* [PATCH 3/8] pseries: phyp dump: use sysfs to release reserved mem
From: Manish Ahuja @ 2008-01-22 19:33 UTC (permalink / raw)
To: ppc-dev, paulus, linasvepstas; +Cc: lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Check to see if there actually is data from a previously
crashed kernel waiting. If so, Allow user-sapce tools to
grab the data (by reading /proc/kcore). When user-space
finishes dumping a section, it must release that memory
by writing to sysfs. For example,
echo "0x40000000 0x10000000" > /sys/kernel/release_region
will release 256MB starting at the 1GB. The released memory
becomes free for general use.
Signed-off-by: Linas Vepstas <linasvepstas@gmail.com>
------
arch/powerpc/platforms/pseries/phyp_dump.c | 102 +++++++++++++++++++++++++++--
1 file changed, 96 insertions(+), 6 deletions(-)
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-18 07:37:33.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-18 22:43:00.000000000 -0600
@@ -12,17 +12,24 @@
*/
#include <linux/init.h>
+#include <linux/kobject.h>
#include <linux/mm.h>
+#include <linux/of.h>
#include <linux/pfn.h>
#include <linux/swap.h>
+#include <linux/sysfs.h>
#include <asm/page.h>
#include <asm/phyp_dump.h>
+#include <asm/rtas.h>
/* Global, used to communicate data between early boot and late boot */
static struct phyp_dump phyp_dump_global;
struct phyp_dump *phyp_dump_info = &phyp_dump_global;
+static int ibm_configure_kernel_dump;
+
+/* ------------------------------------------------- */
/**
* release_memory_range -- release memory previously lmb_reserved
* @start_pfn: starting physical frame number
@@ -52,20 +59,103 @@ release_memory_range(unsigned long start
}
}
-static int __init phyp_dump_setup(void)
+/* ------------------------------------------------- */
+/**
+ * sysfs_release_region -- sysfs interface to release memory range.
+ *
+ * Usage:
+ * "echo <start addr> <length> > /sys/kernel/release_region"
+ *
+ * Example:
+ * "echo 0x40000000 0x10000000 > /sys/kernel/release_region"
+ *
+ * will release 256MB starting at 1GB.
+ */
+static ssize_t
+store_release_region(struct kset *kset, const char *buf, size_t count)
{
+ unsigned long start_addr, length, end_addr;
unsigned long start_pfn, nr_pages;
+ ssize_t ret;
- /* If no memory was reserved in early boot, there is nothing to do */
- if (phyp_dump_info->init_reserve_size == 0)
- return 0;
+ ret = sscanf(buf, "%lx %lx", &start_addr, &length);
+ if (ret != 2)
+ return -EINVAL;
+
+ /* Range-check - don't free any reserved memory that
+ * wasn't reserved for phyp-dump */
+ if (start_addr < phyp_dump_info->init_reserve_start)
+ start_addr = phyp_dump_info->init_reserve_start;
+
+ end_addr = phyp_dump_info->init_reserve_start +
+ phyp_dump_info->init_reserve_size;
+ if (start_addr+length > end_addr)
+ length = end_addr - start_addr;
+
+ /* Release the region of memory assed in by user */
+ start_pfn = PFN_DOWN(start_addr);
+ nr_pages = PFN_DOWN(length);
+ release_memory_range (start_pfn, nr_pages);
- /* Release memory that was reserved in early boot */
+ return count;
+}
+
+static ssize_t
+show_release_region(struct kset * kset, char *buf)
+{
+ return sprintf(buf, "ola\n");
+}
+
+static struct subsys_attribute rr = __ATTR(release_region, 0600,
+ show_release_region,
+ store_release_region);
+
+/* ------------------------------------------------- */
+
+static void release_all (void)
+{
+ unsigned long start_pfn, nr_pages;
+
+ /* Release all memory that was reserved in early boot */
start_pfn = PFN_DOWN(phyp_dump_info->init_reserve_start);
nr_pages = PFN_DOWN(phyp_dump_info->init_reserve_size);
release_memory_range(start_pfn, nr_pages);
+}
+
+static int __init phyp_dump_setup(void)
+{
+ struct device_node *rtas;
+ const int *dump_header;
+ int header_len = 0;
+ int rc;
+
+ /* If no memory was reserved in early boot, there is nothing to do */
+ if (phyp_dump_info->init_reserve_size == 0)
+ return 0;
+
+ /* Return if phyp dump not supported */
+ ibm_configure_kernel_dump = rtas_token("ibm,configure-kernel-dump");
+ if (ibm_configure_kernel_dump == RTAS_UNKNOWN_SERVICE) {
+ release_all();
+ return -ENOSYS;
+ }
+
+ /* Is there dump data waiting for us? */
+ rtas = of_find_node_by_path("/rtas");
+ dump_header = of_get_property(rtas, "ibm,kernel-dump", &header_len);
+ if (dump_header == NULL) {
+ release_all();
+ return 0;
+ }
+
+ /* Should we create a dump_subsys, analogous to s390/ipl.c ? */
+ rc = subsys_create_file(&kernel_subsys, &rr);
+ if (rc) {
+ printk (KERN_ERR "phyp-dump: unable to create sysfs file (%d)\n", rc);
+ release_all();
+ return 0;
+ }
return 0;
}
-
subsys_initcall(phyp_dump_setup);
^ permalink raw reply
* [PATCH 2/8] pseries: phyp dump: reserve-release proof-of-concept
From: Manish Ahuja @ 2008-01-22 19:29 UTC (permalink / raw)
To: ppc-dev, paulus, linasvepstas; +Cc: Larry Kessler, Michael Strosaker
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Initial patch for reserving memory in early boot, and freeing it later.
If the previous boot had ended with a crash, the reserved memory would contain
a copy of the crashed kernel data.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
----
arch/powerpc/kernel/prom.c | 46 ++++++++++++++++++
arch/powerpc/kernel/rtas.c | 27 +++++++++++
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/phyp_dump.c | 71 +++++++++++++++++++++++++++++
include/asm-powerpc/phyp_dump.h | 37 +++++++++++++++
include/asm/rtas.h | 3 +
6 files changed, 185 insertions(+)
Index: 2.6.24-rc5/include/asm-powerpc/phyp_dump.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ 2.6.24-rc5/include/asm-powerpc/phyp_dump.h 2008-01-18 07:37:33.000000000 -0600
@@ -0,0 +1,37 @@
+/*
+ * Hypervisor-assisted dump
+ *
+ * Linas Vepstas, Manish Ahuja 2007
+ * Copyright (c) 2007 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _PPC64_PHYP_DUMP_H
+#define _PPC64_PHYP_DUMP_H
+
+#ifdef CONFIG_PHYP_DUMP
+
+/* The RMR region will be saved for later dumping
+ * whenever the kernel crashes. Set this to 256MB. */
+#define PHYP_DUMP_RMR_START 0x0
+#define PHYP_DUMP_RMR_END (1UL<<28)
+
+struct phyp_dump {
+ /* Memory that is reserved during very early boot. */
+ unsigned long init_reserve_start;
+ unsigned long init_reserve_size;
+ /* Check status during boot if dump active & present*/
+ unsigned long phyp_dump_is_active;
+ /* store cpu & hpte size */
+ unsigned long cpu_state_size;
+ unsigned long hpte_region_size;
+};
+
+extern struct phyp_dump *phyp_dump_info;
+
+#endif /* CONFIG_PHYP_DUMP */
+#endif /* _PPC64_PHYP_DUMP_H */
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-18 07:37:33.000000000 -0600
@@ -0,0 +1,71 @@
+/*
+ * Hypervisor-assisted dump
+ *
+ * Linas Vepstas, Manish Ahuja 2007
+ * Copyrhgit (c) 2007 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <linux/swap.h>
+
+#include <asm/page.h>
+#include <asm/phyp_dump.h>
+
+/* Global, used to communicate data between early boot and late boot */
+static struct phyp_dump phyp_dump_global;
+struct phyp_dump *phyp_dump_info = &phyp_dump_global;
+
+/**
+ * release_memory_range -- release memory previously lmb_reserved
+ * @start_pfn: starting physical frame number
+ * @nr_pages: number of pages to free.
+ *
+ * This routine will release memory that had been previously
+ * lmb_reserved in early boot. The released memory becomes
+ * available for genreal use.
+ */
+static void
+release_memory_range(unsigned long start_pfn, unsigned long nr_pages)
+{
+ struct page *rpage;
+ unsigned long end_pfn;
+ long i;
+
+ end_pfn = start_pfn + nr_pages;
+
+ for (i=start_pfn; i <= end_pfn; i++) {
+ rpage = pfn_to_page(i);
+ if (PageReserved(rpage)) {
+ ClearPageReserved(rpage);
+ init_page_count(rpage);
+ __free_page(rpage);
+ totalram_pages++;
+ }
+ }
+}
+
+static int __init phyp_dump_setup(void)
+{
+ unsigned long start_pfn, nr_pages;
+
+ /* If no memory was reserved in early boot, there is nothing to do */
+ if (phyp_dump_info->init_reserve_size == 0)
+ return 0;
+
+ /* Release memory that was reserved in early boot */
+ start_pfn = PFN_DOWN(phyp_dump_info->init_reserve_start);
+ nr_pages = PFN_DOWN(phyp_dump_info->init_reserve_size);
+ release_memory_range(start_pfn, nr_pages);
+
+ return 0;
+}
+
+subsys_initcall(phyp_dump_setup);
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/Makefile
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/Makefile 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/Makefile 2008-01-18 07:37:33.000000000 -0600
@@ -18,3 +18,4 @@ obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu
obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o
obj-$(CONFIG_HVCS) += hvcserver.o
obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o
+obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o
Index: 2.6.24-rc5/arch/powerpc/kernel/prom.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/kernel/prom.c 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/kernel/prom.c 2008-01-18 07:37:33.000000000 -0600
@@ -51,6 +51,7 @@
#include <asm/machdep.h>
#include <asm/pSeries_reconfig.h>
#include <asm/pci-bridge.h>
+#include <asm/phyp_dump.h>
#include <asm/kexec.h>
#ifdef DEBUG
@@ -1011,6 +1012,48 @@ static void __init early_reserve_mem(voi
#endif
}
+#ifdef CONFIG_PHYP_DUMP
+
+/**
+ * reserve_crashed_mem() - reserve all not-yet-dumped mmemory
+ *
+ * This routine will reserve almost all of the memory in the
+ * system, except for a few hundred megabytes used to boot the
+ * new kernel. As the reserved memory is dumped to the dump
+ * device (by userland tools), it will be freed and made available.
+ */
+static void __init reserve_crashed_mem(void)
+{
+ unsigned long base, size;
+
+ if (phyp_dump_info->phyp_dump_is_active) {
+ /* Reserve *everything* above RMR. We'll free this real soon.*/
+ base = PHYP_DUMP_RMR_END;
+ size = lmb_end_of_DRAM() - base;
+
+ /* XXX crashed_ram_end is wrong, since it may be beyond
+ * the memory_limit, it will need to be adjusted. */
+ lmb_reserve(base, size);
+
+ phyp_dump_info->init_reserve_start = base;
+ phyp_dump_info->init_reserve_size = size;
+ }
+ else {
+ size = phyp_dump_info->cpu_state_size +
+ phyp_dump_info->hpte_region_size +
+ PHYP_DUMP_RMR_END;
+ base = lmb_end_of_DRAM() - size;
+ printk(KERN_ERR "Manish reserve regular kernel space is %ld %ld\n", base, size);
+ lmb_reserve(base, size);
+ phyp_dump_info->init_reserve_start = base;
+ phyp_dump_info->init_reserve_size = size;
+ }
+}
+#else
+static inline void __init reserve_crashed_mem(void) {}
+#endif /* CONFIG_PHYP_DUMP */
+
+
void __init early_init_devtree(void *params)
{
DBG(" -> early_init_devtree(%p)\n", params);
@@ -1022,6 +1065,8 @@ void __init early_init_devtree(void *par
/* Some machines might need RTAS info for debugging, grab it now. */
of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
#endif
+ /* scan tree to see if dump occured during last boot */
+ of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
/* Retrieve various informations from the /chosen node of the
* device-tree, including the platform type, initrd location and
@@ -1043,6 +1088,7 @@ void __init early_init_devtree(void *par
reserve_kdump_trampoline();
reserve_crashkernel();
early_reserve_mem();
+ reserve_crashed_mem();
lmb_enforce_memory_limit(memory_limit);
lmb_analyze();
Index: 2.6.24-rc5/arch/powerpc/kernel/rtas.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/kernel/rtas.c 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/kernel/rtas.c 2008-01-18 07:37:33.000000000 -0600
@@ -39,6 +39,7 @@
#include <asm/syscalls.h>
#include <asm/smp.h>
#include <asm/atomic.h>
+#include <asm/phyp_dump.h>
struct rtas_t rtas = {
.lock = SPIN_LOCK_UNLOCKED
@@ -883,6 +884,32 @@ void __init rtas_initialize(void)
#endif
}
+int __init early_init_dt_scan_phyp_dump(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+#ifdef CONFIG_PHYP_DUMP
+ const unsigned int *sizes;
+
+ phyp_dump_info->phyp_dump_is_active = 0;
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ if (of_get_flat_dt_prop(node, "ibm,dump-kernel", NULL))
+ phyp_dump_info->phyp_dump_is_active++;
+
+ sizes = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes", NULL);
+ if (!sizes)
+ return 0;
+
+ if (sizes[0] == 1)
+ phyp_dump_info->cpu_state_size = *((unsigned long *)&sizes[1]);
+
+ if (sizes[3] == 2)
+ phyp_dump_info->hpte_region_size = *((unsigned long *)&sizes[4]);
+#endif
+ return 1;
+}
+
int __init early_init_dt_scan_rtas(unsigned long node,
const char *uname, int depth, void *data)
{
Index: 2.6.24-rc5/include/asm/rtas.h
===================================================================
--- 2.6.24-rc5.orig/include/asm/rtas.h 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/include/asm/rtas.h 2008-01-18 07:37:33.000000000 -0600
@@ -183,6 +183,9 @@ extern unsigned int rtas_busy_delay(int
extern int early_init_dt_scan_rtas(unsigned long node,
const char *uname, int depth, void *data);
+int early_init_dt_scan_phyp_dump(unsigned long node,
+ const char *uname, int depth, void *data);
+
extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
^ permalink raw reply
* Re: crash in kmem_cache_init
From: Mel Gorman @ 2008-01-22 19:54 UTC (permalink / raw)
To: Olaf Hering
Cc: lee.schermerhorn, Linux MM, linux-kernel, linuxppc-dev,
Pekka Enberg, Aneesh Kumar K.V, hanth Aravamudan, akpm,
KAMEZAWA Hiroyuki, Christoph Lameter
In-Reply-To: <20080118225713.GA31128@aepfle.de>
On (18/01/08 23:57), Olaf Hering didst pronounce:
> On Fri, Jan 18, Christoph Lameter wrote:
>
> > Could you try this patch?
>
> Does not help, same crash.
>
Hi Olaf,
It was suggested this problem was the same as another slab-related boot problem
that was fixed for 2.6.24 by reverting a change. This fix can be found at
http://www.csn.ul.ie/~mel/postings/slab-20080122/partial-revert-slab-changes.patch
. Can you please check on your machine if it fixes your problem?
I am 99.9999% it will *not* fix your problem because there was two bugs, not
one as previously believed. On two test machines here, this kmem_cache_init
problem still happens even with the revert which fixed a third machine. I
was delayed in testing because these boxen unavailable from Friday until
yesterday evening (a stellar display of timing). It was missed on TKO because
it was SLAB-specific and those machines were testing SLUB. I found that the
patch below was necessary to fix the problem.
Olaf, please confirm whether you need the patch below as well as the
revert to make your machine boot.
Christoph/Pekka, this patch is papering over the problem and something
more fundamental may be going wrong. The crash occurs because l3 is NULL
and the cache is kmem_cache so this is early in the boot process. It is
selecting l3 based on node 2 which is correct in terms of available memory
but it initialises the lists on node 0 because that is the node the CPUs are
located. Hence later it uses an uninitialised nodelists and BLAM. Relevant
parts of the log for seeing the memoryless nodes in relation to CPUs is;
early_node_map[1] active PFN ranges
2: 0 -> 1048576
Processor 1 found.
clockevent: decrementer mult[3cf1] shift[16] cpu[2]
Processor 2 found.
clockevent: decrementer mult[3cf1] shift[16] cpu[3]
Processor 3 found.
Brought up 4 CPUs
Node 0 CPUs: 0-3
Node 2 CPUs:
Can you see a better solution than this?
====
Recent changes to how slab operates mean a situation can occur on systems
with memoryless nodes whereby the nodeid used when growing the slab does
not map to the correct kmem_list3. The following patch adds the necessary
check to the indicated preferred nodeid and if it is bogus, use numa_node_id() instead.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
---
mm/slab.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff -rup -X /usr/src/patchset-0.6/bin//dontdiff linux-2.6.24-rc8-005-revert-memoryless-slab/mm/slab.c linux-2.6.24-rc8-010_handle_missing_l3/mm/slab.c
--- linux-2.6.24-rc8-005-revert-memoryless-slab/mm/slab.c 2008-01-22 17:46:32.000000000 +0000
+++ linux-2.6.24-rc8-010_handle_missing_l3/mm/slab.c 2008-01-22 18:42:53.000000000 +0000
@@ -2775,6 +2775,11 @@ static int cache_grow(struct kmem_cache
/* Take the l3 list lock to change the colour_next on this node */
check_irq_off();
l3 = cachep->nodelists[nodeid];
+ if (!l3) {
+ nodeid = numa_node_id();
+ l3 = cachep->nodelists[nodeid];
+ }
+ BUG_ON(!l3);
spin_lock(&l3->list_lock);
/* Get colour for the slab, and cal the next value. */
@@ -3317,6 +3322,10 @@ static void *____cache_alloc_node(struct
int x;
l3 = cachep->nodelists[nodeid];
+ if (!l3) {
+ nodeid = numa_node_id();
+ l3 = cachep->nodelists[nodeid];
+ }
BUG_ON(!l3);
retry:
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
^ permalink raw reply
* [PATCH] [POWERPC]: constify function pointer tables
From: Jan Engelhardt @ 2008-01-22 19:43 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev
In-Reply-To: <54038cd4f87a03884e4f59f8f3697889dfb63c54.1201030614.git.jengelh@computergmbh.de>
Signed-off-by: Jan Engelhardt <jengelh@computergmbh.de>
---
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/platforms/cell/spufs/inode.c | 2 +-
arch/powerpc/platforms/pseries/hvCall_inst.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 2de00f8..57d4f28 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -296,7 +296,7 @@ static void c_stop(struct seq_file *m, void *v)
{
}
-struct seq_operations cpuinfo_op = {
+const struct seq_operations cpuinfo_op = {
.start =c_start,
.next = c_next,
.stop = c_stop,
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index c0e968a..d99fcda 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -110,7 +110,7 @@ spufs_new_file(struct super_block *sb, struct dentry *dentry,
const struct file_operations *fops, int mode,
struct spu_context *ctx)
{
- static struct inode_operations spufs_file_iops = {
+ static const struct inode_operations spufs_file_iops = {
.setattr = spufs_setattr,
};
struct inode *inode;
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index eae51ef..3631a4f 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -71,7 +71,7 @@ static int hc_show(struct seq_file *m, void *p)
return 0;
}
-static struct seq_operations hcall_inst_seq_ops = {
+static const struct seq_operations hcall_inst_seq_ops = {
.start = hc_start,
.next = hc_next,
.stop = hc_stop,
--
1.5.3.4
^ permalink raw reply related
* Re: [PATCH] adder875: Fix flash bus-width and remove duplicate __initdata.
From: Kumar Gala @ 2008-01-22 20:05 UTC (permalink / raw)
To: Scott Wood; +Cc: linuxppc-dev
In-Reply-To: <20080122183141.GB17036@loki.buserror.net>
On Tue, 22 Jan 2008, Scott Wood wrote:
> Signed-off-by: Scott Wood <scottwood@freescale.com>
> ---
> arch/powerpc/boot/dts/adder875-redboot.dts | 2 +-
> arch/powerpc/boot/dts/adder875-uboot.dts | 2 +-
> arch/powerpc/platforms/8xx/adder875.c | 2 +-
> 3 files changed, 3 insertions(+), 3 deletions(-)
>
applied.
- k
^ permalink raw reply
* [PATCH 2/8] pseries: phyp dump: reserve-release proof-of-concept
From: Manish Ahuja @ 2008-01-22 20:09 UTC (permalink / raw)
To: ppc-dev, paulus, linasvepstas
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Initial patch for reserving memory in early boot, and freeing it later.
If the previous boot had ended with a crash, the reserved memory would contain
a copy of the crashed kernel data.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
Signed-off-by: Linas Vepstas <linasvepstas@gmail.com>
----
arch/powerpc/kernel/prom.c | 46 ++++++++++++++++++
arch/powerpc/kernel/rtas.c | 27 +++++++++++
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/phyp_dump.c | 71 +++++++++++++++++++++++++++++
include/asm-powerpc/phyp_dump.h | 37 +++++++++++++++
include/asm/rtas.h | 3 +
6 files changed, 185 insertions(+)
Index: 2.6.24-rc5/include/asm-powerpc/phyp_dump.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ 2.6.24-rc5/include/asm-powerpc/phyp_dump.h 2008-01-18 07:37:33.000000000 -0600
@@ -0,0 +1,37 @@
+/*
+ * Hypervisor-assisted dump
+ *
+ * Linas Vepstas, Manish Ahuja 2007
+ * Copyright (c) 2007 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _PPC64_PHYP_DUMP_H
+#define _PPC64_PHYP_DUMP_H
+
+#ifdef CONFIG_PHYP_DUMP
+
+/* The RMR region will be saved for later dumping
+ * whenever the kernel crashes. Set this to 256MB. */
+#define PHYP_DUMP_RMR_START 0x0
+#define PHYP_DUMP_RMR_END (1UL<<28)
+
+struct phyp_dump {
+ /* Memory that is reserved during very early boot. */
+ unsigned long init_reserve_start;
+ unsigned long init_reserve_size;
+ /* Check status during boot if dump active & present*/
+ unsigned long phyp_dump_is_active;
+ /* store cpu & hpte size */
+ unsigned long cpu_state_size;
+ unsigned long hpte_region_size;
+};
+
+extern struct phyp_dump *phyp_dump_info;
+
+#endif /* CONFIG_PHYP_DUMP */
+#endif /* _PPC64_PHYP_DUMP_H */
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-18 07:37:33.000000000 -0600
@@ -0,0 +1,71 @@
+/*
+ * Hypervisor-assisted dump
+ *
+ * Linas Vepstas, Manish Ahuja 2007
+ * Copyrhgit (c) 2007 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <linux/swap.h>
+
+#include <asm/page.h>
+#include <asm/phyp_dump.h>
+
+/* Global, used to communicate data between early boot and late boot */
+static struct phyp_dump phyp_dump_global;
+struct phyp_dump *phyp_dump_info = &phyp_dump_global;
+
+/**
+ * release_memory_range -- release memory previously lmb_reserved
+ * @start_pfn: starting physical frame number
+ * @nr_pages: number of pages to free.
+ *
+ * This routine will release memory that had been previously
+ * lmb_reserved in early boot. The released memory becomes
+ * available for genreal use.
+ */
+static void
+release_memory_range(unsigned long start_pfn, unsigned long nr_pages)
+{
+ struct page *rpage;
+ unsigned long end_pfn;
+ long i;
+
+ end_pfn = start_pfn + nr_pages;
+
+ for (i=start_pfn; i <= end_pfn; i++) {
+ rpage = pfn_to_page(i);
+ if (PageReserved(rpage)) {
+ ClearPageReserved(rpage);
+ init_page_count(rpage);
+ __free_page(rpage);
+ totalram_pages++;
+ }
+ }
+}
+
+static int __init phyp_dump_setup(void)
+{
+ unsigned long start_pfn, nr_pages;
+
+ /* If no memory was reserved in early boot, there is nothing to do */
+ if (phyp_dump_info->init_reserve_size == 0)
+ return 0;
+
+ /* Release memory that was reserved in early boot */
+ start_pfn = PFN_DOWN(phyp_dump_info->init_reserve_start);
+ nr_pages = PFN_DOWN(phyp_dump_info->init_reserve_size);
+ release_memory_range(start_pfn, nr_pages);
+
+ return 0;
+}
+
+subsys_initcall(phyp_dump_setup);
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/Makefile
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/Makefile 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/Makefile 2008-01-18 07:37:33.000000000 -0600
@@ -18,3 +18,4 @@ obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu
obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o
obj-$(CONFIG_HVCS) += hvcserver.o
obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o
+obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o
Index: 2.6.24-rc5/arch/powerpc/kernel/prom.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/kernel/prom.c 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/kernel/prom.c 2008-01-18 07:37:33.000000000 -0600
@@ -51,6 +51,7 @@
#include <asm/machdep.h>
#include <asm/pSeries_reconfig.h>
#include <asm/pci-bridge.h>
+#include <asm/phyp_dump.h>
#include <asm/kexec.h>
#ifdef DEBUG
@@ -1011,6 +1012,48 @@ static void __init early_reserve_mem(voi
#endif
}
+#ifdef CONFIG_PHYP_DUMP
+
+/**
+ * reserve_crashed_mem() - reserve all not-yet-dumped mmemory
+ *
+ * This routine will reserve almost all of the memory in the
+ * system, except for a few hundred megabytes used to boot the
+ * new kernel. As the reserved memory is dumped to the dump
+ * device (by userland tools), it will be freed and made available.
+ */
+static void __init reserve_crashed_mem(void)
+{
+ unsigned long base, size;
+
+ if (phyp_dump_info->phyp_dump_is_active) {
+ /* Reserve *everything* above RMR. We'll free this real soon.*/
+ base = PHYP_DUMP_RMR_END;
+ size = lmb_end_of_DRAM() - base;
+
+ /* XXX crashed_ram_end is wrong, since it may be beyond
+ * the memory_limit, it will need to be adjusted. */
+ lmb_reserve(base, size);
+
+ phyp_dump_info->init_reserve_start = base;
+ phyp_dump_info->init_reserve_size = size;
+ }
+ else {
+ size = phyp_dump_info->cpu_state_size +
+ phyp_dump_info->hpte_region_size +
+ PHYP_DUMP_RMR_END;
+ base = lmb_end_of_DRAM() - size;
+ printk(KERN_ERR "Manish reserve regular kernel space is %ld %ld\n", base, size);
+ lmb_reserve(base, size);
+ phyp_dump_info->init_reserve_start = base;
+ phyp_dump_info->init_reserve_size = size;
+ }
+}
+#else
+static inline void __init reserve_crashed_mem(void) {}
+#endif /* CONFIG_PHYP_DUMP */
+
+
void __init early_init_devtree(void *params)
{
DBG(" -> early_init_devtree(%p)\n", params);
@@ -1022,6 +1065,8 @@ void __init early_init_devtree(void *par
/* Some machines might need RTAS info for debugging, grab it now. */
of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
#endif
+ /* scan tree to see if dump occured during last boot */
+ of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
/* Retrieve various informations from the /chosen node of the
* device-tree, including the platform type, initrd location and
@@ -1043,6 +1088,7 @@ void __init early_init_devtree(void *par
reserve_kdump_trampoline();
reserve_crashkernel();
early_reserve_mem();
+ reserve_crashed_mem();
lmb_enforce_memory_limit(memory_limit);
lmb_analyze();
Index: 2.6.24-rc5/arch/powerpc/kernel/rtas.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/kernel/rtas.c 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/kernel/rtas.c 2008-01-18 07:37:33.000000000 -0600
@@ -39,6 +39,7 @@
#include <asm/syscalls.h>
#include <asm/smp.h>
#include <asm/atomic.h>
+#include <asm/phyp_dump.h>
struct rtas_t rtas = {
.lock = SPIN_LOCK_UNLOCKED
@@ -883,6 +884,32 @@ void __init rtas_initialize(void)
#endif
}
+int __init early_init_dt_scan_phyp_dump(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+#ifdef CONFIG_PHYP_DUMP
+ const unsigned int *sizes;
+
+ phyp_dump_info->phyp_dump_is_active = 0;
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ if (of_get_flat_dt_prop(node, "ibm,dump-kernel", NULL))
+ phyp_dump_info->phyp_dump_is_active++;
+
+ sizes = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes", NULL);
+ if (!sizes)
+ return 0;
+
+ if (sizes[0] == 1)
+ phyp_dump_info->cpu_state_size = *((unsigned long *)&sizes[1]);
+
+ if (sizes[3] == 2)
+ phyp_dump_info->hpte_region_size = *((unsigned long *)&sizes[4]);
+#endif
+ return 1;
+}
+
int __init early_init_dt_scan_rtas(unsigned long node,
const char *uname, int depth, void *data)
{
Index: 2.6.24-rc5/include/asm/rtas.h
===================================================================
--- 2.6.24-rc5.orig/include/asm/rtas.h 2008-01-18 07:37:28.000000000 -0600
+++ 2.6.24-rc5/include/asm/rtas.h 2008-01-18 07:37:33.000000000 -0600
@@ -183,6 +183,9 @@ extern unsigned int rtas_busy_delay(int
extern int early_init_dt_scan_rtas(unsigned long node,
const char *uname, int depth, void *data);
+int early_init_dt_scan_phyp_dump(unsigned long node,
+ const char *uname, int depth, void *data);
+
extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
^ permalink raw reply
* Re: crash in kmem_cache_init
From: Christoph Lameter @ 2008-01-22 20:11 UTC (permalink / raw)
To: Mel Gorman
Cc: lee.schermerhorn, Olaf Hering, Linux MM, linux-kernel,
linuxppc-dev, Pekka Enberg, Aneesh Kumar K.V, hanth Aravamudan,
akpm, KAMEZAWA Hiroyuki
In-Reply-To: <20080122195448.GA15567@csn.ul.ie>
On Tue, 22 Jan 2008, Mel Gorman wrote:
> Christoph/Pekka, this patch is papering over the problem and something
> more fundamental may be going wrong. The crash occurs because l3 is NULL
> and the cache is kmem_cache so this is early in the boot process. It is
> selecting l3 based on node 2 which is correct in terms of available memory
> but it initialises the lists on node 0 because that is the node the CPUs are
> located. Hence later it uses an uninitialised nodelists and BLAM. Relevant
> parts of the log for seeing the memoryless nodes in relation to CPUs is;
Would it be possible to run the bootstrap on a cpu that has a
node with memory associated to it? I believe we had the same situation
last year when GFP_THISNODE was introduced?
After you reverted the slab memoryless node patch there should be per node
structures created for node 0 unless the node is marked offline. Is it? If
so then you are booting a cpu that is associated with an offline node.
> Can you see a better solution than this?
Well this means that bootstrap will work by introducing foreign objects
into the per cpu queue (should only hold per cpu objects). They will
later be consumed and then the queues will contain the right objects so
the effect of the patch is minimal.
I thought we fixed the similar situation last year by dropping
GFP_THISNODE for some allocations?
^ permalink raw reply
* [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Wade Farnsworth @ 2008-01-22 20:13 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev
In-Reply-To: <1201019917.5716.154.camel@rhino>
Add local bus, flash, and MTD partition nodes to mpc8641_hpcn.dts
Also add compatible field for the soc node, so that it will be picked up
by of_platform_bus_probe().
Signed-off-by: Wade Farnsworth <wfarnsworth@mvista.com>
---
Updated per Kumar's comments.
arch/powerpc/boot/dts/mpc8641_hpcn.dts | 42 +++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/arch/powerpc/boot/dts/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/mpc8641_hpcn.dts
index a719179..556a9ca 100644
--- a/arch/powerpc/boot/dts/mpc8641_hpcn.dts
+++ b/arch/powerpc/boot/dts/mpc8641_hpcn.dts
@@ -60,10 +60,52 @@
reg = <00000000 40000000>; // 1G at 0x0
};
+ localbus@f8005000 {
+ #address-cells = <2>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8641-localbus", "simple-bus";
+ reg = <f8005000 1000>;
+ interrupts = <13 2>;
+ interrupt-parent = <&mpic>;
+
+ ranges = <0 0 ff800000 00800000
+ 1 0 fe000000 01000000
+ 2 0 f8200000 00100000
+ 3 0 f8100000 00100000>;
+
+ flash@0,0 {
+ compatible = "cfi-flash";
+ reg = <0 0 00800000>;
+ bank-width = <2>;
+ device-width = <2>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ partition@0 {
+ label = "kernel";
+ reg = <00000000 00300000>;
+ };
+ partition@300000 {
+ label = "firmware b";
+ reg = <00300000 00100000>;
+ read-only;
+ };
+ partition@400000 {
+ label = "fs";
+ reg = <00400000 00300000>;
+ };
+ partition@700000 {
+ label = "firmware a";
+ reg = <00700000 00100000>;
+ read-only;
+ };
+ };
+ };
+
soc8641@f8000000 {
#address-cells = <1>;
#size-cells = <1>;
device_type = "soc";
+ compatible = "simple-bus";
ranges = <00000000 f8000000 00100000>;
reg = <f8000000 00001000>; // CCSRBAR
bus-frequency = <0>;
^ permalink raw reply related
* [PATCH 4/8] pseries: phyp dump: register dump area.
From: Manish Ahuja @ 2008-01-22 20:15 UTC (permalink / raw)
To: ppc-dev, paulus, linasvepstas; +Cc: mahuja, linasvepstas, lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Set up the actual dump header, register it with the hypervisor.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
Signed-off-by: Linas Vepstas <linasvepstas@gmail.com>
------
arch/powerpc/platforms/pseries/phyp_dump.c | 136 +++++++++++++++++++++++++++--
1 file changed, 129 insertions(+), 7 deletions(-)
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-18 22:43:00.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 23:49:23.000000000 -0600
@@ -30,6 +30,117 @@ struct phyp_dump *phyp_dump_info = &phyp
static int ibm_configure_kernel_dump;
/* ------------------------------------------------- */
+/* RTAS interfaces to declare the dump regions */
+
+struct dump_section {
+ u32 dump_flags;
+ u16 source_type;
+ u16 error_flags;
+ u64 source_address;
+ u64 source_length;
+ u64 length_copied;
+ u64 destination_address;
+};
+
+struct phyp_dump_header {
+ u32 version;
+ u16 num_of_sections;
+ u16 status;
+
+ u32 first_offset_section;
+ u32 dump_disk_section;
+ u64 block_num_dd;
+ u64 num_of_blocks_dd;
+ u32 offset_dd;
+ u32 maxtime_to_auto;
+ /* No dump disk path string used */
+
+ struct dump_section cpu_data;
+ struct dump_section hpte_data;
+ struct dump_section kernel_data;
+};
+
+/* The dump header *must be* in low memory, so .bss it */
+static struct phyp_dump_header phdr;
+
+#define NUM_DUMP_SECTIONS 3
+#define DUMP_HEADER_VERSION 0x1
+#define DUMP_REQUEST_FLAG 0x1
+#define DUMP_SOURCE_CPU 0x0001
+#define DUMP_SOURCE_HPTE 0x0002
+#define DUMP_SOURCE_RMO 0x0011
+
+/**
+ * init_dump_header() - initialize the header declaring a dump
+ * Returns: length of dump save area.
+ *
+ * When the hypervisor saves crashed state, it needs to put
+ * it somewhere. The dump header tells the hypervisor where
+ * the data can be saved.
+ */
+static unsigned long init_dump_header(struct phyp_dump_header *ph)
+{
+ unsigned long addr_offset = 0;
+
+ /* Set up the dump header */
+ ph->version = DUMP_HEADER_VERSION;
+ ph->num_of_sections = NUM_DUMP_SECTIONS;
+ ph->status = 0;
+
+ ph->first_offset_section =
+ (u32)offsetof(struct phyp_dump_header, cpu_data);
+ ph->dump_disk_section = 0;
+ ph->block_num_dd = 0;
+ ph->num_of_blocks_dd = 0;
+ ph->offset_dd = 0;
+
+ ph->maxtime_to_auto = 0; /* disabled */
+
+ /* The first two sections are mandatory */
+ ph->cpu_data.dump_flags = DUMP_REQUEST_FLAG;
+ ph->cpu_data.source_type = DUMP_SOURCE_CPU;
+ ph->cpu_data.source_address = 0;
+ ph->cpu_data.source_length = phyp_dump_info->cpu_state_size;
+ ph->cpu_data.destination_address = addr_offset;
+ addr_offset += phyp_dump_info->cpu_state_size;
+
+ ph->hpte_data.dump_flags = DUMP_REQUEST_FLAG;
+ ph->hpte_data.source_type = DUMP_SOURCE_HPTE;
+ ph->hpte_data.source_address = 0;
+ ph->hpte_data.source_length = phyp_dump_info->hpte_region_size;
+ ph->hpte_data.destination_address = addr_offset;
+ addr_offset += phyp_dump_info->hpte_region_size;
+
+ /* This section describes the low kernel region */
+ ph->kernel_data.dump_flags = DUMP_REQUEST_FLAG;
+ ph->kernel_data.source_type = DUMP_SOURCE_RMO;
+ ph->kernel_data.source_address = PHYP_DUMP_RMR_START;
+ ph->kernel_data.source_length = PHYP_DUMP_RMR_END;
+ ph->kernel_data.destination_address = addr_offset;
+ addr_offset += ph->kernel_data.source_length;
+
+ return addr_offset;
+}
+
+static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
+{
+ int rc;
+ ph->cpu_data.destination_address += addr;
+ ph->hpte_data.destination_address += addr;
+ ph->kernel_data.destination_address += addr;
+
+ do {
+ rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
+ 1, ph, sizeof(struct phyp_dump_header));
+ } while (rtas_busy_delay(rc));
+
+ if (rc)
+ {
+ printk (KERN_ERR "phyp-dump: unexpected error (%d) on register\n", rc);
+ }
+}
+
+/* ------------------------------------------------- */
/**
* release_memory_range -- release memory previously lmb_reserved
* @start_pfn: starting physical frame number
@@ -125,7 +236,9 @@ static void release_all (void)
static int __init phyp_dump_setup(void)
{
struct device_node *rtas;
- const int *dump_header;
+ const struct phyp_dump_header *dump_header;
+ unsigned long dump_area_start;
+ unsigned long dump_area_length;
int header_len = 0;
int rc;
@@ -140,22 +253,31 @@ static int __init phyp_dump_setup(void)
return -ENOSYS;
}
- /* Is there dump data waiting for us? */
+ /* Is there dump data waiting for us? If there isn't,
+ * then register a new dump area, and release all of
+ * the rest of the reserved ram.
+ *
+ * The /rtas/ibm,kernel-dump rtas node is present only
+ * if there is dump data waiting for us.
+ */
rtas = of_find_node_by_path("/rtas");
dump_header = of_get_property(rtas, "ibm,kernel-dump", &header_len);
+ of_node_put(rtas);
+
+ dump_area_length = init_dump_header(&phdr);
+ dump_area_start = phyp_dump_info->init_reserve_start & PAGE_MASK; /* align down */
+
if (dump_header == NULL) {
- release_all();
+ register_dump_area(&phdr, dump_area_start);
return 0;
}
/* Should we create a dump_subsys, analogous to s390/ipl.c ? */
rc = subsys_create_file(&kernel_subsys, &rr);
- if (rc) {
+ if (rc)
printk (KERN_ERR "phyp-dump: unable to create sysfs file (%d)\n", rc);
- release_all();
- return 0;
- }
+ /* ToDo: re-register the dump area, for next time. */
return 0;
}
subsys_initcall(phyp_dump_setup);
^ permalink raw reply
* [PATCH v2 2/2] MPC8641 HPCN: call of_platform_bus_probe()
From: Wade Farnsworth @ 2008-01-22 20:17 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev
In-Reply-To: <1201032819.5716.170.camel@rhino>
Call of_platform_bus_probe() on the MPC8641 HPCN, similar to what is
done for other platforms.
Signed-off-by: Wade Farnsworth <wfarnsworth@mvista.com>
---
Updated per Kumar's comments.
arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 14f4e52..510913e 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -18,6 +18,7 @@
#include <linux/kdev_t.h>
#include <linux/delay.h>
#include <linux/seq_file.h>
+#include <linux/of_platform.h>
#include <asm/system.h>
#include <asm/time.h>
@@ -212,6 +213,19 @@ mpc86xx_time_init(void)
return 0;
}
+static struct of_device_id of_bus_ids[] = {
+ { .compatible = "simple-bus", },
+ {},
+};
+
+static int __init declare_of_platform_devices(void)
+{
+ of_platform_bus_probe(NULL, of_bus_ids, NULL);
+
+ return 0;
+}
+machine_device_initcall(mpc86xx_hpcn, declare_of_platform_devices);
+
define_machine(mpc86xx_hpcn) {
.name = "MPC86xx HPCN",
.probe = mpc86xx_hpcn_probe,
^ permalink raw reply related
* Re: [PATCH v2 2/2] MPC8641 HPCN: call of_platform_bus_probe()
From: Kumar Gala @ 2008-01-22 20:36 UTC (permalink / raw)
To: Wade Farnsworth; +Cc: linuxppc-dev
In-Reply-To: <1201033065.5716.175.camel@rhino>
On Tue, 22 Jan 2008, Wade Farnsworth wrote:
> Call of_platform_bus_probe() on the MPC8641 HPCN, similar to what is
> done for other platforms.
>
> Signed-off-by: Wade Farnsworth <wfarnsworth@mvista.com>
>
> ---
> Updated per Kumar's comments.
>
> arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 14 ++++++++++++++
> 1 file changed, 14 insertions(+)
applied.
- k
^ permalink raw reply
* Re: [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Kumar Gala @ 2008-01-22 20:37 UTC (permalink / raw)
To: Wade Farnsworth; +Cc: linuxppc-dev
In-Reply-To: <1201032819.5716.170.camel@rhino>
On Tue, 22 Jan 2008, Wade Farnsworth wrote:
> Add local bus, flash, and MTD partition nodes to mpc8641_hpcn.dts
>
> Also add compatible field for the soc node, so that it will be picked up
> by of_platform_bus_probe().
>
> Signed-off-by: Wade Farnsworth <wfarnsworth@mvista.com>
>
> ---
> Updated per Kumar's comments.
>
> arch/powerpc/boot/dts/mpc8641_hpcn.dts | 42 +++++++++++++++++++++++
> 1 file changed, 42 insertions(+)
>
applied.
- k
^ permalink raw reply
* Re: [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Jon Loeliger @ 2008-01-22 20:41 UTC (permalink / raw)
To: Wade Farnsworth; +Cc: linuxppc-dev
In-Reply-To: <1201032819.5716.170.camel@rhino>
Wade Farnsworth wrote:
> +
> + ranges = <0 0 ff800000 00800000
> + 1 0 fe000000 01000000
> + 2 0 f8200000 00100000
> + 3 0 f8100000 00100000>;
> +
I think you want just:
ranges = <0 0 f8000000 8000000>
right? And is it really on CS 0?
jdl
^ permalink raw reply
* Re: Trying 10/HALF
From: Andy Fleming @ 2008-01-22 20:55 UTC (permalink / raw)
To: Siva Prasad; +Cc: linuxppc-dev, linuxppc-embedded
In-Reply-To: <D83235F0F3C86D4D889D8B9A0DA8C6D701494071@corpexc01.corp.networkrobots.com>
On Jan 9, 2008, at 13:35, Siva Prasad wrote:
> Hi,
>
>
>
> After booting, my MPC8641 based board keeps printing =93Trying 10/=20
> HALF=94 for ever. I am unable to use the Ethernet, even though there =20=
> are interrupts occuring. Based on /proc/interrupts, both tx and rx =20
> interrupt count is increasing, and zero count for enet_error =20
> interrupt.
>
>
>
> I think this is coming from drivers/net/phy/phy.c during =20
> autonegotiation. However, I am not sure how to take care of this. =20
> Appreciate some pointers.
>
Hm. That's a bit strange. What kind of PHY are you using? The PHY =20
layer acts like that if auto-negotiation fails and it couldn't =20
establish a link using any other method.
Some things to double-check:
* Are your etsec interrupts correct in your dts. Shouldn't be an =20
issue, but if you copied them from the wrong place, or used an out-of-=20=
date dts, the numbers could be wrong
* Are your PHY interrupts correct in your dts. If the PHY interrupts =20=
are wrong, the PHY Lib might never discover that a link was established
Andy=
^ permalink raw reply
* Re: [PATCH 2/8] pseries: phyp dump: reserve-release proof-of-concept
From: Manish Ahuja @ 2008-01-22 21:00 UTC (permalink / raw)
To: ppc-dev, paulus, linasvepstas
In-Reply-To: <47964422.7080505@austin.ibm.com>
Reposted this one. I got the email id wrong in this one.
Sorry about that.
Manish
^ permalink raw reply
* [PATCH 5/8] pseries: phyp dump: debugging print routines.
From: Manish Ahuja @ 2008-01-22 21:02 UTC (permalink / raw)
To: ppc-dev, paulus; +Cc: mahuja, linasvepstas, lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Provide some basic debugging support.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
Signed-off-by: Linas Vepstas <linasvepstas@gmail.com>
-----
arch/powerpc/platforms/pseries/phyp_dump.c | 64 +++++++++++++++++++++++++++--
1 file changed, 60 insertions(+), 4 deletions(-)
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 02:51:54.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 02:58:41.000000000 -0600
@@ -2,7 +2,7 @@
* Hypervisor-assisted dump
*
* Linas Vepstas, Manish Ahuja 2007
- * Copyrhgit (c) 2007 IBM Corp.
+ * Copyright (c) 2007 IBM Corp.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -122,6 +122,61 @@ static unsigned long init_dump_header(st
return addr_offset;
}
+static void print_dump_header(const struct phyp_dump_header *ph)
+{
+#ifdef DEBUG
+ printk(KERN_INFO "dump header:\n");
+ /* setup some ph->sections required */
+ printk(KERN_INFO "version = %d\n", ph->version);
+ printk(KERN_INFO "Sections = %d\n", ph->num_of_sections);
+ printk(KERN_INFO "Status = 0x%x\n", ph->status);
+
+ /* No ph->disk, so all should be set to 0 */
+ printk(KERN_INFO "Offset to first section 0x%x\n",
+ ph->first_offset_section);
+ printk(KERN_INFO "dump disk sections should be zero\n");
+ printk(KERN_INFO "dump disk section = %d\n", ph->dump_disk_section);
+ printk(KERN_INFO "block num = %ld\n", ph->block_num_dd);
+ printk(KERN_INFO "number of blocks = %ld\n", ph->num_of_blocks_dd);
+ printk(KERN_INFO "dump disk offset = %d\n", ph->offset_dd);
+ 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 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);
+ printk(KERN_INFO "cpu source_address =%lx\n",
+ ph->cpu_data.source_address);
+ printk(KERN_INFO "cpu source_length =%lx\n",
+ ph->cpu_data.source_length);
+ printk(KERN_INFO "cpu length_copied =%lx\n",
+ ph->cpu_data.length_copied);
+
+ 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);
+ printk(KERN_INFO "HPTE source_address =%lx\n",
+ ph->hpte_data.source_address);
+ printk(KERN_INFO "HPTE source_length =%lx\n",
+ ph->hpte_data.source_length);
+ printk(KERN_INFO "HPTE length_copied =%lx\n",
+ ph->hpte_data.length_copied);
+
+ 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);
+ printk(KERN_INFO "SRSD source_address =%lx\n",
+ ph->kernel_data.source_address);
+ printk(KERN_INFO "SRSD source_length =%lx\n",
+ ph->kernel_data.source_length);
+ printk(KERN_INFO "SRSD length_copied =%lx\n",
+ ph->kernel_data.length_copied);
+#endif
+}
+
static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
{
int rc;
@@ -134,9 +189,9 @@ static void register_dump_area(struct ph
1, ph, sizeof(struct phyp_dump_header));
} while (rtas_busy_delay(rc));
- if (rc)
- {
- printk (KERN_ERR "phyp-dump: unexpected error (%d) on register\n", rc);
+ if (rc) {
+ printk(KERN_ERR "phyp-dump: unexpected error (%d) on register\n", rc);
+ print_dump_header(ph);
}
}
@@ -249,6 +304,7 @@ static int __init phyp_dump_setup(void)
release_all();
return -ENOSYS;
}
+ print_dump_header(dump_header);
/* Is there dump data waiting for us? If there isn't,
* then register a new dump area, and release all of
^ permalink raw reply
* [PATCH 6/8] pseries: phyp dump: Unregister and print dump areas.
From: Manish Ahuja @ 2008-01-22 21:05 UTC (permalink / raw)
To: ppc-dev, paulus; +Cc: mahuja, linasvepstas, lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
Routines to invalidate and unregister dump routines.
Unregister has not been used yet, I will release another
patch for that at a later stage with the kdump integration patches.
There is also a routine which calculates the regions to be
freed and exports that through sysfs.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
-----
---
arch/powerpc/platforms/pseries/phyp_dump.c | 101 +++++++++++++++++++++++++----
include/asm/phyp_dump.h | 3
2 files changed, 93 insertions(+), 11 deletions(-)
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 23:06:20.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 23:49:10.000000000 -0600
@@ -69,6 +69,10 @@ static struct phyp_dump_header phdr;
#define DUMP_SOURCE_CPU 0x0001
#define DUMP_SOURCE_HPTE 0x0002
#define DUMP_SOURCE_RMO 0x0011
+#define DUMP_ERROR_FLAG 0x2000
+#define DUMP_TRIGGERED 0x4000
+#define DUMP_PERFORMED 0x8000
+
/**
* init_dump_header() - initialize the header declaring a dump
@@ -180,9 +184,15 @@ static void print_dump_header(const stru
static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
{
int rc;
- ph->cpu_data.destination_address += addr;
- ph->hpte_data.destination_address += addr;
- ph->kernel_data.destination_address += addr;
+
+ /* Add addr value if not initialized before */
+ if (ph->cpu_data.destination_address == 0) {
+ ph->cpu_data.destination_address += addr;
+ ph->hpte_data.destination_address += addr;
+ ph->kernel_data.destination_address += addr;
+ }
+
+ /* ToDo Invalidate kdump and free memory range. */
do {
rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
@@ -195,6 +205,46 @@ static void register_dump_area(struct ph
}
}
+static
+void invalidate_last_dump(struct phyp_dump_header *ph, unsigned long addr)
+{
+ int rc;
+
+ /* Add addr value if not initialized before */
+ if (ph->cpu_data.destination_address == 0) {
+ ph->cpu_data.destination_address += addr;
+ ph->hpte_data.destination_address += addr;
+ ph->kernel_data.destination_address += addr;
+ }
+
+ do {
+ rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
+ 2, ph, sizeof(struct phyp_dump_header));
+ } while (rtas_busy_delay(rc));
+
+ if (rc) {
+ printk (KERN_ERR "phyp-dump: unexpected error (%d) "
+ "on invalidate\n", rc);
+ print_dump_header(ph);
+ }
+}
+
+static void unregister_dump_area(struct phyp_dump_header *ph)
+{
+ int rc;
+
+ do {
+ rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
+ 3, ph, sizeof(struct phyp_dump_header));
+ } while (rtas_busy_delay(rc));
+
+ if (rc) {
+ printk (KERN_ERR "phyp-dump: unexpected error (%d) "
+ "on unregister\n", rc);
+ print_dump_header(ph);
+ }
+}
+
/* ------------------------------------------------- */
/**
* release_memory_range -- release memory previously lmb_reserved
@@ -205,8 +255,8 @@ static void register_dump_area(struct ph
* lmb_reserved in early boot. The released memory becomes
* available for genreal use.
*/
-static void
-release_memory_range(unsigned long start_pfn, unsigned long nr_pages)
+static
+void release_memory_range(unsigned long start_pfn, unsigned long nr_pages)
{
struct page *rpage;
unsigned long end_pfn;
@@ -237,8 +287,8 @@ release_memory_range(unsigned long start
*
* will release 256MB starting at 1GB.
*/
-static ssize_t
-store_release_region(struct kset *kset, const char *buf, size_t count)
+static
+ssize_t store_release_region(struct kset *kset, const char *buf, size_t count)
{
unsigned long start_addr, length, end_addr;
unsigned long start_pfn, nr_pages;
@@ -266,10 +316,23 @@ store_release_region(struct kset *kset,
return count;
}
-static ssize_t
-show_release_region(struct kset * kset, char *buf)
+static ssize_t show_release_region(struct kset * kset, char *buf)
{
- return sprintf(buf, "ola\n");
+ u64 second_addr_range;
+
+ /* total reserved size - start of scratch area */
+ second_addr_range = phyp_dump_info->init_reserve_size -
+ phyp_dump_info->reserved_scratch_size;
+ return sprintf(buf, "CPU:0x%lx-0x%lx: HPTE:0x%lx-0x%lx:"
+ " DUMP:0x%lx-0x%lx, 0x%lx-0x%lx:\n",
+ phdr.cpu_data.destination_address,
+ phdr.cpu_data.length_copied,
+ phdr.hpte_data.destination_address,
+ phdr.hpte_data.length_copied,
+ phdr.kernel_data.destination_address,
+ phdr.kernel_data.length_copied,
+ phyp_dump_info->init_reserve_start,
+ second_addr_range);
}
static struct subsys_attribute rr = __ATTR(release_region, 0600,
@@ -307,7 +370,6 @@ static int __init phyp_dump_setup(void)
release_all();
return -ENOSYS;
}
- print_dump_header(dump_header);
/* Is there dump data waiting for us? If there isn't,
* then register a new dump area, and release all of
@@ -319,6 +381,7 @@ static int __init phyp_dump_setup(void)
rtas = of_find_node_by_path("/rtas");
dump_header = of_get_property(rtas, "ibm,kernel-dump", &header_len);
of_node_put(rtas);
+ print_dump_header(dump_header);
dump_area_length = init_dump_header(&phdr);
dump_area_start = phyp_dump_info->init_reserve_start & PAGE_MASK; /* align down */
@@ -328,6 +391,22 @@ static int __init phyp_dump_setup(void)
return 0;
}
+ /* re-register the dump area, if old dump was invalid */
+ if ((dump_header) && (dump_header->status & DUMP_ERROR_FLAG)) {
+ invalidate_last_dump(&phdr, dump_area_start);
+ register_dump_area(&phdr, dump_area_start);
+ return 0;
+ }
+
+ if (dump_header) {
+ phyp_dump_info->reserved_scratch_addr =
+ dump_header->cpu_data.destination_address;
+ phyp_dump_info->reserved_scratch_size =
+ dump_header->cpu_data.source_length +
+ dump_header->hpte_data.source_length +
+ dump_header->kernel_data.source_length;
+ }
+
/* Should we create a dump_subsys, analogous to s390/ipl.c ? */
rc = subsys_create_file(&kernel_subsys, &rr);
if (rc)
Index: 2.6.24-rc5/include/asm/phyp_dump.h
===================================================================
--- 2.6.24-rc5.orig/include/asm/phyp_dump.h 2008-01-21 22:21:01.000000000 -0600
+++ 2.6.24-rc5/include/asm/phyp_dump.h 2008-01-21 23:29:05.000000000 -0600
@@ -29,6 +29,9 @@ struct phyp_dump {
/* store cpu & hpte size */
unsigned long cpu_state_size;
unsigned long hpte_region_size;
+ /* previous scratch area values */
+ unsigned long reserved_scratch_addr;
+ unsigned long reserved_scratch_size;
};
extern struct phyp_dump *phyp_dump_info;
^ permalink raw reply
* Re: [PATCH] Various new ibm405 DCRN #defines
From: Benjamin Herrenschmidt @ 2008-01-22 20:58 UTC (permalink / raw)
To: Josh Boyer; +Cc: linuxppc-dev, Joshua Williams
In-Reply-To: <20080122111038.1072dac4@weaponx>
On Tue, 2008-01-22 at 11:10 -0600, Josh Boyer wrote:
> On Tue, 22 Jan 2008 11:08:38 -0600
> Joshua Williams <joshua.williams@qlogic.com> wrote:
>
> > Benjamin Herrenschmidt wrote:
> > > On Mon, 2008-01-21 at 16:43 -0600, Joshua Williams wrote:
> > >> Various new ibm405 DCRN #defines.
> > >>
> > >> Signed-off-by: Joshua Williams <joshua.williams@qlogic.com>
> > >
> > > May I ask what for ? :-) Also, it's all arch/ppc, not arch/powerpc...
> > > nothing we want to improve to much on at this stage unless there's a
> > > really good reason.
> >
> > The 405x #defines were incomplete and this was meant to
> > make them a bit tighter. Since arch/ppc is in life support
> > mode this can wait until the 405x stuff gets moved over to
> > arch/powerpc.
>
> Which 405x stuff? Walnut is moved over already. Other boards will
> need to be ported by people that have those boards.
I have no objection with adding #define's to arch/powerpc somewhere
though I'd like to avoid having 36 different .h files per processor
type.
Ben.
^ permalink raw reply
* [PATCH 7/8] pseries: phyp dump: Tracking memory range freed.
From: Manish Ahuja @ 2008-01-22 21:07 UTC (permalink / raw)
To: ppc-dev, paulus; +Cc: mahuja, linasvepstas, lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
This patch tracks the size freed. For now it does a simple
rudimentary calculation of the ranges freed. The idea is
to keep it simple at the external shell script level and
send in large chunks for now.
Signed-off-by: Manish Ahuja <mahuja@us.ibm.com>
-----
---
arch/powerpc/platforms/pseries/phyp_dump.c | 35 +++++++++++++++++++++++++++++
1 file changed, 35 insertions(+)
Index: 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c
===================================================================
--- 2.6.24-rc5.orig/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 23:30:18.000000000 -0600
+++ 2.6.24-rc5/arch/powerpc/platforms/pseries/phyp_dump.c 2008-01-21 23:42:04.000000000 -0600
@@ -275,6 +275,39 @@ void release_memory_range(unsigned long
}
}
+/**
+ * track_freed_range -- Counts the range being freed.
+ * Once the counter goes to zero, it re-registers dump for
+ * future use.
+ */
+static void
+track_freed_range(unsigned long addr, unsigned long length)
+{
+ static unsigned long scratch_area_size, reserved_area_size;
+
+ if (addr < phyp_dump_info->init_reserve_start)
+ return;
+
+ if ((addr >= phyp_dump_info->init_reserve_start) &&
+ (addr <= phyp_dump_info->init_reserve_start +
+ phyp_dump_info->init_reserve_size))
+ reserved_area_size += length;
+
+ if ((addr >= phyp_dump_info->reserved_scratch_addr) &&
+ (addr <= phyp_dump_info->reserved_scratch_addr +
+ phyp_dump_info->reserved_scratch_size))
+ scratch_area_size += length;
+
+ if ((reserved_area_size == phyp_dump_info->init_reserve_size) &&
+ (scratch_area_size == phyp_dump_info->reserved_scratch_size)) {
+
+ invalidate_last_dump(&phdr,
+ phyp_dump_info->reserved_scratch_addr);
+ register_dump_area (&phdr,
+ phyp_dump_info->reserved_scratch_addr);
+ }
+}
+
/* ------------------------------------------------- */
/**
* sysfs_release_region -- sysfs interface to release memory range.
@@ -298,6 +331,8 @@ ssize_t store_release_region(struct kset
if (ret != 2)
return -EINVAL;
+ track_freed_range(start_addr, length);
+
/* Range-check - don't free any reserved memory that
* wasn't reserved for phyp-dump */
if (start_addr < phyp_dump_info->init_reserve_start)
^ permalink raw reply
* Re: [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Kumar Gala @ 2008-01-22 21:07 UTC (permalink / raw)
To: Jon Loeliger; +Cc: linuxppc-dev
In-Reply-To: <47965506.9070305@freescale.com>
On Jan 22, 2008, at 2:41 PM, Jon Loeliger wrote:
> Wade Farnsworth wrote:
>
>> +
>> + ranges = <0 0 ff800000 00800000
>> + 1 0 fe000000 01000000
>> + 2 0 f8200000 00100000
>> + 3 0 f8100000 00100000>;
>> +
>
> I think you want just:
>
> ranges = <0 0 f8000000 8000000>
>
> right? And is it really on CS 0?
I'm assuming he's listed CS1, CS2, and CS3 even though we don't have a
children yet. (second flash chip, CF, and pixis).
- k
^ permalink raw reply
* [PATCH 8/8] pseries: phyp dump: config file
From: Manish Ahuja @ 2008-01-22 21:09 UTC (permalink / raw)
To: ppc-dev, paulus; +Cc: mahuja, linasvepstas, lkessler, strosake
In-Reply-To: <4796401D.5010907@austin.ibm.com>
To: linuxppc-dev@ozlabs.org
Add hypervisor-assisted dump to kernel config
Signed-off-by: Linas Vepstas <linasvepstas@gmail.com>
-----
arch/powerpc/Kconfig | 11 +++++++++++
1 file changed, 11 insertions(+)
Index: linux-2.6.24-rc2-git4/arch/powerpc/Kconfig
===================================================================
--- linux-2.6.24-rc2-git4.orig/arch/powerpc/Kconfig 2007-11-14 16:39:20.000000000 -0600
+++ linux-2.6.24-rc2-git4/arch/powerpc/Kconfig 2007-11-15 14:27:33.000000000 -0600
@@ -261,6 +261,17 @@ config CRASH_DUMP
Don't change this unless you know what you are doing.
+config PHYP_DUMP
+ bool "Hypervisor-assisted dump (EXPERIMENTAL)"
+ depends on PPC_PSERIES && EXPERIMENTAL
+ default y
+ help
+ Hypervisor-assisted dump is meant to be a kdump replacement
+ offering robustness and speed not possible without system
+ hypervisor assistence.
+
+ If unsure, say "Y"
+
config PPCBUG_NVRAM
bool "Enable reading PPCBUG NVRAM during boot" if PPLUS || LOPEC
default y if PPC_PREP
^ permalink raw reply
* [PATCH] [POWERPC] Add docs for Freescale DMA & DMA channel device tree nodes
From: Kumar Gala @ 2008-01-22 21:13 UTC (permalink / raw)
To: Timur Tabi, Scott Wood; +Cc: linuxppc-dev
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Ebony Zhu <ebony.zhu@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
Guys please review and make sure I got all your previous comments fixed
up. I've added cell-index. and the examples should represent real HW.
Documentation/powerpc/booting-without-of.txt | 128 ++++++++++++++++++++++++++
1 files changed, 128 insertions(+), 0 deletions(-)
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index da98154..3584c33 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -2615,6 +2615,134 @@ platforms are moved over to use the flattened-device-tree model.
- clock-frequency : The frequency of the input clock, which typically
comes from an on-board dedicated oscillator.
+ * Freescale 83xx DMA Controller
+
+ Freescale PowerPC 83xx have on chip general purpose DMA controllers.
+
+ Required properties:
+
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma", where CHIP is the processor
+ (mpc8349, mpc8360, etc.) and the second is
+ "fsl,elo-dma"
+ - reg : <registers mapping for DMA general status reg>
+ - ranges : Should be defined as specified in 1) to describe the
+ DMA controller channels.
+ - cell-index : controller index. 0 for controller @ 0x8100
+ - interrupts : <interrupt mapping for DMA IRQ>
+ - interrupt-parent : optional, if needed for interrupt mapping
+
+
+ - DMA channel nodes:
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma-channel", where CHIP is the processor
+ (mpc8349, mpc8350, etc.) and the second is
+ "fsl,elo-dma-channel"
+ - reg : <registers mapping for channel>
+ - cell-index : dma channel index starts at 0.
+
+ Optional properties:
+ - interrupts : <interrupt mapping for DMA channel IRQ>
+ (on 83xx this is expected to be identical to
+ the interrupts property of the parent node)
+ - interrupt-parent : optional, if needed for interrupt mapping
+
+ Example:
+ dma@82a8 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
+ reg = <82a8 4>;
+ ranges = <0 8100 1a4>;
+ interrupt-parent = <&ipic>;
+ interrupts = <47 8>;
+ cell-index = <0>;
+ dma-channel@0 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <0>;
+ reg = <0 80>;
+ };
+ dma-channel@80 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <1>;
+ reg = <80 80>;
+ };
+ dma-channel@100 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <2>;
+ reg = <100 80>;
+ };
+ dma-channel@180 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <3>;
+ reg = <180 80>;
+ };
+ };
+
+ * Freescale 85xx/86xx DMA Controller
+
+ Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
+
+ Required properties:
+
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma", where CHIP is the processor
+ (mpc8540, mpc8540, etc.) and the second is
+ "fsl,eloplus-dma"
+ - reg : <registers mapping for DMA general status reg>
+ - cell-index : controller index. 0 for controller @ 0x21000,
+ 1 for controller @ 0xc000
+ - ranges : Should be defined as specified in 1) to describe the
+ DMA controller channels.
+
+ - DMA channel nodes:
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma-channel", where CHIP is the processor
+ (mpc8540, mpc8560, etc.) and the second is
+ "fsl,eloplus-dma-channel"
+ - cell-index : dma channel index starts at 0.
+ - reg : <registers mapping for channel>
+ - interrupts : <interrupt mapping for DMA channel IRQ>
+ - interrupt-parent : optional, if needed for interrupt mapping
+
+ Example:
+ dma@21300 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
+ reg = <21300 4>;
+ ranges = <0 21100 200>;
+ cell-index = <0>;
+ dma-channel@0 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <0 80>;
+ cell-index = <0>;
+ interrupt-parent = <&mpic>;
+ interrupts = <14 2>;
+ };
+ dma-channel@80 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <80 80>;
+ cell-index = <1>;
+ interrupt-parent = <&mpic>;
+ interrupts = <15 2>;
+ };
+ dma-channel@100 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <100 80>;
+ cell-index = <2>;
+ interrupt-parent = <&mpic>;
+ interrupts = <16 2>;
+ };
+ dma-channel@180 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <180 80>;
+ cell-index = <3>;
+ interrupt-parent = <&mpic>;
+ interrupts = <17 2>;
+ };
+ };
+
More devices will be defined as this spec matures.
--
1.5.3.7
^ permalink raw reply related
* Re: [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Wade Farnsworth @ 2008-01-22 21:19 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev
In-Reply-To: <65C80AAA-CC92-41BC-86FC-D74A2C7D5059@kernel.crashing.org>
On Tue, 2008-01-22 at 15:07 -0600, Kumar Gala wrote:
> On Jan 22, 2008, at 2:41 PM, Jon Loeliger wrote:
>
> > Wade Farnsworth wrote:
> >
> >> +
> >> + ranges = <0 0 ff800000 00800000
> >> + 1 0 fe000000 01000000
> >> + 2 0 f8200000 00100000
> >> + 3 0 f8100000 00100000>;
> >> +
> >
> > I think you want just:
> >
> > ranges = <0 0 f8000000 8000000>
Wouldn't that cover all of the CCSR regs, not just CS0?
> >
> > right? And is it really on CS 0?
>
> I'm assuming he's listed CS1, CS2, and CS3 even though we don't have a
> children yet. (second flash chip, CF, and pixis).
Yes that's correct.
--Wade
^ permalink raw reply
* Re: [PATCH v2 1/2] Add localbus and flash nodes to mpc8641_hpcn.dts
From: Jon Loeliger @ 2008-01-22 21:22 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev
In-Reply-To: <65C80AAA-CC92-41BC-86FC-D74A2C7D5059@kernel.crashing.org>
Kumar Gala wrote:
> I'm assuming he's listed CS1, CS2, and CS3 even though we don't have a
> children yet. (second flash chip, CF, and pixis).
>
> - k
OK -- I just wasn't sure if you wanted the other
CS entries for nodes that weren't actually present yet.
jdl
^ permalink raw reply
* Re: crash in kmem_cache_init
From: Mel Gorman @ 2008-01-22 21:26 UTC (permalink / raw)
To: Christoph Lameter
Cc: lee.schermerhorn, Olaf Hering, Linux MM, linux-kernel,
linuxppc-dev, Pekka Enberg, Aneesh Kumar K.V, hanth Aravamudan,
akpm, KAMEZAWA Hiroyuki
In-Reply-To: <Pine.LNX.4.64.0801221203340.27950@schroedinger.engr.sgi.com>
On (22/01/08 12:11), Christoph Lameter didst pronounce:
> On Tue, 22 Jan 2008, Mel Gorman wrote:
>
> > Christoph/Pekka, this patch is papering over the problem and something
> > more fundamental may be going wrong. The crash occurs because l3 is NULL
> > and the cache is kmem_cache so this is early in the boot process. It is
> > selecting l3 based on node 2 which is correct in terms of available memory
> > but it initialises the lists on node 0 because that is the node the CPUs are
> > located. Hence later it uses an uninitialised nodelists and BLAM. Relevant
> > parts of the log for seeing the memoryless nodes in relation to CPUs is;
>
> Would it be possible to run the bootstrap on a cpu that has a
> node with memory associated to it?
Not in the way the machine is currently configured. All the CPUs appear to
be on a node with no memory. It's best to assume I cannot get the machine
reconfigured (which just hides the bug anyway). Physically, it's thousands
of miles away so I can't do the work. I can get lab support to do the job
but that will take a fair while and at the end of the day, it doesn't tell
us a lot. We know that other PPC64 machines work so it's not a general problem.
> I believe we had the same situation
> last year when GFP_THISNODE was introduced?
>
It feels vaguely familiar but I don't recall the details in sufficient detail
to recognise if this is the same problem or not.
> After you reverted the slab memoryless node patch there should be per node
> structures created for node 0 unless the node is marked offline. Is it? If
> so then you are booting a cpu that is associated with an offline node.
>
I'll roll a patch that prints out the online states before startup and
see what it looks like.
> > Can you see a better solution than this?
>
> Well this means that bootstrap will work by introducing foreign objects
> into the per cpu queue (should only hold per cpu objects). They will
> later be consumed and then the queues will contain the right objects so
> the effect of the patch is minimal.
>
By minimal, do you mean that you expect it to break in some other
respect later or minimal as in "this is bad but should not have no
adverse impact".
> I thought we fixed the similar situation last year by dropping
> GFP_THISNODE for some allocations?
>
Whatever this was a problem fixed in the past or not, it's broken again now
:( . It's possible that there is a __GFP_THISNODE that can be dropped early
at boot-time that would also fix this problem in a way that doesn't
affect runtime (like altering cache_grow in my patch does).
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox