[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>

29 files changed, 2630 insertions, 114 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c68eace12a9..9a74b7ab03a 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -12,11 +12,13 @@ CFLAGS_btext.o		+= -fPIC
 endif
 
 obj-y				:= semaphore.o cputable.o ptrace.o syscalls.o \
-				   irq.o signal_32.o pmc.o
+				   irq.o signal_32.o pmc.o vdso.o
+obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
 				   signal_64.o ptrace32.o systbl.o \
 				   paca.o ioctl32.o cpu_setup_power4.o \
 				   firmware.o sysfs.o udbg.o
+obj-$(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 8793102711a..4550eb4f4fb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -37,12 +37,12 @@
 #include <asm/cputable.h>
 #include <asm/thread_info.h>
 #include <asm/rtas.h>
+#include <asm/vdso_datapage.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/lppaca.h>
 #include <asm/iseries/hv_lp_event.h>
 #include <asm/cache.h>
-#include <asm/systemcfg.h>
 #include <asm/compat.h>
 #endif
 
@@ -251,25 +251,42 @@ int main(void)
 
 	DEFINE(TASK_SIZE, TASK_SIZE);
 	DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
-#else /* CONFIG_PPC64 */
-	/* systemcfg offsets for use by vdso */
-	DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp));
-	DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec));
-	DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs));
-	DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec));
-	DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count));
-	DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest));
-	DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime));
-	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32));
-	DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64));
+#endif /* ! CONFIG_PPC64 */
 
-	/* timeval/timezone offsets for use by vdso */
+	/* datapage offsets for use by vdso */
+	DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp));
+	DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec));
+	DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs));
+	DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec));
+	DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count));
+	DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest));
+	DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime));
+	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
+	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
+	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+#ifdef CONFIG_PPC64
+	DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64));
 	DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));
 	DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec));
 	DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec));
 	DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec));
+	DEFINE(TSPC32_TV_SEC, offsetof(struct compat_timespec, tv_sec));
+	DEFINE(TSPC32_TV_NSEC, offsetof(struct compat_timespec, tv_nsec));
+#else
+	DEFINE(TVAL32_TV_SEC, offsetof(struct timeval, tv_sec));
+	DEFINE(TVAL32_TV_USEC, offsetof(struct timeval, tv_usec));
+	DEFINE(TSPEC32_TV_SEC, offsetof(struct timespec, tv_sec));
+	DEFINE(TSPEC32_TV_NSEC, offsetof(struct timespec, tv_nsec));
+#endif
+	/* timeval/timezone offsets for use by vdso */
 	DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
 	DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
-#endif /* CONFIG_PPC64 */
+
+	/* Other bits used by the vdso */
+	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
+	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
+	DEFINE(CLOCK_REALTIME_RES, TICK_NSEC);
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 3cf2517c5f9..a7b68f911eb 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -15,17 +15,10 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/page.h>
-#include <asm/systemcfg.h>
 #include <asm/lppaca.h>
 #include <asm/iseries/it_lp_queue.h>
 #include <asm/paca.h>
 
-static union {
-	struct systemcfg	data;
-	u8			page[PAGE_SIZE];
-} systemcfg_store __attribute__((__section__(".data.page.aligned")));
-struct systemcfg *_systemcfg = &systemcfg_store.data;
-
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c
index a1c19502fe8..7ba42a405f4 100644
--- a/arch/powerpc/kernel/proc_ppc64.c
+++ b/arch/powerpc/kernel/proc_ppc64.c
@@ -23,7 +23,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 
-#include <asm/systemcfg.h>
+#include <asm/vdso_datapage.h>
 #include <asm/rtas.h>
 #include <asm/uaccess.h>
 #include <asm/prom.h>
@@ -72,7 +72,7 @@ static int __init proc_ppc64_init(void)
 	if (!pde)
 		return 1;
 	pde->nlink = 1;
-	pde->data = _systemcfg;
+	pde->data = vdso_data;
 	pde->size = PAGE_SIZE;
 	pde->proc_fops = &page_map_fops;
 
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index ae1a36449cc..7a95b8a2835 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -32,7 +32,6 @@
 #include <asm/rtas.h>
 #include <asm/machdep.h> /* for ppc_md */
 #include <asm/time.h>
-#include <asm/systemcfg.h>
 
 /* Token for Sensors */
 #define KEY_SWITCH		0x0001
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index a754de63450..33e7f2c7f19 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/processor.h>
-#include <asm/systemcfg.h>
+#include <asm/vdso_datapage.h>
 #include <asm/pgtable.h>
 #include <asm/smp.h>
 #include <asm/elf.h>
@@ -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 6791668213e..fdbd9f9122f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -57,7 +57,6 @@
 #include <asm/lmb.h>
 #include <asm/iseries/it_lp_naca.h>
 #include <asm/firmware.h>
-#include <asm/systemcfg.h>
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 
@@ -375,9 +374,8 @@ static void __init initialize_cache_info(void)
 				DBG("Argh, can't find dcache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
-			_systemcfg->dcache_size = ppc64_caches.dsize = size;
-			_systemcfg->dcache_line_size =
-				ppc64_caches.dline_size = lsize;
+			ppc64_caches.dsize = size;
+			ppc64_caches.dline_size = lsize;
 			ppc64_caches.log_dline_size = __ilog2(lsize);
 			ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;
 
@@ -393,22 +391,13 @@ static void __init initialize_cache_info(void)
 				DBG("Argh, can't find icache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
-			_systemcfg->icache_size = ppc64_caches.isize = size;
-			_systemcfg->icache_line_size =
-				ppc64_caches.iline_size = lsize;
+			ppc64_caches.isize = size;
+			ppc64_caches.iline_size = lsize;
 			ppc64_caches.log_iline_size = __ilog2(lsize);
 			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
 		}
 	}
 
-	/* Add an eye catcher and the systemcfg layout version number */
-	strcpy(_systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
-	_systemcfg->version.major = SYSTEMCFG_MAJOR;
-	_systemcfg->version.minor = SYSTEMCFG_MINOR;
-	_systemcfg->processor = mfspr(SPRN_PVR);
-	_systemcfg->platform = _machine;
-	_systemcfg->physicalMemorySize = lmb_phys_mem_size();
-
 	DBG(" <- initialize_cache_info()\n");
 }
 
@@ -495,15 +484,14 @@ void __init setup_system(void)
 
 	printk("-----------------------------------------------------\n");
 	printk("ppc64_pft_size                = 0x%lx\n", ppc64_pft_size);
-	printk("ppc64_interrupt_controller    = 0x%ld\n", ppc64_interrupt_controller);
-	printk("systemcfg                     = 0x%p\n", _systemcfg);
-	printk("systemcfg->platform           = 0x%x\n", _systemcfg->platform);
-	printk("systemcfg->processorCount     = 0x%lx\n", _systemcfg->processorCount);
-	printk("systemcfg->physicalMemorySize = 0x%lx\n", _systemcfg->physicalMemorySize);
+	printk("ppc64_interrupt_controller    = 0x%ld\n",
+	       ppc64_interrupt_controller);
+	printk("platform                      = 0x%x\n", _machine);
+	printk("physicalMemorySize            = 0x%lx\n", lmb_phys_mem_size());
 	printk("ppc64_caches.dcache_line_size = 0x%x\n",
-			ppc64_caches.dline_size);
+	       ppc64_caches.dline_size);
 	printk("ppc64_caches.icache_line_size = 0x%x\n",
-			ppc64_caches.iline_size);
+	       ppc64_caches.iline_size);
 	printk("htab_address                  = 0x%p\n", htab_address);
 	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
 	printk("-----------------------------------------------------\n");
@@ -568,33 +556,6 @@ static void __init emergency_stack_init(void)
 }
 
 /*
- * Called from setup_arch to initialize the bitmap of available
- * syscalls in the systemcfg page
- */
-void __init setup_syscall_map(void)
-{
-	unsigned int i, count64 = 0, count32 = 0;
-	extern unsigned long *sys_call_table;
-	extern unsigned long sys_ni_syscall;
-
-
-	for (i = 0; i < __NR_syscalls; i++) {
-		if (sys_call_table[i*2] != sys_ni_syscall) {
-			count64++;
-			_systemcfg->syscall_map_64[i >> 5] |=
-				0x80000000UL >> (i & 0x1f);
-		}
-		if (sys_call_table[i*2+1] != sys_ni_syscall) {
-			count32++;
-			_systemcfg->syscall_map_32[i >> 5] |=
-				0x80000000UL >> (i & 0x1f);
-		}
-	}
-	printk(KERN_INFO "Syscall map setup, %d 32-bit and %d 64-bit syscalls\n",
-	       count32, count64);
-}
-
-/*
  * Called into from start_kernel, after lock_kernel has been called.
  * Initializes bootmem, which is unsed to manage page allocation until
  * mem_init is called.
@@ -635,9 +596,6 @@ void __init setup_arch(char **cmdline_p)
 	do_init_bootmem();
 	sparse_init();
 
-	/* initialize the syscall map in systemcfg */
-	setup_syscall_map();
-
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;
 #endif
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index a7c4515f320..8bdf95b7e42 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -43,10 +43,10 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/sigcontext.h>
+#include <asm/vdso.h>
 #ifdef CONFIG_PPC64
 #include "ppc32.h"
 #include <asm/unistd.h>
-#include <asm/vdso.h>
 #else
 #include <asm/ucontext.h>
 #include <asm/pgtable.h>
@@ -809,14 +809,11 @@ static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka,
 
 	/* Save user registers on the stack */
 	frame = &rt_sf->uc.uc_mcontext;
-#ifdef CONFIG_PPC64
 	if (vdso32_rt_sigtramp && current->thread.vdso_base) {
 		if (save_user_regs(regs, frame, 0))
 			goto badframe;
 		regs->link = current->thread.vdso_base + vdso32_rt_sigtramp;
-	} else
-#endif
-	{
+	} else {
 		if (save_user_regs(regs, frame, __NR_rt_sigreturn))
 			goto badframe;
 		regs->link = (unsigned long) frame->tramp;
@@ -1090,14 +1087,11 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka,
 	    || __put_user(sig, &sc->signal))
 		goto badframe;
 
-#ifdef CONFIG_PPC64
 	if (vdso32_sigtramp && current->thread.vdso_base) {
 		if (save_user_regs(regs, &frame->mctx, 0))
 			goto badframe;
 		regs->link = current->thread.vdso_base + vdso32_sigtramp;
-	} else
-#endif
-	{
+	} else {
 		if (save_user_regs(regs, &frame->mctx, __NR_sigreturn))
 			goto badframe;
 		regs->link = (unsigned long) frame->mctx.tramp;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e28a139c29d..62dfc5b8d76 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -44,7 +44,7 @@
 #include <asm/cputable.h>
 #include <asm/system.h>
 #include <asm/mpic.h>
-#include <asm/systemcfg.h>
+#include <asm/vdso_datapage.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #endif
@@ -371,7 +371,7 @@ int generic_cpu_disable(void)
 
 	cpu_clear(cpu, cpu_online_map);
 #ifdef CONFIG_PPC64
-	_systemcfg->processorCount--;
+	vdso_data->processorCount--;
 	fixup_irqs(cpu_online_map);
 #endif
 	return 0;
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 850af198fb5..0f0c3a9ae2e 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -16,7 +16,6 @@
 #include <asm/firmware.h>
 #include <asm/hvcall.h>
 #include <asm/prom.h>
-#include <asm/systemcfg.h>
 #include <asm/paca.h>
 #include <asm/lppaca.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 260b6ecd26a..070b4b458aa 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -62,8 +62,8 @@
 #include <asm/irq.h>
 #include <asm/div64.h>
 #include <asm/smp.h>
+#include <asm/vdso_datapage.h>
 #ifdef CONFIG_PPC64
-#include <asm/systemcfg.h>
 #include <asm/firmware.h>
 #endif
 #ifdef CONFIG_PPC_ISERIES
@@ -261,7 +261,6 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 	do_gtod.varp = temp_varp;
 	do_gtod.var_idx = temp_idx;
 
-#ifdef CONFIG_PPC64
 	/*
 	 * tb_update_count is used to allow the userspace gettimeofday code
 	 * to assure itself that it sees a consistent view of the tb_to_xs and
@@ -271,14 +270,15 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
 	 * loops back and reads them again until this criteria is met.
 	 */
-	++(_systemcfg->tb_update_count);
+	++(vdso_data->tb_update_count);
 	smp_wmb();
-	_systemcfg->tb_orig_stamp = new_tb_stamp;
-	_systemcfg->stamp_xsec = new_stamp_xsec;
-	_systemcfg->tb_to_xs = new_tb_to_xs;
+	vdso_data->tb_orig_stamp = new_tb_stamp;
+	vdso_data->stamp_xsec = new_stamp_xsec;
+	vdso_data->tb_to_xs = new_tb_to_xs;
+	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
+	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
 	smp_wmb();
-	++(_systemcfg->tb_update_count);
-#endif
+	++(vdso_data->tb_update_count);
 }
 
 /*
@@ -357,9 +357,8 @@ static void iSeries_tb_recal(void)
 				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 				tb_to_xs = divres.result_low;
 				do_gtod.varp->tb_to_xs = tb_to_xs;
-				_systemcfg->tb_ticks_per_sec =
-					tb_ticks_per_sec;
-				_systemcfg->tb_to_xs = tb_to_xs;
+				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+				vdso_data->tb_to_xs = tb_to_xs;
 			}
 			else {
 				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
@@ -561,10 +560,8 @@ int do_settimeofday(struct timespec *tv)
 	new_xsec += (u64)new_sec * XSEC_PER_SEC - tb_delta_xs;
 	update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs);
 
-#ifdef CONFIG_PPC64
-	_systemcfg->tz_minuteswest = sys_tz.tz_minuteswest;
-	_systemcfg->tz_dsttime = sys_tz.tz_dsttime;
-#endif
+	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 	clock_was_set();
@@ -713,13 +710,12 @@ void __init time_init(void)
 	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 	do_gtod.varp->tb_to_xs = tb_to_xs;
 	do_gtod.tb_to_us = tb_to_us;
-#ifdef CONFIG_PPC64
-	_systemcfg->tb_orig_stamp = tb_last_jiffy;
-	_systemcfg->tb_update_count = 0;
-	_systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
-	_systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
-	_systemcfg->tb_to_xs = tb_to_xs;
-#endif
+
+	vdso_data->tb_orig_stamp = tb_last_jiffy;
+	vdso_data->tb_update_count = 0;
+	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+	vdso_data->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
+	vdso_data->tb_to_xs = tb_to_xs;
 
 	time_freq = 0;
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 2020bb7648f..1511454c469 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -49,7 +49,6 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #include <asm/processor.h>
-#include <asm/systemcfg.h>
 #endif
 
 #ifdef CONFIG_PPC64	/* XXX */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
new file mode 100644
index 00000000000..0d4d8bec0df
--- /dev/null
+++ b/arch/powerpc/kernel/vdso.c
@@ -0,0 +1,746 @@
+/*
+ *  linux/arch/ppc64/kernel/vdso.c
+ *
+ *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ *			 <benh@kernel.crashing.org>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/security.h>
+#include <linux/bootmem.h>
+
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/lmb.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/sections.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+
+#undef DEBUG
+
+#ifdef DEBUG
+#define DBG(fmt...) printk(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+/* Max supported size for symbol names */
+#define MAX_SYMNAME	64
+
+extern char vdso32_start, vdso32_end;
+static void *vdso32_kbase = &vdso32_start;
+unsigned int vdso32_pages;
+unsigned long vdso32_sigtramp;
+unsigned long vdso32_rt_sigtramp;
+
+#ifdef CONFIG_PPC64
+extern char vdso64_start, vdso64_end;
+static void *vdso64_kbase = &vdso64_start;
+unsigned int vdso64_pages;
+unsigned long vdso64_rt_sigtramp;
+#endif /* CONFIG_PPC64 */
+
+/*
+ * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
+ * Once the early boot kernel code no longer needs to muck around
+ * with it, it will become dynamically allocated
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __attribute__((__section__(".data.page_aligned")));
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+/* Format of the patch table */
+struct vdso_patch_def
+{
+	unsigned long	ftr_mask, ftr_value;
+	const char	*gen_name;
+	const char	*fix_name;
+};
+
+/* Table of functions to patch based on the CPU type/revision
+ *
+ * Currently, we only change sync_dicache to do nothing on processors
+ * with a coherent icache
+ */
+static struct vdso_patch_def vdso_patches[] = {
+	{
+		CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE,
+		"__kernel_sync_dicache", "__kernel_sync_dicache_p5"
+	},
+	{
+		CPU_FTR_USE_TB, 0,
+		"__kernel_gettimeofday", NULL
+	},
+};
+
+/*
+ * Some infos carried around for each of them during parsing at
+ * boot time.
+ */
+struct lib32_elfinfo
+{
+	Elf32_Ehdr	*hdr;		/* ptr to ELF */
+	Elf32_Sym	*dynsym;	/* ptr to .dynsym section */
+	unsigned long	dynsymsize;	/* size of .dynsym section */
+	char		*dynstr;	/* ptr to .dynstr section */
+	unsigned long	text;		/* offset of .text section in .so */
+};
+
+struct lib64_elfinfo
+{
+	Elf64_Ehdr	*hdr;
+	Elf64_Sym	*dynsym;
+	unsigned long	dynsymsize;
+	char		*dynstr;
+	unsigned long	text;
+};
+
+
+#ifdef __DEBUG
+static void dump_one_vdso_page(struct page *pg, struct page *upg)
+{
+	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
+	       page_count(pg),
+	       pg->flags);
+	if (upg/* && pg != upg*/) {
+		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
+						       << PAGE_SHIFT),
+		       page_count(upg),
+		       upg->flags);
+	}
+	printk("\n");
+}
+
+static void dump_vdso_pages(struct vm_area_struct * vma)
+{
+	int i;
+
+	if (!vma || test_thread_flag(TIF_32BIT)) {
+		printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
+		for (i=0; i<vdso32_pages; i++) {
+			struct page *pg = virt_to_page(vdso32_kbase +
+						       i*PAGE_SIZE);
+			struct page *upg = (vma && vma->vm_mm) ?
+				follow_page(vma->vm_mm, vma->vm_start +
+					    i*PAGE_SIZE, 0)
+				: NULL;
+			dump_one_vdso_page(pg, upg);
+		}
+	}
+	if (!vma || !test_thread_flag(TIF_32BIT)) {
+		printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
+		for (i=0; i<vdso64_pages; i++) {
+			struct page *pg = virt_to_page(vdso64_kbase +
+						       i*PAGE_SIZE);
+			struct page *upg = (vma && vma->vm_mm) ?
+				follow_page(vma->vm_mm, vma->vm_start +
+					    i*PAGE_SIZE, 0)
+				: NULL;
+			dump_one_vdso_page(pg, upg);
+		}
+	}
+}
+#endif /* DEBUG */
+
+/*
+ * Keep a dummy vma_close for now, it will prevent VMA merging.
+ */
+static void vdso_vma_close(struct vm_area_struct * vma)
+{
+}
+
+/*
+ * Our nopage() function, maps in the actual vDSO kernel pages, they will
+ * be mapped read-only by do_no_page(), and eventually COW'ed, either
+ * right away for an initial write access, or by do_wp_page().
+ */
+static struct page * vdso_vma_nopage(struct vm_area_struct * vma,
+				     unsigned long address, int *type)
+{
+	unsigned long offset = address - vma->vm_start;
+	struct page *pg;
+#ifdef CONFIG_PPC64
+	void *vbase = test_thread_flag(TIF_32BIT) ?
+		vdso32_kbase : vdso64_kbase;
+#else
+	void *vbase = vdso32_kbase;
+#endif
+
+	DBG("vdso_vma_nopage(current: %s, address: %016lx, off: %lx)\n",
+	    current->comm, address, offset);
+
+	if (address < vma->vm_start || address > vma->vm_end)
+		return NOPAGE_SIGBUS;
+
+	/*
+	 * Last page is systemcfg.
+	 */
+	if ((vma->vm_end - address) <= PAGE_SIZE)
+		pg = virt_to_page(vdso_data);
+	else
+		pg = virt_to_page(vbase + offset);
+
+	get_page(pg);
+	DBG(" ->page count: %d\n", page_count(pg));
+
+	return pg;
+}
+
+static struct vm_operations_struct vdso_vmops = {
+	.close	= vdso_vma_close,
+	.nopage	= vdso_vma_nopage,
+};
+
+/*
+ * This is called from binfmt_elf, we create the special vma for the
+ * vDSO and insert it into the mm struct tree
+ */
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+				int executable_stack)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long vdso_pages;
+	unsigned long vdso_base;
+
+#ifdef CONFIG_PPC64
+	if (test_thread_flag(TIF_32BIT)) {
+		vdso_pages = vdso32_pages;
+		vdso_base = VDSO32_MBASE;
+	} else {
+		vdso_pages = vdso64_pages;
+		vdso_base = VDSO64_MBASE;
+	}
+#else
+	vdso_pages = vdso32_pages;
+	vdso_base = VDSO32_MBASE;
+#endif
+
+	current->thread.vdso_base = 0;
+
+	/* vDSO has a problem and was disabled, just don't "enable" it for the
+	 * process
+	 */
+	if (vdso_pages == 0)
+		return 0;
+
+	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+	if (vma == NULL)
+		return -ENOMEM;
+
+	memset(vma, 0, sizeof(*vma));
+
+	/* Add a page to the vdso size for the data page */
+	vdso_pages ++;
+
+	/*
+	 * pick a base address for the vDSO in process space. We try to put it
+	 * at vdso_base which is the "natural" base for it, but we might fail
+	 * and end up putting it elsewhere.
+	 */
+	vdso_base = get_unmapped_area(NULL, vdso_base,
+				      vdso_pages << PAGE_SHIFT, 0, 0);
+	if (vdso_base & ~PAGE_MASK) {
+		kmem_cache_free(vm_area_cachep, vma);
+		return (int)vdso_base;
+	}
+
+	current->thread.vdso_base = vdso_base;
+
+	vma->vm_mm = mm;
+	vma->vm_start = current->thread.vdso_base;
+	vma->vm_end = vma->vm_start + (vdso_pages << PAGE_SHIFT);
+
+	/*
+	 * our vma flags don't have VM_WRITE so by default, the process isn't
+	 * allowed to write those pages.
+	 * gdb can break that with ptrace interface, and thus trigger COW on
+	 * those pages but it's then your responsibility to never do that on
+	 * the "data" page of the vDSO or you'll stop getting kernel updates
+	 * and your nice userland gettimeofday will be totally dead.
+	 * It's fine to use that for setting breakpoints in the vDSO code
+	 * pages though
+	 */
+	vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE |
+		VM_MAYEXEC | VM_RESERVED;
+	vma->vm_flags |= mm->def_flags;
+	vma->vm_page_prot = protection_map[vma->vm_flags & 0x7];
+	vma->vm_ops = &vdso_vmops;
+
+	down_write(&mm->mmap_sem);
+	if (insert_vm_struct(mm, vma)) {
+		up_write(&mm->mmap_sem);
+		kmem_cache_free(vm_area_cachep, vma);
+		return -ENOMEM;
+	}
+	mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	up_write(&mm->mmap_sem);
+
+	return 0;
+}
+
+static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname,
+				  unsigned long *size)
+{
+	Elf32_Shdr *sechdrs;
+	unsigned int i;
+	char *secnames;
+
+	/* Grab section headers an