[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 <[e-mail]>
Signed-off-by: Paul Mackerras <[e-mail]>

arch/powerpc/kernel/Makefile

···
 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

arch/powerpc/kernel/asm-offsets.c

···
 #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
 
···
 
 	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;
 }

arch/powerpc/kernel/paca.c

···
 #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

arch/powerpc/kernel/proc_ppc64.c

···
 #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>
···
 	if (!pde)
 		return 1;
 	pde->nlink = 1;
-	pde->data = _systemcfg;
+	pde->data = vdso_data;
 	pde->size = PAGE_SIZE;
 	pde->proc_fops = &page_map_fops;
 

arch/powerpc/kernel/rtas-proc.c

···
 #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

arch/powerpc/kernel/setup-common.c

···
 #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>
···
 			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 */

arch/powerpc/kernel/setup_64.c

···
 #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>
 
···
 				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;
 
···
 				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");
 }
···
 
 	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");
···
 }
 
 /*
- * 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.
···
 	/* set up the bootmem stuff with available memory */
 	do_init_bootmem();
 	sparse_init();
-
-	/* initialize the syscall map in systemcfg */
-	setup_syscall_map();
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;

arch/powerpc/kernel/signal_32.c

···
 #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>
···
 
 	/* 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;
···
 	    || __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;

arch/powerpc/kernel/smp.c

···
 #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
···
 
 	cpu_clear(cpu, cpu_online_map);
 #ifdef CONFIG_PPC64
-	_systemcfg->processorCount--;
+	vdso_data->processorCount--;
 	fixup_irqs(cpu_online_map);
 #endif
 	return 0;

arch/powerpc/kernel/sysfs.c

···
 #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>

arch/powerpc/kernel/time.c

···
 #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
···
 	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
···
 	 * 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);
 }
 
 /*
···
 				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"
···
 	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();
···
 	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;
 

arch/powerpc/kernel/traps.c

···
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #include <asm/processor.h>
-#include <asm/systemcfg.h>
 #endif
 
 #ifdef CONFIG_PPC64	/* XXX */

arch/powerpc/kernel/vdso.c

···
+/*
+ *  linux/arch/ppc64/kernel/vdso.c
+ *
+ *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ *			 <[e-mail]>
+ *
+ *  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;
+}
+

arch/powerpc/kernel/vdso32/gettimeofday.S

···
+/*
+ * Userland implementation of gettimeofday() for 32 bits processes in a
+ * ppc64 kernel for use in the vDSO
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt ([e-mail],
+ *                    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

arch/powerpc/kernel/vdso64/gettimeofday.S

···
+/*
+ * Userland implementation of gettimeofday() for 64 bits processes in a
+ * ppc64 kernel for use in the vDSO
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt ([e-mail]),
+ *                    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)

arch/powerpc/mm/mem.c

···
 #include <asm/prom.h>
 #include <asm/lmb.h>
 #include <asm/sections.h>
-#ifdef CONFIG_PPC64
 #include <asm/vdso.h>
-#endif
 
 #include "mmu_decl.h"
 
···
 
 	mem_init_done = 1;
 
-#ifdef CONFIG_PPC64
 	/* Initialize the vDSO */
 	vdso_init();
-#endif
 }
 
 /*

arch/powerpc/oprofile/op_model_power4.c

···
 #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>

arch/ppc64/kernel/Makefile

···
 obj-y               +=	idle.o dma.o \
 			align.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
 

arch/ppc64/kernel/vdso32/Makefile arch/powerpc/kernel/vdso32/Makefile

···
 
 # Build rules
 
+ifeq ($(CONFIG_PPC32),y)
+CROSS32CC := $(CC)
+endif
+
 targets := $(obj-vdso32) vdso32.so
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
 

arch/ppc64/kernel/vdso32/datapage.S arch/powerpc/kernel/vdso32/datapage.S

···
 	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)

arch/ppc64/kernel/vdso32/gettimeofday.S

···
-/*
- * Userland implementation of gettimeofday() for 32 bits processes in a
- * ppc64 kernel for use in the vDSO
- *
- * Copyright (C) 2004 Benjamin Herrenschmuidt ([e-mail]), 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

arch/ppc64/kernel/vdso32/vdso32.lds.S arch/powerpc/kernel/vdso32/vdso32.lds.S

···
 {
   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;

arch/ppc64/kernel/vdso32/vdso32_wrapper.S arch/powerpc/kernel/vdso64/vdso64_wrapper.S

···
 
 	.section ".data.page_aligned"
 
-	.globl vdso32_start, vdso32_end
+	.globl vdso64_start, vdso64_end
 	.balign PAGE_SIZE
-vdso32_start:
-	.incbin "arch/ppc64/kernel/vdso32/vdso32.so"
+vdso64_start:
+	.incbin "arch/powerpc/kernel/vdso64/vdso64.so"
 	.balign PAGE_SIZE
-vdso32_end:
+vdso64_end:
 
 	.previous

arch/ppc64/kernel/vdso64/datapage.S arch/powerpc/kernel/vdso64/datapage.S

···
 	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)

arch/ppc64/kernel/vdso64/gettimeofday.S

···
-/*
- * Userland implementation of gettimeofday() for 64 bits processes in a
- * ppc64 kernel for use in the vDSO
- *
- * Copyright (C) 2004 Benjamin Herrenschmuidt ([e-mail]),
- *                    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)

arch/ppc64/kernel/vdso64/vdso64.lds.S arch/powerpc/kernel/vdso64/vdso64.lds.S

···
 {
   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;

arch/ppc64/kernel/vdso64/vdso64_wrapper.S arch/powerpc/kernel/vdso32/vdso32_wrapper.S

···
 
 	.section ".data.page_aligned"
 
-	.globl vdso64_start, vdso64_end
+	.globl vdso32_start, vdso32_end
 	.balign PAGE_SIZE
-vdso64_start:
-	.incbin "arch/ppc64/kernel/vdso64/vdso64.so"
+vdso32_start:
+	.incbin "arch/powerpc/kernel/vdso32/vdso32.so"
 	.balign PAGE_SIZE
-vdso64_end:
+vdso32_end:
 
 	.previous

include/asm-powerpc/auxvec.h

···
 /* 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

include/asm-powerpc/elf.h

···
 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:

include/asm-powerpc/processor.h

···
 #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 */

include/asm-powerpc/systemcfg.h

···
-#ifndef _SYSTEMCFG_H
-#define _SYSTEMCFG_H
-
-/*
- * Copyright (C) 2002 Peter Bergner <[e-mail]>, 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 */

include/asm-powerpc/vdso_datapage.h

···
+#ifndef _VDSO_DATAPAGE_H
+#define _VDSO_DATAPAGE_H
+
+/*
+ * Copyright (C) 2002 Peter Bergner <[e-mail]>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <[e-mail]>,
+ * 		      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 */

include/asm-ppc/page.h

···
 #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
···
 
 #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 */