diff options
62 files changed, 1790 insertions, 787 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ed31062029f..c523029674e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -581,17 +581,12 @@ config ARCH_FLATMEM_ENABLE def_bool y depends on PPC64 && !NUMA -config ARCH_DISCONTIGMEM_ENABLE - def_bool y - depends on SMP && PPC_PSERIES - -config ARCH_DISCONTIGMEM_DEFAULT +config ARCH_SPARSEMEM_ENABLE def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE -config ARCH_SPARSEMEM_ENABLE +config ARCH_SPARSEMEM_DEFAULT def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE + depends on SMP && PPC_PSERIES source "mm/Kconfig" diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c04bbd32059..9a74b7ab03a 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -12,11 +12,13 @@ CFLAGS_btext.o += -fPIC endif obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ - irq.o signal_32.o pmc.o + irq.o signal_32.o pmc.o vdso.o +obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ signal_64.o ptrace32.o systbl.o \ paca.o ioctl32.o cpu_setup_power4.o \ - firmware.o sysfs.o + firmware.o sysfs.o udbg.o +obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o obj-$(CONFIG_POWER4) += idle_power4.o obj-$(CONFIG_PPC_OF) += of_device.o @@ -29,6 +31,10 @@ obj-$(CONFIG_RTAS_PROC) += rtas-proc.o obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o +obj-$(CONFIG_PPC_PSERIES) += udbg_16550.o +obj-$(CONFIG_PPC_MAPLE) += udbg_16550.o +udbgscc-$(CONFIG_PPC64) := udbg_scc.o +obj-$(CONFIG_PPC_PMAC) += $(udbgscc-y) ifeq ($(CONFIG_PPC_MERGE),y) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8793102711a..4550eb4f4fb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -37,12 +37,12 @@ #include <asm/cputable.h> #include <asm/thread_info.h> #include <asm/rtas.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> #include <asm/lppaca.h> #include <asm/iseries/hv_lp_event.h> #include <asm/cache.h> -#include <asm/systemcfg.h> #include <asm/compat.h> #endif @@ -251,25 +251,42 @@ int main(void) DEFINE(TASK_SIZE, TASK_SIZE); DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); -#else /* CONFIG_PPC64 */ - /* systemcfg offsets for use by vdso */ - DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp)); - DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec)); - DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs)); - DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec)); - DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count)); - DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest)); - DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime)); - DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32)); - DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64)); +#endif /* ! CONFIG_PPC64 */ - /* timeval/timezone offsets for use by vdso */ + /* datapage offsets for use by vdso */ + DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp)); + DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec)); + DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs)); + DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec)); + DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count)); + DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest)); + DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); + DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); + DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); + DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); +#ifdef CONFIG_PPC64 + DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64)); DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec)); DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec)); DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec)); DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec)); + DEFINE(TSPC32_TV_SEC, offsetof(struct compat_timespec, tv_sec)); + DEFINE(TSPC32_TV_NSEC, offsetof(struct compat_timespec, tv_nsec)); +#else + DEFINE(TVAL32_TV_SEC, offsetof(struct timeval, tv_sec)); + DEFINE(TVAL32_TV_USEC, offsetof(struct timeval, tv_usec)); + DEFINE(TSPEC32_TV_SEC, offsetof(struct timespec, tv_sec)); + DEFINE(TSPEC32_TV_NSEC, offsetof(struct timespec, tv_nsec)); +#endif + /* timeval/timezone offsets for use by vdso */ DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); -#endif /* CONFIG_PPC64 */ + + /* Other bits used by the vdso */ + DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); + DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); + DEFINE(CLOCK_REALTIME_RES, TICK_NSEC); + return 0; } diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index b102e3a2415..ccdf94731e3 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -1100,6 +1100,7 @@ start_here: mr r3,r31 mr r4,r30 bl machine_init + bl __save_cpu_setup bl MMU_init #ifdef CONFIG_APUS diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 5e954fae031..1b3ba8a440a 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -35,7 +35,7 @@ #include <asm/time.h> #include <asm/iseries/it_exp_vpd_panel.h> #include <asm/prom.h> -#include <asm/systemcfg.h> +#include <asm/vdso_datapage.h> #define MODULE_VERS "1.6" #define MODULE_NAME "lparcfg" @@ -43,7 +43,7 @@ /* #define LPARCFG_DEBUG */ /* find a better place for this function... */ -void log_plpar_hcall_return(unsigned long rc, char *tag) +static void log_plpar_hcall_return(unsigned long rc, char *tag) { if (rc == 0) /* success, return */ return; @@ -213,11 +213,10 @@ static void h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) unsigned long dummy; rc = plpar_hcall(H_PIC, 0, 0, 0, 0, pool_idle_time, num_procs, &dummy); - log_plpar_hcall_return(rc, "H_PIC"); + if (rc != H_Authority) + log_plpar_hcall_return(rc, "H_PIC"); } -static unsigned long get_purr(void); - /* Track sum of all purrs across all processors. This is used to further */ /* calculate usage values by different applications */ @@ -319,8 +318,6 @@ static void parse_system_parameter_string(struct seq_file *m) kfree(local_buffer); } -static int lparcfg_count_active_processors(void); - /* Return the number of processors in the system. * This function reads through the device tree and counts * the virtual processors, this does not include threads. @@ -372,7 +369,7 @@ static int lparcfg_data(struct seq_file *m, void *v) lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity", NULL); if (lrdrp == NULL) { - partition_potential_processors = _systemcfg->processorCount; + partition_potential_processors = vdso_data->processorCount; } else { partition_potential_processors = *(lrdrp + 4); } @@ -548,7 +545,7 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf, retval = -EIO; } - out: +out: kfree(kbuf); return retval; } @@ -561,10 +558,10 @@ static int lparcfg_open(struct inode *inode, struct file *file) } struct file_operations lparcfg_fops = { - .owner = THIS_MODULE, - .read = seq_read, - .open = lparcfg_open, - .release = single_release, + .owner = THIS_MODULE, + .read = seq_read, + .open = lparcfg_open, + .release = single_release, }; int __init lparcfg_init(void) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 3cf2517c5f9..a7b68f911eb 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -15,17 +15,10 @@ #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/page.h> -#include <asm/systemcfg.h> #include <asm/lppaca.h> #include <asm/iseries/it_lp_queue.h> #include <asm/paca.h> -static union { - struct systemcfg data; - u8 page[PAGE_SIZE]; -} systemcfg_store __attribute__((__section__(".data.page.aligned"))); -struct systemcfg *_systemcfg = &systemcfg_store.data; - /* This symbol is provided by the linker - let it fill in the paca * field correctly */ diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c index a1c19502fe8..7ba42a405f4 100644 --- a/arch/powerpc/kernel/proc_ppc64.c +++ b/arch/powerpc/kernel/proc_ppc64.c @@ -23,7 +23,7 @@ #include <linux/slab.h> #include <linux/kernel.h> -#include <asm/systemcfg.h> +#include <asm/vdso_datapage.h> #include <asm/rtas.h> #include <asm/uaccess.h> #include <asm/prom.h> @@ -72,7 +72,7 @@ static int __init proc_ppc64_init(void) if (!pde) return 1; pde->nlink = 1; - pde->data = _systemcfg; + pde->data = vdso_data; pde->size = PAGE_SIZE; pde->proc_fops = &page_map_fops; diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index ae1a36449cc..7a95b8a2835 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -32,7 +32,6 @@ #include <asm/rtas.h> #include <asm/machdep.h> /* for ppc_md */ #include <asm/time.h> -#include <asm/systemcfg.h> /* Token for Sensors */ #define KEY_SWITCH 0x0001 diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bae4bff138f..33e7f2c7f19 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -33,7 +33,7 @@ #include <asm/io.h> #include <asm/prom.h> #include <asm/processor.h> -#include <asm/systemcfg.h> +#include <asm/vdso_datapage.h> #include <asm/pgtable.h> #include <asm/smp.h> #include <asm/elf.h> @@ -444,10 +444,8 @@ void __init check_for_initrd(void) if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE && initrd_end > initrd_start) ROOT_DEV = Root_RAM0; - else { - printk("Bogus initrd %08lx %08lx\n", initrd_start, initrd_end); + else initrd_start = initrd_end = 0; - } if (initrd_start) printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end); @@ -566,7 +564,7 @@ void __init smp_setup_cpu_maps(void) cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]); } - _systemcfg->processorCount = num_present_cpus(); + vdso_data->processorCount = num_present_cpus(); #endif /* CONFIG_PPC64 */ } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6791668213e..fdbd9f9122f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -57,7 +57,6 @@ #include <asm/lmb.h> #include <asm/iseries/it_lp_naca.h> #include <asm/firmware.h> -#include <asm/systemcfg.h> #include <asm/xmon.h> #include <asm/udbg.h> @@ -375,9 +374,8 @@ static void __init initialize_cache_info(void) DBG("Argh, can't find dcache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); - _systemcfg->dcache_size = ppc64_caches.dsize = size; - _systemcfg->dcache_line_size = - ppc64_caches.dline_size = lsize; + ppc64_caches.dsize = size; + ppc64_caches.dline_size = lsize; ppc64_caches.log_dline_size = __ilog2(lsize); ppc64_caches.dlines_per_page = PAGE_SIZE / lsize; @@ -393,22 +391,13 @@ static void __init initialize_cache_info(void) DBG("Argh, can't find icache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); - _systemcfg->icache_size = ppc64_caches.isize = size; - _systemcfg->icache_line_size = - ppc64_caches.iline_size = lsize; + ppc64_caches.isize = size; + ppc64_caches.iline_size = lsize; ppc64_caches.log_iline_size = __ilog2(lsize); ppc64_caches.ilines_per_page = PAGE_SIZE / lsize; } } - /* Add an eye catcher and the systemcfg layout version number */ - strcpy(_systemcfg->eye_catcher, "SYSTEMCFG:PPC64"); - _systemcfg->version.major = SYSTEMCFG_MAJOR; - _systemcfg->version.minor = SYSTEMCFG_MINOR; - _systemcfg->processor = mfspr(SPRN_PVR); - _systemcfg->platform = _machine; - _systemcfg->physicalMemorySize = lmb_phys_mem_size(); - DBG(" <- initialize_cache_info()\n"); } @@ -495,15 +484,14 @@ 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("systemcfg = 0x%p\n", _systemcfg); - printk("systemcfg->platform = 0x%x\n", _systemcfg->platform); - printk("systemcfg->processorCount = 0x%lx\n", _systemcfg->processorCount); - printk("systemcfg->physicalMemorySize = 0x%lx\n", _systemcfg->physicalMemorySize); + printk("ppc64_interrupt_controller = 0x%ld\n", + ppc64_interrupt_controller); + printk("platform = 0x%x\n", _machine); + printk("physicalMemorySize = 0x%lx\n", lmb_phys_mem_size()); printk("ppc64_caches.dcache_line_size = 0x%x\n", - ppc64_caches.dline_size); + ppc64_caches.dline_size); printk("ppc64_caches.icache_line_size = 0x%x\n", - ppc64_caches.iline_size); + ppc64_caches.iline_size); printk("htab_address = 0x%p\n", htab_address); printk("htab_hash_mask = 0x%lx\n", htab_hash_mask); printk("-----------------------------------------------------\n"); @@ -568,33 +556,6 @@ static void __init emergency_stack_init(void) } /* - * Called from setup_arch to initialize the bitmap of available - * syscalls in the systemcfg page - */ -void __init setup_syscall_map(void) -{ - unsigned int i, count64 = 0, count32 = 0; - extern unsigned long *sys_call_table; - extern unsigned long sys_ni_syscall; - - - for (i = 0; i < __NR_syscalls; i++) { - if (sys_call_table[i*2] != sys_ni_syscall) { - count64++; - _systemcfg->syscall_map_64[i >> 5] |= - 0x80000000UL >> (i & 0x1f); - } - if (sys_call_table[i*2+1] != sys_ni_syscall) { - count32++; - _systemcfg->syscall_map_32[i >> 5] |= - 0x80000000UL >> (i & 0x1f); - } - } - printk(KERN_INFO "Syscall map setup, %d 32-bit and %d 64-bit syscalls\n", - count32, count64); -} - -/* * Called into from start_kernel, after lock_kernel has been called. * Initializes bootmem, which is unsed to manage page allocation until * mem_init is called. @@ -635,9 +596,6 @@ void __init setup_arch(char **cmdline_p) do_init_bootmem(); sparse_init(); - /* initialize the syscall map in systemcfg */ - setup_syscall_map(); - #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; #endif diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index a7c4515f320..8bdf95b7e42 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -43,10 +43,10 @@ #include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/sigcontext.h> +#include <asm/vdso.h> #ifdef CONFIG_PPC64 #include "ppc32.h" #include <asm/unistd.h> -#include <asm/vdso.h> #else #include <asm/ucontext.h> #include <asm/pgtable.h> @@ -809,14 +809,11 @@ static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; -#ifdef CONFIG_PPC64 if (vdso32_rt_sigtramp && current->thread.vdso_base) { if (save_user_regs(regs, frame, 0)) goto badframe; regs->link = current->thread.vdso_base + vdso32_rt_sigtramp; - } else -#endif - { + } else { if (save_user_regs(regs, frame, __NR_rt_sigreturn)) goto badframe; regs->link = (unsigned long) frame->tramp; @@ -1090,14 +1087,11 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, || __put_user(sig, &sc->signal)) goto badframe; -#ifdef CONFIG_PPC64 if (vdso32_sigtramp && current->thread.vdso_base) { if (save_user_regs(regs, &frame->mctx, 0)) goto badframe; regs->link = current->thread.vdso_base + vdso32_sigtramp; - } else -#endif - { + } else { if (save_user_regs(regs, &frame->mctx, __NR_sigreturn)) goto badframe; regs->link = (unsigned long) frame->mctx.tramp; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e28a139c29d..62dfc5b8d76 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -44,7 +44,7 @@ #include <asm/cputable.h> #include <asm/system.h> #include <asm/mpic.h> -#include <asm/systemcfg.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> #endif @@ -371,7 +371,7 @@ int generic_cpu_disable(void) cpu_clear(cpu, cpu_online_map); #ifdef CONFIG_PPC64 - _systemcfg->processorCount--; + vdso_data->processorCount--; fixup_irqs(cpu_online_map); #endif return 0; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 850af198fb5..0f0c3a9ae2e 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -16,7 +16,6 @@ #include <asm/firmware.h> #include <asm/hvcall.h> #include <asm/prom.h> -#include <asm/systemcfg.h> #include <asm/paca.h> #include <asm/lppaca.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 260b6ecd26a..070b4b458aa 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -62,8 +62,8 @@ #include <asm/irq.h> #include <asm/div64.h> #include <asm/smp.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 -#include <asm/systemcfg.h> #include <asm/firmware.h> #endif #ifdef CONFIG_PPC_ISERIES @@ -261,7 +261,6 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, do_gtod.varp = temp_varp; do_gtod.var_idx = temp_idx; -#ifdef CONFIG_PPC64 /* * tb_update_count is used to allow the userspace gettimeofday code * to assure itself that it sees a consistent view of the tb_to_xs and @@ -271,14 +270,15 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, * tb_to_xs and stamp_xsec values are consistent. If not, then it * loops back and reads them again until this criteria is met. */ - ++(_systemcfg->tb_update_count); + ++(vdso_data->tb_update_count); smp_wmb(); - _systemcfg->tb_orig_stamp = new_tb_stamp; - _systemcfg->stamp_xsec = new_stamp_xsec; - _systemcfg->tb_to_xs = new_tb_to_xs; + vdso_data->tb_orig_stamp = new_tb_stamp; + vdso_data->stamp_xsec = new_stamp_xsec; + vdso_data->tb_to_xs = new_tb_to_xs; + vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; + vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; smp_wmb(); - ++(_systemcfg->tb_update_count); -#endif + ++(vdso_data->tb_update_count); } /* @@ -357,9 +357,8 @@ static void iSeries_tb_recal(void) do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; tb_to_xs = divres.result_low; do_gtod.varp->tb_to_xs = tb_to_xs; - _systemcfg->tb_ticks_per_sec = - tb_ticks_per_sec; - _systemcfg->tb_to_xs = tb_to_xs; + vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_data->tb_to_xs = tb_to_xs; } else { printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" @@ -561,10 +560,8 @@ int do_settimeofday(struct timespec *tv) new_xsec += (u64)new_sec * XSEC_PER_SEC - tb_delta_xs; update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs); -#ifdef CONFIG_PPC64 - _systemcfg->tz_minuteswest = sys_tz.tz_minuteswest; - _systemcfg->tz_dsttime = sys_tz.tz_dsttime; -#endif + vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; + vdso_data->tz_dsttime = sys_tz.tz_dsttime; write_sequnlock_irqrestore(&xtime_lock, flags); clock_was_set(); @@ -713,13 +710,12 @@ void __init time_init(void) do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; do_gtod.varp->tb_to_xs = tb_to_xs; do_gtod.tb_to_us = tb_to_us; -#ifdef CONFIG_PPC64 - _systemcfg->tb_orig_stamp = tb_last_jiffy; - _systemcfg->tb_update_count = 0; - _systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; - _systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC; - _systemcfg->tb_to_xs = tb_to_xs; -#endif + + vdso_data->tb_orig_stamp = tb_last_jiffy; + vdso_data->tb_update_count = 0; + vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_data->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC; + vdso_data->tb_to_xs = tb_to_xs; time_freq = 0; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 2020bb7648f..1511454c469 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -49,7 +49,6 @@ #ifdef CONFIG_PPC64 #include <asm/firmware.h> #include <asm/processor.h> -#include <asm/systemcfg.h> #endif #ifdef CONFIG_PPC64 /* XXX */ diff --git a/arch/ppc64/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 0d878e72fc4..0d878e72fc4 100644 --- a/arch/ppc64/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c diff --git a/arch/ppc64/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 9313574ab93..9313574ab93 100644 --- a/arch/ppc64/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c diff --git a/arch/ppc64/kernel/udbg_scc.c b/arch/powerpc/kernel/udbg_scc.c index 820c5355150..820c5355150 100644 --- a/arch/ppc64/kernel/udbg_scc.c +++ b/arch/powerpc/kernel/udbg_scc.c diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c new file mode 100644 index 00000000000..0d4d8bec0df --- /dev/null +++ b/arch/powerpc/kernel/vdso.c @@ -0,0 +1,746 @@ +/* + * linux/arch/ppc64/kernel/vdso.c + * + * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp. + * <benh@kernel.crashing.org> + * + * 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/config.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/elf.h> +#include <linux/security.h> +#include <linux/bootmem.h> + +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/processor.h> +#include <asm/mmu.h> +#include <asm/mmu_context.h> +#include <asm/lmb.h> +#include <asm/machdep.h> +#include <asm/cputable.h> +#include <asm/sections.h> +#include <asm/vdso.h> +#include <asm/vdso_datapage.h> + +#undef DEBUG + +#ifdef DEBUG +#define DBG(fmt...) printk(fmt) +#else +#define DBG(fmt...) +#endif + +/* Max supported size for symbol names */ +#define MAX_SYMNAME 64 + +extern char vdso32_start, vdso32_end; +static void *vdso32_kbase = &vdso32_start; +unsigned int vdso32_pages; +unsigned long vdso32_sigtramp; +unsigned long vdso32_rt_sigtramp; + +#ifdef CONFIG_PPC64 +extern char vdso64_start, vdso64_end; +static void *vdso64_kbase = &vdso64_start; +unsigned int vdso64_pages; +unsigned long vdso64_rt_sigtramp; +#endif /* CONFIG_PPC64 */ + +/* + * The vdso data page (aka. systemcfg for old ppc64 fans) is here. + * Once the early boot kernel code no longer needs to muck around + * with it, it will become dynamically allocated + */ +static union { + struct vdso_data data; + u8 page[PAGE_SIZE]; +} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +struct vdso_data *vdso_data = &vdso_data_store.data; + +/* Format of the patch table */ +struct vdso_patch_def +{ + unsigned long ftr_mask, ftr_value; + const char *gen_name; + const char *fix_name; +}; + +/* Table of functions to patch based on the CPU type/revision + * + * Currently, we only change sync_dicache to do nothing on processors + * with a coherent icache + */ +static struct vdso_patch_def vdso_patches[] = { + { + CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE, + "__kernel_sync_dicache", "__kernel_sync_dicache_p5" + }, + { + CPU_FTR_USE_TB, 0, + "__kernel_gettimeofday", NULL + }, +}; + +/* + * Some infos carried around for each of them during parsing at + * boot time. + */ +struct lib32_elfinfo +{ + Elf32_Ehdr *hdr; /* ptr to ELF */ + Elf32_Sym *dynsym; /* ptr to .dynsym section */ + unsigned long dynsymsize; /* size of .dynsym section */ + char *dynstr; /* ptr to .dynstr section */ + unsigned long text; /* offset of .text section in .so */ +}; + +struct lib64_elfinfo +{ + Elf64_Ehdr *hdr; + Elf64_Sym *dynsym; + unsigned long dynsymsize; + char *dynstr; + unsigned long text; +}; + + +#ifdef __DEBUG +static void dump_one_vdso_page(struct page *pg, struct page *upg) +{ + printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT), + page_count(pg), + pg->flags); + if (upg/* && pg != upg*/) { + printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg) + << PAGE_SHIFT), + page_count(upg), + upg->flags); + } + printk("\n"); +} + +static void dump_vdso_pages(struct vm_area_struct * vma) +{ + int i; + + if (!vma || test_thread_flag(TIF_32BIT)) { + printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase); + for (i=0; i<vdso32_pages; i++) { + struct page *pg = virt_to_page(vdso32_kbase + + i*PAGE_SIZE); + struct page *upg = (vma && vma->vm_mm) ? + follow_page(vma->vm_mm, vma->vm_start + + i*PAGE_SIZE, 0) + : NULL; + dump_one_vdso_page(pg, upg); + } + } + if (!vma || !test_thread_flag(TIF_32BIT)) { + printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase); + for (i=0; i<vdso64_pages; i++) { + struct page *pg = virt_to_page(vdso64_kbase + + i*PAGE_SIZE); + struct page *upg = (vma && vma->vm_mm) ? + follow_page(vma->vm_mm, vma->vm_start + + i*PAGE_SIZE, 0) + : NULL; + dump_one_vdso_page(pg, upg); + } + } +} +#endif /* DEBUG */ + +/* + * Keep a dummy vma_close for now, it will prevent VMA merging. + */ +static void vdso_vma_close(struct vm_area_struct * vma) +{ +} + +/* + * Our nopage() function, maps in the actual vDSO kernel pages, they will + * be mapped read-only by do_no_page(), and eventually COW'ed, either + * right away for an initial write access, or by do_wp_page(). + */ +static struct page * vdso_vma_nopage(struct vm_area_struct * vma, + unsigned long address, int *type) +{ + unsigned long offset = address - vma->vm_start; + struct page *pg; +#ifdef CONFIG_PPC64 + void *vbase = test_thread_flag(TIF_32BIT) ? + vdso32_kbase : vdso64_kbase; +#else + void *vbase = vdso32_kbase; +#endif + + DBG("vdso_vma_nopage(current: %s, address: %016lx, off: %lx)\n", + current->comm, address, offset); + + if (address < vma->vm_start || address > vma->vm_end) + return NOPAGE_SIGBUS; + + /* + * Last page is systemcfg. + */ + if ((vma->vm_end - address) <= PAGE_SIZE) + pg = virt_to_page(vdso_data); + else + pg = virt_to_page(vbase + offset); + + get_page(pg); + DBG(" ->page count: %d\n", page_count(pg)); + + return pg; +} + +static struct vm_operations_struct vdso_vmops = { + .close = vdso_vma_close, + .nopage = vdso_vma_nopage, +}; + +/* + * This is called from binfmt_elf, we create the special vma for the + * vDSO and insert it into the mm struct tree + */ +int arch_setup_additional_pages(struct linux_binprm *bprm, + int executable_stack) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long vdso_pages; + unsigned long vdso_base; + +#ifdef CONFIG_PPC64 + if (test_thread_flag(TIF_32BIT)) { + vdso_pages = vdso32_pages; + vdso_base = VDSO32_MBASE; + } else { + vdso_pages = vdso64_pages; + vdso_base = VDSO64_MBASE; + } +#else + vdso_pages = vdso32_pages; + vdso_base = VDSO32_MBASE; +#endif + + current->thread.vdso_base = 0; + + /* vDSO has a problem and was disabled, just don't "enable" it for the + * process + */ + if (vdso_pages == 0) + return 0; + + vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + if (vma == NULL) + return -ENOMEM; + + memset(vma, 0, sizeof(*vma)); + + /* Add a page to the vdso size for the data page */ + vdso_pages ++; + + /* + * pick a base address for the vDSO in process space. We try to put it + * at vdso_base which is the "natural" base for it, but we might fail + * and end up putting it elsewhere. + */ + vdso_base = get_unmapped_area(NULL, vdso_base, + vdso_pages << PAGE_SHIFT, 0, 0); + if (vdso_base & ~PAGE_MASK) { + kmem_cache_free(vm_area_cachep, vma); + return (int)vdso_base; + } + + current->thread.vdso_base = vdso_base; + + vma->vm_mm = mm; + vma->vm_start = current->thread.vdso_base; + vma->vm_end = vma->vm_start + (vdso_pages << PAGE_SHIFT); + + /* + * our vma flags don't have VM_WRITE so by default, the process isn't + * allowed to write those pages. + * gdb can break that with ptrace interface, and thus trigger COW on + * those pages but it's then your responsibility to never do that on + * the "data" page of the vDSO or you'll stop getting kernel updates + * and your nice userland gettimeofday will be totally dead. + * It's fine to use that for setting breakpoints in the vDSO code + * pages though + */ + vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | + VM_MAYEXEC | VM_RESERVED; + vma->vm_flags |= mm->def_flags; + vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; + vma->vm_ops = &vdso_vmops; + + down_write(&mm->mmap_sem); + if (insert_vm_struct(mm, vma)) { + up_write(&mm->mmap_sem); + kmem_cache_free(vm_area_cachep, vma); + return -ENOMEM; + } + mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + up_write(&mm->mmap_sem); + + return 0; +} + +static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname, + unsigned long *size) +{ + Elf32_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + *size = 0; + return NULL; +} + +static Elf32_Sym * __init find_symbol32(struct lib32_elfinfo *lib, + const char *symname) +{ + unsigned int i; + char name[MAX_SYMNAME], *c; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) { + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +/* Note that we assume the section is .text and the symbol is relative to + * the library base + */ +static unsigned long __init find_function32(struct lib32_elfinfo *lib, + const char *symname) +{ + Elf32_Sym *sym = find_symbol32(lib, symname); + + if (sym == NULL) { + printk(KERN_WARNING "vDSO32: function %s not found !\n", + symname); + return 0; + } + return sym->st_value - VDSO32_LBASE; +} + +static int vdso_do_func_patch32(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64, + const char *orig, const char *fix) +{ + Elf32_Sym *sym32_gen, *sym32_fix; + + sym32_gen = find_symbol32(v32, orig); + if (sym32_gen == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", orig); + return -1; + } + if (fix == NULL) { + sym32_gen->st_name = 0; + return 0; + } + sym32_fix = find_symbol32(v32, fix); + if (sym32_fix == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", fix); + return -1; + } + sym32_gen->st_value = sym32_fix->st_value; + sym32_gen->st_size = sym32_fix->st_size; + sym32_gen->st_info = sym32_fix->st_info; + sym32_gen->st_other = sym32_fix->st_other; + sym32_gen->st_shndx = sym32_fix->st_shndx; + + return 0; +} + + +#ifdef CONFIG_PPC64 + +static void * __init find_section64(Elf64_Ehdr *ehdr, const char *secname, + unsigned long *size) +{ + Elf64_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + if (size) + *size = 0; + return NULL; +} + +static Elf64_Sym * __init find_symbol64(struct lib64_elfinfo *lib, + const char *symname) +{ + unsigned int i; + char name[MAX_SYMNAME], *c; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf64_Sym)); i++) { + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +/* Note that we assume the section is .text and the symbol is relative to + * the library base + */ +static unsigned long __init find_function64(struct lib64_elfinfo *lib, + const char *symname) +{ + Elf64_Sym *sym = find_symbol64(lib, symname); + + if (sym == NULL) { + printk(KERN_WARNING "vDSO64: function %s not found !\n", + symname); + return 0; + } +#ifdef VDS64_HAS_DESCRIPTORS + return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) - + VDSO64_LBASE; +#else + return sym->st_value - VDSO64_LBASE; +#endif +} + +static int vdso_do_func_patch64(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64, + const char *orig, const char *fix) +{ + Elf64_Sym *sym64_gen, *sym64_fix; + + sym64_gen = find_symbol64(v64, orig); + if (sym64_gen == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", orig); + return -1; + } + if (fix == NULL) { + sym64_gen->st_name = 0; + return 0; + } + sym64_fix = find_symbol64(v64, fix); + if (sym64_fix == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", fix); + return -1; + } + sym64_gen->st_value = sym64_fix->st_value; + sym64_gen->st_size = sym64_fix->st_size; + sym64_gen->st_info = sym64_fix->st_info; + sym64_gen->st_other = sym64_fix->st_other; + sym64_gen->st_shndx = sym64_fix->st_shndx; + + return 0; +} + +#endif /* CONFIG_PPC64 */ + + +static __init int vdso_do_find_sections(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + void *sect; + + /* + * Locate symbol tables & text section + */ + + v32->dynsym = find_section32(v32->hdr, ".dynsym", &v32->dynsymsize); + v32->dynstr = find_section32(v32->hdr, ".dynstr", NULL); + if (v32->dynsym == NULL || v32->dynstr == NULL) { + printk(KERN_ERR "vDSO32: required symbol section not found\n"); + return -1; + } + sect = find_section32(v32->hdr, ".text", NULL); + if (sect == NULL) { + printk(KERN_ERR "vDSO32: the .text section was not found\n"); + return -1; + } + v32->text = sect - vdso32_kbase; + +#ifdef CONFIG_PPC64 + v64->dynsym = find_section64(v64->hdr, ".dynsym", &v64->dynsymsize); + v64->dynstr = find_section64(v64->hdr, ".dynstr", NULL); + if (v64->dynsym == NULL || v64->dynstr == NULL) { + printk(KERN_ERR "vDSO64: required symbol section not found\n"); + return -1; + } + sect = find_section64(v64->hdr, ".text", NULL); + if (sect == NULL) { + printk(KERN_ERR "vDSO64: the .text section was not found\n"); + return -1; + } + v64->text = sect - vdso64_kbase; +#endif /* CONFIG_PPC64 */ + + return 0; +} + +static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + /* + * Find signal trampolines + */ + +#ifdef CONFIG_PPC64 + vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64"); +#endif + vdso32_sigtramp = find_function32(v32, "__kernel_sigtramp32"); + vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32"); +} + +static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + Elf32_Sym *sym32; +#ifdef CONFIG_PPC64 + Elf64_Sym *sym64; + + sym64 = find_symbol64(v64, "__kernel_datapage_offset"); + if (sym64 == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol " + "__kernel_datapage_offset !\n"); + return -1; + } + *((int *)(vdso64_kbase + sym64->st_value - VDSO64_LBASE)) = + (vdso64_pages << PAGE_SHIFT) - + (sym64->st_value - VDSO64_LBASE); +#endif /* CONFIG_PPC64 */ + + sym32 = find_symbol32(v32, "__kernel_datapage_offset"); + if (sym32 == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol " + "__kernel_datapage_offset !\n"); + return -1; + } + *((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) = + (vdso32_pages << PAGE_SHIFT) - + (sym32->st_value - VDSO32_LBASE); + + return 0; +} + +static __init int vdso_fixup_alt_funcs(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(vdso_patches); i++) { + struct vdso_patch_def *patch = &vdso_patches[i]; + int match = (cur_cpu_spec->cpu_features & patch->ftr_mask) + == patch->ftr_value; + if (!match) + continue; + + DBG("replacing %s with %s...\n", patch->gen_name, + patch->fix_name ? "NONE" : patch->fix_name); + + /* + * Patch the 32 bits and 64 bits symbols. Note that we do not + * patch the "." symbol on 64 bits. + * It would be easy to do, but doesn't seem to be necessary, + * patching the OPD symbol is enough. + */ + vdso_do_func_patch32(v32, v64, patch->gen_name, + patch->fix_name); +#ifdef CONFIG_PPC64 + vdso_do_func_patch64(v32, v64, patch->gen_name, + patch->fix_name); +#endif /* CONFIG_PPC64 */ + } + + return 0; +} + + +static __init int vdso_setup(void) +{ + struct lib32_elfinfo v32; + struct lib64_elfinfo v64; + + v32.hdr = vdso32_kbase; +#ifdef CONFIG_PPC64 + v64.hdr = vdso64_kbase; +#endif + if (vdso_do_find_sections(&v32, &v64)) + return -1; + + if (vdso_fixup_datapage(&v32, &v64)) + return -1; + + if (vdso_fixup_alt_funcs(&v32, &v64)) + return -1; + + vdso_setup_trampolines(&v32, &v64); + + return 0; +} + +/* + * Called from setup_arch to initialize the bitmap of available + * syscalls in the systemcfg page + */ +static void __init vdso_setup_syscall_map(void) +{ + unsigned int i; + extern unsigned long *sys_call_table; + extern unsigned long sys_ni_syscall; + + + for (i = 0; i < __NR_syscalls; i++) { +#ifdef CONFIG_PPC64 + if (sys_call_table[i*2] != sys_ni_syscall) + vdso_data->syscall_map_64[i >> 5] |= + 0x80000000UL >> (i & 0x1f); + if (sys_call_table[i*2+1] != sys_ni_syscall) + vdso_data->syscall_map_32[i >> 5] |= + 0x80000000UL >> (i & 0x1f); +#else /* CONFIG_PPC64 */ + if (sys_call_table[i] != sys_ni_syscall) + vdso_data->syscall_map_32[i >> 5] |= + 0x80000000UL >> (i & 0x1f); +#endif /* CONFIG_PPC64 */ + } +} + + +void __init vdso_init(void) +{ + int i; + +#ifdef CONFIG_PPC64 + /* + * Fill up the "systemcfg" stuff for backward compatiblity + */ + strcpy(vdso_data->eye_catcher, "SYSTEMCFG:PPC64"); + vdso_data->version.major = SYSTEMCFG_MAJOR; + vdso_data->version.minor = SYSTEMCFG_MINOR; + vdso_data->processor = mfspr(SPRN_PVR); + vdso_data->platform = _machine; + vdso_data->physicalMemorySize = lmb_phys_mem_size(); + vdso_data->dcache_size = ppc64_caches.dsize; + vdso_data->dcache_line_size = ppc64_caches.dline_size; + vdso_data->icache_size = ppc64_caches.isize; + vdso_data->icache_line_size = ppc64_caches.iline_size; + + /* + * Calculate the size of the 64 bits vDSO + */ + vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT; + DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages); +#endif /* CONFIG_PPC64 */ + + + /* + * Calculate the size of the 32 bits vDSO + */ + vdso32_pages = (&vdso32_end - &vdso32_start) >> PAGE_SHIFT; + DBG("vdso32_kbase: %p, 0x%x pages\n", vdso32_kbase, vdso32_pages); + + + /* + * Setup the syscall map in the vDOS + */ + vdso_setup_syscall_map(); + /* + * Initialize the vDSO images in memory, that is do necessary + * fixups of vDSO symbols, locate trampolines, etc... + */ + if (vdso_setup()) { + printk(KERN_ERR "vDSO setup failure, not enabled !\n"); + vdso32_pages = 0; +#ifdef CONFIG_PPC64 + vdso64_pages = 0; +#endif + return; + } + + /* Make sure pages are in the correct state */ + for (i = 0; i < vdso32_pages; i++) { + struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + + } +#ifdef CONFIG_PPC64 + for (i = 0; i < vdso64_pages; i++) { + struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + } +#endif /* CONFIG_PPC64 */ + + get_page(virt_to_page(vdso_data)); +} + +int in_gate_area_no_task(unsigned long addr) +{ + return 0; +} + +int in_gate_area(struct task_struct *task, unsigned long addr) +{ + return 0; +} + +struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +{ + return NULL; +} + diff --git a/arch/ppc64/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 0b1b0df973e..8a3bed5f143 100644 --- a/arch/ppc64/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -5,6 +5,10 @@ obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o # Build rules +ifeq ($(CONFIG_PPC32),y) +CROSS32CC := $(CC) +endif + targets := $(obj-vdso32) vdso32.so obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) @@ -15,7 +19,7 @@ EXTRA_AFLAGS := -D__VDSO32__ -s obj-y += vdso32_wrapper.o extra-y += vdso32.lds -CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) +CPPFLAGS_vdso32.lds += -P -C -Upowerpc # Force dependency (incbin is bad) $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so diff --git a/arch/ppc64/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index c8db993574e..c8db993574e 100644 --- a/arch/ppc64/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S diff --git a/arch/ppc64/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 4f4eb0be399..a08c26e8783 100644 --- a/arch/ppc64/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -66,3 +66,19 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) + +/* + * void unsigned long long __kernel_get_tbfreq(void); + * + * returns the timebase frequency in HZ + */ +V_FUNCTION_BEGIN(__kernel_get_tbfreq) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + bl __get_datapage@local + lwz r3,CFG_TB_TICKS_PER_SEC(r3) + lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) + mtlr r12 + .cfi_endproc +V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S new file mode 100644 index 00000000000..aeb5fc9b87b --- /dev/null +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -0,0 +1,315 @@ +/* + * Userland implementation of gettimeofday() for 32 bits processes in a + * ppc64 kernel for use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org, + * IBM Corp. + * + * 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/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text +/* + * Exact prototype of gettimeofday + * + * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); + * + */ +V_FUNCTION_BEGIN(__kernel_gettimeofday) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r10,r3 /* r10 saves tv */ + mr r11,r4 /* r11 saves tz */ + bl __get_datapage@local /* get data page */ + mr r9, r3 /* datapage ptr in r9 */ + bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 2f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r5,r4,12,20,31 + rlwimi r5,r3,12,0,19 + stw r5,TVAL32_TV_SEC(r10) + + /* get remaining xsec and convert to usec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication + */ + rlwinm r5,r4,12,0,19 + lis r6,1000000@h + ori r6,r6,1000000@l + mulhwu r5,r5,r6 + stw r5,TVAL32_TV_USEC(r10) + + cmpli cr0,r11,0 /* check if tz is NULL */ + beq 1f + lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */ + lwz r5,CFG_TZ_DSTTIME(r9) + stw r4,TZONE_TZ_MINWEST(r11) + stw r5,TZONE_TZ_DSTTIME(r11) + +1: mtlr r12 + li r3,0 + blr + +2: + mtlr r12 + mr r3,r10 + mr r4,r11 + li r0,__NR_gettimeofday + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_gettimeofday) + +/* + * Exact prototype of clock_gettime() + * + * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_gettime) + .cfi_startproc + /* Check for supported clock IDs */ + cmpli cr0,r3,CLOCK_REALTIME + cmpli cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + mflr r12 /* r12 saves lr */ + .cfi_register lr,r12 + mr r10,r3 /* r10 saves id */ + mr r11,r4 /* r11 saves tp */ + bl __get_datapage@local /* get data page */ + mr r9, r3 /* datapage ptr in r9 */ + beq cr1,50f /* if monotonic -> jump there */ + + /* + * CLOCK_REALTIME + */ + + bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 98f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r5,r4,12,20,31 + rlwimi r5,r3,12,0,19 + stw r5,TSPC32_TV_SEC(r11) + + /* get remaining xsec and convert to nsec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication, then we multiply by 1000 + */ + rlwinm r5,r4,12,0,19 + lis r6,1000000@h + ori r6,r6,1000000@l + mulhwu r5,r5,r6 + mulli r5,r5,1000 + stw r5,TSPC32_TV_NSEC(r11) + mtlr r12 + li r3,0 + blr + + /* + * CLOCK_MONOTONIC + */ + +50: bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 98f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r6,r4,12,20,31 + rlwimi r6,r3,12,0,19 + + /* get remaining xsec and convert to nsec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication, then we multiply by 1000 + */ + rlwinm r7,r4,12,0,19 + lis r5,1000000@h + ori r5,r5,1000000@l + mulhwu r7,r7,r5 + mulli r7,r7,1000 + + /* now we must fixup using wall to monotonic. We need to snapshot + * that value and do the counter trick again. Fortunately, we still + * have the counter value in r8 that was returned by __do_get_xsec. + * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5 + * can be used + */ + + lwz r3,WTOM_CLOCK_SEC(r9) + lwz r4,WTOM_CLOCK_NSEC(r9) + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r5,r4,r3 + xor r0,r5,r5 + add r9,r9,r0 +#ifdef CONFIG_PPC64 + lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) +#else + lwz r0,(CFG_TB_UPDATE_COUNT)(r9) +#endif + cmpl cr0,r8,r0 /* check if updated */ + bne- 50b + + /* Calculate and store result. Note that this mimmics the C code, + * which may cause funny results if nsec goes negative... is that + * possible at all ? + */ + add r3,r3,r6 + add r4,r4,r7 + lis r5,NSEC_PER_SEC@h + ori r5,r5,NSEC_PER_SEC@l + cmpli cr0,r4,r5 + blt 1f + subf r4,r5,r4 + addi r3,r3,1 +1: stw r3,TSPC32_TV_SEC(r11) + stw r4,TSPC32_TV_NSEC(r11) + + mtlr r12 + li r3,0 + blr + + /* + * syscall fallback + */ +98: + mtlr r12 + mr r3,r10 + mr r4,r11 +99: + li r0,__NR_clock_gettime + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_gettime) + + +/* + * Exact prototype of clock_getres() + * + * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_getres) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + li r3,0 + cmpli cr0,r4,0 + beqlr + lis r5,CLOCK_REALTIME_RES@h + ori r5,r5,CLOCK_REALTIME_RES@l + stw r3,TSPC32_TV_SEC(r4) + stw r5,TSPC32_TV_NSEC(r4) + blr + + /* + * syscall fallback + */ +99: + li r0,__NR_clock_getres + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_getres) + + +/* + * This is the core of gettimeofday() & friends, it returns the xsec + * value in r3 & r4 and expects the datapage ptr (non clobbered) + * in r9. clobbers r0,r4,r5,r6,r7,r8. + * When returning, r8 contains the counter value that can be reused + * by the monotonic clock implementation + */ +__do_get_xsec: + .cfi_startproc + /* Check for update count & load values. We use the low + * order 32 bits of the update count + */ +#ifdef CONFIG_PPC64 +1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) +#else +1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9) +#endif + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r9,r9,r0 + + /* Load orig stamp (offset to TB) */ + lwz r5,CFG_TB_ORIG_STAMP(r9) + lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) + + /* Get a stable TB value */ +2: mftbu r3 + mftbl r4 + mftbu r0 + cmpl cr0,r3,r0 + bne- 2b + + /* Substract tb orig stamp. If the high part is non-zero, we jump to + * the slow path which call the syscall. + * If it's ok, then we have our 32 bits tb_ticks value in r7 + */ + subfc r7,r6,r4 + subfe. r0,r5,r3 + bne- 3f + + /* Load scale factor & do multiplication */ + lwz r5,CFG_TB_TO_XS(r9) /* load values */ + lwz r6,(CFG_TB_TO_XS+4)(r9) + mulhwu r4,r7,r5 + mulhwu r6,r7,r6 + mullw r0,r7,r5 + addc r6,r6,r0 + + /* At this point, we have the scaled xsec value in r4 + XER:CA + * we load & add the stamp since epoch + */ + lwz r5,CFG_STAMP_XSEC(r9) + lwz r6,(CFG_STAMP_XSEC+4)(r9) + adde r4,r4,r6 + addze r3,r5 + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r6,r4,r3 + xor r0,r6,r6 + add r9,r9,r0 +#ifdef CONFIG_PPC64 + lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) +#else + lwz r0,(CFG_TB_UPDATE_COUNT)(r9) +#endif + cmpl cr0,r8,r0 /* check if updated */ + bne- 1b + + /* Warning ! The caller expects CR:EQ to be set to indicate a + * successful calculation (so it won't fallback to the syscall + * method). We have overriden that CR bit in the counter check, + * but fortunately, the loop exit condition _is_ CR:EQ set, so + * we can exit safely here. If you change this code, be careful + * of that side effect. + */ +3: blr + .cfi_endproc diff --git a/arch/ppc64/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso32/note.S index d4b5be4f3d5..d4b5be4f3d5 100644 --- a/arch/ppc64/kernel/vdso32/note.S +++ b/arch/powerpc/kernel/vdso32/note.S diff --git a/arch/ppc64/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S index e0464278191..e0464278191 100644 --- a/arch/ppc64/kernel/vdso32/sigtramp.S +++ b/arch/powerpc/kernel/vdso32/sigtramp.S diff --git a/arch/ppc64/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 6f87a916a39..f4bad720cb0 100644 --- a/arch/ppc64/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -102,9 +102,12 @@ VERSION { VDSO_VERSION_STRING { global: - __kernel_datapage_offset; /* Has to be there for the kernel to find it */ + __kernel_datapage_offset; /* Has to be there for the kernel to find */ __kernel_get_syscall_map; __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + __kernel_get_tbfreq; __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp32; diff --git a/arch/ppc64/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 76ca28e09d2..556f0caa5d8 100644 --- a/arch/ppc64/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -6,7 +6,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/ppc64/kernel/vdso32/vdso32.so" + .incbin "arch/powerpc/kernel/vdso32/vdso32.so" .balign PAGE_SIZE vdso32_end: diff --git a/arch/ppc64/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index ab39988452c..ab39988452c 100644 --- a/arch/ppc64/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile diff --git a/arch/ppc64/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index d4a0ad28d53..d4a0ad28d53 100644 --- a/arch/ppc64/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S diff --git a/arch/ppc64/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index ed6e599ae82..e67eda0f8cd 100644 --- a/arch/ppc64/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -66,3 +66,19 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) + + +/* + * void unsigned long __kernel_get_tbfreq(void); + * + * returns the timebase frequency in HZ + */ +V_FUNCTION_BEGIN(__kernel_get_tbfreq) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + bl V_LOCAL_FUNC(__get_datapage) + ld r3,CFG_TB_TICKS_PER_SEC(r3) + mtlr r12 + .cfi_endproc +V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S new file mode 100644 index 00000000000..d371c02a8c0 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -0,0 +1,242 @@ +/* + * Userland implementation of gettimeofday() for 64 bits processes in a + * ppc64 kernel for use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), + * IBM Corp. + * + * 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/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text +/* + * Exact prototype of gettimeofday + * + * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); + * + */ +V_FUNCTION_BEGIN(__kernel_gettimeofday) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds tv */ + mr r10,r4 /* r10 holds tz */ + bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ + ori r7,r7,16960 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + std r5,TVAL64_TV_SEC(r11) /* store sec in tv */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r0,r0,44,20 + cmpldi cr0,r10,0 /* check if tz is NULL */ + std r0,TVAL64_TV_USEC(r11) /* store usec in tv */ + beq 1f + lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */ + lwz r5,CFG_TZ_DSTTIME(r3) + stw r4,TZONE_TZ_MINWEST(r10) + stw r5,TZONE_TZ_DSTTIME(r10) +1: mtlr r12 + li r3,0 /* always success */ + blr + .cfi_endproc +V_FUNCTION_END(__kernel_gettimeofday) + + +/* + * Exact prototype of clock_gettime() + * + * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_gettime) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + mflr r12 /* r12 saves lr */ + .cfi_register lr,r12 + mr r10,r3 /* r10 saves id */ + mr r11,r4 /* r11 saves tp */ + bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + beq cr1,50f /* if monotonic -> jump there */ + + /* + * CLOCK_REALTIME + */ + + bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + + lis r7,0x3b9a /* r7 = 1000000000 = NSEC_PER_SEC */ + ori r7,r7,0xca00 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + std r5,TSPC64_TV_SEC(r11) /* store sec in tv */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* nsec = (xsec * NSEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r0,r0,44,20 + std r0,TSPC64_TV_NSEC(r11) /* store nsec in tp */ + + mtlr r12 + li r3,0 + blr + + /* + * CLOCK_MONOTONIC + */ + +50: bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + + lis r7,0x3b9a /* r7 = 1000000000 = NSEC_PER_SEC */ + ori r7,r7,0xca00 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* nsec = (xsec * NSEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r6,r0,44,20 + + /* now we must fixup using wall to monotonic. We need to snapshot + * that value and do the counter trick again. Fortunately, we still + * have the counter value in r8 that was returned by __do_get_xsec. + * At this point, r5,r6 contain our sec/nsec values. + * can be used + */ + + lwz r4,WTOM_CLOCK_SEC(r9) + lwz r7,WTOM_CLOCK_NSEC(r9) + + /* We now have our result in r4,r7. We create a fake dependency + * on that result and re-check the counter + */ + or r9,r4,r7 + xor r0,r9,r9 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld cr0,r0,r8 /* check if updated */ + bne- 50b + + /* Calculate and store result. Note that this mimmics the C code, + * which may cause funny results if nsec goes negative... is that + * possible at all ? + */ + add r4,r4,r5 + add r7,r7,r6 + lis r9,NSEC_PER_SEC@h + ori r9,r9,NSEC_PER_SEC@l + cmpli cr0,r7,r9 + blt 1f + subf r7,r9,r7 + addi r4,r4,1 +1: std r4,TSPC64_TV_SEC(r11) + std r7,TSPC64_TV_NSEC(r11) + + mtlr r12 + li r3,0 + blr + + /* + * syscall fallback + */ +98: + mtlr r12 + mr r3,r10 + mr r4,r11 +99: + li r0,__NR_clock_gettime + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_gettime) + + +/* + * Exact prototype of clock_getres() + * + * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_getres) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + li r3,0 + cmpli cr0,r4,0 + beqlr + lis r5,CLOCK_REALTIME_RES@h + ori r5,r5,CLOCK_REALTIME_RES@l + std r3,TSPC64_TV_SEC(r4) + std r5,TSPC64_TV_NSEC(r4) + blr + + /* + * syscall fallback + */ +99: + li r0,__NR_clock_getres + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_getres) + + +/* + * This is the core of gettimeofday(), it returns the xsec + * value in r4 and expects the datapage ptr (non clobbered) + * in r3. clobbers r0,r4,r5,r6,r7,r8 + * When returning, r8 contains the counter value that can be reused + */ +V_FUNCTION_BEGIN(__do_get_xsec) + .cfi_startproc + /* check for update count & load values */ +1: ld r8,CFG_TB_UPDATE_COUNT(r3) + andi. r0,r4,1 /* pending update ? loop */ + bne- 1b + xor r0,r4,r4 /* create dependency */ + add r3,r3,r0 + + /* Get TB & offset it */ + mftb r7 + ld r9,CFG_TB_ORIG_STAMP(r3) + subf r7,r9,r7 + + /* Scale result */ + ld r5,CFG_TB_TO_XS(r3) + mulhdu r7,r7,r5 + + /* Add stamp since epoch */ + ld r6,CFG_STAMP_XSEC(r3) + add r4,r6,r7 + + xor r0,r4,r4 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld cr0,r0,r8 /* check if updated */ + bne- 1b + blr + .cfi_endproc +V_FUNCTION_END(__do_get_xsec) diff --git a/arch/ppc64/kernel/vdso64/note.S b/arch/powerpc/kernel/vdso64/note.S index dc2a509f7e8..dc2a509f7e8 100644 --- a/arch/ppc64/kernel/vdso64/note.S +++ b/arch/powerpc/kernel/vdso64/note.S diff --git a/arch/ppc64/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index 31b604ab56d..31b604ab56d 100644 --- a/arch/ppc64/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S diff --git a/arch/ppc64/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 9cb28181da8..4bdf224464a 100644 --- a/arch/ppc64/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -102,9 +102,12 @@ VERSION { VDSO_VERSION_STRING { global: - __kernel_datapage_offset; /* Has to be there for the kernel to find it */ + __kernel_datapage_offset; /* Has to be there for the kernel to find */ __kernel_get_syscall_map; __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + __kernel_get_tbfreq; __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp_rt64; diff --git a/arch/ppc64/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index 771c2741c49..0529cb9e3b9 100644 --- a/arch/ppc64/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -6,7 +6,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/ppc64/kernel/vdso64/vdso64.so" + .incbin "arch/powerpc/kernel/vdso64/vdso64.so" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 1dd3cc69a49..e2c95fcb805 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -46,9 +46,7 @@ #include <asm/prom.h> #include <asm/lmb.h> #include <asm/sections.h> -#ifdef CONFIG_PPC64 #include <asm/vdso.h> -#endif #include "mmu_decl.h" @@ -397,10 +395,8 @@ void __init mem_init(void) mem_init_done = 1; -#ifdef CONFIG_PPC64 /* Initialize the vDSO */ vdso_init(); -#endif } /* diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index da09ba03c42..bd2cf133688 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -17,9 +17,8 @@ #include <linux/nodemask.h> #include <linux/cpu.h> #include <linux/notifier.h> +#include <asm/sparsemem.h> #include <asm/lmb.h> -#include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/system.h> #include <asm/smp.h> @@ -28,45 +27,113 @@ static int numa_enabled = 1; static int numa_debug; #define dbg(args...) if (numa_debug) { printk(KERN_INFO args); } -#ifdef DEBUG_NUMA -#define ARRAY_INITIALISER -1 -#else -#define ARRAY_INITIALISER 0 -#endif - -int numa_cpu_lookup_table[NR_CPUS] = { [ 0 ... (NR_CPUS - 1)] = - ARRAY_INITIALISER}; -char *numa_memory_lookup_table; +int numa_cpu_lookup_table[NR_CPUS]; cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; -int nr_cpus_in_node[MAX_NUMNODES] = { [0 ... (MAX_NUMNODES -1)] = 0}; - struct pglist_data *node_data[MAX_NUMNODES]; -bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES]; + +EXPORT_SYMBOL(numa_cpu_lookup_table); +EXPORT_SYMBOL(numa_cpumask_lookup_table); +EXPORT_SYMBOL(node_data); + +static bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES]; static int min_common_depth; /* - * We need somewhere to store start/span for each node until we have + * We need somewhere to store start/end/node for each region until we have * allocated the real node_data structures. */ +#define MAX_REGIONS (MAX_LMB_REGIONS*2) static struct { - unsigned long node_start_pfn; - unsigned long node_end_pfn; - unsigned long node_present_pages; -} init_node_data[MAX_NUMNODES] __initdata; + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +} init_node_data[MAX_REGIONS] __initdata; -EXPORT_SYMBOL(node_data); -EXPORT_SYMBOL(numa_cpu_lookup_table); -EXPORT_SYMBOL(numa_memory_lookup_table); -EXPORT_SYMBOL(numa_cpumask_lookup_table); -EXPORT_SYMBOL(nr_cpus_in_node); +int __init early_pfn_to_nid(unsigned long pfn) +{ + unsigned int i; + + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start_pfn = init_node_data[i].start_pfn; + unsigned long end_pfn = init_node_data[i].end_pfn; + + if ((start_pfn <= pfn) && (pfn < end_pfn)) + return init_node_data[i].nid; + } + + return -1; +} + +void __init add_region(unsigned int nid, unsigned long start_pfn, + unsigned long pages) +{ + unsigned int i; + + dbg("add_region nid %d start_pfn 0x%lx pages 0x%lx\n", + nid, start_pfn, pages); + + for (i = 0; init_node_data[i].end_pfn; i++) { + if (init_node_data[i].nid != nid) + continue; + if (init_node_data[i].end_pfn == start_pfn) { + init_node_data[i].end_pfn += pages; + return; + } + if (init_node_data[i].start_pfn == (start_pfn + pages)) { + init_node_data[i].start_pfn -= pages; + return; + } + } + + /* + * Leave last entry NULL so we dont iterate off the end (we use + * entry.end_pfn to terminate the walk). + */ + if (i >= (MAX_REGIONS - 1)) { + printk(KERN_ERR "WARNING: too many memory regions in " + "numa code, truncating\n"); + return; + } + + init_node_data[i].start_pfn = start_pfn; + init_node_data[i].end_pfn = start_pfn + pages; + init_node_data[i].nid = nid; +} + +/* We assume init_node_data has no overlapping regions */ +void __init get_region(unsigned int nid, unsigned long *start_pfn, + unsigned long *end_pfn, unsigned long *pages_present) +{ + unsigned int i; + + *start_pfn = -1UL; + *end_pfn = *pages_present = 0; + + for (i = 0; init_node_data[i].end_pfn; i++) { + if (init_node_data[i].nid != nid) + continue; + + *pages_present += init_node_data[i].end_pfn - + init_node_data[i].start_pfn; + + if (init_node_data[i].start_pfn < *start_pfn) + *start_pfn = init_node_data[i].start_pfn; + + if (init_node_data[i].end_pfn > *end_pfn) + *end_pfn = init_node_data[i].end_pfn; + } + + /* We didnt find a matching region, return start/end as 0 */ + if (*start_pfn == -1UL) + start_pfn = 0; +} static inline void map_cpu_to_node(int cpu, int node) { numa_cpu_lookup_table[cpu] = node; - if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) { + + if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) cpu_set(cpu, numa_cpumask_lookup_table[node]); - nr_cpus_in_node[node]++; - } } #ifdef CONFIG_HOTPLUG_CPU @@ -78,7 +145,6 @@ static void unmap_cpu_from_node(unsigned long cpu) if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) { cpu_clear(cpu, numa_cpumask_lookup_table[node]); - nr_cpus_in_node[node]--; } else { printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n", cpu, node); @@ -86,7 +152,7 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU */ -static struct device_node * __devinit find_cpu_node(unsigned int cpu) +static struct device_node *find_cpu_node(unsigned int cpu) { unsigned int hw_cpuid = get_hard_smp_processor_id(cpu); struct device_node *cpu_node = NULL; @@ -213,7 +279,7 @@ static int __init get_mem_size_cells(void) return rc; } -static unsigned long read_n_cells(int n, unsigned int **buf) +static unsigned long __init read_n_cells(int n, unsigned int **buf) { unsigned long result = 0; @@ -295,7 +361,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, * or zero. If the returned value of size is 0 the region should be * discarded as it lies wholy above the memory limit. */ -static unsigned long __init numa_enforce_memory_limit(unsigned long start, unsigned long size) +static unsigned long __init numa_enforce_memory_limit(unsigned long start, + unsigned long size) { /* * We use lmb_end_of_DRAM() in here instead of memory_limit because @@ -320,8 +387,7 @@ static int __init parse_numa_properties(void) struct device_node *cpu = NULL; struct device_node *memory = NULL; int addr_cells, size_cells; - int max_domain = 0; - long entries = lmb_end_of_DRAM() >> MEMORY_INCREMENT_SHIFT; + int max_domain; unsigned long i; if (numa_enabled == 0) { @@ -329,13 +395,6 @@ static int __init parse_numa_properties(void) return -1; } - numa_memory_lookup_table = - (char *)abs_to_virt(lmb_alloc(entries * sizeof(char), 1)); - memset(numa_memory_lookup_table, 0, entries * sizeof(char)); - - for (i = 0; i < entries ; i++) - numa_memory_lookup_table[i] = ARRAY_INITIALISER; - min_common_depth = find_min_common_depth(); dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth); @@ -387,9 +446,6 @@ new_range: start = read_n_cells(addr_cells, &memcell_buf); size = read_n_cells(size_cells, &memcell_buf); - start = _ALIGN_DOWN(start, MEMORY_INCREMENT); - size = _ALIGN_UP(size, MEMORY_INCREMENT); - numa_domain = of_node_numa_domain(memory); if (numa_domain >= MAX_NUMNODES) { @@ -403,44 +459,15 @@ new_range: if (max_domain < numa_domain) max_domain = numa_domain; - if (! (size = numa_enforce_memory_limit(start, size))) { + if (!(size = numa_enforce_memory_limit(start, size))) { if (--ranges) goto new_range; else continue; } - /* - * Initialize new node struct, or add to an existing one. - */ - if (init_node_data[numa_domain].node_end_pfn) { - if ((start / PAGE_SIZE) < - init_node_data[numa_domain].node_start_pfn) - init_node_data[numa_domain].node_start_pfn = - start / PAGE_SIZE; - if (((start / PAGE_SIZE) + (size / PAGE_SIZE)) > - init_node_data[numa_domain].node_end_pfn) - init_node_data[numa_domain].node_end_pfn = - (start / PAGE_SIZE) + - (size / PAGE_SIZE); - - init_node_data[numa_domain].node_present_pages += - size / PAGE_SIZE; - } else { - node_set_online(numa_domain); - - init_node_data[numa_domain].node_start_pfn = - start / PAGE_SIZE; - init_node_data[numa_domain].node_end_pfn = - init_node_data[numa_domain].node_start_pfn + - size / PAGE_SIZE; - init_node_data[numa_domain].node_present_pages = - size / PAGE_SIZE; - } - - for (i = start ; i < (start+size); i += MEMORY_INCREMENT) - numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] = - numa_domain; + add_region(numa_domain, start >> PAGE_SHIFT, + size >> PAGE_SHIFT); if (--ranges) goto new_range; @@ -456,32 +483,15 @@ static void __init setup_nonnuma(void) { unsigned long top_of_ram = lmb_end_of_DRAM(); unsigned long total_ram = lmb_phys_mem_size(); - unsigned long i; printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n", top_of_ram, total_ram); printk(KERN_INFO "Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20); - if (!numa_memory_lookup_table) { - long entries = top_of_ram >> MEMORY_INCREMENT_SHIFT; - numa_memory_lookup_table = - (char *)abs_to_virt(lmb_alloc(entries * sizeof(char), 1)); - memset(numa_memory_lookup_table, 0, entries * sizeof(char)); - for (i = 0; i < entries ; i++) - numa_memory_lookup_table[i] = ARRAY_INITIALISER; - } - map_cpu_to_node(boot_cpuid, 0); - + add_region(0, 0, lmb_end_of_DRAM() >> PAGE_SHIFT); node_set_online(0); - - init_node_data[0].node_start_pfn = 0; - init_node_data[0].node_end_pfn = lmb_end_of_DRAM() / PAGE_SIZE; - init_node_data[0].node_present_pages = total_ram / PAGE_SIZE; - - for (i = 0 ; i < top_of_ram; i += MEMORY_INCREMENT) - numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] = 0; } static void __init dump_numa_topology(void) @@ -499,8 +509,9 @@ static void __init dump_numa_topology(void) count = 0; - for (i = 0; i < lmb_end_of_DRAM(); i += MEMORY_INCREMENT) { - if (numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] == node) { + for (i = 0; i < lmb_end_of_DRAM(); + i += (1 << SECTION_SIZE_BITS)) { + if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) { if (count == 0) printk(" 0x%lx", i); ++count; @@ -525,10 +536,12 @@ static void __init dump_numa_topology(void) * * Returns the physical address of the memory. */ -static unsigned long careful_allocation(int nid, unsigned long size, - unsigned long align, unsigned long end) +static void __init *careful_allocation(int nid, unsigned long size, + unsigned long align, + unsigned long end_pfn) { - unsigned long ret = lmb_alloc_base(size, align, end); + int new_nid; + unsigned long ret = lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT); /* retry over all memory */ if (!ret) @@ -542,28 +555,27 @@ static unsigned long careful_allocation(int nid, unsigned long size, * If the memory came from a previously allocated node, we must * retry with the bootmem allocator. */ - if (pa_to_nid(ret) < nid) { - nid = pa_to_nid(ret); - ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(nid), + new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT); + if (new_nid < nid) { + ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid), size, align, 0); if (!ret) panic("numa.c: cannot allocate %lu bytes on node %d", - size, nid); + size, new_nid); - ret = virt_to_abs(ret); + ret = __pa(ret); dbg("alloc_bootmem %lx %lx\n", ret, size); } - return ret; + return (void *)ret; } void __init do_init_bootmem(void) { int nid; - int addr_cells, size_cells; - struct device_node *memory = NULL; + unsigned int i; static struct notifier_block ppc64_numa_nb = { .notifier_call = cpu_numa_callback, .priority = 1 /* Must run before sched domains notifier. */ @@ -581,99 +593,66 @@ void __init do_init_bootmem(void) register_cpu_notifier(&ppc64_numa_nb); for_each_online_node(nid) { - unsigned long start_paddr, end_paddr; - int i; + unsigned long start_pfn, end_pfn, pages_present; unsigned long bootmem_paddr; unsigned long bootmap_pages; - start_paddr = init_node_data[nid].node_start_pfn * PAGE_SIZE; - end_paddr = init_node_data[nid].node_end_pfn * PAGE_SIZE; + get_region(nid, &start_pfn, &end_pfn, &pages_present); /* Allocate the node structure node local if possible */ - NODE_DATA(nid) = (struct pglist_data *)careful_allocation(nid, + NODE_DATA(nid) = careful_allocation(nid, sizeof(struct pglist_data), - SMP_CACHE_BYTES, end_paddr); - NODE_DATA(nid) = abs_to_virt(NODE_DATA(nid)); + SMP_CACHE_BYTES, end_pfn); + NODE_DATA(nid) = __va(NODE_DATA(nid)); memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); dbg("node %d\n", nid); dbg("NODE_DATA() = %p\n", NODE_DATA(nid)); NODE_DATA(nid)->bdata = &plat_node_bdata[nid]; - NODE_DATA(nid)->node_start_pfn = - init_node_data[nid].node_start_pfn; - NODE_DATA(nid)->node_spanned_pages = - end_paddr - start_paddr; + NODE_DATA(nid)->node_start_pfn = start_pfn; + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; if (NODE_DATA(nid)->node_spanned_pages == 0) continue; - dbg("start_paddr = %lx\n", start_paddr); - dbg("end_paddr = %lx\n", end_paddr); + dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT); + dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT); - bootmap_pages = bootmem_bootmap_pages((end_paddr - start_paddr) >> PAGE_SHIFT); + bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); + bootmem_paddr = (unsigned long)careful_allocation(nid, + bootmap_pages << PAGE_SHIFT, + PAGE_SIZE, end_pfn); + memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT); - bootmem_paddr = careful_allocation(nid, - bootmap_pages << PAGE_SHIFT, - PAGE_SIZE, end_paddr); - memset(abs_to_virt(bootmem_paddr), 0, - bootmap_pages << PAGE_SHIFT); dbg("bootmap_paddr = %lx\n", bootmem_paddr); init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT, - start_paddr >> PAGE_SHIFT, - end_paddr >> PAGE_SHIFT); + start_pfn, end_pfn); - /* - * We need to do another scan of all memory sections to - * associate memory with the correct node. - */ - addr_cells = get_mem_addr_cells(); - size_cells = get_mem_size_cells(); - memory = NULL; - while ((memory = of_find_node_by_type(memory, "memory")) != NULL) { - unsigned long mem_start, mem_size; - int numa_domain, ranges; - unsigned int *memcell_buf; - unsigned int len; - - memcell_buf = (unsigned int *)get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) - continue; + /* Add free regions on this node */ + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start, end; - ranges = memory->n_addrs; /* ranges in cell */ -new_range: - mem_start = read_n_cells(addr_cells, &memcell_buf); - mem_size = read_n_cells(size_cells, &memcell_buf); - if (numa_enabled) { - numa_domain = of_node_numa_domain(memory); - if (numa_domain >= MAX_NUMNODES) - numa_domain = 0; - } else - numa_domain = 0; - - if (numa_domain != nid) + if (init_node_data[i].nid != nid) continue; - mem_size = numa_enforce_memory_limit(mem_start, mem_size); - if (mem_size) { - dbg("free_bootmem %lx %lx\n", mem_start, mem_size); - free_bootmem_node(NODE_DATA(nid), mem_start, mem_size); - } + start = init_node_data[i].start_pfn << PAGE_SHIFT; + end = init_node_data[i].end_pfn << PAGE_SHIFT; - if (--ranges) /* process all ranges in cell */ - goto new_range; + dbg("free_bootmem %lx %lx\n", start, end - start); + free_bootmem_node(NODE_DATA(nid), start, end - start); } - /* - * Mark reserved regions on this node - */ + /* Mark reserved regions on this node */ for (i = 0; i < lmb.reserved.cnt; i++) { unsigned long physbase = lmb.reserved.region[i].base; unsigned long size = lmb.reserved.region[i].size; + unsigned long start_paddr = start_pfn << PAGE_SHIFT; + unsigned long end_paddr = end_pfn << PAGE_SHIFT; - if (pa_to_nid(physbase) != nid && - pa_to_nid(physbase+size-1) != nid) + if (early_pfn_to_nid(physbase >> PAGE_SHIFT) != nid && + early_pfn_to_nid((physbase+size-1) >> PAGE_SHIFT) != nid) continue; if (physbase < end_paddr && @@ -693,46 +672,19 @@ new_range: size); } } - /* - * This loop may look famaliar, but we have to do it again - * after marking our reserved memory to mark memory present - * for sparsemem. - */ - addr_cells = get_mem_addr_cells(); - size_cells = get_mem_size_cells(); - memory = NULL; - while ((memory = of_find_node_by_type(memory, "memory")) != NULL) { - unsigned long mem_start, mem_size; - int numa_domain, ranges; - unsigned int *memcell_buf; - unsigned int len; - - memcell_buf = (unsigned int *)get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) - continue; - ranges = memory->n_addrs; /* ranges in cell */ -new_range2: - mem_start = read_n_cells(addr_cells, &memcell_buf); - mem_size = read_n_cells(size_cells, &memcell_buf); - if (numa_enabled) { - numa_domain = of_node_numa_domain(memory); - if (numa_domain >= MAX_NUMNODES) - numa_domain = 0; - } else - numa_domain = 0; - - if (numa_domain != nid) + /* Add regions into sparsemem */ + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start, end; + + if (init_node_data[i].nid != nid) continue; - mem_size = numa_enforce_memory_limit(mem_start, mem_size); - memory_present(numa_domain, mem_start >> PAGE_SHIFT, - (mem_start + mem_size) >> PAGE_SHIFT); + start = init_node_data[i].start_pfn; + end = init_node_data[i].end_pfn; - if (--ranges) /* process all ranges in cell */ - goto new_range2; + memory_present(nid, start, end); } - } } @@ -746,21 +698,18 @@ void __init paging_init(void) memset(zholes_size, 0, sizeof(zholes_size)); for_each_online_node(nid) { - unsigned long start_pfn; - unsigned long end_pfn; + unsigned long start_pfn, end_pfn, pages_present; - start_pfn = init_node_data[nid].node_start_pfn; - end_pfn = init_node_data[nid].node_end_pfn; + get_region(nid, &start_pfn, &end_pfn, &pages_present); zones_size[ZONE_DMA] = end_pfn - start_pfn; - zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - - init_node_data[nid].node_present_pages; + zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present; dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid, zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]); - free_area_init_node(nid, NODE_DATA(nid), zones_size, - start_pfn, zholes_size); + free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn, + zholes_size); } } diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index e3a024e324b..a3401b46f3b 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -14,7 +14,6 @@ #include <asm/system.h> #include <asm/processor.h> #include <asm/cputable.h> -#include <asm/systemcfg.h> #include <asm/rtas.h> #include <asm/oprofile_impl.h> #include <asm/reg.h> diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c index 00cf331a1dc..a6f628d4c9d 100644 --- a/arch/powerpc/platforms/pseries/rtasd.c +++ b/arch/powerpc/platforms/pseries/rtasd.c @@ -27,7 +27,6 @@ #include <asm/prom.h> #include <asm/nvram.h> #include <asm/atomic.h> -#include <asm/systemcfg.h> #if 0 #define DEBUG(A...) printk(KERN_ERR A) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e94247c28d4..31990829310 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -306,9 +306,7 @@ static void __init fw_feature_init(void) } of_node_put(dn); - no_rtas: - printk(KERN_INFO "firmware_features = 0x%lx\n", - ppc64_firmware_features); +no_rtas: DBG(" <- fw_feature_init()\n"); } diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 3ba794ca328..5800cde7d5a 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -46,7 +46,7 @@ #include <asm/rtas.h> #include <asm/pSeries_reconfig.h> #include <asm/mpic.h> -#include <asm/systemcfg.h> +#include <asm/vdso_datapage.h> #include "plpar_wrappers.h" @@ -97,7 +97,7 @@ int pSeries_cpu_disable(void) int cpu = smp_processor_id(); cpu_clear(cpu, cpu_online_map); - _systemcfg->processorCount--; + vdso_data->processorCount--; /*fix boot_cpuid here*/ if (cpu == boot_cpuid) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index cfcb2a56d66..ef4356b29a9 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1467,17 +1467,23 @@ read_spr(int n) { unsigned int instrs[2]; unsigned long (*code)(void); - unsigned long opd[3]; unsigned long ret = -1UL; +#ifdef CONFIG_PPC64 + unsigned long opd[3]; - instrs[0] = 0x7c6002a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); - instrs[1] = 0x4e800020; opd[0] = (unsigned long)instrs; opd[1] = 0; opd[2] = 0; + code = (unsigned long (*)(void)) opd; +#else + code = (unsigned long (*)(void)) instrs; +#endif + + /* mfspr r3,n; blr */ + instrs[0] = 0x7c6002a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); + instrs[1] = 0x4e800020; store_inst(instrs); store_inst(instrs+1); - code = (unsigned long (*)(void)) opd; if (setjmp(bus_error_jmp) == 0) { catch_memory_errors = 1; @@ -1499,16 +1505,21 @@ write_spr(int n, unsigned long val) { unsigned int instrs[2]; unsigned long (*code)(unsigned long); +#ifdef CONFIG_PPC64 unsigned long opd[3]; - instrs[0] = 0x7c6003a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); - instrs[1] = 0x4e800020; opd[0] = (unsigned long)instrs; opd[1] = 0; opd[2] = 0; + code = (unsigned long (*)(unsigned long)) opd; +#else + code = (unsigned long (*)(unsigned long)) instrs; +#endif + + instrs[0] = 0x7c6003a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); + instrs[1] = 0x4e800020; store_inst(instrs); store_inst(instrs+1); - code = (unsigned long (*)(unsigned long)) opd; if (setjmp(bus_error_jmp) == 0) { catch_memory_errors = 1; diff --git a/arch/ppc/kernel/asm-offsets.c b/arch/ppc/kernel/asm-offsets.c index 968261d6957..fe0e767fb94 100644 --- a/arch/ppc/kernel/asm-offsets.c +++ b/arch/ppc/kernel/asm-offsets.c @@ -25,6 +25,7 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/thread_info.h> +#include <asm/vdso_datapage.h> #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -143,5 +144,32 @@ main(void) DEFINE(TASK_SIZE, TASK_SIZE); DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); + + /* datapage offsets for use by vdso */ + DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp)); + DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec)); + DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs)); + DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec)); + DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count)); + DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest)); + DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); + DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); + DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); + DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); + DEFINE(TVAL32_TV_SEC, offsetof(struct timeval, tv_sec)); + DEFINE(TVAL32_TV_USEC, offsetof(struct timeval, tv_usec)); + DEFINE(TSPEC32_TV_SEC, offsetof(struct timespec, tv_sec)); + DEFINE(TSPEC32_TV_NSEC, offsetof(struct timespec, tv_nsec)); + + /* timeval/timezone offsets for use by vdso */ + DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); + DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); + + /* Other bits used by the vdso */ + DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); + DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); + DEFINE(CLOCK_REALTIME_RES, TICK_NSEC); + return 0; } diff --git a/arch/ppc/syslib/cpm2_pic.c b/arch/ppc/syslib/cpm2_pic.c index c867be6981c..29d95d415ce 100644 --- a/arch/ppc/syslib/cpm2_pic.c +++ b/arch/ppc/syslib/cpm2_pic.c @@ -37,7 +37,7 @@ static u_char irq_to_siureg[] = { static u_char irq_to_siubit[] = { 0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, - 2, 1, 15, 14, 13, 12, 11, 10, + 2, 1, 0, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 0, 31, 30, 29, 28, 27, 26, 25, 24, 23, 22, 21, 20, 19, 18, 17, 16, diff --git a/arch/ppc64/Kconfig b/arch/ppc64/Kconfig index c9d32db9d76..9d10c12e87f 100644 --- a/arch/ppc64/Kconfig +++ b/arch/ppc64/Kconfig @@ -279,17 +279,12 @@ config ARCH_FLATMEM_ENABLE def_bool y depends on !NUMA -config ARCH_DISCONTIGMEM_ENABLE - def_bool y - depends on SMP && PPC_PSERIES - -config ARCH_DISCONTIGMEM_DEFAULT +config ARCH_SPARSEMEM_ENABLE def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE -config ARCH_SPARSEMEM_ENABLE +config ARCH_SPARSEMEM_DEFAULT def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE + depends on NUMA source "mm/Kconfig" diff --git a/arch/ppc64/kernel/Makefile b/arch/ppc64/kernel/Makefile index 58b19f10765..dac4cc20fa9 100644 --- a/arch/ppc64/kernel/Makefile +++ b/arch/ppc64/kernel/Makefile @@ -13,10 +13,8 @@ endif obj-y += idle.o dma.o \ align.o \ - udbg.o \ rtc.o \ - iommu.o vdso.o -obj-y += vdso32/ vdso64/ + iommu.o pci-obj-$(CONFIG_PPC_MULTIPLATFORM) += pci_dn.o pci_direct_iommu.o @@ -27,8 +25,6 @@ ifneq ($(CONFIG_PPC_MERGE),y) obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o endif -obj-$(CONFIG_PPC_PSERIES) += udbg_16550.o - obj-$(CONFIG_KEXEC) += machine_kexec.o obj-$(CONFIG_MODULES) += module.o ifneq ($(CONFIG_PPC_MERGE),y) @@ -40,10 +36,6 @@ obj-$(CONFIG_BOOTX_TEXT) += btext.o endif obj-$(CONFIG_HVCS) += hvcserver.o -obj-$(CONFIG_PPC_PMAC) += udbg_scc.o - -obj-$(CONFIG_PPC_MAPLE) += udbg_16550.o - obj-$(CONFIG_KPROBES) += kprobes.o ifneq ($(CONFIG_PPC_MERGE),y) diff --git a/arch/ppc64/kernel/misc.S b/arch/ppc64/kernel/misc.S index 492bca6137e..5e089deb0a2 100644 --- a/arch/ppc64/kernel/misc.S +++ b/arch/ppc64/kernel/misc.S @@ -186,7 +186,8 @@ _KPROBE(__flush_icache_range) bdnz 2b isync blr - .previous .text + + .text /* * Like above, but only do the D-cache. * diff --git a/arch/ppc64/kernel/vdso32/gettimeofday.S b/arch/ppc64/kernel/vdso32/gettimeofday.S deleted file mode 100644 index e243c1d24af..00000000000 --- a/arch/ppc64/kernel/vdso32/gettimeofday.S +++ /dev/null @@ -1,140 +0,0 @@ -/* - * Userland implementation of gettimeofday() for 32 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. - * - * 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/config.h> -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/vdso.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - - mr r10,r3 /* r10 saves tv */ - mr r11,r4 /* r11 saves tz */ - bl __get_datapage@local /* get data page */ - mr r9, r3 /* datapage ptr in r9 */ - bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 2f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r5,r4,12,20,31 - rlwimi r5,r3,12,0,19 - stw r5,TVAL32_TV_SEC(r10) - - /* get remaining xsec and convert to usec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication - */ - rlwinm r5,r4,12,0,19 - lis r6,1000000@h - ori r6,r6,1000000@l - mulhwu r5,r5,r6 - stw r5,TVAL32_TV_USEC(r10) - - cmpli cr0,r11,0 /* check if tz is NULL */ - beq 1f - lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */ - lwz r5,CFG_TZ_DSTTIME(r9) - stw r4,TZONE_TZ_MINWEST(r11) - stw r5,TZONE_TZ_DSTTIME(r11) - -1: mtlr r12 - li r3,0 - blr - -2: mr r3,r10 - mr r4,r11 - li r0,__NR_gettimeofday - sc - b 1b - .cfi_endproc -V_FUNCTION_END(__kernel_gettimeofday) - -/* - * This is the core of gettimeofday(), it returns the xsec - * value in r3 & r4 and expects the datapage ptr (non clobbered) - * in r9. clobbers r0,r4,r5,r6,r7,r8 -*/ -__do_get_xsec: - .cfi_startproc - /* Check for update count & load values. We use the low - * order 32 bits of the update count - */ -1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) - andi. r0,r8,1 /* pending update ? loop */ - bne- 1b - xor r0,r8,r8 /* create dependency */ - add r9,r9,r0 - - /* Load orig stamp (offset to TB) */ - lwz r5,CFG_TB_ORIG_STAMP(r9) - lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) - - /* Get a stable TB value */ -2: mftbu r3 - mftbl r4 - mftbu r0 - cmpl cr0,r3,r0 - bne- 2b - - /* Substract tb orig stamp. If the high part is non-zero, we jump to the - * slow path which call the syscall. If it's ok, then we have our 32 bits - * tb_ticks value in r7 - */ - subfc r7,r6,r4 - subfe. r0,r5,r3 - bne- 3f - - /* Load scale factor & do multiplication */ - lwz r5,CFG_TB_TO_XS(r9) /* load values */ - lwz r6,(CFG_TB_TO_XS+4)(r9) - mulhwu r4,r7,r5 - mulhwu r6,r7,r6 - mullw r0,r7,r5 - addc r6,r6,r0 - - /* At this point, we have the scaled xsec value in r4 + XER:CA - * we load & add the stamp since epoch - */ - lwz r5,CFG_STAMP_XSEC(r9) - lwz r6,(CFG_STAMP_XSEC+4)(r9) - adde r4,r4,r6 - addze r3,r5 - - /* We now have our result in r3,r4. We create a fake dependency - * on that result and re-check the counter - */ - xor r0,r4,r4 - add r9,r9,r0 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) - cmpl cr0,r8,r0 /* check if updated */ - bne- 1b - - /* Warning ! The caller expects CR:EQ to be set to indicate a - * successful calculation (so it won't fallback to the syscall - * method). We have overriden that CR bit in the counter check, - * but fortunately, the loop exit condition _is_ CR:EQ set, so - * we can exit safely here. If you change this code, be careful - * of that side effect. - */ -3: blr - .cfi_endproc diff --git a/arch/ppc64/kernel/vdso64/gettimeofday.S b/arch/ppc64/kernel/vdso64/gettimeofday.S deleted file mode 100644 index f6df8028570..00000000000 --- a/arch/ppc64/kernel/vdso64/gettimeofday.S +++ /dev/null @@ -1,91 +0,0 @@ -/* - * Userland implementation of gettimeofday() for 64 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - * - * 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/config.h> -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/vdso.h> -#include <asm/asm-offsets.h> - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - - mr r11,r3 /* r11 holds tv */ - mr r10,r4 /* r10 holds tz */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - std r5,TVAL64_TV_SEC(r11) /* store sec in tv */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / XSEC_PER_SEC */ - rldicl r0,r0,44,20 - cmpldi cr0,r10,0 /* check if tz is NULL */ - std r0,TVAL64_TV_USEC(r11) /* store usec in tv */ - beq 1f - lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */ - lwz r5,CFG_TZ_DSTTIME(r3) - stw r4,TZONE_TZ_MINWEST(r10) - stw r5,TZONE_TZ_DSTTIME(r10) -1: mtlr r12 - li r3,0 /* always success */ - blr - .cfi_endproc -V_FUNCTION_END(__kernel_gettimeofday) - - -/* - * This is the core of gettimeofday(), it returns the xsec - * value in r4 and expects the datapage ptr (non clobbered) - * in r3. clobbers r0,r4,r5,r6,r7,r8 -*/ -V_FUNCTION_BEGIN(__do_get_xsec) - .cfi_startproc - /* check for update count & load values */ -1: ld r7,CFG_TB_UPDATE_COUNT(r3) - andi. r0,r4,1 /* pending update ? loop */ - bne- 1b - xor r0,r4,r4 /* create dependency */ - add r3,r3,r0 - - /* Get TB & offset it */ - mftb r8 - ld r9,CFG_TB_ORIG_STAMP(r3) - subf r8,r9,r8 - - /* Scale result */ - ld r5,CFG_TB_TO_XS(r3) - mulhdu r8,r8,r5 - - /* Add stamp since epoch */ - ld r6,CFG_STAMP_XSEC(r3) - add r4,r6,r8 - - xor r0,r4,r4 - add r3,r3,r0 - ld r0,CFG_TB_UPDATE_COUNT(r3) - cmpld cr0,r0,r7 /* check if updated */ - bne- 1b - blr - .cfi_endproc -V_FUNCTION_END(__do_get_xsec) diff --git a/include/asm-powerpc/auxvec.h b/include/asm-powerpc/auxvec.h index 79d8c473230..19a099b62cd 100644 --- a/include/asm-powerpc/auxvec.h +++ b/include/asm-powerpc/auxvec.h @@ -14,8 +14,6 @@ /* The vDSO location. We have to use the same value as x86 for glibc's * sake :-) */ -#ifdef __powerpc64__ #define AT_SYSINFO_EHDR 33 -#endif #endif diff --git a/include/asm-powerpc/elf.h b/include/asm-powerpc/elf.h index feac3458d71..3dcd65edf97 100644 --- a/include/asm-powerpc/elf.h +++ b/include/asm-powerpc/elf.h @@ -269,14 +269,12 @@ extern int dcache_bsize; extern int icache_bsize; extern int ucache_bsize; -#ifdef __powerpc64__ +/* vDSO has arch_setup_additional_pages */ +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; -#define ARCH_HAS_SETUP_ADDITIONAL_PAGES /* vDSO has arch_setup_additional_pages */ -extern int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack); +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int executable_stack); #define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b); -#else -#define VDSO_AUX_ENT(a,b) -#endif /* __powerpc64__ */ /* * The requirements here are: diff --git a/include/asm-powerpc/irq.h b/include/asm-powerpc/irq.h index c9fbcede0ef..8eb7e857ec4 100644 --- a/include/asm-powerpc/irq.h +++ b/include/asm-powerpc/irq.h @@ -389,6 +389,7 @@ extern u64 ppc64_interrupt_controller; #define SIU_INT_TIMER4 ((uint)0x0f + CPM_IRQ_OFFSET) #define SIU_INT_TMCNT ((uint)0x10 + CPM_IRQ_OFFSET) #define SIU_INT_PIT ((uint)0x11 + CPM_IRQ_OFFSET) +#define SIU_INT_PCI ((uint)0x12 + CPM_IRQ_OFFSET) #define SIU_INT_IRQ1 ((uint)0x13 + CPM_IRQ_OFFSET) #define SIU_INT_IRQ2 ((uint)0x14 + CPM_IRQ_OFFSET) #define SIU_INT_IRQ3 ((uint)0x15 + CPM_IRQ_OFFSET) diff --git a/include/asm-powerpc/processor.h b/include/asm-powerpc/processor.h index f6f186b56b0..d12382d292d 100644 --- a/include/asm-powerpc/processor.h +++ b/include/asm-powerpc/processor.h @@ -177,8 +177,8 @@ struct thread_struct { #ifdef CONFIG_PPC64 unsigned long start_tb; /* Start purr when proc switched in */ unsigned long accum_tb; /* Total accumilated purr for process */ - unsigned long vdso_base; /* base of the vDSO library */ #endif + unsigned long vdso_base; /* base of the vDSO library */ unsigned long dabr; /* Data address breakpoint register */ #ifdef CONFIG_ALTIVEC /* Complete AltiVec register set */ diff --git a/include/asm-powerpc/sparsemem.h b/include/asm-powerpc/sparsemem.h index 58d2aab416f..ba1b34fdb96 100644 --- a/include/asm-powerpc/sparsemem.h +++ b/include/asm-powerpc/sparsemem.h @@ -8,8 +8,8 @@ * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space */ #define SECTION_SIZE_BITS 24 -#define MAX_PHYSADDR_BITS 38 -#define MAX_PHYSMEM_BITS 36 +#define MAX_PHYSADDR_BITS 44 +#define MAX_PHYSMEM_BITS 44 #ifdef CONFIG_MEMORY_HOTPLUG extern void create_section_mapping(unsigned long start, unsigned long end); diff --git a/include/asm-powerpc/systemcfg.h b/include/asm-powerpc/systemcfg.h deleted file mode 100644 index 36b5cbe466f..00000000000 --- a/include/asm-powerpc/systemcfg.h +++ /dev/null @@ -1,64 +0,0 @@ -#ifndef _SYSTEMCFG_H -#define _SYSTEMCFG_H - -/* - * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM - * - * 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. - */ - -/* Change Activity: - * 2002/09/30 : bergner : Created - * End Change Activity - */ - -/* - * If the major version changes we are incompatible. - * Minor version changes are a hint. - */ -#define SYSTEMCFG_MAJOR 1 -#define SYSTEMCFG_MINOR 1 - -#ifndef __ASSEMBLY__ - -#include <linux/unistd.h> - -#define SYSCALL_MAP_SIZE ((__NR_syscalls + 31) / 32) - -struct systemcfg { - __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */ - struct { /* Systemcfg version numbers */ - __u32 major; /* Major number 0x10 */ - __u32 minor; /* Minor number 0x14 */ - } version; - - __u32 platform; /* Platform flags 0x18 */ - __u32 processor; /* Processor type 0x1C */ - __u64 processorCount; /* # of physical processors 0x20 */ - __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */ - __u64 tb_orig_stamp; /* Timebase at boot 0x30 */ - __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */ - __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */ - __u64 stamp_xsec; /* 0x48 */ - __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */ - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */ - __u32 tz_dsttime; /* Type of dst correction 0x5C */ - /* next four are no longer used except to be exported to /proc */ - __u32 dcache_size; /* L1 d-cache size 0x60 */ - __u32 dcache_line_size; /* L1 d-cache line size 0x64 */ - __u32 icache_size; /* L1 i-cache size 0x68 */ - __u32 icache_line_size; /* L1 i-cache line size 0x6C */ - __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of available syscalls 0x70 */ - __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of available syscalls */ -}; - -#ifdef __KERNEL__ -extern struct systemcfg *_systemcfg; /* to be renamed */ -#endif - -#endif /* __ASSEMBLY__ */ - -#endif /* _SYSTEMCFG_H */ diff --git a/include/asm-powerpc/topology.h b/include/asm-powerpc/topology.h index 2512e3836bf..015d28746e1 100644 --- a/include/asm-powerpc/topology.h +++ b/include/asm-powerpc/topology.h @@ -9,15 +9,7 @@ static inline int cpu_to_node(int cpu) { - int node; - - node = numa_cpu_lookup_table[cpu]; - -#ifdef DEBUG_NUMA - BUG_ON(node == -1); -#endif - - return node; + return numa_cpu_lookup_table[cpu]; } #define parent_node(node) (node) @@ -37,8 +29,6 @@ static inline int node_to_first_cpu(int node) #define pcibus_to_node(node) (-1) #define pcibus_to_cpumask(bus) (cpu_online_map) -#define nr_cpus_node(node) (nr_cpus_in_node[node]) - /* sched_domains SD_NODE_INIT for PPC64 machines */ #define SD_NODE_INIT (struct sched_domain) { \ .span = CPU_MASK_NONE, \ diff --git a/include/asm-ppc64/udbg.h b/include/asm-powerpc/udbg.h index e3b92799185..a383383bc4d 100644 --- a/include/asm-ppc64/udbg.h +++ b/include/asm-powerpc/udbg.h @@ -1,9 +1,3 @@ -#ifndef __UDBG_HDR -#define __UDBG_HDR - -#include <linux/compiler.h> -#include <linux/init.h> - /* * c 2001 PPC 64 Team, IBM Corp * @@ -13,6 +7,12 @@ * 2 of the License, or (at your option) any later version. */ +#ifndef _ASM_POWERPC_UDBG_H +#define _ASM_POWERPC_UDBG_H + +#include <linux/compiler.h> +#include <linux/init.h> + extern void (*udbg_putc)(unsigned char c); extern unsigned char (*udbg_getc)(void); extern int (*udbg_getc_poll)(void); @@ -28,4 +28,4 @@ extern void udbg_init_uart(void __iomem *comport, unsigned int speed); struct device_node; extern void udbg_init_scc(struct device_node *np); -#endif +#endif /* _ASM_POWERPC_UDBG_H */ diff --git a/include/asm-ppc64/vdso.h b/include/asm-powerpc/vdso.h index 85d8a7be25c..85d8a7be25c 100644 --- a/include/asm-ppc64/vdso.h +++ b/include/asm-powerpc/vdso.h diff --git a/include/asm-powerpc/vdso_datapage.h b/include/asm-powerpc/vdso_datapage.h new file mode 100644 index 00000000000..fc323b51366 --- /dev/null +++ b/include/asm-powerpc/vdso_datapage.h @@ -0,0 +1,108 @@ +#ifndef _VDSO_DATAPAGE_H +#define _VDSO_DATAPAGE_H + +/* + * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM + * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>, + * IBM Corp. + * + * 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. + */ + + +/* + * Note about this structure: + * + * This structure was historically called systemcfg and exposed to + * userland via /proc/ppc64/systemcfg. Unfortunately, this became an + * ABI issue as some proprietary software started relying on being able + * to mmap() it, thus we have to keep the base layout at least for a + * few kernel versions. + * + * However, since ppc32 doesn't suffer from this backward handicap, + * a simpler version of the data structure is used there with only the + * fields actually used by the vDSO. + * + */ + +/* + * If the major version changes we are incompatible. + * Minor version changes are a hint. + */ +#define SYSTEMCFG_MAJOR 1 +#define SYSTEMCFG_MINOR 1 + +#ifndef __ASSEMBLY__ + +#include <linux/unistd.h> + +#define SYSCALL_MAP_SIZE ((__NR_syscalls + 31) / 32) + +/* + * So here is the ppc64 backward compatible version + */ + +#ifdef CONFIG_PPC64 + +struct vdso_data { + __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */ + struct { /* Systemcfg version numbers */ + __u32 major; /* Major number 0x10 */ + __u32 minor; /* Minor number 0x14 */ + } version; + + __u32 platform; /* Platform flags 0x18 */ + __u32 processor; /* Processor type 0x1C */ + __u64 processorCount; /* # of physical processors 0x20 */ + __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */ + __u64 tb_orig_stamp; /* Timebase at boot 0x30 */ + __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */ + __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */ + __u64 stamp_xsec; /* 0x48 */ + __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */ + __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */ + __u32 tz_dsttime; /* Type of dst correction 0x5C */ + __u32 dcache_size; /* L1 d-cache size 0x60 */ + __u32 dcache_line_size; /* L1 d-cache line size 0x64 */ + __u32 icache_size; /* L1 i-cache size 0x68 */ + __u32 icache_line_size; /* L1 i-cache line size 0x6C */ + + /* those additional ones don't have to be located anywhere + * special as they were not part of the original systemcfg + */ + __s64 wtom_clock_sec; /* Wall to monotonic clock */ + __s32 wtom_clock_nsec; + __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ + __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ +}; + +#else /* CONFIG_PPC64 */ + +/* + * And here is the simpler 32 bits version + */ +struct vdso_data { + __u64 tb_orig_stamp; /* Timebase at boot 0x30 */ + __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */ + __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */ + __u64 stamp_xsec; /* 0x48 */ + __u32 tb_update_count; /* Timebase atomicity ctr 0x50 */ + __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */ + __u32 tz_dsttime; /* Type of dst correction 0x5C */ + __s32 wtom_clock_sec; /* Wall to monotonic clock */ + __s32 wtom_clock_nsec; + __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ +}; + +#endif /* CONFIG_PPC64 */ + +#ifdef __KERNEL__ +extern struct vdso_data *vdso_data; +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _SYSTEMCFG_H */ diff --git a/include/asm-ppc/page.h b/include/asm-ppc/page.h index fc44f7ca62d..538e0c8ab24 100644 --- a/include/asm-ppc/page.h +++ b/include/asm-ppc/page.h @@ -1,9 +1,12 @@ #ifndef _PPC_PAGE_H #define _PPC_PAGE_H +#include <linux/config.h> +#include <asm/asm-compat.h> + /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 -#define PAGE_SIZE (1UL << PAGE_SHIFT) +#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT) /* * Subtle: this is an int (not an unsigned long) and so it @@ -169,5 +172,8 @@ extern __inline__ int get_order(unsigned long size) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +/* We do define AT_SYSINFO_EHDR but don't use the gate mecanism */ +#define __HAVE_ARCH_GATE_AREA 1 + #endif /* __KERNEL__ */ #endif /* _PPC_PAGE_H */ diff --git a/include/asm-ppc64/mmzone.h b/include/asm-ppc64/mmzone.h index 15e777ce0f4..54958d6cae0 100644 --- a/include/asm-ppc64/mmzone.h +++ b/include/asm-ppc64/mmzone.h @@ -8,15 +8,14 @@ #define _ASM_MMZONE_H_ #include <linux/config.h> -#include <asm/smp.h> -/* generic non-linear memory support: +/* + * generic non-linear memory support: * * 1) we will not split memory into more chunks than will fit into the * flags field of the struct page */ - #ifdef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data *node_data[]; @@ -30,44 +29,11 @@ extern struct pglist_data *node_data[]; */ extern int numa_cpu_lookup_table[]; -extern char *numa_memory_lookup_table; extern cpumask_t numa_cpumask_lookup_table[]; -extern int nr_cpus_in_node[]; #ifdef CONFIG_MEMORY_HOTPLUG extern unsigned long max_pfn; #endif -/* 16MB regions */ -#define MEMORY_INCREMENT_SHIFT 24 -#define MEMORY_INCREMENT (1UL << MEMORY_INCREMENT_SHIFT) - -/* NUMA debugging, will not work on a DLPAR machine */ -#undef DEBUG_NUMA - -static inline int pa_to_nid(unsigned long pa) -{ - int nid; - -#ifdef CONFIG_MEMORY_HOTPLUG - /* kludge hot added sections default to node 0 */ - if (pa >= (max_pfn << PAGE_SHIFT)) - return 0; -#endif - nid = numa_memory_lookup_table[pa >> MEMORY_INCREMENT_SHIFT]; - -#ifdef DEBUG_NUMA - /* the physical address passed in is not in the map for the system */ - if (nid == -1) { - printk("bad address: %lx\n", pa); - BUG(); - } -#endif - - return nid; -} - -#define node_localnr(pfn, nid) ((pfn) - NODE_DATA(nid)->node_start_pfn) - /* * Following are macros that each numa implmentation must define. */ @@ -75,39 +41,10 @@ static inline int pa_to_nid(unsigned long pa) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) -#ifdef CONFIG_DISCONTIGMEM - -/* - * Given a kernel address, find the home node of the underlying memory. - */ -#define kvaddr_to_nid(kaddr) pa_to_nid(__pa(kaddr)) - -#define pfn_to_nid(pfn) pa_to_nid((unsigned long)(pfn) << PAGE_SHIFT) - -/* Written this way to avoid evaluating arguments twice */ -#define discontigmem_pfn_to_page(pfn) \ -({ \ - unsigned long __tmp = pfn; \ - (NODE_DATA(pfn_to_nid(__tmp))->node_mem_map + \ - node_localnr(__tmp, pfn_to_nid(__tmp))); \ -}) - -#define discontigmem_page_to_pfn(p) \ -({ \ - struct page *__tmp = p; \ - (((__tmp) - page_zone(__tmp)->zone_mem_map) + \ - page_zone(__tmp)->zone_start_pfn); \ -}) - -/* XXX fix for discontiguous physical memory */ -#define discontigmem_pfn_valid(pfn) ((pfn) < num_physpages) - -#endif /* CONFIG_DISCONTIGMEM */ - #endif /* CONFIG_NEED_MULTIPLE_NODES */ #ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID -#define early_pfn_to_nid(pfn) pa_to_nid(((unsigned long)pfn) << PAGE_SHIFT) +extern int __init early_pfn_to_nid(unsigned long pfn); #endif #endif /* _ASM_MMZONE_H_ */ diff --git a/include/asm-ppc64/page.h b/include/asm-ppc64/page.h index e32f1187aa2..3efc3288f7e 100644 --- a/include/asm-ppc64/page.h +++ b/include/asm-ppc64/page.h @@ -279,11 +279,6 @@ extern u64 ppc64_pft_size; /* Log 2 of page table size */ #define __va(x) ((void *)((unsigned long)(x) + KERNELBASE)) -#ifdef CONFIG_DISCONTIGMEM -#define page_to_pfn(page) discontigmem_page_to_pfn(page) -#define pfn_to_page(pfn) discontigmem_pfn_to_page(pfn) -#define pfn_valid(pfn) discontigmem_pfn_valid(pfn) -#endif #ifdef CONFIG_FLATMEM #define pfn_to_page(pfn) (mem_map + (pfn)) #define page_to_pfn(page) ((unsigned long)((page) - mem_map)) |