diff options
author | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2005-11-11 10:15:21 (GMT) |
---|---|---|
committer | Paul Mackerras <paulus@samba.org> | 2005-11-11 11:25:39 (GMT) |
commit | a7f290dad32ee34d931561b7943c858fe2aae503 (patch) | |
tree | 850f04ed9ffba8aef6e151fa9c9e8a0c667bb795 /arch/powerpc/kernel | |
parent | 6761c4a07378e19e3710bb69cea65795774529b1 (diff) | |
download | linux-fsl-qoriq-a7f290dad32ee34d931561b7943c858fe2aae503.tar.xz |
[PATCH] powerpc: Merge vdso's and add vdso support to 32 bits kernel
This patch moves the vdso's to arch/powerpc, adds support for the 32
bits vdso to the 32 bits kernel, rename systemcfg (finally !), and adds
some new (still untested) routines to both vdso's: clock_gettime() with
support for CLOCK_REALTIME and CLOCK_MONOTONIC, clock_getres() (same
clocks) and get_tbfreq() for glibc to retreive the timebase frequency.
Tom,Steve: The implementation of get_tbfreq() I've done for 32 bits
returns a long long (r3, r4) not a long. This is such that if we ever
add support for >4Ghz timebases on ppc32, the userland interface won't
have to change.
I have tested gettimeofday() using some glibc patches in both ppc32 and
ppc64 kernels using 32 bits userland (I haven't had a chance to test a
64 bits userland yet, but the implementation didn't change and was
tested earlier). I haven't tested yet the new functions.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'arch/powerpc/kernel')
29 files changed, 2630 insertions, 114 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c68eace..9a74b7a 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-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ signal_64.o ptrace32.o systbl.o \ paca.o ioctl32.o cpu_setup_power4.o \ firmware.o sysfs.o udbg.o +obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o obj-$(CONFIG_POWER4) += idle_power4.o obj-$(CONFIG_PPC_OF) += of_device.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8793102..4550eb4 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/paca.c b/arch/powerpc/kernel/paca.c index 3cf2517..a7b68f9 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 a1c1950..7ba42a4 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 ae1a364..7a95b8a 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 a754de6..33e7f2c 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> @@ -564,7 +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 6791668..fdbd9f9 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 a7c4515..8bdf95b 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 e28a139..62dfc5b 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 850af19..0f0c3a9 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 260b6ec..070b4b4 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 2020bb7..1511454 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/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c new file mode 100644 index 0000000..0d4d8be --- /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/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile new file mode 100644 index 0000000..758331d --- /dev/null +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -0,0 +1,40 @@ + +# List of files in the vdso, has to be asm only for now + +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)/, $(obj-vdso32)) + + +EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 +EXTRA_AFLAGS := -D__VDSO32__ -s + +obj-y += vdso32_wrapper.o +extra-y += vdso32.lds +CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) + +# Force dependency (incbin is bad) +$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso32.so: $(src)/vdso32.lds $(obj-vdso32) + $(call if_changed,vdso32ld) + +# assembly rules for the .S files +$(obj-vdso32): %.o: %.S + $(call if_changed_dep,vdso32as) + +# actual build commands +quiet_cmd_vdso32ld = VDSO32L $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso32as = VDSO32A $@ + cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< + diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S new file mode 100644 index 0000000..c8db993 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -0,0 +1,67 @@ +/* + * vDSO provided cache flush routines + * + * 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 + +/* + * Default "generic" version of __kernel_sync_dicache. + * + * void __kernel_sync_dicache(unsigned long start, unsigned long end) + * + * Flushes the data cache & invalidate the instruction cache for the + * provided range [start, end[ + * + * Note: all CPUs supported by this kernel have a 128 bytes cache + * line size so we don't have to peek that info from the datapage + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache) + .cfi_startproc + li r5,127 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + srwi. r8,r8,7 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 + mr r3,r6 +1: dcbst 0,r3 + addi r3,r3,128 + bdnz 1b + sync + mtctr r8 +1: icbi 0,r6 + addi r6,r6,128 + bdnz 1b + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache) + + +/* + * POWER5 version of __kernel_sync_dicache + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache_p5) + .cfi_startproc + sync + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache_p5) + diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S new file mode 100644 index 0000000..a08c26e --- /dev/null +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -0,0 +1,84 @@ +/* + * Access to the shared data page by the vDSO & syscall map + * + * 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/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/vdso.h> + + .text +V_FUNCTION_BEGIN(__get_datapage) + .cfi_startproc + /* We don't want that exposed or overridable as we want other objects + * to be able to bl directly to here + */ + .protected __get_datapage + .hidden __get_datapage + + mflr r0 + .cfi_register lr,r0 + + bcl 20,31,1f + .global __kernel_datapage_offset; +__kernel_datapage_offset: + .long 0 +1: + mflr r3 + mtlr r0 + lwz r0,0(r3) + add r3,r0,r3 + blr + .cfi_endproc +V_FUNCTION_END(__get_datapage) + +/* + * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; + * + * returns a pointer to the syscall map. the map is agnostic to the + * size of "long", unlike kernel bitops, it stores bits from top to + * bottom so that memory actually contains a linear bitmap + * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of + * 32 bits int at N >> 5. + */ +V_FUNCTION_BEGIN(__kernel_get_syscall_map) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r4,r3 + bl __get_datapage@local + mtlr r12 + addi r3,r3,CFG_SYSCALL_MAP32 + cmpli cr0,r4,0 + beqlr + li r0,__NR_syscalls + stw r0,0(r4) + 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 0000000..aeb5fc9 --- /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/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso32/note.S new file mode 100644 index 0000000..d4b5be4 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/note.S @@ -0,0 +1,25 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> + +#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \ + .section name, flags; \ + .balign 4; \ + .long 1f - 0f; /* name length */ \ + .long 3f - 2f; /* data length */ \ + .long type; /* note type */ \ +0: .asciz vendor; /* vendor name */ \ +1: .balign 4; \ +2: + +#define ASM_ELF_NOTE_END \ +3: .balign 4; /* pad out section */ \ + .previous + + ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0) + .long LINUX_VERSION_CODE + ASM_ELF_NOTE_END diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S new file mode 100644 index 0000000..e046427 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/sigtramp.S @@ -0,0 +1,300 @@ +/* + * Signal trampolines for 32 bits processes in a ppc64 kernel for + * use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), 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/unistd.h> +#include <asm/vdso.h> + + .text + +/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from + the return address to get an address in the middle of the presumed + call instruction. Since we don't have a call here, we artifically + extend the range covered by the unwind info by adding a nop before + the real start. */ + nop +V_FUNCTION_BEGIN(__kernel_sigtramp32) +.Lsig_start = . - 4 + li r0,__NR_sigreturn + sc +.Lsig_end: +V_FUNCTION_END(__kernel_sigtramp32) + +.Lsigrt_start: + nop +V_FUNCTION_BEGIN(__kernel_sigtramp_rt32) + li r0,__NR_rt_sigreturn + sc +.Lsigrt_end: +V_FUNCTION_END(__kernel_sigtramp_rt32) + + .section .eh_frame,"a",@progbits + +/* Register r1 can be found at offset 4 of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define cfa_save \ + .byte 0x0f; /* DW_CFA_def_cfa_expression */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ +9: + +/* Register REGNO can be found at offset OFS of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define rsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .ifne ofs; \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ + .endif; \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. The VMX reg struct is at offset VREGS of + the pt_regs struct. This macro is for REGNO == 0, and contains + 'subroutines' that the other macros jump to. */ +#define vsave_msr0(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit0 */ \ +2: \ + .byte 0x40; /* DW_OP_lit16 */ \ + .byte 0x1e; /* DW_OP_mul */ \ +3: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x12; /* DW_OP_dup */ \ + .byte 0x23; /* DW_OP_plus_uconst */ \ + .uleb128 33*RSIZE; /* msr offset */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \ + .byte 0x1a; /* DW_OP_and */ \ + .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \ + .byte 0x30; /* DW_OP_lit0 */ \ + .byte 0x29; /* DW_OP_eq */ \ + .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \ + .byte 0x13; /* DW_OP_drop, pop the 0 */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x22; /* DW_OP_plus */ \ + .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. REGNO is 1 thru 31. */ +#define vsave_msr1(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit n */ \ + .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of + the VMX save block. */ +#define vsave_msr2(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x0a; .short ofs; /* DW_OP_const2u */ \ + .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \ +9: + +/* VMX register REGNO is at offset OFS of the VMX save area. */ +#define vsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ +9: + +/* This is where the pt_regs pointer can be found on the stack. */ +#define PTREGS 64+28 + +/* Size of regs. */ +#define RSIZE 4 + +/* This is the offset of the VMX regs. */ +#define VREGS 48*RSIZE+34*8 + +/* Describe where general purpose regs are saved. */ +#define EH_FRAME_GEN \ + cfa_save; \ + rsave ( 0, 0*RSIZE); \ + rsave ( 2, 2*RSIZE); \ + rsave ( 3, 3*RSIZE); \ + rsave ( 4, 4*RSIZE); \ + rsave ( 5, 5*RSIZE); \ + rsave ( 6, 6*RSIZE); \ + rsave ( 7, 7*RSIZE); \ + rsave ( 8, 8*RSIZE); \ + rsave ( 9, 9*RSIZE); \ + rsave (10, 10*RSIZE); \ + rsave (11, 11*RSIZE); \ + rsave (12, 12*RSIZE); \ + rsave (13, 13*RSIZE); \ + rsave (14, 14*RSIZE); \ + rsave (15, 15*RSIZE); \ + rsave (16, 16*RSIZE); \ + rsave (17, 17*RSIZE); \ + rsave (18, 18*RSIZE); \ + rsave (19, 19*RSIZE); \ + rsave (20, 20*RSIZE); \ + rsave (21, 21*RSIZE); \ + rsave (22, 22*RSIZE); \ + rsave (23, 23*RSIZE); \ + rsave (24, 24*RSIZE); \ + rsave (25, 25*RSIZE); \ + rsave (26, 26*RSIZE); \ + rsave (27, 27*RSIZE); \ + rsave (28, 28*RSIZE); \ + rsave (29, 29*RSIZE); \ + rsave (30, 30*RSIZE); \ + rsave (31, 31*RSIZE); \ + rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ + rsave (65, 36*RSIZE); /* lr */ \ + rsave (70, 38*RSIZE) /* cr */ + +/* Describe where the FP regs are saved. */ +#define EH_FRAME_FP \ + rsave (32, 48*RSIZE + 0*8); \ + rsave (33, 48*RSIZE + 1*8); \ + rsave (34, 48*RSIZE + 2*8); \ + rsave (35, 48*RSIZE + 3*8); \ + rsave (36, 48*RSIZE + 4*8); \ + rsave (37, 48*RSIZE + 5*8); \ + rsave (38, 48*RSIZE + 6*8); \ + rsave (39, 48*RSIZE + 7*8); \ + rsave (40, 48*RSIZE + 8*8); \ + rsave (41, 48*RSIZE + 9*8); \ + rsave (42, 48*RSIZE + 10*8); \ + rsave (43, 48*RSIZE + 11*8); \ + rsave (44, 48*RSIZE + 12*8); \ + rsave (45, 48*RSIZE + 13*8); \ + rsave (46, 48*RSIZE + 14*8); \ + rsave (47, 48*RSIZE + 15*8); \ + rsave (48, 48*RSIZE + 16*8); \ + rsave (49, 48*RSIZE + 17*8); \ + rsave (50, 48*RSIZE + 18*8); \ + rsave (51, 48*RSIZE + 19*8); \ + rsave (52, 48*RSIZE + 20*8); \ + rsave (53, 48*RSIZE + 21*8); \ + rsave (54, 48*RSIZE + 22*8); \ + rsave (55, 48*RSIZE + 23*8); \ + rsave (56, 48*RSIZE + 24*8); \ + rsave (57, 48*RSIZE + 25*8); \ + rsave (58, 48*RSIZE + 26*8); \ + rsave (59, 48*RSIZE + 27*8); \ + rsave (60, 48*RSIZE + 28*8); \ + rsave (61, 48*RSIZE + 29*8); \ + rsave (62, 48*RSIZE + 30*8); \ + rsave (63, 48*RSIZE + 31*8) + +/* Describe where the VMX regs are saved. */ +#ifdef CONFIG_ALTIVEC +#define EH_FRAME_VMX \ + vsave_msr0 ( 0); \ + vsave_msr1 ( 1); \ + vsave_msr1 ( 2); \ + vsave_msr1 ( 3); \ + vsave_msr1 ( 4); \ + vsave_msr1 ( 5); \ + vsave_msr1 ( 6); \ + vsave_msr1 ( 7); \ + vsave_msr1 ( 8); \ + vsave_msr1 ( 9); \ + vsave_msr1 (10); \ + vsave_msr1 (11); \ + vsave_msr1 (12); \ + vsave_msr1 (13); \ + vsave_msr1 (14); \ + vsave_msr1 (15); \ + vsave_msr1 (16); \ + vsave_msr1 (17); \ + vsave_msr1 (18); \ + vsave_msr1 (19); \ + vsave_msr1 (20); \ + vsave_msr1 (21); \ + vsave_msr1 (22); \ + vsave_msr1 (23); \ + vsave_msr1 (24); \ + vsave_msr1 (25); \ + vsave_msr1 (26); \ + vsave_msr1 (27); \ + vsave_msr1 (28); \ + vsave_msr1 (29); \ + vsave_msr1 (30); \ + vsave_msr1 (31); \ + vsave_msr2 (33, 32*16+12); \ + vsave (32, 32*16) +#else +#define EH_FRAME_VMX +#endif + +.Lcie: + .long .Lcie_end - .Lcie_start +.Lcie_start: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 4 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 67 /* Return address register column, ap */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel | DW_EH_PE_sdata4. */ + .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */ + .balign 4 +.Lcie_end: + + .long .Lfde0_end - .Lfde0_start +.Lfde0_start: + .long .Lfde0_start - .Lcie /* CIE pointer. */ + .long .Lsig_start - . /* PC start, length */ + .long .Lsig_end - .Lsig_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX + .balign 4 +.Lfde0_end: + +/* We have a different stack layout for rt_sigreturn. */ +#undef PTREGS +#define PTREGS 64+16+128+20+28 + + .long .Lfde1_end - .Lfde1_start +.Lfde1_start: + .long .Lfde1_start - .Lcie /* CIE pointer. */ + .long .Lsigrt_start - . /* PC start, length */ + .long .Lsigrt_end - .Lsigrt_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX + .balign 4 +.Lfde1_end: diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S new file mode 100644 index 0000000..f4bad72 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -0,0 +1,117 @@ + +/* + * This is the infamous ld script for the 32 bits vdso + * library + */ +#include <asm/vdso.h> + +/* Default link addresses for the vDSOs */ +OUTPUT_FORMAT("elf32-powerpc", "elf32-powerpc", "elf32-powerpc") +OUTPUT_ARCH(powerpc:common) +ENTRY(_start) + +SECTIONS +{ + . = VDSO32_LBASE + SIZEOF_HEADERS; + .hash : { *(.hash) } :text + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN (16); + .text : + { + *(.text .stub .text.* .gnu.linkonce.t.*) + } + PROVIDE (__etext = .); + PROVIDE (_etext = .); + PROVIDE (etext = .); + + /* Other stuff is appended to the text segment: */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table) } + .fixup : { *(.fixup) } + + .dynamic : { *(.dynamic) } :text :dynamic + .got : { *(.got) } + .plt : { *(.plt) } + + _end = .; + __end = .; + PROVIDE (end = .); + + + /* Stabs debugging sections are here too + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + + /DISCARD/ : { *(.note.GNU-stack) } + /DISCARD/ : { *(.data .data.* .gnu.linkonce.d.* .sdata*) } + /DISCARD/ : { *(.bss .sbss .dynbss .dynsbss) } +} + + +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + note PT_NOTE FLAGS(4); /* PF_R */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */ +} + + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + __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; + __kernel_sigtramp_rt32; + local: *; + }; +} diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S new file mode 100644 index 0000000..556f0ca --- /dev/null +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -0,0 +1,13 @@ +#include <linux/init.h> +#include <asm/page.h> + + .section ".data.page_aligned" + + .globl vdso32_start, vdso32_end + .balign PAGE_SIZE +vdso32_start: + .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .balign PAGE_SIZE +vdso32_end: + + .previous diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile new file mode 100644 index 0000000..ab39988 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -0,0 +1,35 @@ +# List of files in the vdso, has to be asm only for now + +obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o + +# Build rules + +targets := $(obj-vdso64) vdso64.so +obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) + +EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 +EXTRA_AFLAGS := -D__VDSO64__ -s + +obj-y += vdso64_wrapper.o +extra-y += vdso64.lds +CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) + +# Force dependency (incbin is bad) +$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso64.so: $(src)/vdso64.lds $(obj-vdso64) + $(call if_changed,vdso64ld) + +# assembly rules for the .S files +$(obj-vdso64): %.o: %.S + $(call if_changed_dep,vdso64as) + +# actual build commands +quiet_cmd_vdso64ld = VDSO64L $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso64as = VDSO64A $@ + cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< + + diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S new file mode 100644 index 0000000..d4a0ad2 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -0,0 +1,66 @@ +/* + * vDSO provided cache flush routines + * + * 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 + +/* + * Default "generic" version of __kernel_sync_dicache. + * + * void __kernel_sync_dicache(unsigned long start, unsigned long end) + * + * Flushes the data cache & invalidate the instruction cache for the + * provided range [start, end[ + * + * Note: all CPUs supported by this kernel have a 128 bytes cache + * line size so we don't have to peek that info from the datapage + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache) + .cfi_startproc + li r5,127 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + srwi. r8,r8,7 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 + mr r3,r6 +1: dcbst 0,r3 + addi r3,r3,128 + bdnz 1b + sync + mtctr r8 +1: icbi 0,r6 + addi r6,r6,128 + bdnz 1b + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache) + + +/* + * POWER5 version of __kernel_sync_dicache + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache_p5) + .cfi_startproc + sync + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache_p5) diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S new file mode 100644 index 0000000..e67eda0 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -0,0 +1,84 @@ +/* + * Access to the shared data page by the vDSO & syscall map + * + * 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/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/vdso.h> + + .text +V_FUNCTION_BEGIN(__get_datapage) + .cfi_startproc + /* We don't want that exposed or overridable as we want other objects + * to be able to bl directly to here + */ + .protected __get_datapage + .hidden __get_datapage + + mflr r0 + .cfi_register lr,r0 + + bcl 20,31,1f + .global __kernel_datapage_offset; +__kernel_datapage_offset: + .long 0 +1: + mflr r3 + mtlr r0 + lwz r0,0(r3) + add r3,r0,r3 + blr + .cfi_endproc +V_FUNCTION_END(__get_datapage) + +/* + * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; + * + * returns a pointer to the syscall map. the map is agnostic to the + * size of "long", unlike kernel bitops, it stores bits from top to + * bottom so that memory actually contains a linear bitmap + * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of + * 32 bits int at N >> 5. + */ +V_FUNCTION_BEGIN(__kernel_get_syscall_map) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r4,r3 + bl V_LOCAL_FUNC(__get_datapage) + mtlr r12 + addi r3,r3,CFG_SYSCALL_MAP64 + cmpli cr0,r4,0 + beqlr + li r0,__NR_syscalls + stw r0,0(r4) + 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 0000000..d371c02 --- /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/powerpc/kernel/vdso64/note.S b/arch/powerpc/kernel/vdso64/note.S new file mode 100644 index 0000000..dc2a509 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/note.S @@ -0,0 +1 @@ +#include "../vdso32/note.S" diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S new file mode 100644 index 0000000..31b604a --- /dev/null +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -0,0 +1,295 @@ +/* + * Signal trampoline for 64 bits processes in a ppc64 kernel for + * use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), 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/unistd.h> +#include <asm/vdso.h> +#include <asm/ptrace.h> /* XXX for __SIGNAL_FRAMESIZE */ + + .text + +/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from + the return address to get an address in the middle of the presumed + call instruction. Since we don't have a call here, we artifically + extend the range covered by the unwind info by padding before the + real start. */ + nop + .balign 8 +V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) +.Lsigrt_start = . - 4 + addi r1, r1, __SIGNAL_FRAMESIZE + li r0,__NR_rt_sigreturn + sc +.Lsigrt_end: +V_FUNCTION_END(__kernel_sigtramp_rt64) +/* The ".balign 8" above and the following zeros mimic the old stack + trampoline layout. The last magic value is the ucontext pointer, + chosen in such a way that older libgcc unwind code returns a zero + for a sigcontext pointer. */ + .long 0,0,0 + .quad 0,-21*8 + +/* Register r1 can be found at offset 8 of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define cfa_save \ + .byte 0x0f; /* DW_CFA_def_cfa_expression */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ +9: + +/* Register REGNO can be found at offset OFS of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define rsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .ifne ofs; \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ + .endif; \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. A pointer to the VMX reg struct is at VREGS in + the pt_regs struct. This macro is for REGNO == 0, and contains + 'subroutines' that the other macros jump to. */ +#define vsave_msr0(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit0 */ \ +2: \ + .byte 0x40; /* DW_OP_lit16 */ \ + .byte 0x1e; /* DW_OP_mul */ \ +3: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x12; /* DW_OP_dup */ \ + .byte 0x23; /* DW_OP_plus_uconst */ \ + .uleb128 33*RSIZE; /* msr offset */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \ + .byte 0x1a; /* DW_OP_and */ \ + .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \ + .byte 0x30; /* DW_OP_lit0 */ \ + .byte 0x29; /* DW_OP_eq */ \ + .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \ + .byte 0x13; /* DW_OP_drop, pop the 0 */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x22; /* DW_OP_plus */ \ + .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. REGNO is 1 thru 31. */ +#define vsave_msr1(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit n */ \ + .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of + the VMX save block. */ +#define vsave_msr2(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x0a; .short ofs; /* DW_OP_const2u */ \ + .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \ +9: + +/* VMX register REGNO is at offset OFS of the VMX save area. */ +#define vsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ +9: + +/* This is where the pt_regs pointer can be found on the stack. */ +#define PTREGS 128+168+56 + +/* Size of regs. */ +#define RSIZE 8 + +/* This is the offset of the VMX reg pointer. */ +#define VREGS 48*RSIZE+33*8 + +/* Describe where general purpose regs are saved. */ +#define EH_FRAME_GEN \ + cfa_save; \ + rsave ( 0, 0*RSIZE); \ + rsave ( 2, 2*RSIZE); \ + rsave ( 3, 3*RSIZE); \ + rsave ( 4, 4*RSIZE); \ + rsave ( 5, 5*RSIZE); \ + rsave ( 6, 6*RSIZE); \ + rsave ( 7, 7*RSIZE); \ + rsave ( 8, 8*RSIZE); \ + rsave ( 9, 9*RSIZE); \ + rsave (10, 10*RSIZE); \ + rsave (11, 11*RSIZE); \ + rsave (12, 12*RSIZE); \ + rsave (13, 13*RSIZE); \ + rsave (14, 14*RSIZE); \ + rsave (15, 15*RSIZE); \ + rsave (16, 16*RSIZE); \ + rsave (17, 17*RSIZE); \ + rsave (18, 18*RSIZE); \ + rsave (19, 19*RSIZE); \ + rsave (20, 20*RSIZE); \ + rsave (21, 21*RSIZE); \ + rsave (22, 22*RSIZE); \ + rsave (23, 23*RSIZE); \ + rsave (24, 24*RSIZE); \ + rsave (25, 25*RSIZE); \ + rsave (26, 26*RSIZE); \ + rsave (27, 27*RSIZE); \ + rsave (28, 28*RSIZE); \ + rsave (29, 29*RSIZE); \ + rsave (30, 30*RSIZE); \ + rsave (31, 31*RSIZE); \ + rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ + rsave (65, 36*RSIZE); /* lr */ \ + rsave (70, 38*RSIZE) /* cr */ + +/* Describe where the FP regs are saved. */ +#define EH_FRAME_FP \ + rsave (32, 48*RSIZE + 0*8); \ + rsave (33, 48*RSIZE + 1*8); \ + rsave (34, 48*RSIZE + 2*8); \ + rsave (35, 48*RSIZE + 3*8); \ + rsave (36, 48*RSIZE + 4*8); \ + rsave (37, 48*RSIZE + 5*8); \ + rsave (38, 48*RSIZE + 6*8); \ + rsave (39, 48*RSIZE + 7*8); \ + rsave (40, 48*RSIZE + 8*8); \ + rsave (41, 48*RSIZE + 9*8); \ + rsave (42, 48*RSIZE + 10*8); \ + rsave (43, 48*RSIZE + 11*8); \ + rsave (44, 48*RSIZE + 12*8); \ + rsave (45, 48*RSIZE + 13*8); \ + rsave (46, 48*RSIZE + 14*8); \ + rsave (47, 48*RSIZE + 15*8); \ + rsave (48, 48*RSIZE + 16*8); \ + rsave (49, 48*RSIZE + 17*8); \ + rsave (50, 48*RSIZE + 18*8); \ + rsave (51, 48*RSIZE + 19*8); \ + rsave (52, 48*RSIZE + 20*8); \ + rsave (53, 48*RSIZE + 21*8); \ + rsave (54, 48*RSIZE + 22*8); \ + rsave (55, 48*RSIZE + 23*8); \ + rsave (56, 48*RSIZE + 24*8); \ + rsave (57, 48*RSIZE + 25*8); \ + rsave (58, 48*RSIZE + 26*8); \ + rsave (59, 48*RSIZE + 27*8); \ + rsave (60, 48*RSIZE + 28*8); \ + rsave (61, 48*RSIZE + 29*8); \ + rsave (62, 48*RSIZE + 30*8); \ + rsave (63, 48*RSIZE + 31*8) + +/* Describe where the VMX regs are saved. */ +#ifdef CONFIG_ALTIVEC +#define EH_FRAME_VMX \ + vsave_msr0 ( 0); \ + vsave_msr1 ( 1); \ + vsave_msr1 ( 2); \ + vsave_msr1 ( 3); \ + vsave_msr1 ( 4); \ + vsave_msr1 ( 5); \ + vsave_msr1 ( 6); \ + vsave_msr1 ( 7); \ + vsave_msr1 ( 8); \ + vsave_msr1 ( 9); \ + vsave_msr1 (10); \ + vsave_msr1 (11); \ + vsave_msr1 (12); \ + vsave_msr1 (13); \ + vsave_msr1 (14); \ + vsave_msr1 (15); \ + vsave_msr1 (16); \ + vsave_msr1 (17); \ + vsave_msr1 (18); \ + vsave_msr1 (19); \ + vsave_msr1 (20); \ + vsave_msr1 (21); \ + vsave_msr1 (22); \ + vsave_msr1 (23); \ + vsave_msr1 (24); \ + vsave_msr1 (25); \ + vsave_msr1 (26); \ + vsave_msr1 (27); \ + vsave_msr1 (28); \ + vsave_msr1 (29); \ + vsave_msr1 (30); \ + vsave_msr1 (31); \ + vsave_msr2 (33, 32*16+12); \ + vsave (32, 33*16) +#else +#define EH_FRAME_VMX +#endif + + .section .eh_frame,"a",@progbits +.Lcie: + .long .Lcie_end - .Lcie_start +.Lcie_start: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 4 /* Code alignment factor */ + .sleb128 -8 /* Data alignment factor */ + .byte 67 /* Return address register column, ap */ + .uleb128 1 /* Augmentation value length */ + .byte 0x14 /* DW_EH_PE_pcrel | DW_EH_PE_udata8. */ + .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */ + .balign 8 +.Lcie_end: + + .long .Lfde0_end - .Lfde0_start +.Lfde0_start: + .long .Lfde0_start - .Lcie /* CIE pointer. */ + .quad .Lsigrt_start - . /* PC start, length */ + .quad .Lsigrt_end - .Lsigrt_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX +# Do we really need to describe the frame at this point? ie. will +# we ever have some call chain that returns somewhere past the addi? +# I don't think so, since gcc doesn't support async signals. +# .byte 0x41 /* DW_CFA_advance_loc 1*4 */ +#undef PTREGS +#define PTREGS 168+56 +# EH_FRAME_GEN +# EH_FRAME_FP +# EH_FRAME_VMX + .balign 8 +.Lfde0_end: diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S new file mode 100644 index 0000000..4bdf224 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -0,0 +1,116 @@ +/* + * This is the infamous ld script for the 64 bits vdso + * library + */ +#include <asm/vdso.h> + +OUTPUT_FORMAT("elf64-powerpc", "elf64-powerpc", "elf64-powerpc") +OUTPUT_ARCH(powerpc:common64) +ENTRY(_start) + +SECTIONS +{ + . = VDSO64_LBASE + SIZEOF_HEADERS; + .hash : { *(.hash) } :text + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN (16); + .text : + { + *(.text .stub .text.* .gnu.linkonce.t.*) + *(.sfpr .glink) + } :text + PROVIDE (__etext = .); + PROVIDE (_etext = .); + PROVIDE (etext = .); + + /* Other stuff is appended to the text segment: */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table) } + + .opd ALIGN(8) : { KEEP (*(.opd)) } + .got ALIGN(8) : { *(.got .toc) } + .rela.dyn ALIGN(8) : { *(.rela.dyn) } + + .dynamic : { *(.dynamic) } :text :dynamic + + _end = .; + PROVIDE (end = .); + + /* Stabs debugging sections are here too + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + /* DWARF debug sectio/ns. + Symbols in the DWARF debugging sections are relative to the beginning + of the section so we begin them at 0. */ + /* DWARF 1 */ + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + /* GNU DWARF 1 extensions */ + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + /* DWARF 1.1 and DWARF 2 */ + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + /* DWARF 2 */ + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + /* SGI/MIPS DWARF 2 extensions */ + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + + /DISCARD/ : { *(.note.GNU-stack) } + /DISCARD/ : { *(.branch_lt) } + /DISCARD/ : { *(.data .data.* .gnu.linkonce.d.*) } + /DISCARD/ : { *(.bss .sbss .dynbss .dynsbss) } +} + +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + note PT_NOTE FLAGS(4); /* PF_R */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */ +} + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + __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; + local: *; + }; +} diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S new file mode 100644 index 0000000..0529cb9 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -0,0 +1,13 @@ +#include <linux/init.h> +#include <asm/page.h> + + .section ".data.page_aligned" + + .globl vdso64_start, vdso64_end + .balign PAGE_SIZE +vdso64_start: + .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .balign PAGE_SIZE +vdso64_end: + + .previous |