + struct irq_host *host; + irq_hw_number_t hwirq; + unsigned int type = IRQ_TYPE_NONE; + unsigned int virq; + + if (controller == NULL) + host = irq_default_host; + else + host = irq_find_host(controller); + if (host == NULL) { + printk(KERN_WARNING "irq: no irq host found for %s !\n", + controller->full_name); + return NO_IRQ; } - return NO_IRQ; + + /* If host has no translation, then we assume interrupt line */ + if (host->ops->xlate == NULL) + hwirq = intspec[0]; + else { + if (host->ops->xlate(host, controller, intspec, intsize, + &hwirq, &type)) + return NO_IRQ; + } + + /* Create mapping */ + virq = irq_create_mapping(host, hwirq); + if (virq == NO_IRQ) + return virq; + + /* Set type if specified and different than the current one */ + if (type != IRQ_TYPE_NONE && + type != (get_irq_desc(virq)->status & IRQF_TRIGGER_MASK)) + set_irq_type(virq, type); + return virq; } +EXPORT_SYMBOL_GPL(irq_create_of_mapping); -/* - * In most cases will get a hit on the very first slot checked in the - * virt_irq_to_real_map. Only when there are a large number of - * IRQs will this be expensive. - */ -unsigned int real_irq_to_virt_slowpath(unsigned int real_irq) +unsigned int irq_of_parse_and_map(struct device_node *dev, int index) { - unsigned int virq; - unsigned int first_virq; + struct of_irq oirq; - virq = real_irq; + if (of_irq_map_one(dev, index, &oirq)) + return NO_IRQ; - if (virq > max_virt_irq) - virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ; + return irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); +} +EXPORT_SYMBOL_GPL(irq_of_parse_and_map); - first_virq = virq; +void irq_dispose_mapping(unsigned int virq) +{ + struct irq_host *host = irq_map[virq].host; + irq_hw_number_t hwirq; + unsigned long flags; - do { - if (virt_irq_to_real_map[virq] == real_irq) - return virq; + WARN_ON (host == NULL); + if (host == NULL) + return; - virq++; + /* Never unmap legacy interrupts */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) + return; - if (virq >= max_virt_irq) - virq = 0; + /* remove chip and handler */ + set_irq_chip_and_handler(virq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(virq); + + /* Tell the PIC about it */ + if (host->ops->unmap) + host->ops->unmap(host, virq); + smp_mb(); + + /* Clear reverse map */ + hwirq = irq_map[virq].hwirq; + switch(host->revmap_type) { + case IRQ_HOST_MAP_LINEAR: + if (hwirq < host->revmap_data.linear.size) + host->revmap_data.linear.revmap[hwirq] = IRQ_NONE; + break; + case IRQ_HOST_MAP_TREE: + /* Check if radix tree allocated yet */ + if (host->revmap_data.tree.gfp_mask == 0) + break; + irq_radix_wrlock(&flags); + radix_tree_delete(&host->revmap_data.tree, hwirq); + irq_radix_wrunlock(flags); + break; + } - } while (first_virq != virq); + /* Destroy map */ + smp_mb(); + irq_map[virq].hwirq = host->inval_irq; - return NO_IRQ; + /* Set some flags */ + get_irq_desc(virq)->status |= IRQ_NOREQUEST; + /* Free it */ + irq_free_virt(virq, 1); } -#endif /* CONFIG_PPC64 */ +EXPORT_SYMBOL_GPL(irq_dispose_mapping); -#ifdef CONFIG_IRQSTACKS -struct thread_info *softirq_ctx[NR_CPUS] __read_mostly; -struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly; +unsigned int irq_find_mapping(struct irq_host *host, + irq_hw_number_t hwirq) +{ + unsigned int i; + unsigned int hint = hwirq % irq_virq_count; + + /* Look for default host if nececssary */ + if (host == NULL) + host = irq_default_host; + if (host == NULL) + return NO_IRQ; + + /* legacy -> bail early */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) + return hwirq; + + /* Slow path does a linear search of the map */ + if (hint < NUM_ISA_INTERRUPTS) + hint = NUM_ISA_INTERRUPTS; + i = hint; + do { + if (irq_map[i].host == host && + irq_map[i].hwirq == hwirq) + return i; + i++; + if (i >= irq_virq_count) + i = NUM_ISA_INTERRUPTS; + } while(i != hint); + return NO_IRQ; +} +EXPORT_SYMBOL_GPL(irq_find_mapping); -void irq_ctx_init(void) + +unsigned int irq_radix_revmap(struct irq_host *host, + irq_hw_number_t hwirq) { - struct thread_info *tp; - int i; + struct radix_tree_root *tree; + struct irq_map_entry *ptr; + unsigned int virq; + unsigned long flags; - for_each_possible_cpu(i) { - memset((void *)softirq_ctx[i], 0, THREAD_SIZE); - tp = softirq_ctx[i]; - tp->cpu = i; - tp->preempt_count = SOFTIRQ_OFFSET; + WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - memset((void *)hardirq_ctx[i], 0, THREAD_SIZE); - tp = hardirq_ctx[i]; - tp->cpu = i; - tp->preempt_count = HARDIRQ_OFFSET; + /* Check if the radix tree exist yet. We test the value of + * the gfp_mask for that. Sneaky but saves another int in the + * structure. If not, we fallback to slow mode + */ + tree = &host->revmap_data.tree; + if (tree->gfp_mask == 0) + return irq_find_mapping(host, hwirq); + + /* Now try to resolve */ + irq_radix_rdlock(&flags); + ptr = radix_tree_lookup(tree, hwirq); + irq_radix_rdunlock(flags); + + /* Found it, return */ + if (ptr) { + virq = ptr - irq_map; + return virq; } + + /* If not there, try to insert it */ + virq = irq_find_mapping(host, hwirq); + if (virq != NO_IRQ) { + irq_radix_wrlock(&flags); + radix_tree_insert(tree, hwirq, &irq_map[virq]); + irq_radix_wrunlock(flags); + } + return virq; } -static inline void do_softirq_onstack(void) +unsigned int irq_linear_revmap(struct irq_host *host, + irq_hw_number_t hwirq) { - struct thread_info *curtp, *irqtp; + unsigned int *revmap; - curtp = current_thread_info(); - irqtp = softirq_ctx[smp_processor_id()]; - irqtp->task = curtp->task; - call_do_softirq(irqtp); - irqtp->task = NULL; + WARN_ON(host->revmap_type != IRQ_HOST_MAP_LINEAR); + + /* Check revmap bounds */ + if (unlikely(hwirq >= host->revmap_data.linear.size)) + return irq_find_mapping(host, hwirq); + + /* Check if revmap was allocated */ + revmap = host->revmap_data.linear.revmap; + if (unlikely(revmap == NULL)) + return irq_find_mapping(host, hwirq); + + /* Fill up revmap with slow path if no mapping found */ + if (unlikely(revmap[hwirq] == NO_IRQ)) + revmap[hwirq] = irq_find_mapping(host, hwirq); + + return revmap[hwirq]; } -#else -#define do_softirq_onstack() __do_softirq() -#endif /* CONFIG_IRQSTACKS */ +unsigned int irq_alloc_virt(struct irq_host *host, + unsigned int count, + unsigned int hint) +{ + unsigned long flags; + unsigned int i, j, found = NO_IRQ; + unsigned int limit = irq_virq_count - count; -void do_softirq(void) + if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS)) + return NO_IRQ; + + spin_lock_irqsave(&irq_big_lock, flags); + + /* Use hint for 1 interrupt if any */ + if (count == 1 && hint >= NUM_ISA_INTERRUPTS && + hint < irq_virq_count && irq_map[hint].host == NULL) { + found = hint; + goto hint_found; + } + + /* Look for count consecutive numbers in the allocatable + * (non-legacy) space + */ + for (i = NUM_ISA_INTERRUPTS; i <= limit; ) { + for (j = i; j < (i + count); j++) + if (irq_map[j].host != NULL) { + i = j + 1; + continue; + } + found = i; + break; + } + if (found == NO_IRQ) { + spin_unlock_irqrestore(&irq_big_lock, flags); + return NO_IRQ; + } + hint_found: + for (i = found; i < (found + count); i++) { + irq_map[i].hwirq = host->inval_irq; + smp_wmb(); + irq_map[i].host = host; + } + spin_unlock_irqrestore(&irq_big_lock, flags); + return found; +} + +void irq_free_virt(unsigned int virq, unsigned int count) { unsigned long flags; + unsigned int i; - if (in_interrupt()) - return; + WARN_ON (virq < NUM_ISA_INTERRUPTS); + WARN_ON (count == 0 || (virq + count) > irq_virq_count); - local_irq_save(flags); + spin_lock_irqsave(&irq_big_lock, flags); + for (i = virq; i < (virq + count); i++) { + struct irq_host *host; - if (local_softirq_pending()) { - account_system_vtime(current); - local_bh_disable(); - do_softirq_onstack(); - account_system_vtime(current); - __local_bh_enable(); + if (i < NUM_ISA_INTERRUPTS || + (virq + count) > irq_virq_count) + continue; + + host = irq_map[i].host; + irq_map[i].hwirq = host->inval_irq; + smp_wmb(); + irq_map[i].host = NULL; } + spin_unlock_irqrestore(&irq_big_lock, flags); +} - local_irq_restore(flags); +void irq_early_init(void) +{ + unsigned int i; + + for (i = 0; i < NR_IRQS; i++) + get_irq_desc(i)->status |= IRQ_NOREQUEST; } -EXPORT_SYMBOL(do_softirq); + +/* We need to create the radix trees late */ +static int irq_late_init(void) +{ + struct irq_host *h; + unsigned long flags; + + irq_radix_wrlock(&flags); + list_for_each_entry(h, &irq_hosts, link) { + if (h->revmap_type == IRQ_HOST_MAP_TREE) + INIT_RADIX_TREE(&h->revmap_data.tree, GFP_ATOMIC); + } + irq_radix_wrunlock(flags); + + return 0; +} +arch_initcall(irq_late_init); + +#endif /* CONFIG_PPC_MERGE */ #ifdef CONFIG_PCI_MSI int pci_enable_msi(struct pci_dev * pdev) @@ -445,12 +876,14 @@ int pci_enable_msi(struct pci_dev * pdev) else return -1; } +EXPORT_SYMBOL(pci_enable_msi); void pci_disable_msi(struct pci_dev * pdev) { if (ppc_md.disable_msi) ppc_md.disable_msi(pdev); } +EXPORT_SYMBOL(pci_disable_msi); void pci_scan_msi_device(struct pci_dev *dev) {} int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) {return -1;} @@ -458,6 +891,8 @@ void pci_disable_msix(struct pci_dev *dev) {} void msi_remove_pci_irq_vectors(struct pci_dev *dev) {} void disable_msi_mode(struct pci_dev *dev, int pos, int type) {} void pci_no_msi(void) {} +EXPORT_SYMBOL(pci_enable_msix); +EXPORT_SYMBOL(pci_disable_msix); #endif diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index f78866367b70..cd65c367b8b6 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -26,7 +26,6 @@ * for PPC64 */ -#include <linux/config.h> #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/preempt.h> @@ -62,6 +61,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (!ret) { memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; + flush_icache_range((unsigned long)p->ainsn.insn, + (unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t)); } return ret; diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index d7f4e982b539..858f28ac8a06 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -40,7 +40,6 @@ Author: Terry Greeniaus (tgree@phys.ualberta.ca) Please e-mail updates to this file to me, thanks! */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 6e67b5b49ba1..5e6ddfa474c0 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/serial.h> #include <linux/serial_8250.h> @@ -29,6 +28,7 @@ static struct legacy_serial_info { struct device_node *np; unsigned int speed; unsigned int clock; + int irq_check_parent; phys_addr_t taddr; } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS]; static unsigned int legacy_serial_count; @@ -37,18 +37,19 @@ static int legacy_serial_console = -1; static int __init add_legacy_port(struct device_node *np, int want_index, int iotype, phys_addr_t base, phys_addr_t taddr, unsigned long irq, - upf_t flags) + upf_t flags, int irq_check_parent) { - u32 *clk, *spd, clock = BASE_BAUD * 16; + const u32 *clk, *spd; + u32 clock = BASE_BAUD * 16; int index; /* get clock freq. if present */ - clk = (u32 *)get_property(np, "clock-frequency", NULL); + clk = get_property(np, "clock-frequency", NULL); if (clk && *clk) clock = *clk; /* get default speed if present */ - spd = (u32 *)get_property(np, "current-speed", NULL); + spd = get_property(np, "current-speed", NULL); /* If we have a location index, then try to use it */ if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS) @@ -69,7 +70,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, if (legacy_serial_infos[index].np != 0) { /* if we still have some room, move it, else override */ if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) { - printk(KERN_INFO "Moved legacy port %d -> %d\n", + printk(KERN_DEBUG "Moved legacy port %d -> %d\n", index, legacy_serial_count); legacy_serial_ports[legacy_serial_count] = legacy_serial_ports[index]; @@ -77,7 +78,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_infos[index]; legacy_serial_count++; } else { - printk(KERN_INFO "Replacing legacy port %d\n", index); + printk(KERN_DEBUG "Replacing legacy port %d\n", index); } } @@ -96,10 +97,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_infos[index].np = of_node_get(np); legacy_serial_infos[index].clock = clock; legacy_serial_infos[index].speed = spd ? *spd : 0; + legacy_serial_infos[index].irq_check_parent = irq_check_parent; - printk(KERN_INFO "Found legacy serial port %d for %s\n", + printk(KERN_DEBUG "Found legacy serial port %d for %s\n", index, np->full_name); - printk(KERN_INFO " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", + printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", (iotype == UPIO_PORT) ? "port" : "mem", (unsigned long long)base, (unsigned long long)taddr, irq, legacy_serial_ports[index].uartclk, @@ -111,9 +113,10 @@ static int __init add_legacy_port(struct device_node *np, int want_index, static int __init add_legacy_soc_port(struct device_node *np, struct device_node *soc_dev) { - phys_addr_t addr; - u32 *addrp; + u64 addr; + const u32 *addrp; upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ; + struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly * encoded in the device-tree. @@ -127,23 +130,30 @@ static int __init add_legacy_soc_port(struct device_node *np, return -1; addr = of_translate_address(soc_dev, addrp); + if (addr == OF_BAD_ADDR) + return -1; /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags); + if (tsi && !strcmp(tsi->type, "tsi-bridge")) + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + else + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, struct device_node *isa_brg) { - u32 *reg; - char *typep; + const u32 *reg; + const char *typep; int index = -1; - phys_addr_t taddr; + u64 taddr; + + DBG(" -> add_legacy_isa_port(%s)\n", np->full_name); /* Get the ISA port number */ - reg = (u32 *)get_property(np, "reg", NULL); + reg = get_property(np, "reg", NULL); if (reg == NULL) return -1; @@ -154,17 +164,23 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Now look for an "ibm,aix-loc" property that gives us ordering * if any... */ - typep = (char *)get_property(np, "ibm,aix-loc", NULL); + typep = get_property(np, "ibm,aix-loc", NULL); /* If we have a location index, then use it */ if (typep && *typep == 'S') index = simple_strtol(typep+1, NULL, 0) - 1; - /* Translate ISA address */ + /* Translate ISA address. If it fails, we still register the port + * with no translated address so that it can be picked up as an IO + * port later by the serial driver + */ taddr = of_translate_address(np, reg); + if (taddr == OF_BAD_ADDR) + taddr = 0; /* Add port, irq will be dealt with later */ - return add_legacy_port(np, index, UPIO_PORT, reg[1], taddr, NO_IRQ, UPF_BOOT_AUTOCONF); + return add_legacy_port(np, index, UPIO_PORT, reg[1], taddr, + NO_IRQ, UPF_BOOT_AUTOCONF, 0); } @@ -172,11 +188,13 @@ static int __init add_legacy_isa_port(struct device_node *np, static int __init add_legacy_pci_port(struct device_node *np, struct device_node *pci_dev) { - phys_addr_t addr, base; - u32 *addrp; + u64 addr, base; + const u32 *addrp; unsigned int flags; int iotype, index = -1, lindex = 0; + DBG(" -> add_legacy_pci_port(%s)\n", np->full_name); + /* We only support ports that have a clock frequency properly * encoded in the device-tree (that is have an fcode). Anything * else can't be used that early and will be normally probed by @@ -195,6 +213,8 @@ static int __init add_legacy_pci_port(struct device_node *np, /* We only support BAR 0 for now */ iotype = (flags & IORESOURCE_MEM) ? UPIO_MEM : UPIO_PORT; addr = of_translate_address(pci_dev, addrp); + if (addr == OF_BAD_ADDR) + return -1; /* Set the IO base to the same as the translated address for MMIO, * or to the domain local IO base for PIO (it will be fixed up later) @@ -208,7 +228,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * we get to their "reg" property */ if (np != pci_dev) { - u32 *reg = (u32 *)get_property(np, "reg", NULL); + const u32 *reg = get_property(np, "reg", NULL); if (reg && (*reg < 4)) index = lindex = *reg; } @@ -232,7 +252,8 @@ static int __init add_legacy_pci_port(struct device_node *np, /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, UPF_BOOT_AUTOCONF); + return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, + UPF_BOOT_AUTOCONF, np != pci_dev); } #endif @@ -265,13 +286,13 @@ static void __init setup_legacy_serial_console(int console) void __init find_legacy_serial_ports(void) { struct device_node *np, *stdout = NULL; - char *path; + const char *path; int index; DBG(" -> find_legacy_serial_port()\n"); /* Now find out if one of these is out firmware console */ - path = (char *)get_property(of_chosen, "linux,stdout-path", NULL); + path = get_property(of_chosen, "linux,stdout-path", NULL); if (path != NULL) { stdout = of_find_node_by_path(path); if (stdout) @@ -302,6 +323,17 @@ void __init find_legacy_serial_ports(void) of_node_put(isa); } + /* First fill our array with tsi-bridge ports */ + for (np = NULL; (np = of_find_compatible_node(np, "serial", "ns16550")) != NULL;) { + struct device_node *tsi = of_get_parent(np); + if (tsi && !strcmp(tsi->type, "tsi-bridge")) { + index = add_legacy_soc_port(np, np); + if (index >= 0 && np == stdout) + legacy_serial_console = index; + } + of_node_put(tsi); + } + #ifdef CONFIG_PCI /* Next, try to locate PCI ports */ for (np = NULL; (np = of_find_all_nodes(np));) { @@ -352,27 +384,22 @@ static void __init fixup_port_irq(int index, struct device_node *np, struct plat_serial8250_port *port) { + unsigned int virq; + DBG("fixup_port_irq(%d)\n", index); - /* Check for interrupts in that node */ - if (np->n_intrs > 0) { - port->irq = np->intrs[0].line; - DBG(" port %d (%s), irq=%d\n", - index, np->full_name, port->irq); - return; + virq = irq_of_parse_and_map(np, 0); + if (virq == NO_IRQ && legacy_serial_infos[index].irq_check_parent) { + np = of_get_parent(np); + if (np == NULL) + return; + virq = irq_of_parse_and_map(np, 0); + of_node_put(np); } - - /* Check for interrupts in the parent */ - np = of_get_parent(np); - if (np == NULL) + if (virq == NO_IRQ) return; - if (np->n_intrs > 0) { - port->irq = np->intrs[0].line; - DBG(" port %d (%s), irq=%d\n", - index, np->full_name, port->irq); - } - of_node_put(np); + port->irq = virq; } static void __init fixup_port_pio(int index, @@ -442,7 +469,7 @@ static int __init serial_dev_init(void) fixup_port_irq(i, np, port); if (port->iotype == UPIO_PORT) fixup_port_pio(i, np, port); - if (port->iotype == UPIO_MEM) + if ((port->iotype == UPIO_MEM) || (port->iotype == UPIO_TSI)) fixup_port_mmio(i, np, port); } @@ -465,8 +492,8 @@ static int __init check_legacy_serial_console(void) { struct device_node *prom_stdout = NULL; int speed = 0, offset = 0; - char *name; - u32 *spd; + const char *name; + const u32 *spd; DBG(" -> check_legacy_serial_console()\n"); @@ -487,7 +514,7 @@ static int __init check_legacy_serial_console(void) } /* We are getting a weird phandle from OF ... */ /* ... So use the full path instead */ - name = (char *)get_property(of_chosen, "linux,stdout-path", NULL); + name = get_property(of_chosen, "linux,stdout-path", NULL); if (name == NULL) { DBG(" no linux,stdout-path !\n"); return -ENODEV; @@ -499,12 +526,12 @@ static int __init check_legacy_serial_console(void) } DBG("stdout is %s\n", prom_stdout->full_name); - name = (char *)get_property(prom_stdout, "name", NULL); + name = get_property(prom_stdout, "name", NULL); if (!name) { DBG(" stdout package has no name !\n"); goto not_found; } - spd = (u32 *)get_property(prom_stdout, "current-speed", NULL); + spd = get_property(prom_stdout, "current-speed", NULL); if (spd) speed = *spd; diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index c02deaab26c7..41c05dcd68f4 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -18,7 +18,6 @@ * keyword - value pairs that specify the configuration of the partition. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/types.h> #include <linux/errno.h> @@ -33,7 +32,6 @@ #include <asm/rtas.h> #include <asm/system.h> #include <asm/time.h> -#include <asm/iseries/it_exp_vpd_panel.h> #include <asm/prom.h> #include <asm/vdso_datapage.h> @@ -45,11 +43,9 @@ static struct proc_dir_entry *proc_ppc64_lparcfg; #define LPARCFG_BUFF_SIZE 4096 -#ifdef CONFIG_PPC_ISERIES - /* - * For iSeries legacy systems, the PPA purr function is available from the - * emulated_time_base field in the paca. + * Track sum of all purrs across all processors. This is used to further + * calculate usage values by different applications */ static unsigned long get_purr(void) { @@ -57,48 +53,31 @@ static unsigned long get_purr(void) int cpu; for_each_possible_cpu(cpu) { - sum_purr += lppaca[cpu].emulated_time_base; + if (firmware_has_feature(FW_FEATURE_ISERIES)) + sum_purr += lppaca[cpu].emulated_time_base; + else { + struct cpu_usage *cu; -#ifdef PURR_DEBUG - printk(KERN_INFO "get_purr for cpu (%d) has value (%ld) \n", - cpu, lppaca[cpu].emulated_time_base); -#endif + cu = &per_cpu(cpu_usage_array, cpu); + sum_purr += cu->current_tb; + } } return sum_purr; } -#define lparcfg_write NULL +#ifdef CONFIG_PPC_ISERIES /* * Methods used to fetch LPAR data when running on an iSeries platform. */ -static int lparcfg_data(struct seq_file *m, void *v) +static int iseries_lparcfg_data(struct seq_file *m, void *v) { - unsigned long pool_id, lp_index; + unsigned long pool_id; int shared, entitled_capacity, max_entitled_capacity; int processors, max_processors; unsigned long purr = get_purr(); - seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); - shared = (int)(get_lppaca()->shared_proc); - seq_printf(m, "serial_number=%c%c%c%c%c%c%c\n", - e2a(xItExtVpdPanel.mfgID[2]), - e2a(xItExtVpdPanel.mfgID[3]), - e2a(xItExtVpdPanel.systemSerial[1]), - e2a(xItExtVpdPanel.systemSerial[2]), - e2a(xItExtVpdPanel.systemSerial[3]), - e2a(xItExtVpdPanel.systemSerial[4]), - e2a(xItExtVpdPanel.systemSerial[5])); - - seq_printf(m, "system_type=%c%c%c%c\n", - e2a(xItExtVpdPanel.machineType[0]), - e2a(xItExtVpdPanel.machineType[1]), - e2a(xItExtVpdPanel.machineType[2]), - e2a(xItExtVpdPanel.machineType[3])); - - lp_index = HvLpConfig_getLpIndex(); - seq_printf(m, "partition_id=%d\n", (int)lp_index); seq_printf(m, "system_active_processors=%d\n", (int)HvLpConfig_getSystemPhysicalProcessors()); @@ -137,6 +116,14 @@ static int lparcfg_data(struct seq_file *m, void *v) return 0; } + +#else /* CONFIG_PPC_ISERIES */ + +static int iseries_lparcfg_data(struct seq_file *m, void *v) +{ + return 0; +} + #endif /* CONFIG_PPC_ISERIES */ #ifdef CONFIG_PPC_PSERIES @@ -195,8 +182,14 @@ static unsigned int h_get_ppp(unsigned long *entitled, unsigned long *resource) { unsigned long rc; - rc = plpar_hcall_4out(H_GET_PPP, 0, 0, 0, 0, entitled, unallocated, - aggregation, resource); + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + rc = plpar_hcall(H_GET_PPP, retbuf); + + *entitled = retbuf[0]; + *unallocated = retbuf[1]; + *aggregation = retbuf[2]; + *resource = retbuf[3]; log_plpar_hcall_return(rc, "H_GET_PPP"); @@ -206,27 +199,15 @@ static unsigned int h_get_ppp(unsigned long *entitled, static void h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) { unsigned long rc; - unsigned long dummy; - rc = plpar_hcall(H_PIC, 0, 0, 0, 0, pool_idle_time, num_procs, &dummy); + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - if (rc != H_AUTHORITY) - log_plpar_hcall_return(rc, "H_PIC"); -} + rc = plpar_hcall(H_PIC, retbuf); -/* Track sum of all purrs across all processors. This is used to further */ -/* calculate usage values by different applications */ + *pool_idle_time = retbuf[0]; + *num_procs = retbuf[1]; -static unsigned long get_purr(void) -{ - unsigned long sum_purr = 0; - int cpu; - struct cpu_usage *cu; - - for_each_possible_cpu(cpu) { - cu = &per_cpu(cpu_usage_array, cpu); - sum_purr += cu->current_tb; - } - return sum_purr; + if (rc != H_AUTHORITY) + log_plpar_hcall_return(rc, "H_PIC"); } #define SPLPAR_CHARACTERISTICS_TOKEN 20 @@ -333,39 +314,16 @@ static int lparcfg_count_active_processors(void) return count; } -static int lparcfg_data(struct seq_file *m, void *v) +static int pseries_lparcfg_data(struct seq_file *m, void *v) { int partition_potential_processors; int partition_active_processors; - struct device_node *rootdn; - const char *model = ""; - const char *system_id = ""; - unsigned int *lp_index_ptr, lp_index = 0; struct device_node *rtas_node; - int *lrdrp = NULL; - - rootdn = find_path_device("/"); - if (rootdn) { - model = get_property(rootdn, "model", NULL); - system_id = get_property(rootdn, "system-id", NULL); - lp_index_ptr = (unsigned int *) - get_property(rootdn, "ibm,partition-no", NULL); - if (lp_index_ptr) - lp_index = *lp_index_ptr; - } - - seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); - - seq_printf(m, "serial_number=%s\n", system_id); - - seq_printf(m, "system_type=%s\n", model); - - seq_printf(m, "partition_id=%d\n", (int)lp_index); + const int *lrdrp = NULL; rtas_node = find_path_device("/rtas"); if (rtas_node) - lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity", - NULL); + lrdrp = get_property(rtas_node, "ibm,lrdr-capacity", NULL); if (lrdrp == NULL) { partition_potential_processors = vdso_data->processorCount; @@ -549,8 +507,61 @@ out: return retval; } +#else /* CONFIG_PPC_PSERIES */ + +static int pseries_lparcfg_data(struct seq_file *m, void *v) +{ + return 0; +} + +static ssize_t lparcfg_write(struct file *file, const char __user * buf, + size_t count, loff_t * off) +{ + return count; +} + #endif /* CONFIG_PPC_PSERIES */ +static int lparcfg_data(struct seq_file *m, void *v) +{ + struct device_node *rootdn; + const char *model = ""; + const char *system_id = ""; + const char *tmp; + const unsigned int *lp_index_ptr; + unsigned int lp_index = 0; + + seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); + + rootdn = find_path_device("/"); + if (rootdn) { + tmp = get_property(rootdn, "model", NULL); + if (tmp) { + model = tmp; + /* Skip "IBM," - see platforms/iseries/dt.c */ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + model += 4; + } + tmp = get_property(rootdn, "system-id", NULL); + if (tmp) { + system_id = tmp; + /* Skip "IBM," - see platforms/iseries/dt.c */ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + system_id += 4; + } + lp_index_ptr = get_property(rootdn, "ibm,partition-no", NULL); + if (lp_index_ptr) + lp_index = *lp_index_ptr; + } + seq_printf(m, "serial_number=%s\n", system_id); + seq_printf(m, "system_type=%s\n", model); + seq_printf(m, "partition_id=%d\n", (int)lp_index); + + if (firmware_has_feature(FW_FEATURE_ISERIES)) + return iseries_lparcfg_data(m, v); + return pseries_lparcfg_data(m, v); +} + static int lparcfg_open(struct inode *inode, struct file *file) { return single_open(file, lparcfg_data, NULL); @@ -569,7 +580,8 @@ int __init lparcfg_init(void) mode_t mode = S_IRUSR | S_IRGRP | S_IROTH; /* Allow writing if we have FW_FEATURE_SPLPAR */ - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + if (firmware_has_feature(FW_FEATURE_SPLPAR) && + !firmware_has_feature(FW_FEATURE_ISERIES)) { lparcfg_fops.write = lparcfg_write; mode |= S_IWUSR; } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index a81ca1b841ec..e60a0c544d63 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/threads.h> #include <asm/machdep.h> +#include <asm/lmb.h> void machine_crash_shutdown(struct pt_regs *regs) { @@ -59,3 +60,58 @@ NORET_TYPE void machine_kexec(struct kimage *image) } for(;;); } + +static int __init early_parse_crashk(char *p) +{ + unsigned long size; + + if (!p) + return 1; + + size = memparse(p, &p); + + if (*p == '@') + crashk_res.start = memparse(p + 1, &p); + else + crashk_res.start = KDUMP_KERNELBASE; + + crashk_res.end = crashk_res.start + size - 1; + + return 0; +} +early_param("crashkernel", early_parse_crashk); + +void __init reserve_crashkernel(void) +{ + unsigned long size; + + if (crashk_res.start == 0) + return; + + /* We might have got these values via the command line or the + * device tree, either way sanitise them now. */ + + size = crashk_res.end - crashk_res.start + 1; + + if (crashk_res.start != KDUMP_KERNELBASE) + printk("Crash kernel location must be 0x%x\n", + KDUMP_KERNELBASE); + + crashk_res.start = KDUMP_KERNELBASE; + size = PAGE_ALIGN(size); + crashk_res.end = crashk_res.start + size - 1; + + /* Crash kernel trumps memory limit */ + if (memory_limit && memory_limit <= crashk_res.end) { + memory_limit = crashk_res.end + 1; + printk("Adjusted memory limit for crashkernel, now 0x%lx\n", + memory_limit); + } + + lmb_reserve(crashk_res.start, size); +} + +int overlaps_crashkernel(unsigned long start, unsigned long size) +{ + return (start + size) > crashk_res.start && start <= crashk_res.end; +} diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c index 443606134dff..cbaa34196797 100644 --- a/arch/powerpc/kernel/machine_kexec_32.c +++ b/arch/powerpc/kernel/machine_kexec_32.c @@ -30,8 +30,8 @@ typedef NORET_TYPE void (*relocate_new_kernel_t)( */ void default_machine_kexec(struct kimage *image) { - const extern unsigned char relocate_new_kernel[]; - const extern unsigned int relocate_new_kernel_size; + extern const unsigned char relocate_new_kernel[]; + extern const unsigned int relocate_new_kernel_size; unsigned long page_list; unsigned long reboot_code_buffer, reboot_code_buffer_phys; relocate_new_kernel_t rnk; diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index a8fa04ef27cd..a24b09c27718 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -10,7 +10,6 @@ */ -#include <linux/cpumask.h> #include <linux/kexec.h> #include <linux/smp.h> #include <linux/thread_info.h> @@ -21,7 +20,6 @@ #include <asm/machdep.h> #include <asm/cacheflush.h> #include <asm/paca.h> -#include <asm/lmb.h> #include <asm/mmu.h> #include <asm/sections.h> /* _end */ #include <asm/prom.h> @@ -33,8 +31,8 @@ int default_machine_kexec_prepare(struct kimage *image) unsigned long begin, end; /* limits of segment */ unsigned long low, high; /* limits of blocked memory range */ struct device_node *node; - unsigned long *basep; - unsigned int *sizep; + const unsigned long *basep; + const unsigned int *sizep; if (!ppc_md.hpte_clear_all) return -ENOENT; @@ -74,10 +72,8 @@ int default_machine_kexec_prepare(struct kimage *image) /* We also should not overwrite the tce tables */ for (node = of_find_node_by_type(NULL, "pci"); node != NULL; node = of_find_node_by_type(node, "pci")) { - basep = (unsigned long *)get_property(node, "linux,tce-base", - NULL); - sizep = (unsigned int *)get_property(node, "linux,tce-size", - NULL); + basep = get_property(node, "linux,tce-base", NULL); + sizep = get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) continue; @@ -378,63 +374,10 @@ static void __init export_crashk_values(void) of_node_put(node); } -void __init kexec_setup(void) +static int __init kexec_setup(void) { export_htab_values(); export_crashk_values(); -} - -static int __init early_parse_crashk(char *p) -{ - unsigned long size; - - if (!p) - return 1; - - size = memparse(p, &p); - - if (*p == '@') - crashk_res.start = memparse(p + 1, &p); - else - crashk_res.start = KDUMP_KERNELBASE; - - crashk_res.end = crashk_res.start + size - 1; - return 0; } -early_param("crashkernel", early_parse_crashk); - -void __init reserve_crashkernel(void) -{ - unsigned long size; - - if (crashk_res.start == 0) - return; - - /* We might have got these values via the command line or the - * device tree, either way sanitise them now. */ - - size = crashk_res.end - crashk_res.start + 1; - - if (crashk_res.start != KDUMP_KERNELBASE) - printk("Crash kernel location must be 0x%x\n", - KDUMP_KERNELBASE); - - crashk_res.start = KDUMP_KERNELBASE; - size = PAGE_ALIGN(size); - crashk_res.end = crashk_res.start + size - 1; - - /* Crash kernel trumps memory limit */ - if (memory_limit && memory_limit <= crashk_res.end) { - memory_limit = crashk_res.end + 1; - printk("Adjusted memory limit for crashkernel, now 0x%lx\n", - memory_limit); - } - - lmb_reserve(crashk_res.start, size); -} - -int overlaps_crashkernel(unsigned long start, unsigned long size) -{ - return (start + size) > crashk_res.start && start <= crashk_res.end; -} +__initcall(kexec_setup); diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S new file mode 100644 index 000000000000..330c9dc7db86 --- /dev/null +++ b/arch/powerpc/kernel/misc.S @@ -0,0 +1,45 @@ +/* + * This file contains miscellaneous low-level functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * + * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <asm/ppc_asm.h> + + .text + +/* + * Returns (address we are running at) - (address we were linked at) + * for use before the text and data are mapped to KERNELBASE. + */ + +_GLOBAL(reloc_offset) + mflr r0 + bl 1f +1: mflr r3 + LOAD_REG_IMMEDIATE(r4,1b) + subf r3,r4,r3 + mtlr r0 + blr + +/* + * add_reloc_offset(x) returns x + reloc_offset(). + */ +_GLOBAL(add_reloc_offset) + mflr r0 + bl 1f +1: mflr r5 + LOAD_REG_IMMEDIATE(r4,1b) + subf r5,r4,r5 + add r3,r3,r5 + mtlr r0 + blr diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 01d3916c4cb1..58758d883361 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -16,7 +16,6 @@ * */ -#include <linux/config.h> #include <linux/sys.h> #include <asm/unistd.h> #include <asm/errno.h> @@ -61,32 +60,6 @@ _GLOBAL(mulhdu) blr /* - * Returns (address we're running at) - (address we were linked at) - * for use before the text and data are mapped to KERNELBASE. - */ -_GLOBAL(reloc_offset) - mflr r0 - bl 1f -1: mflr r3 - LOAD_REG_IMMEDIATE(r4,1b) - subf r3,r4,r3 - mtlr r0 - blr - -/* - * add_reloc_offset(x) returns x + reloc_offset(). - */ -_GLOBAL(add_reloc_offset) - mflr r0 - bl 1f -1: mflr r5 - LOAD_REG_IMMEDIATE(r4,1b) - subf r5,r4,r5 - add r3,r3,r5 - mtlr r0 - blr - -/* * sub_reloc_offset(x) returns x - reloc_offset(). */ _GLOBAL(sub_reloc_offset) @@ -781,136 +754,6 @@ _GLOBAL(atomic_set_mask) blr /* - * I/O string operations - * - * insb(port, buf, len) - * outsb(port, buf, len) - * insw(port, buf, len) - * outsw(port, buf, len) - * insl(port, buf, len) - * outsl(port, buf, len) - * insw_ns(port, buf, len) - * outsw_ns(port, buf, len) - * insl_ns(port, buf, len) - * outsl_ns(port, buf, len) - * - * The *_ns versions don't do byte-swapping. - */ -_GLOBAL(_insb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbz r5,0(r3) - eieio - stbu r5,1(r4) - bdnz 00b - blr - -_GLOBAL(_outsb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbzu r5,1(r4) - stb r5,0(r3) - eieio - bdnz 00b - blr - -_GLOBAL(_insw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhbrx r5,0,r3 - eieio - sthu r5,2(r4) - bdnz 00b - blr - -_GLOBAL(_outsw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - eieio - sthbrx r5,0,r3 - bdnz 00b - blr - -_GLOBAL(_insl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwbrx r5,0,r3 - eieio - stwu r5,4(r4) - bdnz 00b - blr - -_GLOBAL(_outsl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stwbrx r5,0,r3 - eieio - bdnz 00b - blr - -_GLOBAL(__ide_mm_insw) -_GLOBAL(_insw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhz r5,0(r3) - eieio - sthu r5,2(r4) - bdnz 00b - blr - -_GLOBAL(__ide_mm_outsw) -_GLOBAL(_outsw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - sth r5,0(r3) - eieio - bdnz 00b - blr - -_GLOBAL(__ide_mm_insl) -_GLOBAL(_insl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwz r5,0(r3) - eieio - stwu r5,4(r4) - bdnz 00b - blr - -_GLOBAL(__ide_mm_outsl) -_GLOBAL(_outsl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stw r5,0(r3) - eieio - bdnz 00b - blr - -/* * Extended precision shifts. * * Updated to be valid for shift counts from 0 to 63 inclusive. diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e8883d42c43c..e3ed21cd3d94 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -1,14 +1,12 @@ /* - * arch/powerpc/kernel/misc64.S - * * This file contains miscellaneous low-level functions. * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) * * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) * and Paul Mackerras. * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) - * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) - * + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -16,7 +14,6 @@ * */ -#include <linux/config.h> #include <linux/sys.h> #include <asm/unistd.h> #include <asm/errno.h> @@ -30,41 +27,10 @@ .text -/* - * Returns (address we are running at) - (address we were linked at) - * for use before the text and data are mapped to KERNELBASE. - */ - -_GLOBAL(reloc_offset) - mflr r0 - bl 1f -1: mflr r3 - LOAD_REG_IMMEDIATE(r4,1b) - subf r3,r4,r3 - mtlr r0 - blr - -/* - * add_reloc_offset(x) returns x + reloc_offset(). - */ -_GLOBAL(add_reloc_offset) - mflr r0 - bl 1f -1: mflr r5 - LOAD_REG_IMMEDIATE(r4,1b) - subf r5,r4,r5 - add r3,r3,r5 - mtlr r0 - blr - _GLOBAL(get_msr) mfmsr r3 blr -_GLOBAL(get_dar) - mfdar r3 - blr - _GLOBAL(get_srr0) mfsrr0 r3 blr @@ -72,10 +38,6 @@ _GLOBAL(get_srr0) _GLOBAL(get_srr1) mfsrr1 r3 blr - -_GLOBAL(get_sp) - mr r3,r1 - blr #ifdef CONFIG_IRQSTACKS _GLOBAL(call_do_softirq) @@ -89,60 +51,20 @@ _GLOBAL(call_do_softirq) mtlr r0 blr -_GLOBAL(call___do_IRQ) +_GLOBAL(call_handle_irq) + ld r8,0(r7) mflr r0 std r0,16(r1) - stdu r1,THREAD_SIZE-112(r5) - mr r1,r5 - bl .__do_IRQ + mtctr r8 + stdu r1,THREAD_SIZE-112(r6) + mr r1,r6 + bctrl ld r1,0(r1) ld r0,16(r1) mtlr r0 blr #endif /* CONFIG_IRQSTACKS */ - /* - * To be called by C code which needs to do some operations with MMU - * disabled. Note that interrupts have to be disabled by the caller - * prior to calling us. The code called _MUST_ be in the RMO of course - * and part of the linear mapping as we don't attempt to translate the - * stack pointer at all. The function is called with the stack switched - * to this CPU emergency stack - * - * prototype is void *call_with_mmu_off(void *func, void *data); - * - * the called function is expected to be of the form - * - * void *called(void *data); - */ -_GLOBAL(call_with_mmu_off) - mflr r0 /* get link, save it on stackframe */ - std r0,16(r1) - mr r1,r5 /* save old stack ptr */ - ld r1,PACAEMERGSP(r13) /* get emerg. stack */ - subi r1,r1,STACK_FRAME_OVERHEAD - std r0,16(r1) /* save link on emerg. stack */ - std r5,0(r1) /* save old stack ptr in backchain */ - ld r3,0(r3) /* get to real function ptr (assume same TOC) */ - bl 2f /* we need LR to return, continue at label 2 */ - - ld r0,16(r1) /* we return here from the call, get LR and */ - ld r1,0(r1) /* .. old stack ptr */ - mtspr SPRN_SRR0,r0 /* and get back to virtual mode with these */ - mfmsr r4 - ori r4,r4,MSR_IR|MSR_DR - mtspr SPRN_SRR1,r4 - rfid - -2: mtspr SPRN_SRR0,r3 /* coming from above, enter real mode */ - mr r3,r4 /* get parameter */ - mfmsr r0 - ori r0,r0,MSR_IR|MSR_DR - xori r0,r0,MSR_IR|MSR_DR - mtspr SPRN_SRR1,r0 - rfid - - .section ".toc","aw" PPC64_CACHES: .tc ppc64_caches[TC],ppc64_caches @@ -323,144 +245,6 @@ _GLOBAL(__flush_dcache_icache) bdnz 1b isync blr - -/* - * I/O string operations - * - * insb(port, buf, len) - * outsb(port, buf, len) - * insw(port, buf, len) - * outsw(port, buf, len) - * insl(port, buf, len) - * outsl(port, buf, len) - * insw_ns(port, buf, len) - * outsw_ns(port, buf, len) - * insl_ns(port, buf, len) - * outsl_ns(port, buf, len) - * - * The *_ns versions don't do byte-swapping. - */ -_GLOBAL(_insb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbz r5,0(r3) - eieio - stbu r5,1(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsb) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,1 - blelr- -00: lbzu r5,1(r4) - stb r5,0(r3) - bdnz 00b - sync - blr - -_GLOBAL(_insw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhbrx r5,0,r3 - eieio - sthu r5,2(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsw) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - sthbrx r5,0,r3 - bdnz 00b - sync - blr - -_GLOBAL(_insl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwbrx r5,0,r3 - eieio - stwu r5,4(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsl) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stwbrx r5,0,r3 - bdnz 00b - sync - blr - -/* _GLOBAL(ide_insw) now in drivers/ide/ide-iops.c */ -_GLOBAL(_insw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhz r5,0(r3) - eieio - sthu r5,2(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -/* _GLOBAL(ide_outsw) now in drivers/ide/ide-iops.c */ -_GLOBAL(_outsw_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,2 - blelr- -00: lhzu r5,2(r4) - sth r5,0(r3) - bdnz 00b - sync - blr - -_GLOBAL(_insl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwz r5,0(r3) - eieio - stwu r5,4(r4) - bdnz 00b - twi 0,r5,0 - isync - blr - -_GLOBAL(_outsl_ns) - cmpwi 0,r5,0 - mtctr r5 - subi r4,r4,4 - blelr- -00: lwzu r5,4(r4) - stw r5,0(r3) - bdnz 00b - sync - blr /* * identify_cpu and calls setup_cpu @@ -605,6 +389,7 @@ _GLOBAL(real_writeb) blr #endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */ +#ifdef CONFIG_CPU_FREQ_PMAC64 /* * SCOM access functions for 970 (FX only for now) * @@ -673,6 +458,7 @@ _GLOBAL(scom970_write) /* restore interrupts */ mtmsrd r5,1 blr +#endif /* CONFIG_CPU_FREQ_PMAC64 */ /* @@ -901,7 +687,7 @@ _GLOBAL(kexec_sequence) /* clear out hardware hash page table and tlb */ ld r5,0(r27) /* deref function descriptor */ mtctr r5 - bctrl /* ppc_md.hash_clear_all(void); */ + bctrl /* ppc_md.hpte_clear_all(void); */ /* * kexec image calling is: diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index 9feeeef5a875..397c83eda20e 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/init.h> @@ -190,27 +189,9 @@ void of_release_dev(struct device *dev) int of_device_register(struct of_device *ofdev) { int rc; - struct of_device **odprop; BUG_ON(ofdev->node == NULL); - odprop = (struct of_device **)get_property(ofdev->node, "linux,device", NULL); - if (!odprop) { - struct property *new_prop; - - new_prop = kmalloc(sizeof(struct property) + sizeof(struct of_device *), - GFP_KERNEL); - if (new_prop == NULL) - return -ENOMEM; - new_prop->name = "linux,device"; - new_prop->length = sizeof(sizeof(struct of_device *)); - new_prop->value = (unsigned char *)&new_prop[1]; - odprop = (struct of_device **)new_prop->value; - *odprop = NULL; - prom_add_property(ofdev->node, new_prop); - } - *odprop = ofdev; - rc = device_register(&ofdev->dev); if (rc) return rc; @@ -222,14 +203,8 @@ int of_device_register(struct of_device *ofdev) void of_device_unregister(struct of_device *ofdev) { - struct of_device **odprop; - device_remove_file(&ofdev->dev, &dev_attr_devspec); - odprop = (struct of_device **)get_property(ofdev->node, "linux,device", NULL); - if (odprop) - *odprop = NULL; - device_unregister(&ofdev->dev); } diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index f505a8827e3e..55f1a25085cd 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -7,7 +7,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/types.h> #include <linux/threads.h> #include <linux/module.h> @@ -16,9 +15,9 @@ #include <asm/ptrace.h> #include <asm/page.h> #include <asm/lppaca.h> -#include <asm/iseries/it_lp_queue.h> #include <asm/iseries/it_lp_reg_save.h> #include <asm/paca.h> +#include <asm/mmu.h> /* This symbol is provided by the linker - let it fill in the paca @@ -47,6 +46,17 @@ struct lppaca lppaca[] = { }, }; +/* + * 3 persistent SLBs are registered here. The buffer will be zero + * initially, hence will all be invaild until we actually write them. + */ +struct slb_shadow slb_shadow[] __cacheline_aligned = { + [0 ... (NR_CPUS-1)] = { + .persistent = SLB_NUM_BOLTED, + .buffer_length = sizeof(struct slb_shadow), + }, +}; + /* The Paca is an array with one entry per processor. Each contains an * lppaca, which contains the information shared between the * hypervisor and Linux. @@ -61,7 +71,8 @@ struct lppaca lppaca[] = { .lock_token = 0x8000, \ .paca_index = (number), /* Paca Index */ \ .kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL, \ - .hw_cpu_id = 0xffff, + .hw_cpu_id = 0xffff, \ + .slb_shadow_ptr = &slb_shadow[number], #ifdef CONFIG_PPC_ISERIES #define PACA_INIT_ISERIES(number) \ diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index c858eb4bef17..9b49f8691d29 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -2,7 +2,6 @@ * Common pmac/prep/chrp pci routines. -- Cort */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/pci.h> #include <linux/delay.h> @@ -12,6 +11,7 @@ #include <linux/sched.h> #include <linux/errno.h> #include <linux/bootmem.h> +#include <linux/irq.h> #include <asm/processor.h> #include <asm/io.h> @@ -19,7 +19,6 @@ #include <asm/sections.h> #include <asm/pci-bridge.h> #include <asm/byteorder.h> -#include <asm/irq.h> #include <asm/uaccess.h> #include <asm/machdep.h> @@ -99,7 +98,7 @@ pcibios_fixup_resources(struct pci_dev *dev) if (!res->flags) continue; if (res->end == 0xffffffff) { - DBG("PCI:%s Resource %d [%08lx-%08lx] is unassigned\n", + DBG("PCI:%s Resource %d [%016llx-%016llx] is unassigned\n", pci_name(dev), i, res->start, res->end); res->end -= res->start; res->start = 0; @@ -117,7 +116,7 @@ pcibios_fixup_resources(struct pci_dev *dev) res->start += offset; res->end += offset; #ifdef DEBUG - printk("Fixup res %d (%lx) of dev %s: %lx -> %lx\n", + printk("Fixup res %d (%lx) of dev %s: %llx -> %llx\n", i, res->flags, pci_name(dev), res->start - offset, res->start); #endif @@ -173,18 +172,18 @@ EXPORT_SYMBOL(pcibios_bus_to_resource); * but we want to try to avoid allocating at 0x2900-0x2bff * which might have be mirrored at 0x0100-0x03ff.. */ -void pcibios_align_resource(void *data, struct resource *res, unsigned long size, - unsigned long align) +void pcibios_align_resource(void *data, struct resource *res, + resource_size_t size, resource_size_t align) { struct pci_dev *dev = data; if (res->flags & IORESOURCE_IO) { - unsigned long start = res->start; + resource_size_t start = res->start; if (size > 0x100) { printk(KERN_ERR "PCI: I/O Region %s/%d too large" - " (%ld bytes)\n", pci_name(dev), - dev->resource - res, size); + " (%lld bytes)\n", pci_name(dev), + dev->resource - res, (unsigned long long)size); } if (start & 0x300) { @@ -255,8 +254,8 @@ pcibios_allocate_bus_resources(struct list_head *bus_list) } } - DBG("PCI: bridge rsrc %lx..%lx (%lx), parent %p\n", - res->start, res->end, res->flags, pr); + DBG("PCI: bridge rsrc %llx..%llx (%lx), parent %p\n", + res->start, res->end, res->flags, pr); if (pr) { if (request_resource(pr, res) == 0) continue; @@ -306,7 +305,7 @@ reparent_resources(struct resource *parent, struct resource *res) *pp = NULL; for (p = res->child; p != NULL; p = p->sibling) { p->parent = res; - DBG(KERN_INFO "PCI: reparented %s [%lx..%lx] under %s\n", + DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n", p->name, p->start, p->end, res->name); } return 0; @@ -362,13 +361,14 @@ pci_relocate_bridge_resource(struct pci_bus *bus, int i) try = conflict->start - 1; } if (request_resource(pr, res)) { - DBG(KERN_ERR "PCI: huh? couldn't move to %lx..%lx\n", + DBG(KERN_ERR "PCI: huh? couldn't move to %llx..%llx\n", res->start, res->end); return -1; /* "can't happen" */ } update_bridge_base(bus, i); - printk(KERN_INFO "PCI: bridge %d resource %d moved to %lx..%lx\n", - bus->number, i, res->start, res->end); + printk(KERN_INFO "PCI: bridge %d resource %d moved to %llx..%llx\n", + bus->number, i, (unsigned long long)res->start, + (unsigned long long)res->end); return 0; } @@ -479,14 +479,14 @@ static inline void alloc_resource(struct pci_dev *dev, int idx) { struct resource *pr, *r = &dev->resource[idx]; - DBG("PCI:%s: Resource %d: %08lx-%08lx (f=%lx)\n", + DBG("PCI:%s: Resource %d: %016llx-%016llx (f=%lx)\n", pci_name(dev), idx, r->start, r->end, r->flags); pr = pci_find_parent_resource(dev, r); if (!pr || request_resource(pr, r) < 0) { printk(KERN_ERR "PCI: Cannot allocate resource region %d" " of device %s\n", idx, pci_name(dev)); if (pr) - DBG("PCI: parent is %p: %08lx-%08lx (f=%lx)\n", + DBG("PCI: parent is %p: %016llx-%016llx (f=%lx)\n", pr, pr->start, pr->end, pr->flags); /* We'll assign a new address later */ r->flags |= IORESOURCE_UNSET; @@ -633,12 +633,12 @@ pcibios_alloc_controller(void) static void make_one_node_map(struct device_node* node, u8 pci_bus) { - int *bus_range; + const int *bus_range; int len; if (pci_bus >= pci_bus_count) return; - bus_range = (int *) get_property(node, "bus-range", &len); + bus_range = get_property(node, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { printk(KERN_WARNING "Can't get bus-range for %s, " "assuming it starts at 0\n", node->full_name); @@ -648,13 +648,13 @@ make_one_node_map(struct device_node* node, u8 pci_bus) for (node=node->child; node != 0;node = node->sibling) { struct pci_dev* dev; - unsigned int *class_code, *reg; + const unsigned int *class_code, *reg; - class_code = (unsigned int *) get_property(node, "class-code", NULL); + class_code = get_property(node, "class-code", NULL); if (!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI && (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) continue; - reg = (unsigned int *)get_property(node, "reg", NULL); + reg = get_property(node, "reg", NULL); if (!reg) continue; dev = pci_find_slot(pci_bus, ((reg[0] >> 8) & 0xff)); @@ -669,7 +669,7 @@ pcibios_make_OF_bus_map(void) { int i; struct pci_controller* hose; - u8* of_prop_map; + struct property *map_prop; pci_to_OF_bus_map = (u8*)kmalloc(pci_bus_count, GFP_KERNEL); if (!pci_to_OF_bus_map) { @@ -691,9 +691,12 @@ pcibios_make_OF_bus_map(void) continue; make_one_node_map(node, hose->first_busno); } - of_prop_map = get_property(find_path_device("/"), "pci-OF-bus-map", NULL); - if (of_prop_map) - memcpy(of_prop_map, pci_to_OF_bus_map, pci_bus_count); + map_prop = of_find_property(find_path_device("/"), + "pci-OF-bus-map", NULL); + if (map_prop) { + BUG_ON(pci_bus_count > map_prop->length); + memcpy(map_prop->value, pci_to_OF_bus_map, pci_bus_count); + } #ifdef DEBUG printk("PCI->OF bus map:\n"); for (i=0; i<pci_bus_count; i++) { @@ -712,7 +715,7 @@ scan_OF_pci_childs(struct device_node* node, pci_OF_scan_iterator filter, void* struct device_node* sub_node; for (; node != 0;node = node->sibling) { - unsigned int *class_code; + const unsigned int *class_code; if (filter(node, data)) return node; @@ -722,7 +725,7 @@ scan_OF_pci_childs(struct device_node* node, pci_OF_scan_iterator filter, void* * a fake root for all functions of a multi-function device, * we go down them as well. */ - class_code = (unsigned int *) get_property(node, "class-code", NULL); + class_code = get_property(node, "class-code", NULL); if ((!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI && (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) && strcmp(node->name, "multifunc-device")) @@ -737,10 +740,10 @@ scan_OF_pci_childs(struct device_node* node, pci_OF_scan_iterator filter, void* static int scan_OF_pci_childs_iterator(struct device_node* node, void* data) { - unsigned int *reg; + const unsigned int *reg; u8* fdata = (u8*)data; - reg = (unsigned int *) get_property(node, "reg", NULL); + reg = get_property(node, "reg", NULL); if (reg && ((reg[0] >> 8) & 0xff) == fdata[1] && ((reg[0] >> 16) & 0xff) == fdata[0]) return 1; @@ -841,7 +844,7 @@ find_OF_pci_device_filter(struct device_node* node, void* data) int pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) { - unsigned int *reg; + const unsigned int *reg; struct pci_controller* hose; struct pci_dev* dev = NULL; @@ -854,7 +857,7 @@ pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) if (!scan_OF_pci_childs(((struct device_node*)hose->arch_data)->child, find_OF_pci_device_filter, (void *)node)) return -ENODEV; - reg = (unsigned int *) get_property(node, "reg", NULL); + reg = get_property(node, "reg", NULL); if (!reg) return -ENODEV; *bus = (reg[0] >> 16) & 0xff; @@ -885,8 +888,8 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int primary) { static unsigned int static_lc_ranges[256] __initdata; - unsigned int *dt_ranges, *lc_ranges, *ranges, *prev; - unsigned int size; + const unsigned int *dt_ranges; + unsigned int *lc_ranges, *ranges, *prev, size; int rlen = 0, orig_rlen; int memno = 0; struct resource *res; @@ -897,7 +900,7 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose, * that can have more than 3 ranges, fortunately using contiguous * addresses -- BenH */ - dt_ranges = (unsigned int *) get_property(dev, "ranges", &rlen); + dt_ranges = get_property(dev, "ranges", &rlen); if (!dt_ranges) return; /* Sanity check, though hopefully that never happens */ @@ -956,7 +959,7 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose, res = &hose->io_resource; res->flags = IORESOURCE_IO; res->start = ranges[2]; - DBG("PCI: IO 0x%lx -> 0x%lx\n", + DBG("PCI: IO 0x%llx -> 0x%llx\n", res->start, res->start + size - 1); break; case 2: /* memory space */ @@ -978,7 +981,7 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose, if(ranges[0] & 0x40000000) res->flags |= IORESOURCE_PREFETCH; res->start = ranges[na+2]; - DBG("PCI: MEM[%d] 0x%lx -> 0x%lx\n", memno, + DBG("PCI: MEM[%d] 0x%llx -> 0x%llx\n", memno, res->start, res->start + size - 1); } break; @@ -1074,7 +1077,7 @@ do_update_p2p_io_resource(struct pci_bus *bus, int enable_vga) DBG("Remapping Bus %d, bridge: %s\n", bus->number, pci_name(bridge)); res.start -= ((unsigned long) hose->io_base_virt - isa_io_base); res.end -= ((unsigned long) hose->io_base_virt - isa_io_base); - DBG(" IO window: %08lx-%08lx\n", res.start, res.end); + DBG(" IO window: %016llx-%016llx\n", res.start, res.end); /* Set up the top and bottom of the PCI I/O segment for this bus. */ pci_read_config_dword(bridge, PCI_IO_BASE, &l); @@ -1223,8 +1226,8 @@ do_fixup_p2p_level(struct pci_bus *bus) continue; if ((r->flags & IORESOURCE_IO) == 0) continue; - DBG("Trying to allocate from %08lx, size %08lx from parent" - " res %d: %08lx -> %08lx\n", + DBG("Trying to allocate from %016llx, size %016llx from parent" + " res %d: %016llx -> %016llx\n", res->start, res->end, i, r->start, r->end); if (allocate_resource(r, res, res->end + 1, res->start, max, @@ -1404,6 +1407,65 @@ pcibios_update_irq(struct pci_dev *dev, int irq) /* XXX FIXME - update OF device tree node interrupt property */ } +#ifdef CONFIG_PPC_MERGE +/* XXX This is a copy of the ppc64 version. This is temporary until we start + * merging the 2 PCI layers + */ +/* + * Reads the interrupt pin to determine if interrupt is use by card. + * If the interrupt is used, then gets the interrupt line from the + * openfirmware and sets it in the pci_dev and pci_config line. + */ +int pci_read_irq_line(struct pci_dev *pci_dev) +{ + struct of_irq oirq; + unsigned int virq; + + DBG("Try to map irq for %s...\n", pci_name(pci_dev)); + + /* Try to get a mapping from the device-tree */ + if (of_irq_map_pci(pci_dev, &oirq)) { + u8 line, pin; + + /* If that fails, lets fallback to what is in the config + * space and map that through the default controller. We + * also set the type to level low since that's what PCI + * interrupts are. If your platform does differently, then + * either provide a proper interrupt tree or don't use this + * function. + */ + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin)) + return -1; + if (pin == 0) + return -1; + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) || + line == 0xff) { + return -1; + } + DBG(" -> no map ! Using irq line %d from PCI config\n", line); + + virq = irq_create_mapping(NULL, line); + if (virq != NO_IRQ) + set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); + } else { + DBG(" -> got one, spec %d cells (0x%08x...) on %s\n", + oirq.size, oirq.specifier[0], oirq.controller->full_name); + + virq = irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); + } + if(virq == NO_IRQ) { + DBG(" -> failed to map !\n"); + return -1; + } + pci_dev->irq = virq; + pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, virq); + + return 0; +} +EXPORT_SYMBOL(pci_read_irq_line); +#endif /* CONFIG_PPC_MERGE */ + int pcibios_enable_device(struct pci_dev *dev, int mask) { u16 cmd, old_cmd; @@ -1574,8 +1636,8 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, else prot |= _PAGE_GUARDED; - printk("PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, - prot); + printk("PCI map for %s:%llx, prot: %lx\n", pci_name(dev), + (unsigned long long)rp->start, prot); return __pgprot(prot); } @@ -1654,7 +1716,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, vma->vm_page_prot, mmap_state, write_combine); @@ -1756,7 +1817,7 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, - u64 *start, u64 *end) + resource_size_t *start, resource_size_t *end) { struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); unsigned long offset = 0; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 5ad87c426bed..c1b1e14775e4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -13,7 +13,6 @@ #undef DEBUG -#include <linux/config.h> #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> @@ -22,13 +21,13 @@ #include <linux/mm.h> #include <linux/list.h> #include <linux/syscalls.h> +#include <linux/irq.h> #include <asm/processor.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/byteorder.h> -#include <asm/irq.h> #include <asm/machdep.h> #include <asm/ppc-pci.h> @@ -138,11 +137,11 @@ EXPORT_SYMBOL(pcibios_bus_to_resource); * which might have be mirrored at 0x0100-0x03ff.. */ void pcibios_align_resource(void *data, struct resource *res, - unsigned long size, unsigned long align) + resource_size_t size, resource_size_t align) { struct pci_dev *dev = data; struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long start = res->start; + resource_size_t start = res->start; unsigned long alignto; if (res->flags & IORESOURCE_IO) { @@ -186,34 +185,6 @@ static void __devinit pci_setup_pci_controller(struct pci_controller *hose) spin_unlock(&hose_spinlock); } -static void add_linux_pci_domain(struct device_node *dev, - struct pci_controller *phb) -{ - struct property *of_prop; - unsigned int size; - - of_prop = (struct property *) - get_property(dev, "linux,pci-domain", &size); - if (of_prop != NULL) - return; - WARN_ON(of_prop && size < sizeof(int)); - if (of_prop && size < sizeof(int)) - of_prop = NULL; - size = sizeof(struct property) + sizeof(int); - if (of_prop == NULL) { - if (mem_init_done) - of_prop = kmalloc(size, GFP_KERNEL); - else - of_prop = alloc_bootmem(size); - } - memset(of_prop, 0, sizeof(struct property)); - of_prop->name = "linux,pci-domain"; - of_prop->length = sizeof(int); - of_prop->value = (unsigned char *)&of_prop[1]; - *((int *)of_prop->value) = phb->global_number; - prom_add_property(dev, of_prop); -} - struct pci_controller * pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; @@ -227,22 +198,13 @@ struct pci_controller * pcibios_alloc_controller(struct device_node *dev) pci_setup_pci_controller(phb); phb->arch_data = dev; phb->is_dynamic = mem_init_done; - if (dev) { + if (dev) PHB_SET_NODE(phb, of_node_to_nid(dev)); - add_linux_pci_domain(dev, phb); - } return phb; } void pcibios_free_controller(struct pci_controller *phb) { - if (phb->arch_data) { - struct device_node *np = phb->arch_data; - int *domain = (int *)get_property(np, - "linux,pci-domain", NULL); - if (domain) - *domain = -1; - } if (phb->is_dynamic) kfree(phb); } @@ -284,10 +246,10 @@ static void __init pcibios_claim_of_setup(void) #ifdef CONFIG_PPC_MULTIPLATFORM static u32 get_int_prop(struct device_node *np, const char *name, u32 def) { - u32 *prop; + const u32 *prop; int len; - prop = (u32 *) get_property(np, name, &len); + prop = get_property(np, name, &len); if (prop && len >= 4) return *prop; return def; @@ -316,10 +278,11 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) u64 base, size; unsigned int flags; struct resource *res; - u32 *addrs, i; + const u32 *addrs; + u32 i; int proplen; - addrs = (u32 *) get_property(node, "assigned-addresses", &proplen); + addrs = get_property(node, "assigned-addresses", &proplen); if (!addrs) return; DBG(" parse addresses (%d bytes) @ %p\n", proplen, addrs); @@ -399,12 +362,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, } else { dev->hdr_type = PCI_HEADER_TYPE_NORMAL; dev->rom_base_reg = PCI_ROM_ADDRESS; + /* Maybe do a default OF mapping here */ dev->irq = NO_IRQ; - if (node->n_intrs > 0) { - dev->irq = node->intrs[0].line; - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, - dev->irq); - } } pci_parse_of_addrs(node, dev); @@ -423,7 +382,7 @@ void __devinit of_scan_bus(struct device_node *node, struct pci_bus *bus) { struct device_node *child = NULL; - u32 *reg; + const u32 *reg; int reglen, devfn; struct pci_dev *dev; @@ -431,7 +390,7 @@ void __devinit of_scan_bus(struct device_node *node, while ((child = of_get_next_child(node, child)) != NULL) { DBG(" * %s\n", child->full_name); - reg = (u32 *) get_property(child, "reg", ®len); + reg = get_property(child, "reg", ®len); if (reg == NULL || reglen < 20) continue; devfn = (reg[0] >> 8) & 0xff; @@ -455,7 +414,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node, struct pci_dev *dev) { struct pci_bus *bus; - u32 *busrange, *ranges; + const u32 *busrange, *ranges; int len, i, mode; struct resource *res; unsigned int flags; @@ -464,13 +423,13 @@ void __devinit of_scan_pci_bridge(struct device_node *node, DBG("of_scan_pci_bridge(%s)\n", node->full_name); /* parse bus-range property */ - busrange = (u32 *) get_property(node, "bus-range", &len); + busrange = get_property(node, "bus-range", &len); if (busrange == NULL || len != 8) { printk(KERN_DEBUG "Can't get bus-range for PCI-PCI bridge %s\n", node->full_name); return; } - ranges = (u32 *) get_property(node, "ranges", &len); + ranges = get_property(node, "ranges", &len); if (ranges == NULL) { printk(KERN_DEBUG "Can't get ranges for PCI-PCI bridge %s\n", node->full_name); @@ -877,7 +836,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, vma->vm_page_prot, mmap_state, write_combine); @@ -935,13 +893,13 @@ static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, unsigned int size; }; - struct isa_range *range; + const struct isa_range *range; unsigned long pci_addr; unsigned int isa_addr; unsigned int size; int rlen = 0; - range = (struct isa_range *) get_property(isa_node, "ranges", &rlen); + range = get_property(isa_node, "ranges", &rlen); if (range == NULL || (rlen < sizeof(struct isa_range))) { printk(KERN_ERR "no ISA ranges or unexpected isa range size," "mapping 64k\n"); @@ -982,7 +940,8 @@ static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int prim) { - unsigned int *ranges, pci_space; + const unsigned int *ranges; + unsigned int pci_space; unsigned long size; int rlen = 0; int memno = 0; @@ -1000,7 +959,7 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, * (size depending on dev->n_addr_cells) * cells 4+5 or 5+6: the size of the range */ - ranges = (unsigned int *) get_property(dev, "ranges", &rlen); + ranges = get_property(dev, "ranges", &rlen); if (ranges == NULL) return; hose->io_base_phys = 0; @@ -1290,23 +1249,55 @@ EXPORT_SYMBOL(pcibios_fixup_bus); */ int pci_read_irq_line(struct pci_dev *pci_dev) { - u8 intpin; - struct device_node *node; + struct of_irq oirq; + unsigned int virq; - pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &intpin); - if (intpin == 0) - return 0; + DBG("Try to map irq for %s...\n", pci_name(pci_dev)); - node = pci_device_to_OF_node(pci_dev); - if (node == NULL) - return -1; +#ifdef DEBUG + memset(&oirq, 0xff, sizeof(oirq)); +#endif + /* Try to get a mapping from the device-tree */ + if (of_irq_map_pci(pci_dev, &oirq)) { + u8 line, pin; + + /* If that fails, lets fallback to what is in the config + * space and map that through the default controller. We + * also set the type to level low since that's what PCI + * interrupts are. If your platform does differently, then + * either provide a proper interrupt tree or don't use this + * function. + */ + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin)) + return -1; + if (pin == 0) + return -1; + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) || + line == 0xff) { + return -1; + } + DBG(" -> no map ! Using irq line %d from PCI config\n", line); + + virq = irq_create_mapping(NULL, line); + if (virq != NO_IRQ) + set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); + } else { + DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n", + oirq.size, oirq.specifier[0], oirq.specifier[1], + oirq.controller->full_name); - if (node->n_intrs == 0) + virq = irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); + } + if(virq == NO_IRQ) { + DBG(" -> failed to map !\n"); return -1; + } - pci_dev->irq = node->intrs[0].line; + DBG(" -> mapped to linux irq %d\n", virq); - pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, pci_dev->irq); + pci_dev->irq = virq; + pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, virq); return 0; } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 1c18953514c3..68df018dae0e 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -40,8 +40,8 @@ static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) { struct pci_controller *phb = data; - int *type = (int *)get_property(dn, "ibm,pci-config-space-type", NULL); - u32 *regs; + const int *type = get_property(dn, "ibm,pci-config-space-type", NULL); + const u32 *regs; struct pci_dn *pdn; if (mem_init_done) @@ -54,14 +54,14 @@ static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) dn->data = pdn; pdn->node = dn; pdn->phb = phb; - regs = (u32 *)get_property(dn, "reg", NULL); + regs = get_property(dn, "reg", NULL); if (regs) { /* First register entry is addr (00BBSS00) */ pdn->busno = (regs[0] >> 16) & 0xff; pdn->devfn = (regs[0] >> 8) & 0xff; } if (firmware_has_feature(FW_FEATURE_ISERIES)) { - u32 *busp = (u32 *)get_property(dn, "linux,subbus", NULL); + const u32 *busp = get_property(dn, "linux,subbus", NULL); if (busp) pdn->bussubno = *busp; } @@ -96,10 +96,11 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre, /* We started with a phb, iterate all childs */ for (dn = start->child; dn; dn = nextdn) { - u32 *classp, class; + const u32 *classp; + u32 class; nextdn = NULL; - classp = (u32 *)get_property(dn, "class-code", NULL); + classp = get_property(dn, "class-code", NULL); class = classp ? *classp : 0; if (pre && ((ret = pre(dn, data)) != NULL)) diff --git a/arch/powerpc/kernel/perfmon_fsl_booke.c b/arch/powerpc/kernel/perfmon_fsl_booke.c index 32455dfcc36b..bdc3977a7b06 100644 --- a/arch/powerpc/kernel/perfmon_fsl_booke.c +++ b/arch/powerpc/kernel/perfmon_fsl_booke.c @@ -21,7 +21,6 @@ #include <linux/user.h> #include <linux/a.out.h> #include <linux/interrupt.h> -#include <linux/config.h> #include <linux/init.h> #include <linux/module.h> #include <linux/prctl.h> diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c index e6fb194fe537..a0a2efadeabf 100644 --- a/arch/powerpc/kernel/pmc.c +++ b/arch/powerpc/kernel/pmc.c @@ -12,7 +12,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/spinlock.h> #include <linux/module.h> diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 4b052ae5dc34..807193a3c784 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/module.h> #include <linux/threads.h> #include <linux/smp.h> @@ -6,7 +5,7 @@ #include <linux/elfcore.h> #include <linux/string.h> #include <linux/interrupt.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/vt_kern.h> #include <linux/nvram.h> #include <linux/console.h> @@ -92,25 +91,10 @@ EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__strncpy_from_user); EXPORT_SYMBOL(__strnlen_user); - -#ifndef __powerpc64__ -EXPORT_SYMBOL(__ide_mm_insl); -EXPORT_SYMBOL(__ide_mm_outsw); -EXPORT_SYMBOL(__ide_mm_insw); -EXPORT_SYMBOL(__ide_mm_outsl); +#ifdef CONFIG_PPC64 +EXPORT_SYMBOL(copy_4K_page); #endif -EXPORT_SYMBOL(_insb); -EXPORT_SYMBOL(_outsb); -EXPORT_SYMBOL(_insw); -EXPORT_SYMBOL(_outsw); -EXPORT_SYMBOL(_insl); -EXPORT_SYMBOL(_outsl); -EXPORT_SYMBOL(_insw_ns); -EXPORT_SYMBOL(_outsw_ns); -EXPORT_SYMBOL(_insl_ns); -EXPORT_SYMBOL(_outsl_ns); - #if defined(CONFIG_PPC32) && (defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)) EXPORT_SYMBOL(ppc_ide_md); #endif @@ -127,10 +111,6 @@ EXPORT_SYMBOL(pci_bus_mem_base_phys); EXPORT_SYMBOL(pci_bus_to_hose); #endif /* CONFIG_PCI */ -#ifdef CONFIG_NOT_COHERENT_CACHE -EXPORT_SYMBOL(flush_dcache_all); -#endif - EXPORT_SYMBOL(start_thread); EXPORT_SYMBOL(kernel_thread); diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c index 2b87f82df135..f598cb519539 100644 --- a/arch/powerpc/kernel/proc_ppc64.c +++ b/arch/powerpc/kernel/proc_ppc64.c @@ -16,7 +16,6 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/config.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/proc_fs.h> @@ -115,8 +114,6 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) { struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode); - vma->vm_flags |= VM_SHM | VM_LOCKED; - if ((vma->vm_end - vma->vm_start) > dp->size) return -EINVAL; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e4732459c485..a127a1e3c097 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -14,7 +14,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 483455c5bb02..eb913f80bfb1 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -16,7 +16,6 @@ #undef DEBUG #include <stdarg.h> -#include <linux/config.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> @@ -30,6 +29,8 @@ #include <linux/bitops.h> #include <linux/module.h> #include <linux/kexec.h> +#include <linux/debugfs.h> +#include <linux/irq.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -86,424 +87,6 @@ static DEFINE_RWLOCK(devtree_lock); /* export that to outside world */ struct device_node *of_chosen; -struct device_node *dflt_interrupt_controller; -int num_interrupt_controllers; - -/* - * Wrapper for allocating memory for various data that needs to be - * attached to device nodes as they are processed at boot or when - * added to the device tree later (e.g. DLPAR). At boot there is - * already a region reserved so we just increment *mem_start by size; - * otherwise we call kmalloc. - */ -static void * prom_alloc(unsigned long size, unsigned long *mem_start) -{ - unsigned long tmp; - - if (!mem_start) - return kmalloc(size, GFP_KERNEL); - - tmp = *mem_start; - *mem_start += size; - return (void *)tmp; -} - -/* - * Find the device_node with a given phandle. - */ -static struct device_node * find_phandle(phandle ph) -{ - struct device_node *np; - - for (np = allnodes; np != 0; np = np->allnext) - if (np->linux_phandle == ph) - return np; - return NULL; -} - -/* - * Find the interrupt parent of a node. - */ -static struct device_node * __devinit intr_parent(struct device_node *p) -{ - phandle *parp; - - parp = (phandle *) get_property(p, "interrupt-parent", NULL); - if (parp == NULL) - return p->parent; - p = find_phandle(*parp); - if (p != NULL) - return p; - /* - * On a powermac booted with BootX, we don't get to know the - * phandles for any nodes, so find_phandle will return NULL. - * Fortunately these machines only have one interrupt controller - * so there isn't in fact any ambiguity. -- paulus - */ - if (num_interrupt_controllers == 1) - p = dflt_interrupt_controller; - return p; -} - -/* - * Find out the size of each entry of the interrupts property - * for a node. - */ -int __devinit prom_n_intr_cells(struct device_node *np) -{ - struct device_node *p; - unsigned int *icp; - - for (p = np; (p = intr_parent(p)) != NULL; ) { - icp = (unsigned int *) - get_property(p, "#interrupt-cells", NULL); - if (icp != NULL) - return *icp; - if (get_property(p, "interrupt-controller", NULL) != NULL - || get_property(p, "interrupt-map", NULL) != NULL) { - printk("oops, node %s doesn't have #interrupt-cells\n", - p->full_name); - return 1; - } - } -#ifdef DEBUG_IRQ - printk("prom_n_intr_cells failed for %s\n", np->full_name); -#endif - return 1; -} - -/* - * Map an interrupt from a device up to the platform interrupt - * descriptor. - */ -static int __devinit map_interrupt(unsigned int **irq, struct device_node **ictrler, - struct device_node *np, unsigned int *ints, - int nintrc) -{ - struct device_node *p, *ipar; - unsigned int *imap, *imask, *ip; - int i, imaplen, match; - int newintrc = 0, newaddrc = 0; - unsigned int *reg; - int naddrc; - - reg = (unsigned int *) get_property(np, "reg", NULL); - naddrc = prom_n_addr_cells(np); - p = intr_parent(np); - while (p != NULL) { - if (get_property(p, "interrupt-controller", NULL) != NULL) - /* this node is an interrupt controller, stop here */ - break; - imap = (unsigned int *) - get_property(p, "interrupt-map", &imaplen); - if (imap == NULL) { - p = intr_parent(p); - continue; - } - imask = (unsigned int *) - get_property(p, "interrupt-map-mask", NULL); - if (imask == NULL) { - printk("oops, %s has interrupt-map but no mask\n", - p->full_name); - return 0; - } - imaplen /= sizeof(unsigned int); - match = 0; - ipar = NULL; - while (imaplen > 0 && !match) { - /* check the child-interrupt field */ - match = 1; - for (i = 0; i < naddrc && match; ++i) - match = ((reg[i] ^ imap[i]) & imask[i]) == 0; - for (; i < naddrc + nintrc && match; ++i) - match = ((ints[i-naddrc] ^ imap[i]) & imask[i]) == 0; - imap += naddrc + nintrc; - imaplen -= naddrc + nintrc; - /* grab the interrupt parent */ - ipar = find_phandle((phandle) *imap++); - --imaplen; - if (ipar == NULL && num_interrupt_controllers == 1) - /* cope with BootX not giving us phandles */ - ipar = dflt_interrupt_controller; - if (ipar == NULL) { - printk("oops, no int parent %x in map of %s\n", - imap[-1], p->full_name); - return 0; - } - /* find the parent's # addr and intr cells */ - ip = (unsigned int *) - get_property(ipar, "#interrupt-cells", NULL); - if (ip == NULL) { - printk("oops, no #interrupt-cells on %s\n", - ipar->full_name); - return 0; - } - newintrc = *ip; - ip = (unsigned int *) - get_property(ipar, "#address-cells", NULL); - newaddrc = (ip == NULL)? 0: *ip; - imap += newaddrc + newintrc; - imaplen -= newaddrc + newintrc; - } - if (imaplen < 0) { - printk("oops, error decoding int-map on %s, len=%d\n", - p->full_name, imaplen); - return 0; - } - if (!match) { -#ifdef DEBUG_IRQ - printk("oops, no match in %s int-map for %s\n", - p->full_name, np->full_name); -#endif - return 0; - } - p = ipar; - naddrc = newaddrc; - nintrc = newintrc; - ints = imap - nintrc; - reg = ints - naddrc; - } - if (p == NULL) { -#ifdef DEBUG_IRQ - printk("hmmm, int tree for %s doesn't have ctrler\n", - np->full_name); -#endif - return 0; - } - *irq = ints; - *ictrler = p; - return nintrc; -} - -static unsigned char map_isa_senses[4] = { - IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, - IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE, - IRQ_SENSE_EDGE | IRQ_POLARITY_NEGATIVE, - IRQ_SENSE_EDGE | IRQ_POLARITY_POSITIVE -}; - -static unsigned char map_mpic_senses[4] = { - IRQ_SENSE_EDGE | IRQ_POLARITY_POSITIVE, - IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, - /* 2 seems to be used for the 8259 cascade... */ - IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE, - IRQ_SENSE_EDGE | IRQ_POLARITY_NEGATIVE, -}; - -static int __devinit finish_node_interrupts(struct device_node *np, - unsigned long *mem_start, - int measure_only) -{ - unsigned int *ints; - int intlen, intrcells, intrcount; - int i, j, n, sense; - unsigned int *irq, virq; - struct device_node *ic; - int trace = 0; - - //#define TRACE(fmt...) do { if (trace) { printk(fmt); mdelay(1000); } } while(0) -#define TRACE(fmt...) - - if (!strcmp(np->name, "smu-doorbell")) - trace = 1; - - TRACE("Finishing SMU doorbell ! num_interrupt_controllers = %d\n", - num_interrupt_controllers); - - if (num_interrupt_controllers == 0) { - /* - * Old machines just have a list of interrupt numbers - * and no interrupt-controller nodes. - */ - ints = (unsigned int *) get_property(np, "AAPL,interrupts", - &intlen); - /* XXX old interpret_pci_props looked in parent too */ - /* XXX old interpret_macio_props looked for interrupts - before AAPL,interrupts */ - if (ints == NULL) - ints = (unsigned int *) get_property(np, "interrupts", - &intlen); - if (ints == NULL) - return 0; - - np->n_intrs = intlen / sizeof(unsigned int); - np->intrs = prom_alloc(np->n_intrs * sizeof(np->intrs[0]), - mem_start); - if (!np->intrs) - return -ENOMEM; - if (measure_only) - return 0; - - for (i = 0; i < np->n_intrs; ++i) { - np->intrs[i].line = *ints++; - np->intrs[i].sense = IRQ_SENSE_LEVEL - | IRQ_POLARITY_NEGATIVE; - } - return 0; - } - - ints = (unsigned int *) get_property(np, "interrupts", &intlen); - TRACE("ints=%p, intlen=%d\n", ints, intlen); - if (ints == NULL) - return 0; - intrcells = prom_n_intr_cells(np); - intlen /= intrcells * sizeof(unsigned int); - TRACE("intrcells=%d, new intlen=%d\n", intrcells, intlen); - np->intrs = prom_alloc(intlen * sizeof(*(np->intrs)), mem_start); - if (!np->intrs) - return -ENOMEM; - - if (measure_only) - return 0; - - intrcount = 0; - for (i = 0; i < intlen; ++i, ints += intrcells) { - n = map_interrupt(&irq, &ic, np, ints, intrcells); - TRACE("map, irq=%d, ic=%p, n=%d\n", irq, ic, n); - if (n <= 0) - continue; - - /* don't map IRQ numbers under a cascaded 8259 controller */ - if (ic && device_is_compatible(ic, "chrp,iic")) { - np->intrs[intrcount].line = irq[0]; - sense = (n > 1)? (irq[1] & 3): 3; - np->intrs[intrcount].sense = map_isa_senses[sense]; - } else { - virq = virt_irq_create_mapping(irq[0]); - TRACE("virq=%d\n", virq); -#ifdef CONFIG_PPC64 - if (virq == NO_IRQ) { - printk(KERN_CRIT "Could not allocate interrupt" - " number for %s\n", np->full_name); - continue; - } -#endif - np->intrs[intrcount].line = irq_offset_up(virq); - sense = (n > 1)? (irq[1] & 3): 1; - - /* Apple uses bits in there in a different way, let's - * only keep the real sense bit on macs - */ - if (machine_is(powermac)) - sense &= 0x1; - np->intrs[intrcount].sense = map_mpic_senses[sense]; - } - -#ifdef CONFIG_PPC64 - /* We offset irq numbers for the u3 MPIC by 128 in PowerMac */ - if (machine_is(powermac) && ic && ic->parent) { - char *name = get_property(ic->parent, "name", NULL); - if (name && !strcmp(name, "u3")) - np->intrs[intrcount].line += 128; - else if (!(name && (!strcmp(name, "mac-io") || - !strcmp(name, "u4")))) - /* ignore other cascaded controllers, such as - the k2-sata-root */ - break; - } -#endif /* CONFIG_PPC64 */ - if (n > 2) { - printk("hmmm, got %d intr cells for %s:", n, - np->full_name); - for (j = 0; j < n; ++j) - printk(" %d", irq[j]); - printk("\n"); - } - ++intrcount; - } - np->n_intrs = intrcount; - - return 0; -} - -static int __devinit finish_node(struct device_node *np, - unsigned long *mem_start, - int measure_only) -{ - struct device_node *child; - int rc = 0; - - rc = finish_node_interrupts(np, mem_start, measure_only); - if (rc) - goto out; - - for (child = np->child; child != NULL; child = child->sibling) { - rc = finish_node(child, mem_start, measure_only); - if (rc) - goto out; - } -out: - return rc; -} - -static void __init scan_interrupt_controllers(void) -{ - struct device_node *np; - int n = 0; - char *name, *ic; - int iclen; - - for (np = allnodes; np != NULL; np = np->allnext) { - ic = get_property(np, "interrupt-controller", &iclen); - name = get_property(np, "name", NULL); - /* checking iclen makes sure we don't get a false - match on /chosen.interrupt_controller */ - if ((name != NULL - && strcmp(name, "interrupt-controller") == 0) - || (ic != NULL && iclen == 0 - && strcmp(name, "AppleKiwi"))) { - if (n == 0) - dflt_interrupt_controller = np; - ++n; - } - } - num_interrupt_controllers = n; -} - -/** - * finish_device_tree is called once things are running normally - * (i.e. with text and data mapped to the address they were linked at). - * It traverses the device tree and fills in some of the additional, - * fields in each node like {n_}addrs and {n_}intrs, the virt interrupt - * mapping is also initialized at this point. - */ -void __init finish_device_tree(void) -{ - unsigned long start, end, size = 0; - - DBG(" -> finish_device_tree\n"); - -#ifdef CONFIG_PPC64 - /* Initialize virtual IRQ map */ - virt_irq_init(); -#endif - scan_interrupt_controllers(); - - /* - * Finish device-tree (pre-parsing some properties etc...) - * We do this in 2 passes. One with "measure_only" set, which - * will only measure the amount of memory needed, then we can - * allocate that memory, and call finish_node again. However, - * we must be careful as most routines will fail nowadays when - * prom_alloc() returns 0, so we must make sure our first pass - * doesn't start at 0. We pre-initialize size to 16 for that - * reason and then remove those additional 16 bytes - */ - size = 16; - finish_node(allnodes, &size, 1); - size -= 16; - - if (0 == size) - end = start = 0; - else - end = start = (unsigned long)__va(lmb_alloc(size, 128)); - - finish_node(allnodes, &end, 0); - BUG_ON(end != start + size); - - DBG(" <- finish_device_tree\n"); -} - static inline char *find_flat_dt_string(u32 offset) { return ((char *)initial_boot_params) + @@ -952,6 +535,7 @@ static struct ibm_pa_feature { /* put this back once we know how to test if firmware does 64k IO */ {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, #endif + {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; static void __init check_cpu_pa_features(unsigned long node) @@ -1124,24 +708,6 @@ static int __init early_init_dt_scan_chosen(unsigned long node, tce_alloc_end = *lprop; #endif -#ifdef CONFIG_PPC_RTAS - /* To help early debugging via the front panel, we retrieve a minimal - * set of RTAS infos now if available - */ - { - u64 *basep, *entryp, *sizep; - - basep = of_get_flat_dt_prop(node, "linux,rtas-base", NULL); - entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL); - sizep = of_get_flat_dt_prop(node, "linux,rtas-size", NULL); - if (basep && entryp && sizep) { - rtas.base = *basep; - rtas.entry = *entryp; - rtas.size = *sizep; - } - } -#endif /* CONFIG_PPC_RTAS */ - #ifdef CONFIG_KEXEC lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); if (lprop) @@ -1191,24 +757,9 @@ static int __init early_init_dt_scan_root(unsigned long node, static unsigned long __init dt_mem_next_cell(int s, cell_t **cellp) { cell_t *p = *cellp; - unsigned long r; - /* Ignore more than 2 cells */ - while (s > sizeof(unsigned long) / 4) { - p++; - s--; - } - r = *p++; -#ifdef CONFIG_PPC64 - if (s > 1) { - r <<= 32; - r |= *(p++); - s--; - } -#endif - - *cellp = p; - return r; + *cellp = p + s; + return of_read_ulong(p, s); } @@ -1326,6 +877,11 @@ void __init early_init_devtree(void *params) /* Setup flat device-tree pointer */ initial_boot_params = params; +#ifdef CONFIG_PPC_RTAS + /* Some machines might need RTAS info for debugging, grab it now. */ + of_scan_flat_dt(early_init_dt_scan_rtas, NULL); +#endif + /* Retrieve various informations from the /chosen node of the * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... @@ -1371,11 +927,11 @@ void __init early_init_devtree(void *params) int prom_n_addr_cells(struct device_node* np) { - int* ip; + const int *ip; do { if (np->parent) np = np->parent; - ip = (int *) get_property(np, "#address-cells", NULL); + ip = get_property(np, "#address-cells", NULL); if (ip != NULL) return *ip; } while (np->parent); @@ -1387,11 +943,11 @@ EXPORT_SYMBOL(prom_n_addr_cells); int prom_n_size_cells(struct device_node* np) { - int* ip; + const int* ip; do { if (np->parent) np = np->parent; - ip = (int *) get_property(np, "#size-cells", NULL); + ip = get_property(np, "#size-cells", NULL); if (ip != NULL) return *ip; } while (np->parent); @@ -1401,27 +957,6 @@ prom_n_size_cells(struct device_node* np) EXPORT_SYMBOL(prom_n_size_cells); /** - * Work out the sense (active-low level / active-high edge) - * of each interrupt from the device tree. - */ -void __init prom_get_irq_senses(unsigned char *senses, int off, int max) -{ - struct device_node *np; - int i, j; - - /* default to level-triggered */ - memset(senses, IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, max - off); - - for (np = allnodes; np != 0; np = np->allnext) { - for (j = 0; j < np->n_intrs; j++) { - i = np->intrs[j].line; - if (i >= off && i < max) - senses[i-off] = np->intrs[j].sense; - } - } -} - -/** * Construct and return a list of the device_nodes with a given name. */ struct device_node *find_devices(const char *name) @@ -1484,7 +1019,7 @@ int device_is_compatible(struct device_node *device, const char *compat) const char* cp; int cplen, l; - cp = (char *) get_property(device, "compatible", &cplen); + cp = get_property(device, "compatible", &cplen); if (cp == NULL) return 0; while (cplen > 0) { @@ -1820,7 +1355,6 @@ static void of_node_release(struct kref *kref) node->deadprops = NULL; } } - kfree(node->intrs); kfree(node->full_name); kfree(node->data); kfree(node); @@ -1893,20 +1427,14 @@ void of_detach_node(const struct device_node *np) #ifdef CONFIG_PPC_PSERIES /* * Fix up the uninitialized fields in a new device node: - * name, type, n_addrs, addrs, n_intrs, intrs, and pci-specific fields - * - * A lot of boot-time code is duplicated here, because functions such - * as finish_node_interrupts, interpret_pci_props, etc. cannot use the - * slab allocator. - * - * This should probably be split up into smaller chunks. + * name, type and pci-specific fields */ static int of_finish_dynamic_node(struct device_node *node) { struct device_node *parent = of_get_parent(node); int err = 0; - phandle *ibm_phandle; + const phandle *ibm_phandle; node->name = get_property(node, "name", NULL); node->type = get_property(node, "device_type", NULL); @@ -1923,8 +1451,7 @@ static int of_finish_dynamic_node(struct device_node *node) return -ENODEV; /* fix up new node's linux_phandle field */ - if ((ibm_phandle = (unsigned int *)get_property(node, - "ibm,phandle", NULL))) + if ((ibm_phandle = get_property(node, "ibm,phandle", NULL))) node->linux_phandle = *ibm_phandle; out: @@ -1940,8 +1467,6 @@ static int prom_reconfig_notifier(struct notifier_block *nb, switch (action) { case PSERIES_RECONFIG_ADD: err = of_finish_dynamic_node(node); - if (!err) - finish_node(node, NULL, 0); if (err < 0) { printk(KERN_ERR "finish_node returned %d\n", err); err = NOTIFY_BAD; @@ -1987,8 +1512,7 @@ struct property *of_find_property(struct device_node *np, const char *name, * Find a property with a given name for a given node * and return the value. */ -unsigned char *get_property(struct device_node *np, const char *name, - int *lenp) +const void *get_property(struct device_node *np, const char *name, int *lenp) { struct property *pp = of_find_property(np,name,lenp); return pp ? pp->value : NULL; @@ -2118,16 +1642,16 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) hardid = get_hard_smp_processor_id(cpu); for_each_node_by_type(np, "cpu") { - u32 *intserv; + const u32 *intserv; unsigned int plen, t; /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist * fallback to "reg" property and assume no threads */ - intserv = (u32 *)get_property(np, "ibm,ppc-interrupt-server#s", - &plen); + intserv = get_property(np, "ibm,ppc-interrupt-server#s", + &plen); if (intserv == NULL) { - u32 *reg = (u32 *)get_property(np, "reg", NULL); + const u32 *reg = get_property(np, "reg", NULL); if (reg == NULL) continue; if (*reg == hardid) { @@ -2148,3 +1672,27 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) } return NULL; } + +#ifdef DEBUG +static struct debugfs_blob_wrapper flat_dt_blob; + +static int __init export_flat_device_tree(void) +{ + struct dentry *d; + + d = debugfs_create_dir("powerpc", NULL); + if (!d) + return 1; + + flat_dt_blob.data = initial_boot_params; + flat_dt_blob.size = initial_boot_params->totalsize; + + d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR, + d, &flat_dt_blob); + if (!d) + return 1; + + return 0; +} +__initcall(export_flat_device_tree); +#endif diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 8c28eb0cbdac..b91761639d96 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -16,7 +16,6 @@ #undef DEBUG_PROM #include <stdarg.h> -#include <linux/config.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> @@ -558,7 +557,9 @@ unsigned long prom_memparse(const char *ptr, const char **retptr) static void __init early_cmdline_parse(void) { struct prom_t *_prom = &RELOC(prom); +#ifdef CONFIG_PPC64 const char *opt; +#endif char *p; int l = 0; @@ -645,13 +646,13 @@ static unsigned char ibm_architecture_vec[] = { 5 - 1, /* 5 option vectors */ /* option vector 1: processor architectures supported */ - 3 - 1, /* length */ + 3 - 2, /* 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 */ + 34 - 2, /* length */ OV2_REAL_MODE, 0, 0, W(0xffffffff), /* real_base */ @@ -665,16 +666,16 @@ static unsigned char ibm_architecture_vec[] = { 48, /* max log_2(hash table size) */ /* option vector 3: processor options supported */ - 3 - 1, /* length */ + 3 - 2, /* length */ 0, /* don't ignore, don't halt */ OV3_FP | OV3_VMX, /* option vector 4: IBM PAPR implementation */ - 2 - 1, /* length */ + 2 - 2, /* length */ 0, /* don't halt */ /* option vector 5: PAPR/OF options */ - 3 - 1, /* length */ + 3 - 2, /* length */ 0, /* don't ignore, don't halt */ OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES, }; @@ -988,7 +989,7 @@ static void reserve_mem(u64 base, u64 size) } /* - * Initialize memory allocation mecanism, parse "memory" nodes and + * Initialize memory allocation mechanism, parse "memory" nodes and * obtain that way the top of memory and RMO to setup out local allocator */ static void __init prom_init_mem(void) @@ -1991,12 +1992,22 @@ static void __init flatten_device_tree(void) static void __init fixup_device_tree_maple(void) { phandle isa; + u32 rloc = 0x01002000; /* IO space; PCI device = 4 */ u32 isa_ranges[6]; - - isa = call_prom("finddevice", 1, 1, ADDR("/ht@0/isa@4")); + char *name; + + name = "/ht@0/isa@4"; + isa = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(isa)) { + name = "/ht@0/isa@6"; + isa = call_prom("finddevice", 1, 1, ADDR(name)); + rloc = 0x01003000; /* IO space; PCI device = 6 */ + } if (!PHANDLE_VALID(isa)) return; + if (prom_getproplen(isa, "ranges") != 12) + return; if (prom_getprop(isa, "ranges", isa_ranges, sizeof(isa_ranges)) == PROM_ERROR) return; @@ -2006,21 +2017,60 @@ static void __init fixup_device_tree_maple(void) isa_ranges[2] != 0x00010000) return; - prom_printf("fixing up bogus ISA range on Maple...\n"); + prom_printf("Fixing up bogus ISA range on Maple/Apache...\n"); isa_ranges[0] = 0x1; isa_ranges[1] = 0x0; - isa_ranges[2] = 0x01002000; /* IO space; PCI device = 4 */ + isa_ranges[2] = rloc; isa_ranges[3] = 0x0; isa_ranges[4] = 0x0; isa_ranges[5] = 0x00010000; - prom_setprop(isa, "/ht@0/isa@4", "ranges", + prom_setprop(isa, name, "ranges", isa_ranges, sizeof(isa_ranges)); } #else #define fixup_device_tree_maple() #endif +#ifdef CONFIG_PPC_CHRP +/* Pegasos and BriQ lacks the "ranges" property in the isa node */ +static void __init fixup_device_tree_chrp(void) +{ + phandle isa; + u32 isa_ranges[6]; + u32 rloc = 0x01006000; /* IO space; PCI device = 12 */ + char *name; + int rc; + + name = "/pci@80000000/isa@c"; + isa = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(isa)) { + name = "/pci@ff500000/isa@6"; + isa = call_prom("finddevice", 1, 1, ADDR(name)); + rloc = 0x01003000; /* IO space; PCI device = 6 */ + } + if (!PHANDLE_VALID(isa)) + return; + + rc = prom_getproplen(isa, "ranges"); + if (rc != 0 && rc != PROM_ERROR) + return; + + prom_printf("Fixing up missing ISA range on Pegasos...\n"); + + isa_ranges[0] = 0x1; + isa_ranges[1] = 0x0; + isa_ranges[2] = rloc; + isa_ranges[3] = 0x0; + isa_ranges[4] = 0x0; + isa_ranges[5] = 0x00010000; + prom_setprop(isa, name, "ranges", + isa_ranges, sizeof(isa_ranges)); +} +#else +#define fixup_device_tree_chrp() +#endif + #if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC) static void __init fixup_device_tree_pmac(void) { @@ -2068,6 +2118,7 @@ static void __init fixup_device_tree_pmac(void) static void __init fixup_device_tree(void) { fixup_device_tree_maple(); + fixup_device_tree_chrp(); fixup_device_tree_pmac(); } diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 45df420383cc..603dff3ad62a 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -27,7 +27,7 @@ /* Debug utility */ #ifdef DEBUG -static void of_dump_addr(const char *s, u32 *addr, int na) +static void of_dump_addr(const char *s, const u32 *addr, int na) { printk("%s", s); while(na--) @@ -35,17 +35,9 @@ static void of_dump_addr(const char *s, u32 *addr, int na) printk("\n"); } #else -static void of_dump_addr(const char *s, u32 *addr, int na) { } +static void of_dump_addr(const char *s, const u32 *addr, int na) { } #endif -/* Read a big address */ -static inline u64 of_read_addr(u32 *cell, int size) -{ - u64 r = 0; - while (size--) - r = (r << 32) | *(cell++); - return r; -} /* Callbacks for bus specific translators */ struct of_bus { @@ -54,9 +46,10 @@ struct of_bus { int (*match)(struct device_node *parent); void (*count_cells)(struct device_node *child, int *addrc, int *sizec); - u64 (*map)(u32 *addr, u32 *range, int na, int ns, int pna); + u64 (*map)(u32 *addr, const u32 *range, + int na, int ns, int pna); int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(u32 *addr); + unsigned int (*get_flags)(const u32 *addr); }; @@ -73,13 +66,14 @@ static void of_bus_default_count_cells(struct device_node *dev, *sizec = prom_n_size_cells(dev); } -static u64 of_bus_default_map(u32 *addr, u32 *range, int na, int ns, int pna) +static u64 of_bus_default_map(u32 *addr, const u32 *range, + int na, int ns, int pna) { u64 cp, s, da; - cp = of_read_addr(range, na); - s = of_read_addr(range + na + pna, ns); - da = of_read_addr(addr, na); + cp = of_read_number(range, na); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr, na); DBG("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); @@ -91,7 +85,7 @@ static u64 of_bus_default_map(u32 *addr, u32 *range, int na, int ns, int pna) static int of_bus_default_translate(u32 *addr, u64 offset, int na) { - u64 a = of_read_addr(addr, na); + u64 a = of_read_number(addr, na); memset(addr, 0, na * 4); a += offset; if (na > 1) @@ -101,7 +95,7 @@ static int of_bus_default_translate(u32 *addr, u64 offset, int na) return 0; } -static unsigned int of_bus_default_get_flags(u32 *addr) +static unsigned int of_bus_default_get_flags(const u32 *addr) { return IORESOURCE_MEM; } @@ -126,7 +120,7 @@ static void of_bus_pci_count_cells(struct device_node *np, *sizec = 2; } -static u64 of_bus_pci_map(u32 *addr, u32 *range, int na, int ns, int pna) +static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) { u64 cp, s, da; @@ -135,9 +129,9 @@ static u64 of_bus_pci_map(u32 *addr, u32 *range, int na, int ns, int pna) return OF_BAD_ADDR; /* Read address values, skipping high cell */ - cp = of_read_addr(range + 1, na - 1); - s = of_read_addr(range + na + pna, ns); - da = of_read_addr(addr + 1, na - 1); + cp = of_read_number(range + 1, na - 1); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr + 1, na - 1); DBG("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); @@ -151,7 +145,7 @@ static int of_bus_pci_translate(u32 *addr, u64 offset, int na) return of_bus_default_translate(addr + 1, offset, na - 1); } -static unsigned int of_bus_pci_get_flags(u32 *addr) +static unsigned int of_bus_pci_get_flags(const u32 *addr) { unsigned int flags = 0; u32 w = addr[0]; @@ -186,7 +180,7 @@ static void of_bus_isa_count_cells(struct device_node *child, *sizec = 1; } -static u64 of_bus_isa_map(u32 *addr, u32 *range, int na, int ns, int pna) +static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) { u64 cp, s, da; @@ -195,9 +189,9 @@ static u64 of_bus_isa_map(u32 *addr, u32 *range, int na, int ns, int pna) return OF_BAD_ADDR; /* Read address values, skipping high cell */ - cp = of_read_addr(range + 1, na - 1); - s = of_read_addr(range + na + pna, ns); - da = of_read_addr(addr + 1, na - 1); + cp = of_read_number(range + 1, na - 1); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr + 1, na - 1); DBG("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); @@ -211,7 +205,7 @@ static int of_bus_isa_translate(u32 *addr, u64 offset, int na) return of_bus_default_translate(addr + 1, offset, na - 1); } -static unsigned int of_bus_isa_get_flags(u32 *addr) +static unsigned int of_bus_isa_get_flags(const u32 *addr) { unsigned int flags = 0; u32 w = addr[0]; @@ -276,7 +270,7 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, struct of_bus *pbus, u32 *addr, int na, int ns, int pna) { - u32 *ranges; + const u32 *ranges; unsigned int rlen; int rone; u64 offset = OF_BAD_ADDR; @@ -293,9 +287,9 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, * to translate addresses that aren't supposed to be translated in * the first place. --BenH. */ - ranges = (u32 *)get_property(parent, "ranges", &rlen); + ranges = get_property(parent, "ranges", &rlen); if (ranges == NULL || rlen == 0) { - offset = of_read_addr(addr, na); + offset = of_read_number(addr, na); memset(addr, 0, pna * 4); DBG("OF: no ranges, 1:1 translation\n"); goto finish; @@ -336,7 +330,7 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, * that can be mapped to a cpu physical address). This is not really specified * that way, but this is traditionally the way IBM at least do things */ -u64 of_translate_address(struct device_node *dev, u32 *in_addr) +u64 of_translate_address(struct device_node *dev, const u32 *in_addr) { struct device_node *parent = NULL; struct of_bus *bus, *pbus; @@ -378,7 +372,7 @@ u64 of_translate_address(struct device_node *dev, u32 *in_addr) /* If root, we have finished */ if (parent == NULL) { DBG("OF: reached root node\n"); - result = of_read_addr(addr, na); + result = of_read_number(addr, na); break; } @@ -413,10 +407,10 @@ u64 of_translate_address(struct device_node *dev, u32 *in_addr) } EXPORT_SYMBOL(of_translate_address); -u32 *of_get_address(struct device_node *dev, int index, u64 *size, +const u32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { - u32 *prop; + const u32 *prop; unsigned int psize; struct device_node *parent; struct of_bus *bus; @@ -433,7 +427,7 @@ u32 *of_get_address(struct device_node *dev, int index, u64 *size, return NULL; /* Get "reg" or "assigned-addresses" property */ - prop = (u32 *)get_property(dev, bus->addresses, &psize); + prop = get_property(dev, bus->addresses, &psize); if (prop == NULL) return NULL; psize /= 4; @@ -442,7 +436,7 @@ u32 *of_get_address(struct device_node *dev, int index, u64 *size, for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) if (i == index) { if (size) - *size = of_read_addr(prop + na, ns); + *size = of_read_number(prop + na, ns); if (flags) *flags = bus->get_flags(prop); return prop; @@ -451,10 +445,10 @@ u32 *of_get_address(struct device_node *dev, int index, u64 *size, } EXPORT_SYMBOL(of_get_address); -u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, +const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags) { - u32 *prop; + const u32 *prop; unsigned int psize; struct device_node *parent; struct of_bus *bus; @@ -475,7 +469,7 @@ u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, return NULL; /* Get "reg" or "assigned-addresses" property */ - prop = (u32 *)get_property(dev, bus->addresses, &psize); + prop = get_property(dev, bus->addresses, &psize); if (prop == NULL) return NULL; psize /= 4; @@ -484,7 +478,7 @@ u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { if (size) - *size = of_read_addr(prop + na, ns); + *size = of_read_number(prop + na, ns); if (flags) *flags = bus->get_flags(prop); return prop; @@ -493,7 +487,7 @@ u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, } EXPORT_SYMBOL(of_get_pci_address); -static int __of_address_to_resource(struct device_node *dev, u32 *addrp, +static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, u64 size, unsigned int flags, struct resource *r) { @@ -524,7 +518,7 @@ static int __of_address_to_resource(struct device_node *dev, u32 *addrp, int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { - u32 *addrp; + const u32 *addrp; u64 size; unsigned int flags; @@ -538,7 +532,7 @@ EXPORT_SYMBOL_GPL(of_address_to_resource); int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r) { - u32 *addrp; + const u32 *addrp; u64 size; unsigned int flags; @@ -549,13 +543,14 @@ int of_pci_address_to_resource(struct device_node *dev, int bar, } EXPORT_SYMBOL_GPL(of_pci_address_to_resource); -void of_parse_dma_window(struct device_node *dn, unsigned char *dma_window_prop, +void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, unsigned long *busno, unsigned long *phys, unsigned long *size) { - u32 *dma_window, cells; - unsigned char *prop; + const u32 *dma_window; + u32 cells; + const unsigned char *prop; - dma_window = (u32 *)dma_window_prop; + dma_window = dma_window_prop; /* busno is always one cell */ *busno = *(dma_window++); @@ -565,11 +560,425 @@ void of_parse_dma_window(struct device_node *dn, unsigned char *dma_window_prop, prop = get_property(dn, "#address-cells", NULL); cells = prop ? *(u32 *)prop : prom_n_addr_cells(dn); - *phys = of_read_addr(dma_window, cells); + *phys = of_read_number(dma_window, cells); dma_window += cells; prop = get_property(dn, "ibm,#dma-size-cells", NULL); cells = prop ? *(u32 *)prop : prom_n_size_cells(dn); - *size = of_read_addr(dma_window, cells); + *size = of_read_number(dma_window, cells); +} + +/* + * Interrupt remapper + */ + +static unsigned int of_irq_workarounds; +static struct device_node *of_irq_dflt_pic; + +static struct device_node *of_irq_find_parent(struct device_node *child) +{ + struct device_node *p; + const phandle *parp; + + if (!of_node_get(child)) + return NULL; + + do { + parp = get_property(child, "interrupt-parent", NULL); + if (parp == NULL) + p = of_get_parent(child); + else { + if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) + p = of_node_get(of_irq_dflt_pic); + else + p = of_find_node_by_phandle(*parp); + } + of_node_put(child); + child = p; + } while (p && get_property(p, "#interrupt-cells", NULL) == NULL); + + return p; +} + +/* This doesn't need to be called if you don't have any special workaround + * flags to pass + */ +void of_irq_map_init(unsigned int flags) +{ + of_irq_workarounds = flags; + + /* OldWorld, don't bother looking at other things */ + if (flags & OF_IMAP_OLDWORLD_MAC) + return; + + /* If we don't have phandles, let's try to locate a default interrupt + * controller (happens when booting with BootX). We do a first match + * here, hopefully, that only ever happens on machines with one + * controller. + */ + if (flags & OF_IMAP_NO_PHANDLE) { + struct device_node *np; + + for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) { + if (get_property(np, "interrupt-controller", NULL) + == NULL) + continue; + /* Skip /chosen/interrupt-controller */ + if (strcmp(np->name, "chosen") == 0) + continue; + /* It seems like at least one person on this planet wants + * to use BootX on a machine with an AppleKiwi controller + * which happens to pretend to be an interrupt + * controller too. + */ + if (strcmp(np->name, "AppleKiwi") == 0) + continue; + /* I think we found one ! */ + of_irq_dflt_pic = np; + break; + } + } + +} + +int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize, + const u32 *addr, struct of_irq *out_irq) +{ + struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; + const u32 *tmp, *imap, *imask; + u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; + int imaplen, match, i; + + DBG("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n", + parent->full_name, intspec[0], intspec[1], ointsize); + + ipar = of_node_get(parent); + + /* First get the #interrupt-cells property of the current cursor + * that tells us how to interpret the passed-in intspec. If there + * is none, we are nice and just walk up the tree + */ + do { + tmp = get_property(ipar, "#interrupt-cells", NULL); + if (tmp != NULL) { + intsize = *tmp; + break; + } + tnode = ipar; + ipar = of_irq_find_parent(ipar); + of_node_put(tnode); + } while (ipar); + if (ipar == NULL) { + DBG(" -> no parent found !\n"); + goto fail; + } + + DBG("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize); + + if (ointsize != intsize) + return -EINVAL; + + /* Look for this #address-cells. We have to implement the old linux + * trick of looking for the parent here as some device-trees rely on it + */ + old = of_node_get(ipar); + do { + tmp = get_property(old, "#address-cells", NULL); + tnode = of_get_parent(old); + of_node_put(old); + old = tnode; + } while(old && tmp == NULL); + of_node_put(old); + old = NULL; + addrsize = (tmp == NULL) ? 2 : *tmp; + + DBG(" -> addrsize=%d\n", addrsize); + + /* Now start the actual "proper" walk of the interrupt tree */ + while (ipar != NULL) { + /* Now check if cursor is an interrupt-controller and if it is + * then we are done + */ + if (get_property(ipar, "interrupt-controller", NULL) != NULL) { + DBG(" -> got it !\n"); + memcpy(out_irq->specifier, intspec, + intsize * sizeof(u32)); + out_irq->size = intsize; + out_irq->controller = ipar; + of_node_put(old); + return 0; + } + + /* Now look for an interrupt-map */ + imap = get_property(ipar, "interrupt-map", &imaplen); + /* No interrupt map, check for an interrupt parent */ + if (imap == NULL) { + DBG(" -> no map, getting parent\n"); + newpar = of_irq_find_parent(ipar); + goto skiplevel; + } + imaplen /= sizeof(u32); + + /* Look for a mask */ + imask = get_property(ipar, "interrupt-map-mask", NULL); + + /* If we were passed no "reg" property and we attempt to parse + * an interrupt-map, then #address-cells must be 0. + * Fail if it's not. + */ + if (addr == NULL && addrsize != 0) { + DBG(" -> no reg passed in when needed !\n"); + goto fail; + } + + /* Parse interrupt-map */ + match = 0; + while (imaplen > (addrsize + intsize + 1) && !match) { + /* Compare specifiers */ + match = 1; + for (i = 0; i < addrsize && match; ++i) { + u32 mask = imask ? imask[i] : 0xffffffffu; + match = ((addr[i] ^ imap[i]) & mask) == 0; + } + for (; i < (addrsize + intsize) && match; ++i) { + u32 mask = imask ? imask[i] : 0xffffffffu; + match = + ((intspec[i-addrsize] ^ imap[i]) & mask) == 0; + } + imap += addrsize + intsize; + imaplen -= addrsize + intsize; + + DBG(" -> match=%d (imaplen=%d)\n", match, imaplen); + + /* Get the interrupt parent */ + if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) + newpar = of_node_get(of_irq_dflt_pic); + else + newpar = of_find_node_by_phandle((phandle)*imap); + imap++; + --imaplen; + + /* Check if not found */ + if (newpar == NULL) { + DBG(" -> imap parent not found !\n"); + goto fail; + } + + /* Get #interrupt-cells and #address-cells of new + * parent + */ + tmp = get_property(newpar, "#interrupt-cells", + NULL); + if (tmp == NULL) { + DBG(" -> parent lacks #interrupt-cells !\n"); + goto fail; + } + newintsize = *tmp; + tmp = get_property(newpar, "#address-cells", + NULL); + newaddrsize = (tmp == NULL) ? 0 : *tmp; + + DBG(" -> newintsize=%d, newaddrsize=%d\n", + newintsize, newaddrsize); + + /* Check for malformed properties */ + if (imaplen < (newaddrsize + newintsize)) + goto fail; + + imap += newaddrsize + newintsize; + imaplen -= newaddrsize + newintsize; + + DBG(" -> imaplen=%d\n", imaplen); + } + if (!match) + goto fail; + + of_node_put(old); + old = of_node_get(newpar); + addrsize = newaddrsize; + intsize = newintsize; + intspec = imap - intsize; + addr = intspec - addrsize; + + skiplevel: + /* Iterate again with new parent */ + DBG(" -> new parent: %s\n", newpar ? newpar->full_name : "<>"); + of_node_put(ipar); + ipar = newpar; + newpar = NULL; + } + fail: + of_node_put(ipar); + of_node_put(old); + of_node_put(newpar); + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(of_irq_map_raw); + +#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) +static int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + const u32 *ints; + int intlen; + + /* + * Old machines just have a list of interrupt numbers + * and no interrupt-controller nodes. + */ + ints = get_property(device, "AAPL,interrupts", &intlen); + if (ints == NULL) + return -EINVAL; + intlen /= sizeof(u32); + + if (index >= intlen) + return -EINVAL; + + out_irq->controller = NULL; + out_irq->specifier[0] = ints[index]; + out_irq->size = 1; + + return 0; +} +#else /* defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) */ +static int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + return -EINVAL; +} +#endif /* !(defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)) */ + +int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq) +{ + struct device_node *p; + const u32 *intspec, *tmp, *addr; + u32 intsize, intlen; + int res; + + DBG("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index); + + /* OldWorld mac stuff is "special", handle out of line */ + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return of_irq_map_oldworld(device, index, out_irq); + + /* Get the interrupts property */ + intspec = get_property(device, "interrupts", &intlen); + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(u32); + + /* Get the reg property (if any) */ + addr = get_property(device, "reg", NULL); + + /* Look for the interrupt parent. */ + p = of_irq_find_parent(device); + if (p == NULL) + return -EINVAL; + + /* Get size of interrupt specifier */ + tmp = get_property(p, "#interrupt-cells", NULL); + if (tmp == NULL) { + of_node_put(p); + return -EINVAL; + } + intsize = *tmp; + + DBG(" intsize=%d intlen=%d\n", intsize, intlen); + + /* Check index */ + if ((index + 1) * intsize > intlen) + return -EINVAL; + + /* Get new specifier and map it */ + res = of_irq_map_raw(p, intspec + index * intsize, intsize, + addr, out_irq); + of_node_put(p); + return res; +} +EXPORT_SYMBOL_GPL(of_irq_map_one); + +#ifdef CONFIG_PCI +static u8 of_irq_pci_swizzle(u8 slot, u8 pin) +{ + return (((pin - 1) + slot) % 4) + 1; +} + +int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) +{ + struct device_node *dn, *ppnode; + struct pci_dev *ppdev; + u32 lspec; + u32 laddr[3]; + u8 pin; + int rc; + + /* Check if we have a device node, if yes, fallback to standard OF + * parsing + */ + dn = pci_device_to_OF_node(pdev); + if (dn) + return of_irq_map_one(dn, 0, out_irq); + + /* Ok, we don't, time to have fun. Let's start by building up an + * interrupt spec. we assume #interrupt-cells is 1, which is standard + * for PCI. If you do different, then don't use that routine. + */ + rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin); + if (rc != 0) + return rc; + /* No pin, exit */ + if (pin == 0) + return -ENODEV; + + /* Now we walk up the PCI tree */ + lspec = pin; + for (;;) { + /* Get the pci_dev of our parent */ + ppdev = pdev->bus->self; + + /* Ouch, it's a host bridge... */ + if (ppdev == NULL) { +#ifdef CONFIG_PPC64 + ppnode = pci_bus_to_OF_node(pdev->bus); +#else + struct pci_controller *host; + host = pci_bus_to_host(pdev->bus); + ppnode = host ? host->arch_data : NULL; +#endif + /* No node for host bridge ? give up */ + if (ppnode == NULL) + return -EINVAL; + } else + /* We found a P2P bridge, check if it has a node */ + ppnode = pci_device_to_OF_node(ppdev); + + /* Ok, we have found a parent with a device-node, hand over to + * the OF parsing code. + * We build a unit address from the linux device to be used for + * resolution. Note that we use the linux bus number which may + * not match your firmware bus numbering. + * Fortunately, in most cases, interrupt-map-mask doesn't include + * the bus number as part of the matching. + * You should still be careful about that though if you intend + * to rely on this function (you ship a firmware that doesn't + * create device nodes for all PCI devices). + */ + if (ppnode) + break; + + /* We can only get here if we hit a P2P bridge with no node, + * let's do standard swizzling and try again + */ + lspec = of_irq_pci_swizzle(PCI_SLOT(pdev->devfn), lspec); + pdev = ppdev; + } + + laddr[0] = (pdev->bus->number << 16) + | (pdev->devfn << 8); + laddr[1] = laddr[2] = 0; + return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq); } +EXPORT_SYMBOL_GPL(of_irq_map_pci); +#endif /* CONFIG_PCI */ diff --git a/arch/powerpc/kernel/ptrace-common.h b/arch/powerpc/kernel/ptrace-common.h index c42a860c8d25..8797ae737a7b 100644 --- a/arch/powerpc/kernel/ptrace-common.h +++ b/arch/powerpc/kernel/ptrace-common.h @@ -10,7 +10,6 @@ #ifndef _PPC64_PTRACE_COMMON_H #define _PPC64_PTRACE_COMMON_H -#include <linux/config.h> #include <asm/system.h> /* diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 5563e2e7d89c..dea75d73f983 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -15,7 +15,6 @@ * this archive for more details. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 826ee3d056de..9b9a230349bc 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -17,7 +17,6 @@ * this archive for more details. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 9c9ad1fa9cce..2fe82abf1c52 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -246,12 +246,12 @@ struct file_operations ppc_rtas_rmo_buf_ops = { static int ppc_rtas_find_all_sensors(void); static void ppc_rtas_process_sensor(struct seq_file *m, - struct individual_sensor *s, int state, int error, char *loc); + struct individual_sensor *s, int state, int error, const char *loc); static char *ppc_rtas_process_error(int error); static void get_location_code(struct seq_file *m, - struct individual_sensor *s, char *loc); -static void check_location_string(struct seq_file *m, char *c); -static void check_location(struct seq_file *m, char *c); + struct individual_sensor *s, const char *loc); +static void check_location_string(struct seq_file *m, const char *c); +static void check_location(struct seq_file *m, const char *c); static int __init proc_rtas_init(void) { @@ -446,11 +446,11 @@ static int ppc_rtas_sensors_show(struct seq_file *m, void *v) for (i=0; i<sensors.quant; i++) { struct individual_sensor *p = &sensors.sensor[i]; char rstr[64]; - char *loc; + const char *loc; int llen, offs; sprintf (rstr, SENSOR_PREFIX"%04d", p->token); - loc = (char *) get_property(rtas_node, rstr, &llen); + loc = get_property(rtas_node, rstr, &llen); /* A sensor may have multiple instances */ for (j = 0, offs = 0; j <= p->quant; j++) { @@ -474,10 +474,10 @@ static int ppc_rtas_sensors_show(struct seq_file *m, void *v) static int ppc_rtas_find_all_sensors(void) { - unsigned int *utmp; + const unsigned int *utmp; int len, i; - utmp = (unsigned int *) get_property(rtas_node, "rtas-sensors", &len); + utmp = get_property(rtas_node, "rtas-sensors", &len); if (utmp == NULL) { printk (KERN_ERR "error: could not get rtas-sensors\n"); return 1; @@ -530,7 +530,7 @@ static char *ppc_rtas_process_error(int error) */ static void ppc_rtas_process_sensor(struct seq_file *m, - struct individual_sensor *s, int state, int error, char *loc) + struct individual_sensor *s, int state, int error, const char *loc) { /* Defined return vales */ const char * key_switch[] = { "Off\t", "Normal\t", "Secure\t", @@ -682,7 +682,7 @@ static void ppc_rtas_process_sensor(struct seq_file *m, /* ****************************************************************** */ -static void check_location(struct seq_file *m, char *c) +static void check_location(struct seq_file *m, const char *c) { switch (c[0]) { case LOC_PLANAR: @@ -719,7 +719,7 @@ static void check_location(struct seq_file *m, char *c) * ${LETTER}${NUMBER}[[-/]${LETTER}${NUMBER} [ ... ] ] * the '.' may be an abbrevation */ -static void check_location_string(struct seq_file *m, char *c) +static void check_location_string(struct seq_file *m, const char *c) { while (*c) { if (isalpha(*c) || *c == '.') @@ -733,7 +733,8 @@ static void check_location_string(struct seq_file *m, char *c) /* ****************************************************************** */ -static void get_location_code(struct seq_file *m, struct individual_sensor *s, char *loc) +static void get_location_code(struct seq_file *m, struct individual_sensor *s, + const char *loc) { if (!loc || !*loc) { seq_printf(m, "---");/* does not have a location */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 17dc79198515..6ef80d4e38d3 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -38,16 +38,19 @@ struct rtas_t rtas = { .lock = SPIN_LOCK_UNLOCKED }; +EXPORT_SYMBOL(rtas); struct rtas_suspend_me_data { long waiting; struct rtas_args *args; }; -EXPORT_SYMBOL(rtas); - DEFINE_SPINLOCK(rtas_data_buf_lock); +EXPORT_SYMBOL(rtas_data_buf_lock); + char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; +EXPORT_SYMBOL(rtas_data_buf); + unsigned long rtas_rmo_buf; /* @@ -106,18 +109,80 @@ static void call_rtas_display_status_delay(char c) } } -void __init udbg_init_rtas(void) +void __init udbg_init_rtas_panel(void) { udbg_putc = call_rtas_display_status_delay; } +#ifdef CONFIG_UDBG_RTAS_CONSOLE + +/* If you think you're dying before early_init_dt_scan_rtas() does its + * work, you can hard code the token values for your firmware here and + * hardcode rtas.base/entry etc. + */ +static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE; +static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE; + +static void udbg_rtascon_putc(char c) +{ + int tries; + + if (!rtas.base) + return; + + /* Add CRs before LFs */ + if (c == '\n') + udbg_rtascon_putc('\r'); + + /* if there is more than one character to be displayed, wait a bit */ + for (tries = 0; tries < 16; tries++) { + if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0) + break; + udelay(1000); + } +} + +static int udbg_rtascon_getc_poll(void) +{ + int c; + + if (!rtas.base) + return -1; + + if (rtas_call(rtas_getchar_token, 0, 2, &c)) + return -1; + + return c; +} + +static int udbg_rtascon_getc(void) +{ + int c; + + while ((c = udbg_rtascon_getc_poll()) == -1) + ; + + return c; +} + + +void __init udbg_init_rtas_console(void) +{ + udbg_putc = udbg_rtascon_putc; + udbg_getc = udbg_rtascon_getc; + udbg_getc_poll = udbg_rtascon_getc_poll; +} +#endif /* CONFIG_UDBG_RTAS_CONSOLE */ + void rtas_progress(char *s, unsigned short hex) { struct device_node *root; - int width, *p; + int width; + const int *p; char *os; static int display_character, set_indicator; - static int display_width, display_lines, *row_width, form_feed; + static int display_width, display_lines, form_feed; + const static int *row_width; static DEFINE_SPINLOCK(progress_lock); static int current_line; static int pending_newline = 0; /* did last write end with unprinted newline? */ @@ -128,16 +193,16 @@ void rtas_progress(char *s, unsigned short hex) if (display_width == 0) { display_width = 0x10; if ((root = find_path_device("/rtas"))) { - if ((p = (unsigned int *)get_property(root, + if ((p = get_property(root, "ibm,display-line-length", NULL))) display_width = *p; - if ((p = (unsigned int *)get_property(root, + if ((p = get_property(root, "ibm,form-feed", NULL))) form_feed = *p; - if ((p = (unsigned int *)get_property(root, + if ((p = get_property(root, "ibm,display-number-of-lines", NULL))) display_lines = *p; - row_width = (unsigned int *)get_property(root, + row_width = get_property(root, "ibm,display-truncation-length", NULL); } display_character = rtas_token("display-character"); @@ -230,12 +295,13 @@ EXPORT_SYMBOL(rtas_progress); /* needed by rtas_flash module */ int rtas_token(const char *service) { - int *tokp; + const int *tokp; if (rtas.dev == NULL) return RTAS_UNKNOWN_SERVICE; - tokp = (int *) get_property(rtas.dev, service, NULL); + tokp = get_property(rtas.dev, service, NULL); return tokp ? *tokp : RTAS_UNKNOWN_SERVICE; } +EXPORT_SYMBOL(rtas_token); #ifdef CONFIG_RTAS_ERROR_LOGGING /* @@ -328,7 +394,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) char *buff_copy = NULL; int ret; - if (token == RTAS_UNKNOWN_SERVICE) + if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) return -1; /* Gotta do something different here, use global lock for now... */ @@ -369,6 +435,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) } return ret; } +EXPORT_SYMBOL(rtas_call); /* For RTAS_BUSY (-2), delay for 1 millisecond. For an extended busy status * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds. @@ -388,6 +455,7 @@ unsigned int rtas_busy_delay_time(int status) return ms; } +EXPORT_SYMBOL(rtas_busy_delay_time); /* For an RTAS busy status code, perform the hinted delay. */ unsigned int rtas_busy_delay(int status) @@ -401,6 +469,7 @@ unsigned int rtas_busy_delay(int status) return ms; } +EXPORT_SYMBOL(rtas_busy_delay); int rtas_error_rc(int rtas_rc) { @@ -446,6 +515,7 @@ int rtas_get_power_level(int powerdomain, int *level) return rtas_error_rc(rc); return rc; } +EXPORT_SYMBOL(rtas_get_power_level); int rtas_set_power_level(int powerdomain, int level, int *setlevel) { @@ -463,6 +533,7 @@ int rtas_set_power_level(int powerdomain, int level, int *setlevel) return rtas_error_rc(rc); return rc; } +EXPORT_SYMBOL(rtas_set_power_level); int rtas_get_sensor(int sensor, int index, int *state) { @@ -480,6 +551,7 @@ int rtas_get_sensor(int sensor, int index, int *state) return rtas_error_rc(rc); return rc; } +EXPORT_SYMBOL(rtas_get_sensor); int rtas_set_indicator(int indicator, int index, int new_value) { @@ -497,6 +569,28 @@ int rtas_set_indicator(int indicator, int index, int new_value) return rtas_error_rc(rc); return rc; } +EXPORT_SYMBOL(rtas_set_indicator); + +/* + * Ignoring RTAS extended delay + */ +int rtas_set_indicator_fast(int indicator, int index, int new_value) +{ + int rc; + int token = rtas_token("set-indicator"); + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value); + + WARN_ON(rc == -2 || (rc >= 9900 && rc <= 9905)); + + if (rc < 0) + return rtas_error_rc(rc); + + return rc; +} void rtas_restart(char *cmd) { @@ -534,6 +628,9 @@ void rtas_os_term(char *str) { int status; + if (panic_timeout) + return; + if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term")) return; @@ -595,15 +692,14 @@ static int rtas_ibm_suspend_me(struct rtas_args *args) int i; long state; long rc; - unsigned long dummy; - + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; /* Make sure the state is valid */ - rc = plpar_hcall(H_VASI_STATE, - ((u64)args->args[0] << 32) | args->args[1], - 0, 0, 0, - &state, &dummy, &dummy); + rc = plpar_hcall(H_VASI_STATE, retbuf, + ((u64)args->args[0] << 32) | args->args[1]); + + state = retbuf[0]; if (rc) { printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc); @@ -753,15 +849,15 @@ void __init rtas_initialize(void) */ rtas.dev = of_find_node_by_name(NULL, "rtas"); if (rtas.dev) { - u32 *basep, *entryp; - u32 *sizep; + const u32 *basep, *entryp, *sizep; - basep = (u32 *)get_property(rtas.dev, "linux,rtas-base", NULL); - sizep = (u32 *)get_property(rtas.dev, "rtas-size", NULL); + basep = get_property(rtas.dev, "linux,rtas-base", NULL); + sizep = get_property(rtas.dev, "rtas-size", NULL); if (basep != NULL && sizep != NULL) { rtas.base = *basep; rtas.size = *sizep; - entryp = (u32 *)get_property(rtas.dev, "linux,rtas-entry", NULL); + entryp = get_property(rtas.dev, + "linux,rtas-entry", NULL); if (entryp == NULL) /* Ugh */ rtas.entry = rtas.base; else @@ -791,14 +887,39 @@ void __init rtas_initialize(void) #endif } +int __init early_init_dt_scan_rtas(unsigned long node, + const char *uname, int depth, void *data) +{ + u32 *basep, *entryp, *sizep; -EXPORT_SYMBOL(rtas_token); -EXPORT_SYMBOL(rtas_call); -EXPORT_SYMBOL(rtas_data_buf); -EXPORT_SYMBOL(rtas_data_buf_lock); -EXPORT_SYMBOL(rtas_busy_delay_time); -EXPORT_SYMBOL(rtas_busy_delay); -EXPORT_SYMBOL(rtas_get_sensor); -EXPORT_SYMBOL(rtas_get_power_level); -EXPORT_SYMBOL(rtas_set_power_level); -EXPORT_SYMBOL(rtas_set_indicator); + if (depth != 1 || strcmp(uname, "rtas") != 0) + return 0; + + basep = of_get_flat_dt_prop(node, "linux,rtas-base", NULL); + entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL); + sizep = of_get_flat_dt_prop(node, "rtas-size", NULL); + + if (basep && entryp && sizep) { + rtas.base = *basep; + rtas.entry = *entryp; + rtas.size = *sizep; + } + +#ifdef CONFIG_UDBG_RTAS_CONSOLE + basep = of_get_flat_dt_prop(node, "put-term-char", NULL); + if (basep) + rtas_putchar_token = *basep; + + basep = of_get_flat_dt_prop(node, "get-term-char", NULL); + if (basep) + rtas_getchar_token = *basep; + + if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE && + rtas_getchar_token != RTAS_UNKNOWN_SERVICE) + udbg_init_rtas_console(); + +#endif + + /* break now */ + return 1; +} diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 6eb7e49b394a..b4a0de79c060 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -57,7 +57,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where) static int of_device_available(struct device_node * dn) { - char * status; + const char *status; status = get_property(dn, "status", NULL); @@ -81,8 +81,7 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; - addr = ((where & 0xf00) << 20) | (pdn->busno << 16) | - (pdn->devfn << 8) | (where & 0xff); + addr = rtas_config_addr(pdn->busno, pdn->devfn, where); buid = pdn->phb->buid; if (buid) { ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval, @@ -134,8 +133,7 @@ int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; - addr = ((where & 0xf00) << 20) | (pdn->busno << 16) | - (pdn->devfn << 8) | (where & 0xff); + addr = rtas_config_addr(pdn->busno, pdn->devfn, where); buid = pdn->phb->buid; if (buid) { ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr, @@ -178,7 +176,7 @@ struct pci_ops rtas_pci_ops = { int is_python(struct device_node *dev) { - char *model = (char *)get_property(dev, "model", NULL); + const char *model = get_property(dev, "model", NULL); if (model && strstr(model, "Python")) return 1; @@ -234,7 +232,7 @@ void __init init_pci_config_tokens (void) unsigned long __devinit get_phb_buid (struct device_node *phb) { int addr_cells; - unsigned int *buid_vals; + const unsigned int *buid_vals; unsigned int len; unsigned long buid; @@ -247,7 +245,7 @@ unsigned long __devinit get_phb_buid (struct device_node *phb) if (phb->parent->parent) return 0; - buid_vals = (unsigned int *) get_property(phb, "reg", &len); + buid_vals = get_property(phb, "reg", &len); if (buid_vals == NULL) return 0; @@ -264,10 +262,10 @@ unsigned long __devinit get_phb_buid (struct device_node *phb) static int phb_set_bus_ranges(struct device_node *dev, struct pci_controller *phb) { - int *bus_range; + const int *bus_range; unsigned int len; - bus_range = (int *) get_property(dev, "bus-range", &len); + bus_range = get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { return 1; } @@ -297,19 +295,9 @@ unsigned long __init find_and_init_phbs(void) struct device_node *node; struct pci_controller *phb; unsigned int index; - unsigned int root_size_cells = 0; - unsigned int *opprop = NULL; struct device_node *root = of_find_node_by_path("/"); - if (ppc64_interrupt_controller == IC_OPEN_PIC) { - opprop = (unsigned int *)get_property(root, - "platform-open-pic", NULL); - } - - root_size_cells = prom_n_size_cells(root); - index = 0; - for (node = of_get_next_child(root, NULL); node != NULL; node = of_get_next_child(root, node)) { @@ -324,13 +312,6 @@ unsigned long __init find_and_init_phbs(void) setup_phb(node, phb); pci_process_bridge_OF_ranges(phb, node, 0); pci_setup_phb_io(phb, index == 0); -#ifdef CONFIG_PPC_PSERIES - /* XXX This code need serious fixing ... --BenH */ - if (ppc64_interrupt_controller == IC_OPEN_PIC && pSeries_mpic) { - int addr = root_size_cells * (index + 2) - 1; - mpic_assign_isu(pSeries_mpic, index, opprop[addr]); - } -#endif index++; } @@ -342,15 +323,15 @@ unsigned long __init find_and_init_phbs(void) * in chosen. */ if (of_chosen) { - int *prop; + const int *prop; - prop = (int *)get_property(of_chosen, "linux,pci-probe-only", - NULL); + prop = get_property(of_chosen, + "linux,pci-probe-only", NULL); if (prop) pci_probe_only = *prop; - prop = (int *)get_property(of_chosen, - "linux,pci-assign-all-buses", NULL); + prop = get_property(of_chosen, + "linux,pci-assign-all-buses", NULL); if (prop) pci_assign_all_buses = *prop; } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bd328123af75..0af3fc1bdcc9 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -12,7 +12,6 @@ #undef DEBUG -#include <linux/config.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched.h> @@ -27,7 +26,7 @@ #include <linux/ioport.h> #include <linux/console.h> #include <linux/utsname.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/root_dev.h> #include <linux/notifier.h> #include <linux/cpu.h> @@ -305,19 +304,21 @@ struct seq_operations cpuinfo_op = { void __init check_for_initrd(void) { #ifdef CONFIG_BLK_DEV_INITRD - unsigned long *prop; + const unsigned int *prop; + int len; DBG(" -> check_for_initrd()\n"); if (of_chosen) { - prop = (unsigned long *)get_property(of_chosen, - "linux,initrd-start", NULL); + prop = get_property(of_chosen, "linux,initrd-start", &len); if (prop != NULL) { - initrd_start = (unsigned long)__va(*prop); - prop = (unsigned long *)get_property(of_chosen, - "linux,initrd-end", NULL); + initrd_start = (unsigned long) + __va(of_read_ulong(prop, len / 4)); + prop = get_property(of_chosen, + "linux,initrd-end", &len); if (prop != NULL) { - initrd_end = (unsigned long)__va(*prop); + initrd_end = (unsigned long) + __va(of_read_ulong(prop, len / 4)); initrd_below_start_ok = 1; } else initrd_start = 0; @@ -367,15 +368,14 @@ void __init smp_setup_cpu_maps(void) int cpu = 0; while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) { - int *intserv; + const int *intserv; int j, len = sizeof(u32), nthreads = 1; - intserv = (int *)get_property(dn, "ibm,ppc-interrupt-server#s", - &len); + intserv = get_property(dn, "ibm,ppc-interrupt-server#s", &len); if (intserv) nthreads = len / sizeof(int); else { - intserv = (int *) get_property(dn, "reg", NULL); + intserv = get_property(dn, "reg", NULL); if (!intserv) intserv = &cpu; /* assume logical == phys */ } @@ -396,13 +396,12 @@ void __init smp_setup_cpu_maps(void) if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) && (dn = of_find_node_by_path("/rtas"))) { int num_addr_cell, num_size_cell, maxcpus; - unsigned int *ireg; + const unsigned int *ireg; num_addr_cell = prom_n_addr_cells(dn); num_size_cell = prom_n_size_cells(dn); - ireg = (unsigned int *) - get_property(dn, "ibm,lrdr-capacity", NULL); + ireg = get_property(dn, "ibm,lrdr-capacity", NULL); if (!ireg) goto out; @@ -445,6 +444,8 @@ void __init smp_setup_cpu_maps(void) int __initdata do_early_xmon; #ifdef CONFIG_XMON +extern int xmon_no_auto_backtrace; + static int __init early_xmon(char *p) { /* ensure xmon is enabled */ @@ -453,6 +454,8 @@ static int __init early_xmon(char *p) xmon_init(1); if (strncmp(p, "off", 3) == 0) xmon_init(0); + if (strncmp(p, "nobt", 4) == 0) + xmon_no_auto_backtrace = 1; if (strncmp(p, "early", 5) != 0) return 0; } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index e5a44812441a..e0df2ba1ab9f 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -2,7 +2,6 @@ * Common prep/pmac/chrp boot and setup code. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched.h> @@ -52,7 +51,6 @@ extern void bootx_init(unsigned long r4, unsigned long phys); -boot_infos_t *boot_infos; struct ide_machdep_calls ppc_ide_md; int boot_cpuid; @@ -215,7 +213,7 @@ int __init ppc_init(void) /* register CPU devices */ for_each_possible_cpu(i) - register_cpu(&cpu_devices[i], i, NULL); + register_cpu(&cpu_devices[i], i); /* call platform init */ if (ppc_md.init != NULL) { @@ -241,7 +239,6 @@ void __init setup_arch(char **cmdline_p) ppc_md.init_early(); find_legacy_serial_ports(); - finish_device_tree(); smp_setup_cpu_maps(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 78f3a5fd43f6..00d6b8addd78 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -12,7 +12,6 @@ #undef DEBUG -#include <linux/config.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched.h> @@ -57,7 +56,6 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/lmb.h> -#include <asm/iseries/it_lp_naca.h> #include <asm/firmware.h> #include <asm/xmon.h> #include <asm/udbg.h> @@ -80,10 +78,10 @@ u64 ppc64_pft_size; * before we've read this from the device tree. */ struct ppc64_caches ppc64_caches = { - .dline_size = 0x80, - .log_dline_size = 7, - .iline_size = 0x80, - .log_iline_size = 7 + .dline_size = 0x40, + .log_dline_size = 6, + .iline_size = 0x40, + .log_iline_size = 6 }; EXPORT_SYMBOL_GPL(ppc64_caches); @@ -108,7 +106,7 @@ static int smt_enabled_cmdline; static void check_smt_enabled(void) { struct device_node *dn; - char *smt_option; + const char *smt_option; /* Allow the command line to overrule the OF option */ if (smt_enabled_cmdline) @@ -117,7 +115,7 @@ static void check_smt_enabled(void) dn = of_find_node_by_path("/options"); if (dn) { - smt_option = (char *)get_property(dn, "ibm,smt-enabled", NULL); + smt_option = get_property(dn, "ibm,smt-enabled", NULL); if (smt_option) { if (!strcmp(smt_option, "on")) @@ -149,6 +147,13 @@ early_param("smt-enabled", early_smt_enabled); #define check_smt_enabled() #endif /* CONFIG_SMP */ +/* Put the paca pointer into r13 and SPRG3 */ +void __init setup_paca(int cpu) +{ + local_paca = &paca[cpu]; + mtspr(SPRN_SPRG3, local_paca); +} + /* * Early initialization entry point. This is called by head.S * with MMU translation disabled. We rely on the "feature" of @@ -170,6 +175,9 @@ early_param("smt-enabled", early_smt_enabled); void __init early_setup(unsigned long dt_ptr) { + /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ + setup_paca(0); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); @@ -183,7 +191,7 @@ void __init early_setup(unsigned long dt_ptr) early_init_devtree(__va(dt_ptr)); /* Now we know the logical id of our boot cpu, setup the paca. */ - setup_boot_paca(); + setup_paca(boot_cpuid); /* Fix up paca fields required for the boot cpu */ get_paca()->cpu_start = 1; @@ -284,7 +292,7 @@ static void __init initialize_cache_info(void) */ if ( num_cpus == 1 ) { - u32 *sizep, *lsizep; + const u32 *sizep, *lsizep; u32 size, lsize; const char *dc, *ic; @@ -299,10 +307,10 @@ static void __init initialize_cache_info(void) size = 0; lsize = cur_cpu_spec->dcache_bsize; - sizep = (u32 *)get_property(np, "d-cache-size", NULL); + sizep = get_property(np, "d-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = (u32 *) get_property(np, dc, NULL); + lsizep = get_property(np, dc, NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -316,10 +324,10 @@ static void __init initialize_cache_info(void) size = 0; lsize = cur_cpu_spec->icache_bsize; - sizep = (u32 *)get_property(np, "i-cache-size", NULL); + sizep = get_property(np, "i-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = (u32 *)get_property(np, ic, NULL); + lsizep = get_property(np, ic, NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -350,22 +358,17 @@ void __init setup_system(void) */ unflatten_device_tree(); -#ifdef CONFIG_KEXEC - kexec_setup(); /* requires unflattened device tree. */ -#endif - /* * Fill the ppc64_caches & systemcfg structures with informations - * retrieved from the device-tree. Need to be called before - * finish_device_tree() since the later requires some of the - * informations filled up here to properly parse the interrupt - * tree. - * It also sets up the cache line sizes which allows to call - * routines like flush_icache_range (used by the hash init - * later on). + * retrieved from the device-tree. */ initialize_cache_info(); + /* + * Initialize irq remapping subsystem + */ + irq_early_init(); + #ifdef CONFIG_PPC_RTAS /* * Initialize RTAS if available @@ -393,12 +396,6 @@ void __init setup_system(void) find_legacy_serial_ports(); /* - * "Finish" the device-tree, that is do the actual parsing of - * some of the properties like the interrupt map - */ - finish_device_tree(); - - /* * Initialize xmon */ #ifdef CONFIG_XMON_DEFAULT @@ -426,8 +423,6 @@ void __init setup_system(void) printk("-----------------------------------------------------\n"); printk("ppc64_pft_size = 0x%lx\n", ppc64_pft_size); - printk("ppc64_interrupt_controller = 0x%ld\n", - ppc64_interrupt_controller); printk("physicalMemorySize = 0x%lx\n", lmb_phys_mem_size()); printk("ppc64_caches.dcache_line_size = 0x%x\n", ppc64_caches.dline_size); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index d73b25e22fca..320353f0926f 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -17,7 +17,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 6e75d7ab6d4d..f72e8e823d78 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -12,7 +12,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index 9adef3bddad4..de59c6c31a5b 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -5,7 +5,6 @@ * */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/smp.h> @@ -46,8 +45,9 @@ void __devinit smp_generic_take_timebase(void) { int cmd; u64 tb; + unsigned long flags; - local_irq_disable(); + local_irq_save(flags); while (!running) barrier(); rmb(); @@ -71,7 +71,7 @@ void __devinit smp_generic_take_timebase(void) set_tb(tb >> 32, tb & 0xfffffffful); enter_contest(tbsync->mark, -1); } - local_irq_enable(); + local_irq_restore(flags); } static int __devinit start_contest(int cmd, long offset, int num) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c5d179d4f818..6a9bc9ce54e0 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -17,7 +17,6 @@ #undef DEBUG -#include <linux/config.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> @@ -145,13 +144,15 @@ void smp_message_recv(int msg, struct pt_regs *regs) void smp_send_reschedule(int cpu) { - smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE); + if (likely(smp_ops)) + smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE); } #ifdef CONFIG_DEBUGGER void smp_send_debugger_break(int cpu) { - smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); + if (likely(smp_ops)) + smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); } #endif @@ -159,7 +160,7 @@ void smp_send_debugger_break(int cpu) void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; - if (crash_ipi_callback) { + if (crash_ipi_callback && smp_ops) { mb(); smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK); } @@ -221,6 +222,9 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic, /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); + if (unlikely(smp_ops == NULL)) + return -1; + data.func = func; data.info = info; atomic_set(&data.started, 0); @@ -358,7 +362,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus) smp_store_cpu_info(boot_cpuid); cpu_callin_map[boot_cpuid] = 1; - max_cpus = smp_ops->probe(); + if (smp_ops) + max_cpus = smp_ops->probe(); + else + max_cpus = 1; smp_space_timers(max_cpus); @@ -454,7 +461,7 @@ void generic_mach_cpu_die(void) static int __devinit cpu_enable(unsigned int cpu) { - if (smp_ops->cpu_enable) + if (smp_ops && smp_ops->cpu_enable) return smp_ops->cpu_enable(cpu); return -ENOSYS; @@ -468,7 +475,8 @@ int __devinit __cpu_up(unsigned int cpu) if (!cpu_enable(cpu)) return 0; - if (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)) + if (smp_ops == NULL || + (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu))) return -EINVAL; /* Make sure callin-map entry is 0 (can be leftover a CPU @@ -569,7 +577,8 @@ void __init smp_cpus_done(unsigned int max_cpus) old_mask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid)); - smp_ops->setup_cpu(boot_cpuid); + if (smp_ops) + smp_ops->setup_cpu(boot_cpuid); set_cpus_allowed(current, old_mask); diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 69773cc1a85f..69e8f86aa4f8 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/threads.h> #include <asm/processor.h> #include <asm/page.h> @@ -160,8 +159,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) isync /* Load ptr the list of pages to copy in r3 */ - lis r11,(pagedir_nosave - KERNELBASE)@h - ori r11,r11,pagedir_nosave@l + lis r11,(restore_pblist - KERNELBASE)@h + ori r11,r11,restore_pblist@l lwz r10,0(r11) /* Copy the pages. This is a very basic implementation, to diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index ec274e688816..5e391fc25340 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -14,7 +14,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/fs.h> @@ -741,7 +740,7 @@ asmlinkage long compat_sys_umask(u32 mask) return sys_umask((int)mask); } -#ifdef CONFIG_SYSCTL +#ifdef CONFIG_SYSCTL_SYSCALL struct __sysctl_args32 { u32 name; int nlen; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5bc2585c8036..406f308ddead 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/sysdev.h> #include <linux/cpu.h> #include <linux/smp.h> @@ -61,7 +60,7 @@ static int smt_snooze_cmdline; static int __init smt_setup(void) { struct device_node *options; - unsigned int *val; + const unsigned int *val; unsigned int cpu; if (!cpu_has_feature(CPU_FTR_SMT)) @@ -71,8 +70,7 @@ static int __init smt_setup(void) if (!options) return -ENODEV; - val = (unsigned int *)get_property(options, "ibm,smt-snooze-delay", - NULL); + val = get_property(options, "ibm,smt-snooze-delay", NULL); if (!smt_snooze_cmdline && val) { for_each_possible_cpu(cpu) per_cpu(smt_snooze_delay, cpu) = *val; @@ -232,7 +230,7 @@ static void register_cpu_online(unsigned int cpu) if (cur_cpu_spec->num_pmcs >= 8) sysdev_create_file(s, &attr_pmc8); - if (cpu_has_feature(CPU_FTR_SMT)) + if (cpu_has_feature(CPU_FTR_PURR)) sysdev_create_file(s, &attr_purr); } @@ -274,12 +272,12 @@ static void unregister_cpu_online(unsigned int cpu) if (cur_cpu_spec->num_pmcs >= 8) sysdev_remove_file(s, &attr_pmc8); - if (cpu_has_feature(CPU_FTR_SMT)) + if (cpu_has_feature(CPU_FTR_PURR)) sysdev_remove_file(s, &attr_purr); } #endif /* CONFIG_HOTPLUG_CPU */ -static int sysfs_cpu_notify(struct notifier_block *self, +static int __cpuinit sysfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned int)(long)hcpu; @@ -297,30 +295,19 @@ static int sysfs_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block sysfs_cpu_nb = { +static struct notifier_block __cpuinitdata sysfs_cpu_nb = { .notifier_call = sysfs_cpu_notify, }; /* NUMA stuff */ #ifdef CONFIG_NUMA -static struct node node_devices[MAX_NUMNODES]; - static void register_nodes(void) { int i; - for (i = 0; i < MAX_NUMNODES; i++) { - if (node_online(i)) { - int p_node = parent_node(i); - struct node *parent = NULL; - - if (p_node != i) - parent = &node_devices[p_node]; - - register_node(&node_devices[i], i, parent); - } - } + for (i = 0; i < MAX_NUMNODES; i++) + register_one_node(i); } int sysfs_add_device_to_node(struct sys_device *dev, int nid) @@ -359,23 +346,13 @@ static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL); static int __init topology_init(void) { int cpu; - struct node *parent = NULL; register_nodes(); - register_cpu_notifier(&sysfs_cpu_nb); for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); -#ifdef CONFIG_NUMA - /* The node to which a cpu belongs can't be known - * until the cpu is made present. - */ - parent = NULL; - if (cpu_present(cpu)) - parent = &node_devices[cpu_to_node(cpu)]; -#endif /* * For now, we just see if the system supports making * the RTAS calls for CPU hotplug. But, there may be a @@ -387,7 +364,7 @@ static int __init topology_init(void) c->no_control = 1; if (cpu_online(cpu) || (c->no_control == 0)) { - register_cpu(c, cpu, parent); + register_cpu(c, cpu); sysdev_create_file(&c->sysdev, &attr_physical_id); } diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index ee75ccf1a802..579de70e0b4d 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -14,7 +14,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/ppc_asm.h> #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 26bd8ea35a4e..368a4934f7ee 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -11,7 +11,6 @@ * life in portables, and add a 'performance/watt' metric somewhere in /proc */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/kernel.h> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index d20907561f46..71f71da98e7d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -32,7 +32,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/sched.h> @@ -102,7 +101,7 @@ EXPORT_SYMBOL(tb_ticks_per_sec); /* for cputime_t conversions */ u64 tb_to_xs; unsigned tb_to_us; -#define TICKLEN_SCALE (SHIFT_SCALE - 10) +#define TICKLEN_SCALE TICK_LENGTH_SHIFT u64 last_tick_len; /* units are ns / 2^TICKLEN_SCALE */ u64 ticklen_to_xs; /* 0.64 fraction */ @@ -126,15 +125,8 @@ static long timezone_offset; unsigned long ppc_proc_freq; unsigned long ppc_tb_freq; -u64 tb_last_jiffy __cacheline_aligned_in_smp; -unsigned long tb_last_stamp; - -/* - * Note that on ppc32 this only stores the bottom 32 bits of - * the timebase value, but that's enough to tell when a jiffy - * has passed. - */ -DEFINE_PER_CPU(unsigned long, last_jiffy); +static u64 tb_last_jiffy __cacheline_aligned_in_smp; +static DEFINE_PER_CPU(u64, last_jiffy); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* @@ -418,7 +410,7 @@ static __inline__ void timer_check_rtc(void) /* * This version of gettimeofday has microsecond resolution. */ -static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val) +static inline void __do_gettimeofday(struct timeval *tv) { unsigned long sec, usec; u64 tb_ticks, xsec; @@ -432,7 +424,12 @@ static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val) * without a divide (and in fact, without a multiply) */ temp_varp = do_gtod.varp; - tb_ticks = tb_val - temp_varp->tb_orig_stamp; + + /* Sampling the time base must be done after loading + * do_gtod.varp in order to avoid racing with update_gtod. + */ + data_barrier(temp_varp); + tb_ticks = get_tb() - temp_varp->tb_orig_stamp; temp_tb_to_xs = temp_varp->tb_to_xs; temp_stamp_xsec = temp_varp->stamp_xsec; xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs); @@ -454,7 +451,7 @@ void do_gettimeofday(struct timeval *tv) do { seq = read_seqbegin_irqsave(&xtime_lock, flags); sec = xtime.tv_sec; - nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp); + nsec = xtime.tv_nsec + tb_ticks_since(tb_last_jiffy); } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); usec = nsec / 1000; while (usec >= 1000000) { @@ -465,7 +462,7 @@ void do_gettimeofday(struct timeval *tv) tv->tv_usec = usec; return; } - __do_gettimeofday(tv, get_tb()); + __do_gettimeofday(tv); } EXPORT_SYMBOL(do_gettimeofday); @@ -651,6 +648,7 @@ void timer_interrupt(struct pt_regs * regs) int next_dec; int cpu = smp_processor_id(); unsigned long ticks; + u64 tb_next_jiffy; #ifdef CONFIG_PPC32 if (atomic_read(&ppc_n_lost_interrupts) != 0) @@ -692,11 +690,13 @@ void timer_interrupt(struct pt_regs * regs) continue; write_seqlock(&xtime_lock); - tb_last_jiffy += tb_ticks_per_jiffy; - tb_last_stamp = per_cpu(last_jiffy, cpu); - do_timer(regs); - timer_recalc_offset(tb_last_jiffy); - timer_check_rtc(); + tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy; + if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) { + tb_last_jiffy = tb_next_jiffy; + do_timer(1); + timer_recalc_offset(tb_last_jiffy); + timer_check_rtc(); + } write_sequnlock(&xtime_lock); } @@ -741,7 +741,7 @@ void __init smp_space_timers(unsigned int max_cpus) int i; unsigned long half = tb_ticks_per_jiffy / 2; unsigned long offset = tb_ticks_per_jiffy / max_cpus; - unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid); + u64 previous_tb = per_cpu(last_jiffy, boot_cpuid); /* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */ previous_tb -= tb_ticks_per_jiffy; @@ -822,7 +822,7 @@ int do_settimeofday(struct timespec *tv) * and therefore the (jiffies - wall_jiffies) computation * has been removed. */ - tb_delta = tb_ticks_since(tb_last_stamp); + tb_delta = tb_ticks_since(tb_last_jiffy); tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */ new_nsec -= SCALE_XSEC(tb_delta, 1000000000); @@ -860,19 +860,17 @@ EXPORT_SYMBOL(do_settimeofday); static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; - unsigned int *fp; + const unsigned int *fp; int found = 0; /* The cpu node should have timebase and clock frequency properties */ cpu = of_find_node_by_type(NULL, "cpu"); if (cpu) { - fp = (unsigned int *)get_property(cpu, name, NULL); + fp = get_property(cpu, name, NULL); if (fp) { found = 1; - *val = 0; - while (cells--) - *val = (*val << 32) | *fp++; + *val = of_read_ulong(fp, cells); } of_node_put(cpu); @@ -942,8 +940,7 @@ void __init time_init(void) if (__USE_RTC()) { /* 601 processor: dec counts down by 128 every 128ns */ ppc_tb_freq = 1000000000; - tb_last_stamp = get_rtcl(); - tb_last_jiffy = tb_last_stamp; + tb_last_jiffy = get_rtcl(); } else { /* Normal PowerPC with timebase register */ ppc_md.calibrate_decr(); @@ -951,7 +948,7 @@ void __init time_init(void) ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); - tb_last_stamp = tb_last_jiffy = get_tb(); + tb_last_jiffy = get_tb(); } tb_ticks_per_jiffy = ppc_tb_freq / HZ; @@ -1028,7 +1025,7 @@ void __init time_init(void) do_gtod.varp = &do_gtod.vars[0]; do_gtod.var_idx = 0; do_gtod.varp->tb_orig_stamp = tb_last_jiffy; - __get_cpu_var(last_jiffy) = tb_last_stamp; + __get_cpu_var(last_jiffy) = tb_last_jiffy; do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; do_gtod.varp->tb_to_xs = tb_to_xs; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 91a6e04d9741..d9f10f2fc372 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -14,7 +14,6 @@ * This file handles the architecture-dependent parts of hardware exceptions */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -32,6 +31,7 @@ #include <linux/delay.h> #include <linux/kprobes.h> #include <linux/kexec.h> +#include <linux/backlight.h> #include <asm/kdebug.h> #include <asm/pgtable.h> @@ -51,6 +51,7 @@ #include <asm/firmware.h> #include <asm/processor.h> #endif +#include <asm/kexec.h> #ifdef CONFIG_PPC64 /* XXX */ #define _IO_BASE pci_io_base @@ -96,7 +97,7 @@ static DEFINE_SPINLOCK(die_lock); int die(const char *str, struct pt_regs *regs, long err) { - static int die_counter, crash_dump_start = 0; + static int die_counter; if (debugger(regs)) return 1; @@ -105,10 +106,18 @@ int die(const char *str, struct pt_regs *regs, long err) spin_lock_irq(&die_lock); bust_spinlocks(1); #ifdef CONFIG_PMAC_BACKLIGHT - if (machine_is(powermac)) { - set_backlight_enable(1); - set_backlight_level(BACKLIGHT_MAX); + mutex_lock(&pmac_backlight_mutex); + if (machine_is(powermac) && pmac_backlight) { + struct backlight_properties *props; + + down(&pmac_backlight->sem); + props = pmac_backlight->props; + props->brightness = props->max_brightness; + props->power = FB_BLANK_UNBLANK; + props->update_status(pmac_backlight); + up(&pmac_backlight->sem); } + mutex_unlock(&pmac_backlight_mutex); #endif printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); #ifdef CONFIG_PREEMPT @@ -128,32 +137,19 @@ int die(const char *str, struct pt_regs *regs, long err) print_modules(); show_regs(regs); bust_spinlocks(0); + spin_unlock_irq(&die_lock); - if (!crash_dump_start && kexec_should_crash(current)) { - crash_dump_start = 1; - spin_unlock_irq(&die_lock); + if (kexec_should_crash(current) || + kexec_sr_activated(smp_processor_id())) crash_kexec(regs); - /* NOTREACHED */ - } - spin_unlock_irq(&die_lock); - if (crash_dump_start) - /* - * Only for soft-reset: Other CPUs will be responded to an IPI - * sent by first kexec CPU. - */ - for(;;) - ; + crash_kexec_secondary(regs); if (in_interrupt()) panic("Fatal exception in interrupt"); - if (panic_on_oops) { -#ifdef CONFIG_PPC64 - printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); - ssleep(5); -#endif + if (panic_on_oops) panic("Fatal exception"); - } + do_exit(err); return 0; @@ -206,8 +202,25 @@ void system_reset_exception(struct pt_regs *regs) return; } +#ifdef CONFIG_KEXEC + cpu_set(smp_processor_id(), cpus_in_sr); +#endif + die("System Reset", regs, SIGABRT); + /* + * Some CPUs when released from the debugger will execute this path. + * These CPUs entered the debugger via a soft-reset. If the CPU was + * hung before entering the debugger it will return to the hung + * state when exiting this function. This causes a problem in + * kdump since the hung CPU(s) will not respond to the IPI sent + * from kdump. To prevent the problem we call crash_kexec_secondary() + * here. If a kdump had not been initiated or we exit the debugger + * with the "exit and recover" command (x) crash_kexec_secondary() + * will return after 5ms and the CPU returns to its previous state. + */ + crash_kexec_secondary(regs); + /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) panic("Unrecoverable System Reset"); @@ -572,19 +585,22 @@ static void parse_fpe(struct pt_regs *regs) #define INST_MFSPR_PVR_MASK 0xfc1fffff #define INST_DCBA 0x7c0005ec -#define INST_DCBA_MASK 0x7c0007fe +#define INST_DCBA_MASK 0xfc0007fe #define INST_MCRXR 0x7c000400 -#define INST_MCRXR_MASK 0x7c0007fe +#define INST_MCRXR_MASK 0xfc0007fe #define INST_STRING 0x7c00042a -#define INST_STRING_MASK 0x7c0007fe -#define INST_STRING_GEN_MASK 0x7c00067e +#define INST_STRING_MASK 0xfc0007fe +#define INST_STRING_GEN_MASK 0xfc00067e #define INST_LSWI 0x7c0004aa #define INST_LSWX 0x7c00042a #define INST_STSWI 0x7c0005aa #define INST_STSWX 0x7c00052a +#define INST_POPCNTB 0x7c0000f4 +#define INST_POPCNTB_MASK 0xfc0007fe + static int emulate_string_inst(struct pt_regs *regs, u32 instword) { u8 rT = (instword >> 21) & 0x1f; @@ -653,6 +669,23 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword) return 0; } +static int emulate_popcntb_inst(struct pt_regs *regs, u32 instword) +{ + u32 ra,rs; + unsigned long tmp; + + ra = (instword >> 16) & 0x1f; + rs = (instword >> 21) & 0x1f; + + tmp = regs->gpr[rs]; + tmp = tmp - ((tmp >> 1) & 0x5555555555555555ULL); + tmp = (tmp & 0x3333333333333333ULL) + ((tmp >> 2) & 0x3333333333333333ULL); + tmp = (tmp + (tmp >> 4)) & 0x0f0f0f0f0f0f0f0fULL; + regs->gpr[ra] = tmp; + + return 0; +} + static int emulate_instruction(struct pt_regs *regs) { u32 instword; @@ -690,6 +723,11 @@ static int emulate_instruction(struct pt_regs *regs) if ((instword & INST_STRING_GEN_MASK) == INST_STRING) return emulate_string_inst(regs, instword); + /* Emulate the popcntb (Population Count Bytes) instruction. */ + if ((instword & INST_POPCNTB_MASK) == INST_POPCNTB) { + return emulate_popcntb_inst(regs, instword); + } + return -EINVAL; } diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 67d9fd9ae2b5..5730906b23d5 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -10,7 +10,6 @@ */ #include <stdarg.h> -#include <linux/config.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/console.h> @@ -34,9 +33,12 @@ void __init udbg_early_init(void) #elif defined(CONFIG_PPC_EARLY_DEBUG_G5) /* For use on Apple G5 machines */ udbg_init_pmac_realmode(); -#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS) +#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL) /* RTAS panel debug */ - udbg_init_rtas(); + udbg_init_rtas_panel(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE) + /* RTAS console debug */ + udbg_init_rtas_console(); #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE) /* Maple real mode debug */ udbg_init_maple_realmode(); diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 5d29dcca523c..2d17f2b8eda7 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -8,7 +8,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/types.h> #include <asm/udbg.h> #include <asm/io.h> @@ -82,10 +81,14 @@ static int udbg_550_getc(void) void udbg_init_uart(void __iomem *comport, unsigned int speed, unsigned int clock) { - unsigned int dll, base_bauds = clock / 16; + unsigned int dll, base_bauds; + if (clock == 0) + clock = 1843200; if (speed == 0) speed = 9600; + + base_bauds = clock / 16; dll = base_bauds / speed; if (comport) { diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index bc3e15be3087..1a7e19cdab39 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -8,7 +8,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/sched.h> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 8a3bed5f143a..3726358faae8 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -14,7 +14,8 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin -EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ + $(call ld-option, -Wl$(comma)--hash-style=sysv) EXTRA_AFLAGS := -D__VDSO32__ -s obj-y += vdso32_wrapper.o diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index 09629aea3e47..9cb319992c38 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -9,7 +9,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 4709f1d9542c..dc21e891d2e7 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -9,7 +9,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 7eebff03a041..05909f754307 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -10,7 +10,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S index 0c6a37b29dde..68d49dd71dcc 100644 --- a/arch/powerpc/kernel/vdso32/sigtramp.S +++ b/arch/powerpc/kernel/vdso32/sigtramp.S @@ -10,7 +10,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/unistd.h> diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index f4bad720cb0a..6187af2d54c3 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -14,6 +14,7 @@ SECTIONS { . = VDSO32_LBASE + SIZEOF_HEADERS; .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } .dynsym : { *(.dynsym) } .dynstr : { *(.dynstr) } .gnu.version : { *(.gnu.version) } diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index ab39988452cc..43af9b2a6f3b 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -8,7 +8,8 @@ targets := $(obj-vdso64) vdso64.so obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin -EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ + $(call ld-option, -Wl$(comma)--hash-style=sysv) EXTRA_AFLAGS := -D__VDSO64__ -s obj-y += vdso64_wrapper.o diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index cb4ae0a5edd0..66a36d3cc6ad 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -9,7 +9,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index 3b2dd7d0c1eb..79796de11737 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -9,7 +9,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 4ee871f1cadb..56e76ff5498f 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -11,7 +11,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index 7479edb101b8..17a83fa6dc52 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -10,7 +10,6 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/unistd.h> diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 4bdf224464ab..4a2b6dc0960c 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -12,6 +12,7 @@ SECTIONS { . = VDSO64_LBASE + SIZEOF_HEADERS; .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } .dynsym : { *(.dynsym) } .dynstr : { *(.dynstr) } .gnu.version : { *(.gnu.version) } diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 9416b4ab92ec..49ac3d6e1399 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <asm/ppc_asm.h> #include <asm/reg.h> diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index cdf5867838a6..cb87e71eec66 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -77,7 +77,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) } else #endif { - unsigned char *dma_window; + const unsigned char *dma_window; struct iommu_table *tbl; unsigned long offset, size; @@ -217,8 +217,7 @@ static void __devinit vio_dev_release(struct device *dev) struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node) { struct vio_dev *viodev; - unsigned int *unit_address; - unsigned int *irq_p; + const unsigned int *unit_address; /* we need the 'device_type' property, in order to match with drivers */ if (of_node->type == NULL) { @@ -228,7 +227,7 @@ struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node) return NULL; } - unit_address = (unsigned int *)get_property(of_node, "reg", NULL); + unit_address = get_property(of_node, "reg", NULL); if (unit_address == NULL) { printk(KERN_WARNING "%s: node %s missing 'reg'\n", __FUNCTION__, @@ -243,23 +242,14 @@ struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node) viodev->dev.platform_data = of_node_get(of_node); - viodev->irq = NO_IRQ; - irq_p = (unsigned int *)get_property(of_node, "interrupts", NULL); - if (irq_p) { - int virq = virt_irq_create_mapping(*irq_p); - if (virq == NO_IRQ) { - printk(KERN_ERR "Unable to allocate interrupt " - "number for %s\n", of_node->full_name); - } else - viodev->irq = irq_offset_up(virq); - } + viodev->irq = irq_of_parse_and_map(of_node, 0); snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address); viodev->name = of_node->name; viodev->type = of_node->type; viodev->unit_address = *unit_address; if (firmware_has_feature(FW_FEATURE_ISERIES)) { - unit_address = (unsigned int *)get_property(of_node, + unit_address = get_property(of_node, "linux,unit_address", NULL); if (unit_address != NULL) viodev->unit_address = *unit_address; @@ -433,7 +423,7 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp, { const struct vio_dev *vio_dev = to_vio_dev(dev); struct device_node *dn = dev->platform_data; - char *cp; + const char *cp; int length; if (!num_envp) @@ -441,7 +431,7 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp, if (!dn) return -ENODEV; - cp = (char *)get_property(dn, "compatible", &length); + cp = get_property(dn, "compatible", &length); if (!cp) return -ENODEV; @@ -503,11 +493,11 @@ static struct vio_dev *vio_find_name(const char *kobj_name) */ struct vio_dev *vio_find_node(struct device_node *vnode) { - uint32_t *unit_address; + const uint32_t *unit_address; char kobj_name[BUS_ID_SIZE]; /* construct the kobject name from the device node */ - unit_address = (uint32_t *)get_property(vnode, "reg", NULL); + unit_address = get_property(vnode, "reg", NULL); if (!unit_address) return NULL; snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8b25953dc4f0..02665a02130d 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -1,4 +1,3 @@ -#include <linux/config.h> #ifdef CONFIG_PPC64 #include <asm/page.h> #define PROVIDE32(x) PROVIDE(__unused__##x) |
