---

yaml
---
r: 73961
b: refs/heads/master
c: 072ef40
h: refs/heads/master
i:
  73959: 6c3a64b
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: bebfa06c61da6246d4aab38efa06a460eb3db4ed
+refs/heads/master: 072ef40e08a71aae4ff2835e3c7f601b29daf227

trunk/arch/powerpc/kernel/asm-offsets.c

@@ -284,6 +284,10 @@ int main(void)
 	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
 	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
+	DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
+	DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
+	DEFINE(CFG_DCACHE_LOGBLOCKSZ, offsetof(struct vdso_data, dcache_log_block_size));
 #ifdef CONFIG_PPC64
 	DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64));
 	DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));

trunk/arch/powerpc/kernel/rtas.c

@@ -19,6 +19,9 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <linux/cpumask.h>
 
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -34,15 +37,19 @@
 #include <asm/lmb.h>
 #include <asm/udbg.h>
 #include <asm/syscalls.h>
+#include <asm/smp.h>
+#include <asm/atomic.h>
 
 struct rtas_t rtas = {
 	.lock = SPIN_LOCK_UNLOCKED
 };
 EXPORT_SYMBOL(rtas);
 
 struct rtas_suspend_me_data {
-	long waiting;
-	struct rtas_args *args;
+	atomic_t working; /* number of cpus accessing this struct */
+	int token; /* ibm,suspend-me */
+	int error;
+	struct completion *complete; /* wait on this until working == 0 */
 };
 
 DEFINE_SPINLOCK(rtas_data_buf_lock);
@@ -631,18 +638,18 @@ void rtas_halt(void)
 /* Must be in the RMO region, so we place it here */
 static char rtas_os_term_buf[2048];
 
-void rtas_os_term(char *str)
+void rtas_panic_msg(char *str)
 {
-	int status;
+	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
+}
 
-	if (panic_timeout)
-		return;
+void rtas_os_term(void)
+{
+	int status;
 
 	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term"))
 		return;
 
-	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
-
 	do {
 		status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL,
 				   __pa(rtas_os_term_buf));
@@ -657,50 +664,62 @@ static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
 static void rtas_percpu_suspend_me(void *info)
 {
-	int i;
 	long rc;
-	long flags;
+	unsigned long msr_save;
+	int cpu;
 	struct rtas_suspend_me_data *data =
 		(struct rtas_suspend_me_data *)info;
 
-	/*
-	 * We use "waiting" to indicate our state.  As long
-	 * as it is >0, we are still trying to all join up.
-	 * If it goes to 0, we have successfully joined up and
-	 * one thread got H_CONTINUE.  If any error happens,
-	 * we set it to <0.
-	 */
-	local_irq_save(flags);
-	do {
-		rc = plpar_hcall_norets(H_JOIN);
-		smp_rmb();
-	} while (rc == H_SUCCESS && data->waiting > 0);
-	if (rc == H_SUCCESS)
-		goto out;
+	atomic_inc(&data->working);
+
+	/* really need to ensure MSR.EE is off for H_JOIN */
+	msr_save = mfmsr();
+	mtmsr(msr_save & ~(MSR_EE));
+
+	rc = plpar_hcall_norets(H_JOIN);
 
-	if (rc == H_CONTINUE) {
-		data->waiting = 0;
-		data->args->args[data->args->nargs] =
-			rtas_call(ibm_suspend_me_token, 0, 1, NULL);
-		for_each_possible_cpu(i)
-			plpar_hcall_norets(H_PROD,i);
+	mtmsr(msr_save);
+
+	if (rc == H_SUCCESS) {
+		/* This cpu was prodded and the suspend is complete. */
+		goto out;
+	} else if (rc == H_CONTINUE) {
+		/* All other cpus are in H_JOIN, this cpu does
+		 * the suspend.
+		 */
+		printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n",
+		       smp_processor_id());
+		data->error = rtas_call(data->token, 0, 1, NULL);
+
+		if (data->error)
+			printk(KERN_DEBUG "ibm,suspend-me returned %d\n",
+			       data->error);
 	} else {
-		data->waiting = -EBUSY;
-		printk(KERN_ERR "Error on H_JOIN hypervisor call\n");
+		printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n",
+		       smp_processor_id(), rc);
+		data->error = rc;
 	}
-
+	/* This cpu did the suspend or got an error; in either case,
+	 * we need to prod all other other cpus out of join state.
+	 * Extra prods are harmless.
+	 */
+	for_each_online_cpu(cpu)
+		plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
 out:
-	local_irq_restore(flags);
-	return;
+	if (atomic_dec_return(&data->working) == 0)
+		complete(data->complete);
 }
 
 static int rtas_ibm_suspend_me(struct rtas_args *args)
 {
-	int i;
 	long state;
 	long rc;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 	struct rtas_suspend_me_data data;
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	if (!rtas_service_present("ibm,suspend-me"))
+		return -ENOSYS;
 
 	/* Make sure the state is valid */
 	rc = plpar_hcall(H_VASI_STATE, retbuf,
@@ -721,25 +740,23 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
 		return 0;
 	}
 
-	data.waiting = 1;
-	data.args = args;
+	atomic_set(&data.working, 0);
+	data.token = rtas_token("ibm,suspend-me");
+	data.error = 0;
+	data.complete = &done;
 
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
 	 */
 	if (on_each_cpu(rtas_percpu_suspend_me, &data, 1, 0))
-		data.waiting = -EINVAL;
+		data.error = -EINVAL;
 
-	if (data.waiting != 0)
-		printk(KERN_ERR "Error doing global join\n");
+	wait_for_completion(&done);
 
-	/* Prod each CPU.  This won't hurt, and will wake
-	 * anyone we successfully put to sleep with H_JOIN.
-	 */
-	for_each_possible_cpu(i)
-		plpar_hcall_norets(H_PROD, i);
+	if (data.error != 0)
+		printk(KERN_ERR "Error doing global join\n");
 
-	return data.waiting;
+	return data.error;
 }
 #else /* CONFIG_PPC_PSERIES */
 static int rtas_ibm_suspend_me(struct rtas_args *args)

trunk/arch/powerpc/kernel/time.c

@@ -241,8 +241,9 @@ void account_system_vtime(struct task_struct *tsk)
 		/* deltascaled includes both user and system time.
 		 * Hence scale it based on the purr ratio to estimate
 		 * the system time */
-		deltascaled = deltascaled * get_paca()->system_time /
-			(get_paca()->system_time + get_paca()->user_time);
+		if (get_paca()->user_time)
+			deltascaled = deltascaled * get_paca()->system_time /
+			     (get_paca()->system_time + get_paca()->user_time);
 		delta += get_paca()->system_time;
 		get_paca()->system_time = 0;
 	}

trunk/arch/powerpc/kernel/vdso.c

@@ -699,11 +699,22 @@ static int __init vdso_init(void)
 	vdso_data->icache_size = ppc64_caches.isize;
 	vdso_data->icache_line_size = ppc64_caches.iline_size;
 
+	/* XXXOJN: Blocks should be added to ppc64_caches and used instead */
+	vdso_data->dcache_block_size = ppc64_caches.dline_size;
+	vdso_data->icache_block_size = ppc64_caches.iline_size;
+	vdso_data->dcache_log_block_size = ppc64_caches.log_dline_size;
+	vdso_data->icache_log_block_size = ppc64_caches.log_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);
+#else
+	vdso_data->dcache_block_size = L1_CACHE_BYTES;
+	vdso_data->dcache_log_block_size = L1_CACHE_SHIFT;
+	vdso_data->icache_block_size = L1_CACHE_BYTES;
+	vdso_data->icache_log_block_size = L1_CACHE_SHIFT;
 #endif /* CONFIG_PPC64 */
 
 

trunk/arch/powerpc/kernel/vdso32/cacheflush.S

@@ -23,29 +23,46 @@
  *
  * 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 */
+	mflr	r12
+  .cfi_register lr,r12
+	mr	r11,r3
+	bl	__get_datapage@local
+	mtlr	r12
+	mr	r10,r3
+
+	lwz	r7,CFG_DCACHE_BLOCKSZ(r10)
+	addi	r5,r7,-1
+	andc	r6,r11,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 */
+	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
+	srw.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8
-	mr	r3,r6
-1:	dcbst	0,r3
-	addi	r3,r3,128
+1:	dcbst	0,r6
+	add	r6,r6,r7
 	bdnz	1b
 	sync
+
+/* Now invalidate the instruction cache */
+
+	lwz	r7,CFG_ICACHE_BLOCKSZ(r10)
+	addi	r5,r7,-1
+	andc	r6,r11,r5		/* round low to line bdy */
+	subf	r8,r6,r4		/* compute length */
+	add	r8,r8,r5
+	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)
+	srw.	r8,r8,r9		/* compute line count */
+	crclr	cr0*4+so
+	beqlr				/* nothing to do? */
 	mtctr	r8
-1:	icbi	0,r6
-	addi	r6,r6,128
-	bdnz	1b
+2:	icbi	0,r6
+	add	r6,r6,r7
+	bdnz	2b
 	isync
 	li	r3,0
 	blr

trunk/arch/powerpc/kernel/vdso64/cacheflush.S

@@ -23,29 +23,46 @@
  *
  * 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 */
+	mflr	r12
+  .cfi_register lr,r12
+	mr	r11,r3
+	bl	V_LOCAL_FUNC(__get_datapage)
+	mtlr	r12
+	mr	r10,r3
+
+	lwz	r7,CFG_DCACHE_BLOCKSZ(r10)
+	addi	r5,r7,-1
+	andc	r6,r11,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 */
+	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
+	srw.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8
-	mr	r3,r6
-1:	dcbst	0,r3
-	addi	r3,r3,128
+1:	dcbst	0,r6
+	add	r6,r6,r7
 	bdnz	1b
 	sync
+
+/* Now invalidate the instruction cache */
+
+	lwz	r7,CFG_ICACHE_BLOCKSZ(r10)
+	addi	r5,r7,-1
+	andc	r6,r11,r5		/* round low to line bdy */
+	subf	r8,r6,r4		/* compute length */
+	add	r8,r8,r5
+	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)
+	srw.	r8,r8,r9		/* compute line count */
+	crclr	cr0*4+so
+	beqlr				/* nothing to do? */
 	mtctr	r8
-1:	icbi	0,r6
-	addi	r6,r6,128
-	bdnz	1b
+2:	icbi	0,r6
+	add	r6,r6,r7
+	bdnz	2b
 	isync
 	li	r3,0
 	blr

trunk/arch/powerpc/mm/stab.c

@@ -20,6 +20,7 @@
 #include <asm/lmb.h>
 #include <asm/abs_addr.h>
 #include <asm/firmware.h>
+#include <asm/iseries/hv_call.h>
 
 struct stab_entry {
 	unsigned long esid_data;

trunk/arch/powerpc/platforms/40x/walnut.c

@@ -17,12 +17,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 
 static struct of_device_id walnut_of_bus[] = {
 	{ .compatible = "ibm,plb3", },

trunk/arch/powerpc/platforms/44x/bamboo.c

@@ -14,12 +14,13 @@
  * option) any later version.
  */
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 #include "44x.h"
 
 static struct of_device_id bamboo_of_bus[] = {