From 61c03ddbdff2e080702521bc1b757854ca58c46a Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 13 Jan 2010 12:04:11 +0000
Subject: powerpc: Replace per_cpu(, smp_processor_id()) with __get_cpu_var()

The cputime code has a few places that do per_cpu(, smp_processor_id()).
Replace them with __get_cpu_var().

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/time.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6c6093d67f30..0a5b1081a50e 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -265,8 +265,8 @@ void account_system_vtime(struct task_struct *tsk)
 		account_system_time(tsk, 0, delta, deltascaled);
 	else
 		account_idle_time(delta);
-	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
-	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
+	__get_cpu_var(cputime_last_delta) = delta;
+	__get_cpu_var(cputime_scaled_last_delta) = deltascaled;
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
-- 
cgit v1.2.3


From 5be3492f972b73051ead7ecbac6fb9efd1e8e0ec Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 12 Jan 2010 00:50:14 +0000
Subject: powerpc: Mark some variables in the page fault path __read_mostly

Using perf to trace L1 dcache misses and dumping data addresses I found a few
variables taking a lot of misses. Since they are almost never written, they
should go into the __read_mostly section.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/traps.c | 14 +++++++-------
 arch/powerpc/xmon/xmon.c    |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index d069ff8a7e03..4588d1eb18d2 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -60,13 +60,13 @@
 #endif
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
-int (*__debugger)(struct pt_regs *regs);
-int (*__debugger_ipi)(struct pt_regs *regs);
-int (*__debugger_bpt)(struct pt_regs *regs);
-int (*__debugger_sstep)(struct pt_regs *regs);
-int (*__debugger_iabr_match)(struct pt_regs *regs);
-int (*__debugger_dabr_match)(struct pt_regs *regs);
-int (*__debugger_fault_handler)(struct pt_regs *regs);
+int (*__debugger)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_ipi)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_bpt)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_sstep)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_iabr_match)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_dabr_match)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_fault_handler)(struct pt_regs *regs) __read_mostly;
 
 EXPORT_SYMBOL(__debugger);
 EXPORT_SYMBOL(__debugger_ipi);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 4e6152c13764..8bad7d5f32af 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -61,7 +61,7 @@ static int xmon_owner;
 static int xmon_gate;
 #endif /* CONFIG_SMP */
 
-static unsigned long in_xmon = 0;
+static unsigned long in_xmon __read_mostly = 0;
 
 static unsigned long adrs;
 static int size = 1;
-- 
cgit v1.2.3


From 28bb9ee13aa0ee4c57dc3568f539cc84920b43aa Mon Sep 17 00:00:00 2001
From: "jschopp@austin.ibm.com" <jschopp@austin.ibm.com>
Date: Mon, 1 Feb 2010 12:50:48 +0000
Subject: powerpc: Add static fields to ibm,client-architecture call

This patch adds 2 fields to the ibm_architecture_vec array.

The first of these fields indicates the number of cores which Linux can
boot.  It does not account for SMT, so it may result in cpus assigned to
Linux which cannot be booted.  A second patch follows that dynamically
updates this for SMT.

The second field just indicates that our OS is Linux, and not another
OS.  The system may or may not use this hint to performance tune
settings for Linux.

Signed-off-by: Joel Schopp <jschopp@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/prom_init.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index bafac2e41ae1..59d5bd1c064d 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -654,6 +654,9 @@ static void __init early_cmdline_parse(void)
 #define OV5_CMO			0x00
 #endif
 
+/* Option Vector 6: IBM PAPR hints */
+#define OV6_LINUX		0x02	/* Linux is our OS */
+
 /*
  * The architecture vector has an array of PVR mask/value pairs,
  * followed by # option vectors - 1, followed by the option vectors.
@@ -665,7 +668,7 @@ static unsigned char ibm_architecture_vec[] = {
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
 	W(0xffffffff), W(0x0f000002),	/* all 2.05-compliant */
 	W(0xfffffffe), W(0x0f000001),	/* all 2.04-compliant and earlier */
-	5 - 1,				/* 5 option vectors */
+	6 - 1,				/* 6 option vectors */
 
 	/* option vector 1: processor architectures supported */
 	3 - 2,				/* length */
@@ -697,12 +700,24 @@ static unsigned char ibm_architecture_vec[] = {
 	0,				/* don't halt */
 
 	/* option vector 5: PAPR/OF options */
-	5 - 2,				/* length */
+	13 - 2,				/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY |
 	OV5_DONATE_DEDICATE_CPU | OV5_MSI,
 	0,
 	OV5_CMO,
+	0,
+	0,
+	0,
+	0,
+	W(NR_CPUS),			/* number of cores supported*/
+
+	/* option vector 6: IBM PAPR hints */
+	4 - 2,				/* length */
+	0,
+	0,
+	OV6_LINUX,
+
 };
 
 /* Old method - ELF header with PT_NOTE sections */
-- 
cgit v1.2.3


From efec959f63de850fbd2442189f7dfc9c38efe251 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 4 Feb 2010 14:33:54 +1100
Subject: powerpc/pseries: Pass more accurate number of supported cores to
 firmware

Updated variant of a patch by Joel Schopp.

The field containing the number of supported cores which we pass to
firmware via the ibm,client-architecture call was set by a previous
patch statically as high as is possible (NR_CPUS).

However, that value isn't quite right for a system that supports
multiple threads per core, thus permitting the firmware to assign
more cores to a Linux partition than it can really cope with.

This patch improves it by using the device-tree to determine the
number of threads supported by the processors in order to adjust
the value passed to firmware.

Signed-off-by: Joel Schopp <jschopp@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/prom_init.c | 64 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 59d5bd1c064d..5f306c4946e5 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -710,7 +710,12 @@ static unsigned char ibm_architecture_vec[] = {
 	0,
 	0,
 	0,
-	W(NR_CPUS),			/* number of cores supported*/
+	/* WARNING: The offset of the "number of cores" field below
+	 * must match by the macro below. Update the definition if
+	 * the structure layout changes.
+	 */
+#define IBM_ARCH_VEC_NRCORES_OFFSET	100
+	W(NR_CPUS),			/* number of cores supported */
 
 	/* option vector 6: IBM PAPR hints */
 	4 - 2,				/* length */
@@ -807,13 +812,70 @@ static struct fake_elf {
 	}
 };
 
+static int __init prom_count_smt_threads(void)
+{
+	phandle node;
+	char type[64];
+	unsigned int plen;
+
+	/* Pick up th first CPU node we can find */
+	for (node = 0; prom_next_node(&node); ) {
+		type[0] = 0;
+		prom_getprop(node, "device_type", type, sizeof(type));
+
+		if (strcmp(type, RELOC("cpu")))
+			continue;
+		/*
+		 * There is an entry for each smt thread, each entry being
+		 * 4 bytes long.  All cpus should have the same number of
+		 * smt threads, so return after finding the first.
+		 */
+		plen = prom_getproplen(node, "ibm,ppc-interrupt-server#s");
+		if (plen == PROM_ERROR)
+			break;
+		plen >>= 2;
+		prom_debug("Found 0x%x smt threads per core\n", (unsigned long)plen);
+
+		/* Sanity check */
+		if (plen < 1 || plen > 64) {
+			prom_printf("Threads per core 0x%x out of bounds, assuming 1\n",
+				    (unsigned long)plen);
+			return 1;
+		}
+		return plen;
+	}
+	prom_debug("No threads found, assuming 1 per core\n");
+
+	return 1;
+
+}
+
+
 static void __init prom_send_capabilities(void)
 {
 	ihandle elfloader, root;
 	prom_arg_t ret;
+	u32 *cores;
 
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
+		/* We need to tell the FW about the number of cores we support.
+		 *
+		 * To do that, we count the number of threads on the first core
+		 * (we assume this is the same for all cores) and use it to
+		 * divide NR_CPUS.
+		 */
+		cores = (u32 *)PTRRELOC(&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET]);
+		if (*cores != NR_CPUS) {
+			prom_printf("WARNING ! "
+				    "ibm_architecture_vec structure inconsistent: 0x%x !\n",
+				    *cores);
+		} else {
+			*cores = NR_CPUS / prom_count_smt_threads();
+			prom_printf("Max number of cores passed to firmware: 0x%x\n",
+				    (unsigned long)*cores);
+		}
+
 		/* try calling the ibm,client-architecture-support method */
 		prom_printf("Calling ibm,client-architecture-support...");
 		if (call_prom_ret("call-method", 3, 2, &ret,
-- 
cgit v1.2.3


From 5a2ad98e920dd8ac4cfbc0c1556e930ba2d65427 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 31 Jan 2010 10:02:03 +0000
Subject: arch/powerpc: Fix continuation line formats

String constants that are continued on subsequent lines with \
are not good.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/nvram_64.c               | 6 +++---
 arch/powerpc/platforms/pseries/hotplug-cpu.c | 8 ++++----
 arch/powerpc/platforms/pseries/smp.c         | 4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index ad461e735aec..9cf197f01e94 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -338,8 +338,8 @@ static int __init nvram_create_os_partition(void)
 
 	rc = nvram_write_header(new_part);
 	if (rc <= 0) {
-		printk(KERN_ERR "nvram_create_os_partition: nvram_write_header \
-				failed (%d)\n", rc);
+		printk(KERN_ERR "nvram_create_os_partition: nvram_write_header "
+				"failed (%d)\n", rc);
 		return rc;
 	}
 
@@ -349,7 +349,7 @@ static int __init nvram_create_os_partition(void)
 	rc = ppc_md.nvram_write((char *)&seq_init, sizeof(seq_init), &tmp_index);
 	if (rc <= 0) {
 		printk(KERN_ERR "nvram_create_os_partition: nvram_write "
-				"failed (%d)\n", rc);
+		       "failed (%d)\n", rc);
 		return rc;
 	}
 	
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6ea4698d9176..a70de10332d8 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -397,12 +397,12 @@ static int parse_cede_parameters(void)
 				CEDE_LATENCY_PARAM_MAX_LENGTH);
 
 	if (call_status != 0)
-		printk(KERN_INFO "CEDE_LATENCY: \
-			%s %s Error calling get-system-parameter(0x%x)\n",
+		printk(KERN_INFO "CEDE_LATENCY: "
+			"%s %s Error calling get-system-parameter(0x%x)\n",
 			__FILE__, __func__, call_status);
 	else
-		printk(KERN_INFO "CEDE_LATENCY: \
-			get-system-parameter successful.\n");
+		printk(KERN_INFO "CEDE_LATENCY: "
+			"get-system-parameter successful.\n");
 
 	return call_status;
 }
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index b4886635972c..4e7f89a84561 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -144,8 +144,8 @@ static void __devinit smp_pSeries_kick_cpu(int nr)
 		hcpuid = get_hard_smp_processor_id(nr);
 		rc = plpar_hcall_norets(H_PROD, hcpuid);
 		if (rc != H_SUCCESS)
-			printk(KERN_ERR "Error: Prod to wake up processor %d\
-						Ret= %ld\n", nr, rc);
+			printk(KERN_ERR "Error: Prod to wake up processor %d "
+						"Ret= %ld\n", nr, rc);
 	}
 }
 
-- 
cgit v1.2.3


From 66fcb1059deeae072c1bf1536a8e2613028bce3e Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 7 Feb 2010 14:44:16 +0000
Subject: powerpc: Add last sysfs file and dump of ftrace buffer to oops
 printout

Add printout of last accessed sysfs file, added to x86 in
ae87221d3ce49d9de1e43756da834fd0bf05a2ad (sysfs: crash debugging)

Also add the notify_die hook that allows us to print out the ftrace
buffer on oops. This is useful in conjunction with ftrace function_graph:

Oops: Kernel access of bad area, sig: 11 [#1]
SMP NR_CPUS=128 NUMA pSeries
last sysfs file: /sys/class/net/tunl0/type
Dumping ftrace buffer:

...

  0)               |                .sysrq_handle_crash() {
  0)   0.476 us    |                  .hash_page();
  0)   0.488 us    |                  .xmon_fault_handler();
  0)               |                  .bad_page_fault() {
  0)               |                    .search_exception_tables() {
  0)   0.590 us    |                      .search_module_extables();
  0)   2.546 us    |                    }
  0)               |                    .printk() {
  0)               |                      .vprintk() {
  0)   0.488 us    |                        ._raw_spin_lock();
  0)   0.572 us    |                        .emit_log_char();

Showing the function graph of a sysrq-c crash.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/traps.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4588d1eb18d2..0a320dbd950a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -146,6 +146,11 @@ int die(const char *str, struct pt_regs *regs, long err)
 #endif
 		printk("%s\n", ppc_md.name ? ppc_md.name : "");
 
+		sysfs_printk_last_file();
+		if (notify_die(DIE_OOPS, str, regs, err, 255,
+			       SIGSEGV) == NOTIFY_STOP)
+			return 1;
+
 		print_modules();
 		show_regs(regs);
 	} else {
-- 
cgit v1.2.3


From 0b9612c210f6bf6efb32ab84b8f34018eaacb08d Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 7 Feb 2010 13:07:36 +0000
Subject: powerpc: Make powerpc_firmware_features __read_mostly

We use firmware_has_feature quite a lot these days, so it's worth putting
powerpc_firmware_features into __read_mostly.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/firmware.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 1679a70bbcad..6b1f4271eb53 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -17,5 +17,5 @@
 
 #include <asm/firmware.h>
 
-unsigned long powerpc_firmware_features;
+unsigned long powerpc_firmware_features __read_mostly;
 EXPORT_SYMBOL_GPL(powerpc_firmware_features);
-- 
cgit v1.2.3


From 8354be9c104db8e92bb079e29540fbafb7f09b5c Mon Sep 17 00:00:00 2001
From: Frans Pop <elendil@planet.nl>
Date: Sat, 6 Feb 2010 07:47:20 +0000
Subject: powerpc: Remove trailing space in messages

Signed-off-by: Frans Pop <elendil@planet.nl>
Cc: linuxppc-dev@ozlabs.org
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/lparcfg.c                | 10 +++++-----
 arch/powerpc/kernel/pci_of_scan.c            |  2 +-
 arch/powerpc/platforms/85xx/stx_gp3.c        |  2 +-
 arch/powerpc/platforms/iseries/proc.c        |  2 +-
 arch/powerpc/platforms/iseries/setup.c       |  2 +-
 arch/powerpc/platforms/powermac/bootx_init.c |  4 ++--
 arch/powerpc/platforms/pseries/eeh_driver.c  |  6 +++---
 arch/powerpc/platforms/pseries/pci_dlpar.c   |  2 +-
 arch/powerpc/platforms/pseries/phyp_dump.c   |  6 +++---
 arch/powerpc/platforms/pseries/xics.c        |  2 +-
 arch/powerpc/sysdev/mpic.c                   |  2 +-
 arch/powerpc/sysdev/qe_lib/qe_ic.c           |  2 +-
 arch/powerpc/sysdev/qe_lib/qe_io.c           |  8 ++++----
 drivers/macintosh/therm_adt746x.c            |  2 +-
 drivers/ps3/ps3av.c                          |  2 +-
 15 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 79a00bb9c64c..d09d1c615150 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -359,7 +359,7 @@ static void parse_system_parameter_string(struct seq_file *m)
 
 	unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
 	if (!local_buffer) {
-		printk(KERN_ERR "%s %s kmalloc failure at line %d \n",
+		printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
 		       __FILE__, __func__, __LINE__);
 		return;
 	}
@@ -383,13 +383,13 @@ static void parse_system_parameter_string(struct seq_file *m)
 		int idx, w_idx;
 		char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
 		if (!workbuffer) {
-			printk(KERN_ERR "%s %s kmalloc failure at line %d \n",
+			printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
 			       __FILE__, __func__, __LINE__);
 			kfree(local_buffer);
 			return;
 		}
 #ifdef LPARCFG_DEBUG
-		printk(KERN_INFO "success calling get-system-parameter \n");
+		printk(KERN_INFO "success calling get-system-parameter\n");
 #endif
 		splpar_strlen = local_buffer[0] * 256 + local_buffer[1];
 		local_buffer += 2;	/* step over strlen value */
@@ -440,7 +440,7 @@ static int lparcfg_count_active_processors(void)
 
 	while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
 #ifdef LPARCFG_DEBUG
-		printk(KERN_ERR "cpus_dn %p \n", cpus_dn);
+		printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
 #endif
 		count++;
 	}
@@ -725,7 +725,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 	const unsigned int *lp_index_ptr;
 	unsigned int lp_index = 0;
 
-	seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS);
+	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
 
 	rootdn = of_find_node_by_path("/");
 	if (rootdn) {
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 4aa17401657b..cd11d5ca80df 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -304,7 +304,7 @@ static void __devinit __of_scan_bus(struct device_node *node,
 	int reglen, devfn;
 	struct pci_dev *dev;
 
-	pr_debug("of_scan_bus(%s) bus no %d... \n",
+	pr_debug("of_scan_bus(%s) bus no %d...\n",
 		 node->full_name, bus->number);
 
 	/* Scan direct children */
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index f559918f3c6f..bc33d1859ae7 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -134,7 +134,7 @@ static void stx_gp3_show_cpuinfo(struct seq_file *m)
 	pvid = mfspr(SPRN_PVR);
 	svid = mfspr(SPRN_SVR);
 
-	seq_printf(m, "Vendor\t\t: RPC Electronics STx \n");
+	seq_printf(m, "Vendor\t\t: RPC Electronics STx\n");
 	seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
 	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
 
diff --git a/arch/powerpc/platforms/iseries/proc.c b/arch/powerpc/platforms/iseries/proc.c
index 91f4c6cd4b99..06763682db47 100644
--- a/arch/powerpc/platforms/iseries/proc.c
+++ b/arch/powerpc/platforms/iseries/proc.c
@@ -85,7 +85,7 @@ static int proc_titantod_show(struct seq_file *m, void *v)
 
 		seq_printf(m, "  titan elapsed = %lu uSec\n", titan_usec);
 		seq_printf(m, "  tb elapsed    = %lu ticks\n", tb_ticks);
-		seq_printf(m, "  titan jiffies = %lu.%04lu \n", titan_jiffies,
+		seq_printf(m, "  titan jiffies = %lu.%04lu\n", titan_jiffies,
 			   titan_jiff_rem_usec);
 		seq_printf(m, "  tb jiffies    = %lu.%04lu\n", tb_jiffies,
 			   tb_jiff_rem_usec);
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index a6cd3394feaa..b0863410517f 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -256,7 +256,7 @@ static unsigned long iSeries_process_mainstore_vpd(struct MemoryBlock *mb_array,
 		mem_blocks = iSeries_process_Condor_mainstore_vpd(mb_array,
 				max_entries);
 
-	printk("Mainstore_VPD: numMemoryBlocks = %ld \n", mem_blocks);
+	printk("Mainstore_VPD: numMemoryBlocks = %ld\n", mem_blocks);
 	for (i = 0; i < mem_blocks; ++i) {
 		printk("Mainstore_VPD: block %3ld logical chunks %016lx - %016lx\n"
 		       "                             abs chunks %016lx - %016lx\n",
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index 9dd789a7370d..84d7fd9bcc69 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -539,7 +539,7 @@ void __init bootx_init(unsigned long r3, unsigned long r4)
 		if (model
 		    && (strcmp(model, "iMac,1") == 0
 			|| strcmp(model, "PowerMac1,1") == 0)) {
-			bootx_printf("iMac,1 detected, shutting down USB \n");
+			bootx_printf("iMac,1 detected, shutting down USB\n");
 			out_le32((unsigned __iomem *)0x80880008, 1);	/* XXX */
 		}
 	}
@@ -554,7 +554,7 @@ void __init bootx_init(unsigned long r3, unsigned long r4)
 	} else
 		space = bi->totalParamsSize;
 
-	bootx_printf("Total space used by parameters & ramdisk: 0x%x \n", space);
+	bootx_printf("Total space used by parameters & ramdisk: 0x%x\n", space);
 
 	/* New BootX will have flushed all TLBs and enters kernel with
 	 * MMU switched OFF, so this should not be useful anymore.
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index ef8e45448480..0c252c3a5f9f 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -478,9 +478,9 @@ excess_failures:
 	 * due to actual, failed cards.
 	 */
 	printk(KERN_ERR
-	   "EEH: PCI device at location=%s driver=%s pci addr=%s \n"
+	   "EEH: PCI device at location=%s driver=%s pci addr=%s\n"
 		"has failed %d times in the last hour "
-		"and has been permanently disabled. \n"
+		"and has been permanently disabled.\n"
 		"Please try reseating this device or replacing it.\n",
 		location, drv_str, pci_str, frozen_pdn->eeh_freeze_count);
 	goto perm_error;
@@ -488,7 +488,7 @@ excess_failures:
 hard_fail:
 	printk(KERN_ERR
 	   "EEH: Unable to recover from failure of PCI device "
-	   "at location=%s driver=%s pci addr=%s \n"
+	   "at location=%s driver=%s pci addr=%s\n"
 	   "Please try reseating this device or replacing it.\n",
 		location, drv_str, pci_str);
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index b6fa3e4b51b5..4b7a062dee15 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -165,7 +165,7 @@ int remove_phb_dynamic(struct pci_controller *phb)
 	struct resource *res;
 	int rc, i;
 
-	pr_debug("PCI: Removing PHB %04x:%02x... \n",
+	pr_debug("PCI: Removing PHB %04x:%02x...\n",
 		 pci_domain_nr(b), b->number);
 
 	/* We cannot to remove a root bus that has children */
diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c
index 15eb6107bcd2..225a50ab14be 100644
--- a/arch/powerpc/platforms/pseries/phyp_dump.c
+++ b/arch/powerpc/platforms/pseries/phyp_dump.c
@@ -150,7 +150,7 @@ static void print_dump_header(const struct phyp_dump_header *ph)
 	printk(KERN_INFO "Max auto time= %d\n", ph->maxtime_to_auto);
 
 	/*set cpu state and hpte states as well scratch pad area */
-	printk(KERN_INFO " CPU AREA \n");
+	printk(KERN_INFO " CPU AREA\n");
 	printk(KERN_INFO "cpu dump_flags =%d\n", ph->cpu_data.dump_flags);
 	printk(KERN_INFO "cpu source_type =%d\n", ph->cpu_data.source_type);
 	printk(KERN_INFO "cpu error_flags =%d\n", ph->cpu_data.error_flags);
@@ -161,7 +161,7 @@ static void print_dump_header(const struct phyp_dump_header *ph)
 	printk(KERN_INFO "cpu length_copied =%llx\n",
 		ph->cpu_data.length_copied);
 
-	printk(KERN_INFO " HPTE AREA \n");
+	printk(KERN_INFO " HPTE AREA\n");
 	printk(KERN_INFO "HPTE dump_flags =%d\n", ph->hpte_data.dump_flags);
 	printk(KERN_INFO "HPTE source_type =%d\n", ph->hpte_data.source_type);
 	printk(KERN_INFO "HPTE error_flags =%d\n", ph->hpte_data.error_flags);
@@ -172,7 +172,7 @@ static void print_dump_header(const struct phyp_dump_header *ph)
 	printk(KERN_INFO "HPTE length_copied =%llx\n",
 		ph->hpte_data.length_copied);
 
-	printk(KERN_INFO " SRSD AREA \n");
+	printk(KERN_INFO " SRSD AREA\n");
 	printk(KERN_INFO "SRSD dump_flags =%d\n", ph->kernel_data.dump_flags);
 	printk(KERN_INFO "SRSD source_type =%d\n", ph->kernel_data.source_type);
 	printk(KERN_INFO "SRSD error_flags =%d\n", ph->kernel_data.error_flags);
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 1ee66db003be..e9a52ec05a0f 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -127,7 +127,7 @@ static inline unsigned int lpar_xirr_info_get(void)
 
 	lpar_rc = plpar_xirr(&return_value);
 	if (lpar_rc != H_SUCCESS)
-		panic(" bad return code xirr - rc = %lx \n", lpar_rc);
+		panic(" bad return code xirr - rc = %lx\n", lpar_rc);
 	return (unsigned int)return_value;
 }
 
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 470dc6c11d57..314f0fa46924 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1575,7 +1575,7 @@ void mpic_request_ipis(void)
 	int i;
 	BUG_ON(mpic == NULL);
 
-	printk(KERN_INFO "mpic: requesting IPIs ... \n");
+	printk(KERN_INFO "mpic: requesting IPIs...\n");
 
 	for (i = 0; i < 4; i++) {
 		unsigned int vipi = irq_create_mapping(mpic->irqhost,
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 2acc928d1920..5f0b0368a209 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -256,7 +256,7 @@ static int qe_ic_host_map(struct irq_host *h, unsigned int virq,
 	struct irq_chip *chip;
 
 	if (qe_ic_info[hw].mask == 0) {
-		printk(KERN_ERR "Can't map reserved IRQ \n");
+		printk(KERN_ERR "Can't map reserved IRQ\n");
 		return -EINVAL;
 	}
 	/* Default chip */
diff --git a/arch/powerpc/sysdev/qe_lib/qe_io.c b/arch/powerpc/sysdev/qe_lib/qe_io.c
index 7c87460179ef..77e4934b88c5 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_io.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_io.c
@@ -157,13 +157,13 @@ int par_io_of_config(struct device_node *np)
 	const unsigned int *pio_map;
 
 	if (par_io == NULL) {
-		printk(KERN_ERR "par_io not initialized \n");
+		printk(KERN_ERR "par_io not initialized\n");
 		return -1;
 	}
 
 	ph = of_get_property(np, "pio-handle", NULL);
 	if (ph == NULL) {
-		printk(KERN_ERR "pio-handle not available \n");
+		printk(KERN_ERR "pio-handle not available\n");
 		return -1;
 	}
 
@@ -171,12 +171,12 @@ int par_io_of_config(struct device_node *np)
 
 	pio_map = of_get_property(pio, "pio-map", &pio_map_len);
 	if (pio_map == NULL) {
-		printk(KERN_ERR "pio-map is not set! \n");
+		printk(KERN_ERR "pio-map is not set!\n");
 		return -1;
 	}
 	pio_map_len /= sizeof(unsigned int);
 	if ((pio_map_len % 6) != 0) {
-		printk(KERN_ERR "pio-map format wrong! \n");
+		printk(KERN_ERR "pio-map format wrong!\n");
 		return -1;
 	}
 
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index 58809b0510f9..c42eeb43042d 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -316,7 +316,7 @@ static void update_fans_speed (struct thermostat *th)
 
 			if (verbose)
 				printk(KERN_DEBUG "adt746x: Setting fans speed to %d "
-						 "(limit exceeded by %d on %s) \n",
+						 "(limit exceeded by %d on %s)\n",
 						new_speed, var,
 						sensor_location[fan_number+1]);
 			write_both_fan_speed(th, new_speed);
diff --git a/drivers/ps3/ps3av.c b/drivers/ps3/ps3av.c
index e82d8c9c6cda..95a689befc84 100644
--- a/drivers/ps3/ps3av.c
+++ b/drivers/ps3/ps3av.c
@@ -532,7 +532,7 @@ static void ps3av_set_videomode_packet(u32 id)
 	res = ps3av_cmd_avb_param(&avb_param, len);
 	if (res == PS3AV_STATUS_NO_SYNC_HEAD)
 		printk(KERN_WARNING
-		       "%s: Command failed. Please try your request again. \n",
+		       "%s: Command failed. Please try your request again.\n",
 		       __func__);
 	else if (res)
 		dev_dbg(&ps3av->dev->core, "ps3av_cmd_avb_param failed\n");
-- 
cgit v1.2.3


From 44c9f3cc1a07503b653b571eac5792436da39a30 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 7 Feb 2010 19:37:29 +0000
Subject: powerpc: Clear MSR_RI during RTAS calls

RTAS should never cause an exception but if it does (for example accessing
outside our RMO) then we might go a long way through the kernel before
oopsing. If we unset MSR_RI we should at least stop things on exception
exit.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/entry_64.S | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index bdcb557d470a..07109d843787 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -791,9 +791,8 @@ _GLOBAL(enter_rtas)
 	
         li      r9,1
         rldicr  r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
-	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP
+	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI
 	andc	r6,r0,r9
-	ori	r6,r6,MSR_RI
 	sync				/* disable interrupts so SRR0/1 */
 	mtmsrd	r0			/* don't get trashed */
 
-- 
cgit v1.2.3


From b919ee827e048826786fd7e889a2b04f63382fe6 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 7 Feb 2010 19:26:29 +0000
Subject: powerpc: Only print clockevent settings once

The clockevent multiplier and shift is useful information, but we
only need to print it once.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/time.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0a5b1081a50e..ed1c0f58344a 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -935,8 +935,8 @@ static void register_decrementer_clockevent(int cpu)
 	*dec = decrementer_clockevent;
 	dec->cpumask = cpumask_of(cpu);
 
-	printk(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
-	       dec->name, dec->mult, dec->shift, cpu);
+	printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
+		    dec->name, dec->mult, dec->shift, cpu);
 
 	clockevents_register_device(dec);
 }
-- 
cgit v1.2.3


From 8c007bfdf1bab536f824d91fccc76596c18aba78 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 31 Jan 2010 20:30:23 +0000
Subject: powerpc: Reduce footprint of irq_stat

PowerPC is currently using asm-generic/hardirq.h which statically allocates an
NR_CPUS irq_stat array. Switch to an arch specific implementation which uses
per cpu data:

On a kernel with NR_CPUS=1024, this saves quite a lot of memory:

   text    data     bss      dec         hex    filename
8767938 2944132 1636796 13348866         cbb002 vmlinux.baseline
8767779 2944260 1505724 13217763         c9afe3 vmlinux.irq_cpustat

A saving of around 128kB.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hardirq.h | 23 ++++++++++++++++++++++-
 arch/powerpc/kernel/irq.c          |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index fb3c05a0cbbf..9bf3467581b1 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -1 +1,22 @@
-#include <asm-generic/hardirq.h>
+#ifndef _ASM_POWERPC_HARDIRQ_H
+#define _ASM_POWERPC_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+
+#define __ARCH_IRQ_STAT
+
+#define local_softirq_pending()	__get_cpu_var(irq_stat).__softirq_pending
+
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+
+#endif /* _ASM_POWERPC_HARDIRQ_H */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9040330b0530..c6ac5583672a 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -73,6 +73,9 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
 int __irq_offset_value;
 static int ppc_spurious_interrupts;
 
-- 
cgit v1.2.3


From c86845ede8b643ca025aec277dec1892d0ccac01 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 31 Jan 2010 20:33:18 +0000
Subject: powerpc: Rework /proc/interrupts

On a large machine I noticed the columns of /proc/interrupts failed to line up
with the header after CPU9. At sufficiently large numbers of CPUs it becomes
impossible to line up the CPU number with the counts.

While fixing this I noticed x86 has a number of updates that we may as well
pull in. On PowerPC we currently omit an interrupt completely if there is no
active handler, whereas on x86 it is printed if there is a non zero count.

The x86 code also spaces the first column correctly based on nr_irqs.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/irq.c | 79 +++++++++++++++++++++++++++--------------------
 1 file changed, 46 insertions(+), 33 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c6ac5583672a..b9cbb4570048 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -183,30 +183,46 @@ notrace void raw_local_irq_restore(unsigned long en)
 EXPORT_SYMBOL(raw_local_irq_restore);
 #endif /* CONFIG_PPC64 */
 
+static int show_other_interrupts(struct seq_file *p, int prec)
+{
+	int j;
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
+	if (tau_initialized) {
+		seq_printf(p, "%*s: ", prec, "TAU");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", tau_interrupts(j));
+		seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
+	}
+#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */
+
+	seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts);
+
+	return 0;
+}
+
 int show_interrupts(struct seq_file *p, void *v)
 {
-	int i = *(loff_t *)v, j;
+	unsigned long flags, any_count = 0;
+	int i = *(loff_t *) v, j, prec;
 	struct irqaction *action;
 	struct irq_desc *desc;
-	unsigned long flags;
 
+	if (i > nr_irqs)
+		return 0;
+
+	for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+		j *= 10;
+
+	if (i == nr_irqs)
+		return show_other_interrupts(p, prec);
+
+	/* print header */
 	if (i == 0) {
-		seq_puts(p, "           ");
+		seq_printf(p, "%*s", prec + 8, "");
 		for_each_online_cpu(j)
-			seq_printf(p, "CPU%d       ", j);
+			seq_printf(p, "CPU%-8d", j);
 		seq_putc(p, '\n');
-	} else if (i == nr_irqs) {
-#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
-		if (tau_initialized){
-			seq_puts(p, "TAU: ");
-			for_each_online_cpu(j)
-				seq_printf(p, "%10u ", tau_interrupts(j));
-			seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
-		}
-#endif /* CONFIG_PPC32 && CONFIG_TAU_INT*/
-		seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
-
-		return 0;
 	}
 
 	desc = irq_to_desc(i);
@@ -214,34 +230,31 @@ int show_interrupts(struct seq_file *p, void *v)
 		return 0;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-
+	for_each_online_cpu(j)
+		any_count |= kstat_irqs_cpu(i, j);
 	action = desc->action;
-	if (!action || !action->handler)
-		goto skip;
+	if (!action && !any_count)
+		goto out;
 
-	seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
+	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-	seq_printf(p, "%10u ", kstat_irqs(i));
-#endif /* CONFIG_SMP */
 
 	if (desc->chip)
-		seq_printf(p, " %s ", desc->chip->name);
+		seq_printf(p, "  %-16s", desc->chip->name);
 	else
-		seq_puts(p, "  None      ");
+		seq_printf(p, "  %-16s", "None");
+	seq_printf(p, " %-8s", (desc->status & IRQ_LEVEL) ? "Level" : "Edge");
 
-	seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
-	seq_printf(p, "    %s", action->name);
+	if (action) {
+		seq_printf(p, "     %s", action->name);
+		while ((action = action->next) != NULL)
+			seq_printf(p, ", %s", action->name);
+	}
 
-	for (action = action->next; action; action = action->next)
-		seq_printf(p, ", %s", action->name);
 	seq_putc(p, '\n');
-
-skip:
+out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 89713ed10815401a1bfe12e3a076b64048381b56 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 31 Jan 2010 20:34:06 +0000
Subject: powerpc: Add timer, performance monitor and machine check counts to
 /proc/interrupts

With NO_HZ it is useful to know how often the decrementer is going off. The
patch below adds an entry for it and also adds it into the /proc/stat
summaries.

While here, I added performance monitoring and machine check exceptions.
I found it useful to keep an eye on the PMU exception rate
when using the perf tool. Since it's possible to take a completely
handled machine check on a System p box it also sounds like a good idea to
keep a machine check summary.

The event naming matches x86 to keep gratuitous differences to a minimum.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hardirq.h |  9 +++++++++
 arch/powerpc/kernel/irq.c          | 35 +++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/time.c         |  2 ++
 arch/powerpc/kernel/traps.c        |  4 ++++
 4 files changed, 50 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 9bf3467581b1..cd2d4be882aa 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -6,6 +6,9 @@
 
 typedef struct {
 	unsigned int __softirq_pending;
+	unsigned int timer_irqs;
+	unsigned int pmu_irqs;
+	unsigned int mce_exceptions;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
@@ -19,4 +22,10 @@ static inline void ack_bad_irq(unsigned int irq)
 	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
 }
 
+extern u64 arch_irq_stat_cpu(unsigned int cpu);
+#define arch_irq_stat_cpu	arch_irq_stat_cpu
+
+extern u64 arch_irq_stat(void);
+#define arch_irq_stat		arch_irq_stat
+
 #endif /* _ASM_POWERPC_HARDIRQ_H */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index b9cbb4570048..710505240f2f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -196,6 +196,21 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	}
 #endif /* CONFIG_PPC32 && CONFIG_TAU_INT */
 
+	seq_printf(p, "%*s: ", prec, "LOC");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
+        seq_printf(p, "  Local timer interrupts\n");
+
+	seq_printf(p, "%*s: ", prec, "CNT");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
+	seq_printf(p, "  Performance monitoring interrupts\n");
+
+	seq_printf(p, "%*s: ", prec, "MCE");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
+	seq_printf(p, "  Machine check exceptions\n");
+
 	seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts);
 
 	return 0;
@@ -258,6 +273,26 @@ out:
 	return 0;
 }
 
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+	u64 sum = per_cpu(irq_stat, cpu).timer_irqs;
+
+	sum += per_cpu(irq_stat, cpu).pmu_irqs;
+	sum += per_cpu(irq_stat, cpu).mce_exceptions;
+
+	return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+	u64 sum = ppc_spurious_interrupts;
+
+	return sum;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(cpumask_t map)
 {
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index ed1c0f58344a..1b16b9a3e49a 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -575,6 +575,8 @@ void timer_interrupt(struct pt_regs * regs)
 
 	trace_timer_interrupt_entry(regs);
 
+	__get_cpu_var(irq_stat).timer_irqs++;
+
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continuue to take decrementer exceptions */
 	set_dec(DECREMENTER_MAX);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 0a320dbd950a..895da29e7db8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -483,6 +483,8 @@ void machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
 
+	__get_cpu_var(irq_stat).mce_exceptions++;
+
 	/* See if any machine dependent calls. In theory, we would want
 	 * to call the CPU first, and call the ppc_md. one if the CPU
 	 * one returns a positive number. However there is existing code
@@ -965,6 +967,8 @@ void vsx_unavailable_exception(struct pt_regs *regs)
 
 void performance_monitor_exception(struct pt_regs *regs)
 {
+	__get_cpu_var(irq_stat).pmu_irqs++;
+
 	perf_irq(regs);
 }
 
-- 
cgit v1.2.3


From 17081102a6e0fe32cf47cdbdf8f2e9ab55273b08 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 31 Jan 2010 20:34:36 +0000
Subject: powerpc: Convert global "BAD" interrupt to per cpu spurious

I often get asked if BAD interrupts are really bad. On some boxes (eg
IBM machines running a hypervisor) there are valid cases where are
presented with an interrupt that is not for us. These cases are common
enough to show up as thousands of BAD interrupts a day.

Tone them down by calling them spurious. Since they can be a significant cause
of OS jitter, we may as well log them per cpu so we know where they are
occurring.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hardirq.h |  4 +---
 arch/powerpc/kernel/irq.c          | 19 +++++++------------
 2 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index cd2d4be882aa..3147a2970125 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -9,6 +9,7 @@ typedef struct {
 	unsigned int timer_irqs;
 	unsigned int pmu_irqs;
 	unsigned int mce_exceptions;
+	unsigned int spurious_irqs;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
@@ -25,7 +26,4 @@ static inline void ack_bad_irq(unsigned int irq)
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu	arch_irq_stat_cpu
 
-extern u64 arch_irq_stat(void);
-#define arch_irq_stat		arch_irq_stat
-
 #endif /* _ASM_POWERPC_HARDIRQ_H */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 710505240f2f..9ae77e52f9d3 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -77,7 +77,6 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
 int __irq_offset_value;
-static int ppc_spurious_interrupts;
 
 #ifdef CONFIG_PPC32
 EXPORT_SYMBOL(__irq_offset_value);
@@ -201,6 +200,11 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
         seq_printf(p, "  Local timer interrupts\n");
 
+	seq_printf(p, "%*s: ", prec, "SPU");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
+	seq_printf(p, "  Spurious interrupts\n");
+
 	seq_printf(p, "%*s: ", prec, "CNT");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
@@ -211,8 +215,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
 	seq_printf(p, "  Machine check exceptions\n");
 
-	seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts);
-
 	return 0;
 }
 
@@ -282,13 +284,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 
 	sum += per_cpu(irq_stat, cpu).pmu_irqs;
 	sum += per_cpu(irq_stat, cpu).mce_exceptions;
-
-	return sum;
-}
-
-u64 arch_irq_stat(void)
-{
-	u64 sum = ppc_spurious_interrupts;
+	sum += per_cpu(irq_stat, cpu).spurious_irqs;
 
 	return sum;
 }
@@ -404,8 +400,7 @@ void do_IRQ(struct pt_regs *regs)
 	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
 		handle_one_irq(irq);
 	else if (irq != NO_IRQ_IGNORE)
-		/* That's not SMP safe ... but who cares ? */
-		ppc_spurious_interrupts++;
+		__get_cpu_var(irq_stat).spurious_irqs++;
 
 	irq_exit();
 	set_irq_regs(old_regs);
-- 
cgit v1.2.3


From 172ae2e7f8ff9053905a36672453a6d2ff95b182 Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Date: Mon, 8 Feb 2010 11:50:57 +0000
Subject: powerpc/booke: Introduce new CONFIG options for advanced debug
 registers

powerpc/booke: Introduce new CONFIG options for advanced debug registers

From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>

Introduce new config options to simplify the ifdefs pertaining to the
advanced debug registers for booke and 40x processors:

CONFIG_PPC_ADV_DEBUG_REGS - boolean: true for dac-based processors
CONFIG_PPC_ADV_DEBUG_IACS - number of IAC registers
CONFIG_PPC_ADV_DEBUG_DACS - number of DAC registers
CONFIG_PPC_ADV_DEBUG_DVCS - number of DVC registers
CONFIG_PPC_ADV_DEBUG_DAC_RANGE - DAC ranges supported

Beginning conservatively, since I only have the facilities to test 440
hardware.  I believe all 40x and booke platforms support at least 2 IAC
and 2 DAC registers.  For 440, 4 IAC and 2 DVC registers are enabled, as
well as the DAC ranges.

Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Acked-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/Kconfig            | 27 +++++++++++++++++++++++++++
 arch/powerpc/kernel/kgdb.c      |  2 +-
 arch/powerpc/kernel/kprobes.c   |  4 ++--
 arch/powerpc/kernel/process.c   | 10 +++++-----
 arch/powerpc/kernel/ptrace.c    | 18 +++++++-----------
 arch/powerpc/kernel/signal.c    |  2 +-
 arch/powerpc/kernel/signal_32.c |  8 ++++----
 arch/powerpc/kernel/traps.c     |  6 +++---
 8 files changed, 50 insertions(+), 27 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bf15e7b4cd3d..654bba5cf6b4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -240,6 +240,33 @@ config PPC_OF_PLATFORM_PCI
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config PPC_ADV_DEBUG_REGS
+	bool
+	depends on 40x || BOOKE
+	default y
+
+config PPC_ADV_DEBUG_IACS
+	int
+	depends on PPC_ADV_DEBUG_REGS
+	default 4 if 44x
+	default 2
+
+config PPC_ADV_DEBUG_DACS
+	int
+	depends on PPC_ADV_DEBUG_REGS
+	default 2
+
+config PPC_ADV_DEBUG_DVCS
+	int
+	depends on PPC_ADV_DEBUG_REGS
+	default 2 if 44x
+	default 0
+
+config PPC_ADV_DEBUG_DAC_RANGE
+	bool
+	depends on PPC_ADV_DEBUG_REGS && 44x
+	default y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index b6bd1eaa1c24..41bada0298c8 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -333,7 +333,7 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code,
 		atomic_set(&kgdb_cpu_doing_single_step, -1);
 		/* set the trace bit if we're stepping */
 		if (remcom_in_buffer[0] == 's') {
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 			mtspr(SPRN_DBCR0,
 			      mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
 			linux_regs->msr |= MSR_DE;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index c9329786073b..3fd1af902112 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -36,7 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
-#ifdef CONFIG_BOOKE
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 #define MSR_SINGLESTEP	(MSR_DE)
 #else
 #define MSR_SINGLESTEP	(MSR_SE)
@@ -110,7 +110,7 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 	 * like Decrementer or External Interrupt */
 	regs->msr &= ~MSR_EE;
 	regs->msr |= MSR_SINGLESTEP;
-#ifdef CONFIG_BOOKE
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	regs->msr &= ~MSR_CE;
 	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
 #endif
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7b816daf3eba..9be77e3936fb 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -258,7 +258,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address,
 		return;
 
 	/* Clear the DAC and struct entries.  One shot trigger */
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R | DBSR_DAC1W
 							| DBCR0_IDM));
 #endif
@@ -284,7 +284,7 @@ int set_dabr(unsigned long dabr)
 		return ppc_md.set_dabr(dabr);
 
 	/* XXX should we have a CPU_FTR_HAS_DABR ? */
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	mtspr(SPRN_DAC1, dabr);
 #elif defined(CONFIG_PPC_BOOK3S)
 	mtspr(SPRN_DABR, dabr);
@@ -371,7 +371,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 #endif /* CONFIG_SMP */
 
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/* If new thread DAC (HW breakpoint) is the same then leave it */
 	if (new->thread.dabr)
 		set_dabr(new->thread.dabr);
@@ -514,7 +514,7 @@ void show_regs(struct pt_regs * regs)
 	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
 	if (trap == 0x300 || trap == 0x600)
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
 #else
 		printk("DAR: "REG", DSISR: "REG"\n", regs->dar, regs->dsisr);
@@ -560,7 +560,7 @@ void flush_thread(void)
 		current->thread.dabr = 0;
 		set_dabr(0);
 
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W);
 #endif
 	}
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index ef149880c145..292c81432014 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -46,7 +46,7 @@
 /*
  * Set of msr bits that gdb can change on behalf of a process.
  */
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 #define MSR_DEBUGCHANGE	0
 #else
 #define MSR_DEBUGCHANGE	(MSR_SE | MSR_BE)
@@ -703,7 +703,7 @@ void user_enable_single_step(struct task_struct *task)
 	struct pt_regs *regs = task->thread.regs;
 
 	if (regs != NULL) {
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		task->thread.dbcr0 &= ~DBCR0_BT;
 		task->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC;
 		regs->msr |= MSR_DE;
@@ -720,7 +720,7 @@ void user_enable_block_step(struct task_struct *task)
 	struct pt_regs *regs = task->thread.regs;
 
 	if (regs != NULL) {
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		task->thread.dbcr0 &= ~DBCR0_IC;
 		task->thread.dbcr0 = DBCR0_IDM | DBCR0_BT;
 		regs->msr |= MSR_DE;
@@ -737,7 +737,7 @@ void user_disable_single_step(struct task_struct *task)
 	struct pt_regs *regs = task->thread.regs;
 
 	if (regs != NULL) {
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		/* If DAC don't clear DBCRO_IDM or MSR_DE */
 		if (task->thread.dabr)
 			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
@@ -745,9 +745,6 @@ void user_disable_single_step(struct task_struct *task)
 			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
 			regs->msr &= ~MSR_DE;
 		}
-#elif defined(CONFIG_40x)
-		task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
-		regs->msr &= ~MSR_DE;
 #else
 		regs->msr &= ~(MSR_SE | MSR_BE);
 #endif
@@ -769,7 +766,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	if ((data & ~0x7UL) >= TASK_SIZE)
 		return -EIO;
 
-#ifndef CONFIG_BOOKE
+#ifndef CONFIG_PPC_ADV_DEBUG_REGS
 
 	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
 	 *  It was assumed, on previous implementations, that 3 bits were
@@ -790,8 +787,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	/* Move contents to the DABR register */
 	task->thread.dabr = data;
 
-#endif
-#if defined(CONFIG_BOOKE)
+#else /* CONFIG_PPC_ADV_DEBUG_REGS */
 
 	/* As described above, it was assumed 3 bits were passed with the data
 	 *  address, but we will assume only the mode bits will be passed
@@ -824,7 +820,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 		task->thread.dbcr0 |= DBSR_DAC1W;
 
 	task->thread.regs->msr |= MSR_DE;
-#endif
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 00b5078da9a3..ad7044b5a2c7 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -147,7 +147,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 	 */
 	if (current->thread.dabr) {
 		set_dabr(current->thread.dabr);
-#if defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 		mtspr(SPRN_DBCR0, current->thread.dbcr0);
 #endif
 	}
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d670429a1608..e4883ae36277 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1078,7 +1078,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx,
 	int i;
 	unsigned char tmp;
 	unsigned long new_msr = regs->msr;
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	unsigned long new_dbcr0 = current->thread.dbcr0;
 #endif
 
@@ -1087,7 +1087,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx,
 			return -EFAULT;
 		switch (op.dbg_type) {
 		case SIG_DBG_SINGLE_STEPPING:
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 			if (op.dbg_value) {
 				new_msr |= MSR_DE;
 				new_dbcr0 |= (DBCR0_IDM | DBCR0_IC);
@@ -1103,7 +1103,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx,
 #endif
 			break;
 		case SIG_DBG_BRANCH_TRACING:
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 			return -EINVAL;
 #else
 			if (op.dbg_value)
@@ -1124,7 +1124,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx,
 	   failure is a problem, anyway, and it's very unlikely unless
 	   the user is really doing something wrong. */
 	regs->msr = new_msr;
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	current->thread.dbcr0 = new_dbcr0;
 #endif
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 895da29e7db8..4e293b75f951 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -299,7 +299,7 @@ static inline int check_io_access(struct pt_regs *regs)
 	return 0;
 }
 
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 /* On 4xx, the reason for the machine check or program exception
    is in the ESR. */
 #define get_reason(regs)	((regs)->dsisr)
@@ -1033,7 +1033,7 @@ void SoftwareEmulation(struct pt_regs *regs)
 }
 #endif /* CONFIG_8xx */
 
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 
 void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 {
@@ -1102,7 +1102,7 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 		do_dabr(regs, mfspr(SPRN_DAC1), debug_status);
 	}
 }
-#endif /* CONFIG_4xx || CONFIG_BOOKE */
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 
 #if !defined(CONFIG_TAU_INT)
 void TAUException(struct pt_regs *regs)
-- 
cgit v1.2.3


From 3162d92dfb79a0b5fc03380b8819fa5f870ebf1e Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Date: Mon, 8 Feb 2010 11:51:05 +0000
Subject: powerpc: Extended ptrace interface

powerpc: Extended ptrace interface

From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>

Based on patches originally written by Torez Smith.

Add a new extended ptrace interface so that user-space has a single
interface for powerpc, without having to know the specific layout
of the debug registers.

Implement:
PPC_PTRACE_GETHWDEBUGINFO
PPC_PTRACE_SETHWDEBUG
PPC_PTRACE_DELHWDEBUG

Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Acked-by: David Gibson <dwg@au1.ibm.com>
Cc: Torez Smith  <lnxtorez@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Sergio Durigan Junior <sergiodj@br.ibm.com>
Cc: Thiago Jung Bauermann <bauerman@br.ibm.com>
Cc: linuxppc-dev list <Linuxppc-dev@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 Documentation/powerpc/ptrace.txt  | 134 ++++++++++++++++++++++++++++++++++++++
 arch/powerpc/include/asm/ptrace.h |  77 ++++++++++++++++++++++
 arch/powerpc/kernel/ptrace.c      |  90 +++++++++++++++++++++++++
 3 files changed, 301 insertions(+)
 create mode 100644 Documentation/powerpc/ptrace.txt

(limited to 'arch/powerpc/kernel')

diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt
new file mode 100644
index 000000000000..f4a5499b7bc6
--- /dev/null
+++ b/Documentation/powerpc/ptrace.txt
@@ -0,0 +1,134 @@
+GDB intends to support the following hardware debug features of BookE
+processors:
+
+4 hardware breakpoints (IAC)
+2 hardware watchpoints (read, write and read-write) (DAC)
+2 value conditions for the hardware watchpoints (DVC)
+
+For that, we need to extend ptrace so that GDB can query and set these
+resources. Since we're extending, we're trying to create an interface
+that's extendable and that covers both BookE and server processors, so
+that GDB doesn't need to special-case each of them. We added the
+following 3 new ptrace requests.
+
+1. PTRACE_PPC_GETHWDEBUGINFO
+
+Query for GDB to discover the hardware debug features. The main info to
+be returned here is the minimum alignment for the hardware watchpoints.
+BookE processors don't have restrictions here, but server processors have
+an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
+adding special cases to GDB based on what it sees in AUXV.
+
+Since we're at it, we added other useful info that the kernel can return to
+GDB: this query will return the number of hardware breakpoints, hardware
+watchpoints and whether it supports a range of addresses and a condition.
+The query will fill the following structure provided by the requesting process:
+
+struct ppc_debug_info {
+       unit32_t version;
+       unit32_t num_instruction_bps;
+       unit32_t num_data_bps;
+       unit32_t num_condition_regs;
+       unit32_t data_bp_alignment;
+       unit32_t sizeof_condition; /* size of the DVC register */
+       uint64_t features; /* bitmask of the individual flags */
+};
+
+features will have bits indicating whether there is support for:
+
+#define PPC_DEBUG_FEATURE_INSN_BP_RANGE		0x1
+#define PPC_DEBUG_FEATURE_INSN_BP_MASK		0x2
+#define PPC_DEBUG_FEATURE_DATA_BP_RANGE		0x4
+#define PPC_DEBUG_FEATURE_DATA_BP_MASK		0x8
+
+2. PTRACE_SETHWDEBUG
+
+Sets a hardware breakpoint or watchpoint, according to the provided structure:
+
+struct ppc_hw_breakpoint {
+        uint32_t version;
+#define PPC_BREAKPOINT_TRIGGER_EXECUTE  0x1
+#define PPC_BREAKPOINT_TRIGGER_READ     0x2
+#define PPC_BREAKPOINT_TRIGGER_WRITE    0x4
+        uint32_t trigger_type;       /* only some combinations allowed */
+#define PPC_BREAKPOINT_MODE_EXACT               0x0
+#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE     0x1
+#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE     0x2
+#define PPC_BREAKPOINT_MODE_MASK                0x3
+        uint32_t addr_mode;          /* address match mode */
+
+#define PPC_BREAKPOINT_CONDITION_MODE   0x3
+#define PPC_BREAKPOINT_CONDITION_NONE   0x0
+#define PPC_BREAKPOINT_CONDITION_AND    0x1
+#define PPC_BREAKPOINT_CONDITION_EXACT  0x1	/* different name for the same thing as above */
+#define PPC_BREAKPOINT_CONDITION_OR     0x2
+#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
+#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000	/* byte enable bits */
+#define PPC_BREAKPOINT_CONDITION_BE(n)  (1<<((n)+16))
+        uint32_t condition_mode;     /* break/watchpoint condition flags */
+
+        uint64_t addr;
+        uint64_t addr2;
+        uint64_t condition_value;
+};
+
+A request specifies one event, not necessarily just one register to be set.
+For instance, if the request is for a watchpoint with a condition, both the
+DAC and DVC registers will be set in the same request.
+
+With this GDB can ask for all kinds of hardware breakpoints and watchpoints
+that the BookE supports. COMEFROM breakpoints available in server processors
+are not contemplated, but that is out of the scope of this work.
+
+ptrace will return an integer (handle) uniquely identifying the breakpoint or
+watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
+request to ask for its removal. Return -ENOSPC if the requested breakpoint
+can't be allocated on the registers.
+
+Some examples of using the structure to:
+
+- set a breakpoint in the first breakpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers on reads in the second watchpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers only with a specific value
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = (uint64_t) condition;
+
+- set a ranged hardware breakpoint
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) begin_range;
+  p.addr2           = (uint64_t) end_range;
+  p.condition_value = 0;
+
+3. PTRACE_DELHWDEBUG
+
+Takes an integer which identifies an existing breakpoint or watchpoint
+(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
+corresponding breakpoint or watchpoint..
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index cbd759e3cd78..b45108126562 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -24,6 +24,12 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <stdint.h>
+#endif
+
 #ifndef __ASSEMBLY__
 
 struct pt_regs {
@@ -294,4 +300,75 @@ extern void user_disable_single_step(struct task_struct *);
 
 #define PTRACE_SINGLEBLOCK	0x100	/* resume execution until next branch */
 
+#define PPC_PTRACE_GETHWDBGINFO	0x89
+#define PPC_PTRACE_SETHWDEBUG	0x88
+#define PPC_PTRACE_DELHWDEBUG	0x87
+
+#ifndef __ASSEMBLY__
+
+struct ppc_debug_info {
+	uint32_t version;		/* Only version 1 exists to date */
+	uint32_t num_instruction_bps;
+	uint32_t num_data_bps;
+	uint32_t num_condition_regs;
+	uint32_t data_bp_alignment;
+	uint32_t sizeof_condition;	/* size of the DVC register */
+	uint64_t features;
+};
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * features will have bits indication whether there is support for:
+ */
+#define PPC_DEBUG_FEATURE_INSN_BP_RANGE		0x0000000000000001
+#define PPC_DEBUG_FEATURE_INSN_BP_MASK		0x0000000000000002
+#define PPC_DEBUG_FEATURE_DATA_BP_RANGE		0x0000000000000004
+#define PPC_DEBUG_FEATURE_DATA_BP_MASK		0x0000000000000008
+
+#ifndef __ASSEMBLY__
+
+struct ppc_hw_breakpoint {
+	uint32_t version;		/* currently, version must be 1 */
+	uint32_t trigger_type;		/* only some combinations allowed */
+	uint32_t addr_mode;		/* address match mode */
+	uint32_t condition_mode;	/* break/watchpoint condition flags */
+	uint64_t addr;			/* break/watchpoint address */
+	uint64_t addr2;			/* range end or mask */
+	uint64_t condition_value;	/* contents of the DVC register */
+};
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Trigger Type
+ */
+#define PPC_BREAKPOINT_TRIGGER_EXECUTE	0x00000001
+#define PPC_BREAKPOINT_TRIGGER_READ	0x00000002
+#define PPC_BREAKPOINT_TRIGGER_WRITE	0x00000004
+#define PPC_BREAKPOINT_TRIGGER_RW	\
+	(PPC_BREAKPOINT_TRIGGER_READ | PPC_BREAKPOINT_TRIGGER_WRITE)
+
+/*
+ * Address Mode
+ */
+#define PPC_BREAKPOINT_MODE_EXACT		0x00000000
+#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE	0x00000001
+#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE	0x00000002
+#define PPC_BREAKPOINT_MODE_MASK		0x00000003
+
+/*
+ * Condition Mode
+ */
+#define PPC_BREAKPOINT_CONDITION_MODE	0x00000003
+#define PPC_BREAKPOINT_CONDITION_NONE	0x00000000
+#define PPC_BREAKPOINT_CONDITION_AND	0x00000001
+#define PPC_BREAKPOINT_CONDITION_EXACT	PPC_BREAKPOINT_CONDITION_AND
+#define PPC_BREAKPOINT_CONDITION_OR	0x00000002
+#define PPC_BREAKPOINT_CONDITION_AND_OR	0x00000003
+#define PPC_BREAKPOINT_CONDITION_BE_ALL	0x00ff0000
+#define PPC_BREAKPOINT_CONDITION_BE_SHIFT	16
+#define PPC_BREAKPOINT_CONDITION_BE(n)	\
+	(1<<((n)+PPC_BREAKPOINT_CONDITION_BE_SHIFT))
+
 #endif /* _ASM_POWERPC_PTRACE_H */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 292c81432014..8847bd618cec 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -835,6 +835,52 @@ void ptrace_disable(struct task_struct *child)
 	user_disable_single_step(child);
 }
 
+static long ppc_set_hwdebug(struct task_struct *child,
+		     struct ppc_hw_breakpoint *bp_info)
+{
+	/*
+	 * We currently support one data breakpoint
+	 */
+	if (((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0) ||
+	    ((bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0) ||
+	    (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_WRITE) ||
+	    (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) ||
+	    (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE))
+		return -EINVAL;
+
+	if (child->thread.dabr)
+		return -ENOSPC;
+
+	if ((unsigned long)bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	child->thread.dabr = (unsigned long)bp_info->addr;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	child->thread.dbcr0 = DBCR0_IDM;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+		child->thread.dbcr0 |= DBSR_DAC1R;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+		child->thread.dbcr0 |= DBSR_DAC1W;
+	child->thread.regs->msr |= MSR_DE;
+#endif
+	return 1;
+}
+
+static long ppc_del_hwdebug(struct task_struct *child, long addr, long data)
+{
+	if (data != 1)
+		return -EINVAL;
+	if (child->thread.dabr == 0)
+		return -ENOENT;
+
+	child->thread.dabr = 0;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	child->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W | DBCR0_IDM);
+	child->thread.regs->msr &= ~MSR_DE;
+#endif
+	return 0;
+}
+
 /*
  * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls,
  * we mark them as obsolete now, they will be removed in a future version
@@ -928,6 +974,50 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 	}
 
+	case PPC_PTRACE_GETHWDBGINFO: {
+		struct ppc_debug_info dbginfo;
+
+		dbginfo.version = 1;
+		dbginfo.num_instruction_bps = 0;
+		dbginfo.num_data_bps = 1;
+		dbginfo.num_condition_regs = 0;
+#ifdef CONFIG_PPC64
+		dbginfo.data_bp_alignment = 8;
+#else
+		dbginfo.data_bp_alignment = 4;
+#endif
+		dbginfo.sizeof_condition = 0;
+		dbginfo.features = 0;
+
+		if (!access_ok(VERIFY_WRITE, data,
+			       sizeof(struct ppc_debug_info)))
+			return -EFAULT;
+		ret = __copy_to_user((struct ppc_debug_info __user *)data,
+				     &dbginfo, sizeof(struct ppc_debug_info)) ?
+		      -EFAULT : 0;
+		break;
+	}
+
+	case PPC_PTRACE_SETHWDEBUG: {
+		struct ppc_hw_breakpoint bp_info;
+
+		if (!access_ok(VERIFY_READ, data,
+			       sizeof(struct ppc_hw_breakpoint)))
+			return -EFAULT;
+		ret = __copy_from_user(&bp_info,
+				       (struct ppc_hw_breakpoint __user *)data,
+				       sizeof(struct ppc_hw_breakpoint)) ?
+		      -EFAULT : 0;
+		if (!ret)
+			ret = ppc_set_hwdebug(child, &bp_info);
+		break;
+	}
+
+	case PPC_PTRACE_DELHWDEBUG: {
+		ret = ppc_del_hwdebug(child, addr, data);
+		break;
+	}
+
 	case PTRACE_GET_DEBUGREG: {
 		ret = -EINVAL;
 		/* We only support one DABR and no IABRS at the moment */
-- 
cgit v1.2.3


From 3bffb6529cf10d48a97ac0d6d789986894c25c37 Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Date: Mon, 8 Feb 2010 11:51:18 +0000
Subject: powerpc/booke: Add support for advanced debug registers

powerpc/booke: Add support for advanced debug registers

From: Dave Kleikamp <shaggy@linux.vnet.ibm.com>

Based on patches originally written by Torez Smith.

This patch defines context switch and trap related functionality
for BookE specific Debug Registers. It adds support to ptrace()
for setting and getting BookE related Debug Registers

Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Torez Smith  <lnxtorez@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Gibson <dwg@au1.ibm.com>
Cc: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Sergio Durigan Junior <sergiodj@br.ibm.com>
Cc: Thiago Jung Bauermann <bauerman@br.ibm.com>
Cc: linuxppc-dev list <Linuxppc-dev@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/system.h |   5 +
 arch/powerpc/kernel/process.c     | 110 ++++++++--
 arch/powerpc/kernel/ptrace.c      | 434 +++++++++++++++++++++++++++++++++++---
 arch/powerpc/kernel/signal.c      |   6 +-
 arch/powerpc/kernel/signal_32.c   |   8 +-
 arch/powerpc/kernel/traps.c       |  91 ++++++--
 6 files changed, 582 insertions(+), 72 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index aa59f5b794e8..a6297c67c3d6 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -112,8 +112,13 @@ static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
 #endif
 
 extern int set_dabr(unsigned long dabr);
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+extern void do_send_trap(struct pt_regs *regs, unsigned long address,
+			 unsigned long error_code, int signal_code, int brkpt);
+#else
 extern void do_dabr(struct pt_regs *regs, unsigned long address,
 		    unsigned long error_code);
+#endif
 extern void print_backtrace(unsigned long *);
 extern void show_regs(struct pt_regs * regs);
 extern void flush_instruction_cache(void);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9be77e3936fb..e4d71ced97ef 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -245,6 +245,24 @@ void discard_lazy_cpu_state(void)
 }
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+void do_send_trap(struct pt_regs *regs, unsigned long address,
+		  unsigned long error_code, int signal_code, int breakpt)
+{
+	siginfo_t info;
+
+	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+			11, SIGSEGV) == NOTIFY_STOP)
+		return;
+
+	/* Deliver the signal to userspace */
+	info.si_signo = SIGTRAP;
+	info.si_errno = breakpt;	/* breakpoint or watchpoint id */
+	info.si_code = signal_code;
+	info.si_addr = (void __user *)address;
+	force_sig_info(SIGTRAP, &info, current);
+}
+#else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
 void do_dabr(struct pt_regs *regs, unsigned long address,
 		    unsigned long error_code)
 {
@@ -257,12 +275,6 @@ void do_dabr(struct pt_regs *regs, unsigned long address,
 	if (debugger_dabr_match(regs))
 		return;
 
-	/* Clear the DAC and struct entries.  One shot trigger */
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R | DBSR_DAC1W
-							| DBCR0_IDM));
-#endif
-
 	/* Clear the DABR */
 	set_dabr(0);
 
@@ -273,9 +285,82 @@ void do_dabr(struct pt_regs *regs, unsigned long address,
 	info.si_addr = (void __user *)address;
 	force_sig_info(SIGTRAP, &info, current);
 }
+#endif	/* CONFIG_PPC_ADV_DEBUG_REGS */
 
 static DEFINE_PER_CPU(unsigned long, current_dabr);
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+/*
+ * Set the debug registers back to their default "safe" values.
+ */
+static void set_debug_reg_defaults(struct thread_struct *thread)
+{
+	thread->iac1 = thread->iac2 = 0;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	thread->iac3 = thread->iac4 = 0;
+#endif
+	thread->dac1 = thread->dac2 = 0;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+	thread->dvc1 = thread->dvc2 = 0;
+#endif
+	thread->dbcr0 = 0;
+#ifdef CONFIG_BOOKE
+	/*
+	 * Force User/Supervisor bits to b11 (user-only MSR[PR]=1)
+	 */
+	thread->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US |	\
+			DBCR1_IAC3US | DBCR1_IAC4US;
+	/*
+	 * Force Data Address Compare User/Supervisor bits to be User-only
+	 * (0b11 MSR[PR]=1) and set all other bits in DBCR2 register to be 0.
+	 */
+	thread->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US;
+#else
+	thread->dbcr1 = 0;
+#endif
+}
+
+static void prime_debug_regs(struct thread_struct *thread)
+{
+	mtspr(SPRN_IAC1, thread->iac1);
+	mtspr(SPRN_IAC2, thread->iac2);
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	mtspr(SPRN_IAC3, thread->iac3);
+	mtspr(SPRN_IAC4, thread->iac4);
+#endif
+	mtspr(SPRN_DAC1, thread->dac1);
+	mtspr(SPRN_DAC2, thread->dac2);
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+	mtspr(SPRN_DVC1, thread->dvc1);
+	mtspr(SPRN_DVC2, thread->dvc2);
+#endif
+	mtspr(SPRN_DBCR0, thread->dbcr0);
+	mtspr(SPRN_DBCR1, thread->dbcr1);
+#ifdef CONFIG_BOOKE
+	mtspr(SPRN_DBCR2, thread->dbcr2);
+#endif
+}
+/*
+ * Unless neither the old or new thread are making use of the
+ * debug registers, set the debug registers from the values
+ * stored in the new thread.
+ */
+static void switch_booke_debug_regs(struct thread_struct *new_thread)
+{
+	if ((current->thread.dbcr0 & DBCR0_IDM)
+		|| (new_thread->dbcr0 & DBCR0_IDM))
+			prime_debug_regs(new_thread);
+}
+#else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
+static void set_debug_reg_defaults(struct thread_struct *thread)
+{
+	if (thread->dabr) {
+		thread->dabr = 0;
+		set_dabr(0);
+	}
+}
+#endif	/* CONFIG_PPC_ADV_DEBUG_REGS */
+
 int set_dabr(unsigned long dabr)
 {
 	__get_cpu_var(current_dabr) = dabr;
@@ -372,9 +457,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	/* If new thread DAC (HW breakpoint) is the same then leave it */
-	if (new->thread.dabr)
-		set_dabr(new->thread.dabr);
+	switch_booke_debug_regs(&new->thread);
 #else
 	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
 		set_dabr(new->thread.dabr);
@@ -556,14 +639,7 @@ void flush_thread(void)
 {
 	discard_lazy_cpu_state();
 
-	if (current->thread.dabr) {
-		current->thread.dabr = 0;
-		set_dabr(0);
-
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W);
-#endif
-	}
+	set_debug_reg_defaults(&current->thread);
 }
 
 void
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 8847bd618cec..d9b05866615f 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -738,11 +738,22 @@ void user_disable_single_step(struct task_struct *task)
 
 	if (regs != NULL) {
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		/* If DAC don't clear DBCRO_IDM or MSR_DE */
-		if (task->thread.dabr)
-			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
-		else {
-			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
+		/*
+		 * The logic to disable single stepping should be as
+		 * simple as turning off the Instruction Complete flag.
+		 * And, after doing so, if all debug flags are off, turn
+		 * off DBCR0(IDM) and MSR(DE) .... Torez
+		 */
+		task->thread.dbcr0 &= ~DBCR0_IC;
+		/*
+		 * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
+		 */
+		if (!DBCR_ACTIVE_EVENTS(task->thread.dbcr0,
+					task->thread.dbcr1)) {
+			/*
+			 * All debug events were off.....
+			 */
+			task->thread.dbcr0 &= ~DBCR0_IDM;
 			regs->msr &= ~MSR_DE;
 		}
 #else
@@ -767,7 +778,6 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 		return -EIO;
 
 #ifndef CONFIG_PPC_ADV_DEBUG_REGS
-
 	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
 	 *  It was assumed, on previous implementations, that 3 bits were
 	 *  passed together with the data address, fitting the design of the
@@ -786,20 +796,22 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 
 	/* Move contents to the DABR register */
 	task->thread.dabr = data;
-
 #else /* CONFIG_PPC_ADV_DEBUG_REGS */
-
 	/* As described above, it was assumed 3 bits were passed with the data
 	 *  address, but we will assume only the mode bits will be passed
 	 *  as to not cause alignment restrictions for DAC-based processors.
 	 */
 
 	/* DAC's hold the whole address without any mode flags */
-	task->thread.dabr = data & ~0x3UL;
-
-	if (task->thread.dabr == 0) {
-		task->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W | DBCR0_IDM);
-		task->thread.regs->msr &= ~MSR_DE;
+	task->thread.dac1 = data & ~0x3UL;
+
+	if (task->thread.dac1 == 0) {
+		dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+		if (!DBCR_ACTIVE_EVENTS(task->thread.dbcr0,
+					task->thread.dbcr1)) {
+			task->thread.regs->msr &= ~MSR_DE;
+			task->thread.dbcr0 &= ~DBCR0_IDM;
+		}
 		return 0;
 	}
 
@@ -810,15 +822,15 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 
 	/* Set the Internal Debugging flag (IDM bit 1) for the DBCR0
 	   register */
-	task->thread.dbcr0 = DBCR0_IDM;
+	task->thread.dbcr0 |= DBCR0_IDM;
 
 	/* Check for write and read flags and set DBCR0
 	   accordingly */
+	dbcr_dac(task) &= ~(DBCR_DAC1R|DBCR_DAC1W);
 	if (data & 0x1UL)
-		task->thread.dbcr0 |= DBSR_DAC1R;
+		dbcr_dac(task) |= DBCR_DAC1R;
 	if (data & 0x2UL)
-		task->thread.dbcr0 |= DBSR_DAC1W;
-
+		dbcr_dac(task) |= DBCR_DAC1W;
 	task->thread.regs->msr |= MSR_DE;
 #endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 	return 0;
@@ -835,11 +847,344 @@ void ptrace_disable(struct task_struct *child)
 	user_disable_single_step(child);
 }
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+static long set_intruction_bp(struct task_struct *child,
+			      struct ppc_hw_breakpoint *bp_info)
+{
+	int slot;
+	int slot1_in_use = ((child->thread.dbcr0 & DBCR0_IAC1) != 0);
+	int slot2_in_use = ((child->thread.dbcr0 & DBCR0_IAC2) != 0);
+	int slot3_in_use = ((child->thread.dbcr0 & DBCR0_IAC3) != 0);
+	int slot4_in_use = ((child->thread.dbcr0 & DBCR0_IAC4) != 0);
+
+	if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+		slot2_in_use = 1;
+	if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+		slot4_in_use = 1;
+
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+
+		/* Make sure range is valid. */
+		if (bp_info->addr2 >= TASK_SIZE)
+			return -EIO;
+
+		/* We need a pair of IAC regsisters */
+		if ((!slot1_in_use) && (!slot2_in_use)) {
+			slot = 1;
+			child->thread.iac1 = bp_info->addr;
+			child->thread.iac2 = bp_info->addr2;
+			child->thread.dbcr0 |= DBCR0_IAC1;
+			if (bp_info->addr_mode ==
+					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+				dbcr_iac_range(child) |= DBCR_IAC12X;
+			else
+				dbcr_iac_range(child) |= DBCR_IAC12I;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+		} else if ((!slot3_in_use) && (!slot4_in_use)) {
+			slot = 3;
+			child->thread.iac3 = bp_info->addr;
+			child->thread.iac4 = bp_info->addr2;
+			child->thread.dbcr0 |= DBCR0_IAC3;
+			if (bp_info->addr_mode ==
+					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+				dbcr_iac_range(child) |= DBCR_IAC34X;
+			else
+				dbcr_iac_range(child) |= DBCR_IAC34I;
+#endif
+		} else
+			return -ENOSPC;
+	} else {
+		/* We only need one.  If possible leave a pair free in
+		 * case a range is needed later
+		 */
+		if (!slot1_in_use) {
+			/*
+			 * Don't use iac1 if iac1-iac2 are free and either
+			 * iac3 or iac4 (but not both) are free
+			 */
+			if (slot2_in_use || (slot3_in_use == slot4_in_use)) {
+				slot = 1;
+				child->thread.iac1 = bp_info->addr;
+				child->thread.dbcr0 |= DBCR0_IAC1;
+				goto out;
+			}
+		}
+		if (!slot2_in_use) {
+			slot = 2;
+			child->thread.iac2 = bp_info->addr;
+			child->thread.dbcr0 |= DBCR0_IAC2;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+		} else if (!slot3_in_use) {
+			slot = 3;
+			child->thread.iac3 = bp_info->addr;
+			child->thread.dbcr0 |= DBCR0_IAC3;
+		} else if (!slot4_in_use) {
+			slot = 4;
+			child->thread.iac4 = bp_info->addr;
+			child->thread.dbcr0 |= DBCR0_IAC4;
+#endif
+		} else
+			return -ENOSPC;
+	}
+out:
+	child->thread.dbcr0 |= DBCR0_IDM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return slot;
+}
+
+static int del_instruction_bp(struct task_struct *child, int slot)
+{
+	switch (slot) {
+	case 1:
+		if (child->thread.iac1 == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
+			/* address range - clear slots 1 & 2 */
+			child->thread.iac2 = 0;
+			dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
+		}
+		child->thread.iac1 = 0;
+		child->thread.dbcr0 &= ~DBCR0_IAC1;
+		break;
+	case 2:
+		if (child->thread.iac2 == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+			/* used in a range */
+			return -EINVAL;
+		child->thread.iac2 = 0;
+		child->thread.dbcr0 &= ~DBCR0_IAC2;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case 3:
+		if (child->thread.iac3 == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
+			/* address range - clear slots 3 & 4 */
+			child->thread.iac4 = 0;
+			dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
+		}
+		child->thread.iac3 = 0;
+		child->thread.dbcr0 &= ~DBCR0_IAC3;
+		break;
+	case 4:
+		if (child->thread.iac4 == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+			/* Used in a range */
+			return -EINVAL;
+		child->thread.iac4 = 0;
+		child->thread.dbcr0 &= ~DBCR0_IAC4;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+	int byte_enable =
+		(bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
+		& 0xf;
+	int condition_mode =
+		bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
+	int slot;
+
+	if (byte_enable && (condition_mode == 0))
+		return -EINVAL;
+
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
+		slot = 1;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+			dbcr_dac(child) |= DBCR_DAC1R;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+			dbcr_dac(child) |= DBCR_DAC1W;
+		child->thread.dac1 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		if (byte_enable) {
+			child->thread.dvc1 =
+				(unsigned long)bp_info->condition_value;
+			child->thread.dbcr2 |=
+				((byte_enable << DBCR2_DVC1BE_SHIFT) |
+				 (condition_mode << DBCR2_DVC1M_SHIFT));
+		}
+#endif
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+	} else if (child->thread.dbcr2 & DBCR2_DAC12MODE) {
+		/* Both dac1 and dac2 are part of a range */
+		return -ENOSPC;
+#endif
+	} else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
+		slot = 2;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+			dbcr_dac(child) |= DBCR_DAC2R;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+			dbcr_dac(child) |= DBCR_DAC2W;
+		child->thread.dac2 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		if (byte_enable) {
+			child->thread.dvc2 =
+				(unsigned long)bp_info->condition_value;
+			child->thread.dbcr2 |=
+				((byte_enable << DBCR2_DVC2BE_SHIFT) |
+				 (condition_mode << DBCR2_DVC2M_SHIFT));
+		}
+#endif
+	} else
+		return -ENOSPC;
+	child->thread.dbcr0 |= DBCR0_IDM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return slot + 4;
+}
+
+static int del_dac(struct task_struct *child, int slot)
+{
+	if (slot == 1) {
+		if (child->thread.dac1 == 0)
+			return -ENOENT;
+
+		child->thread.dac1 = 0;
+		dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		if (child->thread.dbcr2 & DBCR2_DAC12MODE) {
+			child->thread.dac2 = 0;
+			child->thread.dbcr2 &= ~DBCR2_DAC12MODE;
+		}
+		child->thread.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		child->thread.dvc1 = 0;
+#endif
+	} else if (slot == 2) {
+		if (child->thread.dac1 == 0)
+			return -ENOENT;
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		if (child->thread.dbcr2 & DBCR2_DAC12MODE)
+			/* Part of a range */
+			return -EINVAL;
+		child->thread.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		child->thread.dvc2 = 0;
+#endif
+		child->thread.dac2 = 0;
+		dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+static int set_dac_range(struct task_struct *child,
+			 struct ppc_hw_breakpoint *bp_info)
+{
+	int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
+
+	/* We don't allow range watchpoints to be used with DVC */
+	if (bp_info->condition_mode)
+		return -EINVAL;
+
+	/*
+	 * Best effort to verify the address range.  The user/supervisor bits
+	 * prevent trapping in kernel space, but let's fail on an obvious bad
+	 * range.  The simple test on the mask is not fool-proof, and any
+	 * exclusive range will spill over into kernel space.
+	 */
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+	if (mode == PPC_BREAKPOINT_MODE_MASK) {
+		/*
+		 * dac2 is a bitmask.  Don't allow a mask that makes a
+		 * kernel space address from a valid dac1 value
+		 */
+		if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
+			return -EIO;
+	} else {
+		/*
+		 * For range breakpoints, addr2 must also be a valid address
+		 */
+		if (bp_info->addr2 >= TASK_SIZE)
+			return -EIO;
+	}
+
+	if (child->thread.dbcr0 &
+	    (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
+		return -ENOSPC;
+
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+		child->thread.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+		child->thread.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
+	child->thread.dac1 = bp_info->addr;
+	child->thread.dac2 = bp_info->addr2;
+	if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+		child->thread.dbcr2  |= DBCR2_DAC12M;
+	else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+		child->thread.dbcr2  |= DBCR2_DAC12MX;
+	else	/* PPC_BREAKPOINT_MODE_MASK */
+		child->thread.dbcr2  |= DBCR2_DAC12MM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return 5;
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
+
 static long ppc_set_hwdebug(struct task_struct *child,
 		     struct ppc_hw_breakpoint *bp_info)
 {
+	if (bp_info->version != 1)
+		return -ENOTSUPP;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	/*
+	 * Check for invalid flags and combinations
+	 */
+	if ((bp_info->trigger_type == 0) ||
+	    (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
+				       PPC_BREAKPOINT_TRIGGER_RW)) ||
+	    (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
+	    (bp_info->condition_mode &
+	     ~(PPC_BREAKPOINT_CONDITION_MODE |
+	       PPC_BREAKPOINT_CONDITION_BE_ALL)))
+		return -EINVAL;
+#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
+	if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+		return -EINVAL;
+#endif
+
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
+		if ((bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE) ||
+		    (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE))
+			return -EINVAL;
+		return set_intruction_bp(child, bp_info);
+	}
+	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+		return set_dac(child, bp_info);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+	return set_dac_range(child, bp_info);
+#else
+	return -EINVAL;
+#endif
+#else /* !CONFIG_PPC_ADV_DEBUG_DVCS */
 	/*
-	 * We currently support one data breakpoint
+	 * We only support one data breakpoint
 	 */
 	if (((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0) ||
 	    ((bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0) ||
@@ -855,30 +1200,39 @@ static long ppc_set_hwdebug(struct task_struct *child,
 		return -EIO;
 
 	child->thread.dabr = (unsigned long)bp_info->addr;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	child->thread.dbcr0 = DBCR0_IDM;
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
-		child->thread.dbcr0 |= DBSR_DAC1R;
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
-		child->thread.dbcr0 |= DBSR_DAC1W;
-	child->thread.regs->msr |= MSR_DE;
-#endif
+
 	return 1;
+#endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */
 }
 
 static long ppc_del_hwdebug(struct task_struct *child, long addr, long data)
 {
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	int rc;
+
+	if (data <= 4)
+		rc = del_instruction_bp(child, (int)data);
+	else
+		rc = del_dac(child, (int)data - 4);
+
+	if (!rc) {
+		if (!DBCR_ACTIVE_EVENTS(child->thread.dbcr0,
+					child->thread.dbcr1)) {
+			child->thread.dbcr0 &= ~DBCR0_IDM;
+			child->thread.regs->msr &= ~MSR_DE;
+		}
+	}
+	return rc;
+#else
 	if (data != 1)
 		return -EINVAL;
 	if (child->thread.dabr == 0)
 		return -ENOENT;
 
 	child->thread.dabr = 0;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	child->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W | DBCR0_IDM);
-	child->thread.regs->msr &= ~MSR_DE;
-#endif
+
 	return 0;
+#endif
 }
 
 /*
@@ -978,6 +1332,20 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		struct ppc_debug_info dbginfo;
 
 		dbginfo.version = 1;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+		dbginfo.num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
+		dbginfo.num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
+		dbginfo.num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
+		dbginfo.data_bp_alignment = 4;
+		dbginfo.sizeof_condition = 4;
+		dbginfo.features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
+				   PPC_DEBUG_FEATURE_INSN_BP_MASK;
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		dbginfo.features |=
+				   PPC_DEBUG_FEATURE_DATA_BP_RANGE |
+				   PPC_DEBUG_FEATURE_DATA_BP_MASK;
+#endif
+#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
 		dbginfo.num_instruction_bps = 0;
 		dbginfo.num_data_bps = 1;
 		dbginfo.num_condition_regs = 0;
@@ -988,6 +1356,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 #endif
 		dbginfo.sizeof_condition = 0;
 		dbginfo.features = 0;
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 
 		if (!access_ok(VERIFY_WRITE, data,
 			       sizeof(struct ppc_debug_info)))
@@ -1023,8 +1392,13 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		/* We only support one DABR and no IABRS at the moment */
 		if (addr > 0)
 			break;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+		ret = put_user(child->thread.dac1,
+			       (unsigned long __user *)data);
+#else
 		ret = put_user(child->thread.dabr,
 			       (unsigned long __user *)data);
+#endif
 		break;
 	}
 
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index ad7044b5a2c7..a0afb555a7c9 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -140,17 +140,15 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 		return 0;               /* no signals delivered */
 	}
 
+#ifndef CONFIG_PPC_ADV_DEBUG_REGS
         /*
 	 * Reenable the DABR before delivering the signal to
 	 * user space. The DABR will have been cleared if it
 	 * triggered inside the kernel.
 	 */
-	if (current->thread.dabr) {
+	if (current->thread.dabr)
 		set_dabr(current->thread.dabr);
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		mtspr(SPRN_DBCR0, current->thread.dbcr0);
 #endif
-	}
 
 	if (is32) {
         	if (ka.sa.sa_flags & SA_SIGINFO)
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index e4883ae36277..266610119f66 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1092,8 +1092,12 @@ int sys_debug_setcontext(struct ucontext __user *ctx,
 				new_msr |= MSR_DE;
 				new_dbcr0 |= (DBCR0_IDM | DBCR0_IC);
 			} else {
-				new_msr &= ~MSR_DE;
-				new_dbcr0 &= ~(DBCR0_IDM | DBCR0_IC);
+				new_dbcr0 &= ~DBCR0_IC;
+				if (!DBCR_ACTIVE_EVENTS(new_dbcr0,
+						current->thread.dbcr1)) {
+					new_msr &= ~MSR_DE;
+					new_dbcr0 &= ~DBCR0_IDM;
+				}
 			}
 #else
 			if (op.dbg_value)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4e293b75f951..987437e04e61 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1034,9 +1034,68 @@ void SoftwareEmulation(struct pt_regs *regs)
 #endif /* CONFIG_8xx */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
+static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
+{
+	int changed = 0;
+	/*
+	 * Determine the cause of the debug event, clear the
+	 * event flags and send a trap to the handler. Torez
+	 */
+	if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
+		dbcr_dac(current) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		current->thread.dbcr2 &= ~DBCR2_DAC12MODE;
+#endif
+		do_send_trap(regs, mfspr(SPRN_DAC1), debug_status, TRAP_HWBKPT,
+			     5);
+		changed |= 0x01;
+	}  else if (debug_status & (DBSR_DAC2R | DBSR_DAC2W)) {
+		dbcr_dac(current) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+		do_send_trap(regs, mfspr(SPRN_DAC2), debug_status, TRAP_HWBKPT,
+			     6);
+		changed |= 0x01;
+	}  else if (debug_status & DBSR_IAC1) {
+		current->thread.dbcr0 &= ~DBCR0_IAC1;
+		dbcr_iac_range(current) &= ~DBCR_IAC12MODE;
+		do_send_trap(regs, mfspr(SPRN_IAC1), debug_status, TRAP_HWBKPT,
+			     1);
+		changed |= 0x01;
+	}  else if (debug_status & DBSR_IAC2) {
+		current->thread.dbcr0 &= ~DBCR0_IAC2;
+		do_send_trap(regs, mfspr(SPRN_IAC2), debug_status, TRAP_HWBKPT,
+			     2);
+		changed |= 0x01;
+	}  else if (debug_status & DBSR_IAC3) {
+		current->thread.dbcr0 &= ~DBCR0_IAC3;
+		dbcr_iac_range(current) &= ~DBCR_IAC34MODE;
+		do_send_trap(regs, mfspr(SPRN_IAC3), debug_status, TRAP_HWBKPT,
+			     3);
+		changed |= 0x01;
+	}  else if (debug_status & DBSR_IAC4) {
+		current->thread.dbcr0 &= ~DBCR0_IAC4;
+		do_send_trap(regs, mfspr(SPRN_IAC4), debug_status, TRAP_HWBKPT,
+			     4);
+		changed |= 0x01;
+	}
+	/*
+	 * At the point this routine was called, the MSR(DE) was turned off.
+	 * Check all other debug flags and see if that bit needs to be turned
+	 * back on or not.
+	 */
+	if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0, current->thread.dbcr1))
+		regs->msr |= MSR_DE;
+	else
+		/* Make sure the IDM flag is off */
+		current->thread.dbcr0 &= ~DBCR0_IDM;
+
+	if (changed & 0x01)
+		mtspr(SPRN_DBCR0, current->thread.dbcr0);
+}
 
 void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 {
+	current->thread.dbsr = debug_status;
+
 	/* Hack alert: On BookE, Branch Taken stops on the branch itself, while
 	 * on server, it stops on the target of the branch. In order to simulate
 	 * the server behaviour, we thus restart right away with a single step
@@ -1080,27 +1139,21 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 		if (debugger_sstep(regs))
 			return;
 
-		if (user_mode(regs))
-			current->thread.dbcr0 &= ~(DBCR0_IC);
-
-		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
-	} else if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
-		regs->msr &= ~MSR_DE;
-
 		if (user_mode(regs)) {
-			current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W |
-								DBCR0_IDM);
-		} else {
-			/* Disable DAC interupts */
-			mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R |
-						DBSR_DAC1W | DBCR0_IDM));
-
-			/* Clear the DAC event */
-			mtspr(SPRN_DBSR, (DBSR_DAC1R | DBSR_DAC1W));
+			current->thread.dbcr0 &= ~DBCR0_IC;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+			if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0,
+					       current->thread.dbcr1))
+				regs->msr |= MSR_DE;
+			else
+				/* Make sure the IDM bit is off */
+				current->thread.dbcr0 &= ~DBCR0_IDM;
+#endif
 		}
-		/* Setup and send the trap to the handler */
-		do_dabr(regs, mfspr(SPRN_DAC1), debug_status);
-	}
+
+		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+	} else
+		handle_debug(regs, debug_status);
 }
 #endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 
-- 
cgit v1.2.3


From 51adc548cb0b2441ee9d4c428a84b77021f4d3fa Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 15 Jan 2010 17:41:35 +0100
Subject: powerpc/fsl-booke: replace a hardcoded constant

24 is offset between the opcode past bl and past rfi. This makes it more
obvious.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/kernel/head_fsl_booke.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 7f4bd7f3b6af..25793bb0e782 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -214,11 +214,11 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	bl	1f		/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
-	addi	r7,r7,24
+	addi	r7,r7,(2f - 1b)
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r6
 	rfi
-
+2:
 /* 4. Clear out PIDs & Search info */
 	li	r6,0
 	mtspr   SPRN_MAS6,r6
-- 
cgit v1.2.3


From f95e085b2531c86262b97a081eb0d1cf793606d3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 18 Feb 2010 02:22:24 +0000
Subject: powerpc: Convert big_irq_lock to raw_spinlock

big_irq_lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/irq.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9ae77e52f9d3..64f6f2031c22 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -520,7 +520,7 @@ void do_softirq(void)
  */
 
 static LIST_HEAD(irq_hosts);
-static DEFINE_SPINLOCK(irq_big_lock);
+static DEFINE_RAW_SPINLOCK(irq_big_lock);
 static unsigned int revmap_trees_allocated;
 static DEFINE_MUTEX(revmap_trees_mutex);
 struct irq_map_entry irq_map[NR_IRQS];
@@ -566,14 +566,14 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 	if (host->ops->match == NULL)
 		host->ops->match = default_irq_host_match;
 
-	spin_lock_irqsave(&irq_big_lock, flags);
+	raw_spin_lock_irqsave(&irq_big_lock, flags);
 
 	/* If it's a legacy controller, check for duplicates and
 	 * mark it as allocated (we use irq 0 host pointer for that
 	 */
 	if (revmap_type == IRQ_HOST_MAP_LEGACY) {
 		if (irq_map[0].host != NULL) {
-			spin_unlock_irqrestore(&irq_big_lock, flags);
+			raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 			/* If we are early boot, we can't free the structure,
 			 * too bad...
 			 * this will be fixed once slab is made available early
@@ -587,7 +587,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 	}
 
 	list_add(&host->link, &irq_hosts);
-	spin_unlock_irqrestore(&irq_big_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 
 	/* Additional setups per revmap type */
 	switch(revmap_type) {
@@ -638,13 +638,13 @@ struct irq_host *irq_find_host(struct device_node *node)
 	 * the absence of a device node. This isn't a problem so far
 	 * yet though...
 	 */
-	spin_lock_irqsave(&irq_big_lock, flags);
+	raw_spin_lock_irqsave(&irq_big_lock, flags);
 	list_for_each_entry(h, &irq_hosts, link)
 		if (h->ops->match(h, node)) {
 			found = h;
 			break;
 		}
-	spin_unlock_irqrestore(&irq_big_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 	return found;
 }
 EXPORT_SYMBOL_GPL(irq_find_host);
@@ -1013,7 +1013,7 @@ unsigned int irq_alloc_virt(struct irq_host *host,
 	if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS))
 		return NO_IRQ;
 
-	spin_lock_irqsave(&irq_big_lock, flags);
+	raw_spin_lock_irqsave(&irq_big_lock, flags);
 
 	/* Use hint for 1 interrupt if any */
 	if (count == 1 && hint >= NUM_ISA_INTERRUPTS &&
@@ -1037,7 +1037,7 @@ unsigned int irq_alloc_virt(struct irq_host *host,
 		}
 	}
 	if (found == NO_IRQ) {
-		spin_unlock_irqrestore(&irq_big_lock, flags);
+		raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 		return NO_IRQ;
 	}
  hint_found:
@@ -1046,7 +1046,7 @@ unsigned int irq_alloc_virt(struct irq_host *host,
 		smp_wmb();
 		irq_map[i].host = host;
 	}
-	spin_unlock_irqrestore(&irq_big_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 	return found;
 }
 
@@ -1058,7 +1058,7 @@ void irq_free_virt(unsigned int virq, unsigned int count)
 	WARN_ON (virq < NUM_ISA_INTERRUPTS);
 	WARN_ON (count == 0 || (virq + count) > irq_virq_count);
 
-	spin_lock_irqsave(&irq_big_lock, flags);
+	raw_spin_lock_irqsave(&irq_big_lock, flags);
 	for (i = virq; i < (virq + count); i++) {
 		struct irq_host *host;
 
@@ -1071,7 +1071,7 @@ void irq_free_virt(unsigned int virq, unsigned int count)
 		smp_wmb();
 		irq_map[i].host = NULL;
 	}
-	spin_unlock_irqrestore(&irq_big_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_big_lock, flags);
 }
 
 int arch_early_irq_init(void)
-- 
cgit v1.2.3


From b8f87782e82709d613c5d2a165d1443478e57c00 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 18 Feb 2010 02:22:31 +0000
Subject: powerpc: Convert die.lock to raw_spinlock

die.lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/traps.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 987437e04e61..696626a2e835 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -102,11 +102,11 @@ static inline void pmac_backlight_unblank(void) { }
 int die(const char *str, struct pt_regs *regs, long err)
 {
 	static struct {
-		spinlock_t lock;
+		raw_spinlock_t lock;
 		u32 lock_owner;
 		int lock_owner_depth;
 	} die = {
-		.lock =			__SPIN_LOCK_UNLOCKED(die.lock),
+		.lock =			__RAW_SPIN_LOCK_UNLOCKED(die.lock),
 		.lock_owner =		-1,
 		.lock_owner_depth =	0
 	};
@@ -120,7 +120,7 @@ int die(const char *str, struct pt_regs *regs, long err)
 
 	if (die.lock_owner != raw_smp_processor_id()) {
 		console_verbose();
-		spin_lock_irqsave(&die.lock, flags);
+		raw_spin_lock_irqsave(&die.lock, flags);
 		die.lock_owner = smp_processor_id();
 		die.lock_owner_depth = 0;
 		bust_spinlocks(1);
@@ -160,7 +160,7 @@ int die(const char *str, struct pt_regs *regs, long err)
 	bust_spinlocks(0);
 	die.lock_owner = -1;
 	add_taint(TAINT_DIE);
-	spin_unlock_irqrestore(&die.lock, flags);
+	raw_spin_unlock_irqrestore(&die.lock, flags);
 
 	if (kexec_should_crash(current) ||
 		kexec_sr_activated(smp_processor_id()))
-- 
cgit v1.2.3


From 071c06cb570d38efe23a124e885f2f3e643a9206 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 18 Feb 2010 02:22:27 +0000
Subject: powerpc: Convert pmc_owner_lock to raw_spinlock

pmc_owner_lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pmc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index 0516e2d3e02e..461499b43cff 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -37,7 +37,7 @@ static void dummy_perf(struct pt_regs *regs)
 }
 
 
-static DEFINE_SPINLOCK(pmc_owner_lock);
+static DEFINE_RAW_SPINLOCK(pmc_owner_lock);
 static void *pmc_owner_caller; /* mostly for debugging */
 perf_irq_t perf_irq = dummy_perf;
 
@@ -45,7 +45,7 @@ int reserve_pmc_hardware(perf_irq_t new_perf_irq)
 {
 	int err = 0;
 
-	spin_lock(&pmc_owner_lock);
+	raw_spin_lock(&pmc_owner_lock);
 
 	if (pmc_owner_caller) {
 		printk(KERN_WARNING "reserve_pmc_hardware: "
@@ -59,21 +59,21 @@ int reserve_pmc_hardware(perf_irq_t new_perf_irq)
 	perf_irq = new_perf_irq ? new_perf_irq : dummy_perf;
 
  out:
-	spin_unlock(&pmc_owner_lock);
+	raw_spin_unlock(&pmc_owner_lock);
 	return err;
 }
 EXPORT_SYMBOL_GPL(reserve_pmc_hardware);
 
 void release_pmc_hardware(void)
 {
-	spin_lock(&pmc_owner_lock);
+	raw_spin_lock(&pmc_owner_lock);
 
 	WARN_ON(! pmc_owner_caller);
 
 	pmc_owner_caller = NULL;
 	perf_irq = dummy_perf;
 
-	spin_unlock(&pmc_owner_lock);
+	raw_spin_unlock(&pmc_owner_lock);
 }
 EXPORT_SYMBOL_GPL(release_pmc_hardware);
 
-- 
cgit v1.2.3