[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20111031171158.12259.16461.stgit@mars.in.ibm.com>
Date: Mon, 31 Oct 2011 22:41:58 +0530
From: Mahesh J Salgaonkar <mahesh@...ux.vnet.ibm.com>
To: linuxppc-dev <linuxppc-dev@...abs.org>,
Linux Kernel <linux-kernel@...r.kernel.org>,
Benjamin Herrenschmidt <benh@...nel.crashing.org>
Cc: Haren Myneni <hbabu@...ibm.com>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Amerigo Wang <amwang@...hat.com>,
Milton Miller <miltonm@....com>,
Anton Blanchard <anton@...ba.org>
Subject: [RFC PATCH v3 08/10] fadump: Invalidate registration and release
reserved memory for general use.
From: Mahesh Salgaonkar <mahesh@...ux.vnet.ibm.com>
This patch introduces an sysfs interface '/sys/kernel/fadump_release_mem' to
invalidate the last fadump registration, invalidate '/proc/vmcore', release
the reserved memory for general use and re-register for future kernel dump.
Once the dump is copied to the disk, the userspace tool will echo 1 to
'/sys/kernel/fadump_release_mem'.
Release the reserved memory region excluding the size of the memory required
for future kernel dump registration.
Change in v3:
- Syncronize the fadump invalidation step to handle simultaneous writes to
/sys/kernel/fadump_release_mem.
Change in v2:
- Introduced cpu_notes_buf_free() function to free memory allocated for
cpu notes buffer.
Signed-off-by: Mahesh Salgaonkar <mahesh@...ux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 3 +
arch/powerpc/kernel/fadump.c | 170 ++++++++++++++++++++++++++++++++++++-
2 files changed, 169 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 4a7d63e..2d983e8 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -196,6 +196,9 @@ extern int fadump_reserve_mem(void);
extern int setup_fadump(void);
extern int is_fadump_active(void);
extern void crash_fadump(struct pt_regs *, const char *);
+extern void fadump_cleanup(void);
+
+extern void vmcore_cleanup(void);
#else /* CONFIG_FA_DUMP */
static inline int is_fadump_active(void) { return 0; }
#endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 4d42fe5..ecdf81b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,8 @@
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -560,6 +562,19 @@ static void *cpu_notes_buf_alloc(unsigned long size)
return vaddr;
}
+static void cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+}
+
/*
* Read CPU state dump data and convert it into ELF notes.
* The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
@@ -944,6 +959,131 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
return 0;
}
+static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Invalidating firmware-assisted dump registration\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_INVALIDATE, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+ } while (wait_time);
+
+ if (rc) {
+ printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
+ "rgistration. unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_active = 0;
+ fdm_active = NULL;
+ return 0;
+}
+
+void fadump_cleanup(void)
+{
+ /* Invalidate the registration only if dump is active. */
+ if (fw_dump.dump_active) {
+ init_fadump_mem_struct(&fdm,
+ fdm_active->cpu_state_data.destination_address);
+ fadump_invalidate_dump(&fdm);
+ }
+}
+
+/*
+ * Release the memory that was reserved in early boot to preserve the memory
+ * contents. The released memory will be available for general use.
+ */
+static void fadump_release_memory(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+ unsigned long ra_start, ra_end;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ /*
+ * exclude the dump reserve area. Will reuse it for next
+ * fadump registration.
+ */
+ if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
+ continue;
+
+ ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+ init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+ free_page((unsigned long)__va(addr));
+ totalram_pages++;
+ }
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+ unsigned long reserved_area_start, reserved_area_end;
+ unsigned long destination_address;
+
+ mutex_lock(&fadump_mutex);
+ if (!fw_dump.dump_active) {
+ mutex_unlock(&fadump_mutex);
+ return;
+ }
+
+ destination_address = fdm_active->cpu_state_data.destination_address;
+ fadump_cleanup();
+ mutex_unlock(&fadump_mutex);
+
+ /*
+ * Save the current reserved memory bounds we will require them
+ * later for releasing the memory for general use.
+ */
+ reserved_area_start = fw_dump.reserve_dump_area_start;
+ reserved_area_end = reserved_area_start +
+ fw_dump.reserve_dump_area_size;
+ /*
+ * Setup reserve_dump_area_start and its size so that we can
+ * reuse this reserved memory for Re-registration.
+ */
+ fw_dump.reserve_dump_area_start = destination_address;
+ fw_dump.reserve_dump_area_size = get_dump_area_size();
+
+ fadump_release_memory(reserved_area_start, reserved_area_end);
+ if (fw_dump.cpu_notes_buf) {
+ cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ }
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+}
+
+static ssize_t fadump_release_memory_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ if (!fw_dump.dump_active)
+ return -EPERM;
+
+ if (buf[0] == '1') {
+ /*
+ * Take away the '/proc/vmcore'. We are releasing the dump
+ * memory, hence it will not be valid anymore.
+ */
+ vmcore_cleanup();
+ fadump_invalidate_release_mem();
+
+ } else
+ return -EINVAL;
+ return count;
+}
+
static ssize_t fadump_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
@@ -1003,10 +1143,13 @@ static int fadump_region_show(struct seq_file *m, void *private)
if (!fw_dump.fadump_enabled)
return 0;
+ mutex_lock(&fadump_mutex);
if (fdm_active)
fdm_ptr = fdm_active;
- else
+ else {
+ mutex_unlock(&fadump_mutex);
fdm_ptr = &fdm;
+ }
seq_printf(m,
"CPU : [%#016llx-%#016llx] %#llx bytes, "
@@ -1036,7 +1179,7 @@ static int fadump_region_show(struct seq_file *m, void *private)
if (!fdm_active ||
(fw_dump.reserve_dump_area_start ==
fdm_ptr->cpu_state_data.destination_address))
- return 0;
+ goto out;
/* Dump is active. Show reserved memory region. */
seq_printf(m,
@@ -1048,9 +1191,15 @@ static int fadump_region_show(struct seq_file *m, void *private)
fw_dump.reserve_dump_area_start,
fdm_ptr->cpu_state_data.destination_address -
fw_dump.reserve_dump_area_start);
+out:
+ if (fdm_active)
+ mutex_unlock(&fadump_mutex);
return 0;
}
+static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
+ 0200, NULL,
+ fadump_release_memory_store);
static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
0444, fadump_enabled_show,
NULL);
@@ -1091,6 +1240,13 @@ static void fadump_init_files(void)
if (!debugfs_file)
printk(KERN_ERR "fadump: unable to create debugfs file"
" fadump_region\n");
+
+ if (fw_dump.dump_active) {
+ rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_release_mem (%d)\n", rc);
+ }
return;
}
@@ -1110,8 +1266,14 @@ int __init setup_fadump(void)
* If dump data is available then see if it is valid and prepare for
* saving it to the disk.
*/
- if (fw_dump.dump_active)
- process_fadump(fdm_active);
+ if (fw_dump.dump_active) {
+ /*
+ * if dump process fails then invalidate the registration
+ * and release memory before proceeding for re-registration.
+ */
+ if (process_fadump(fdm_active) < 0)
+ fadump_invalidate_release_mem();
+ }
/* Initialize the kernel dump memory structure for FAD registration. */
else if (fw_dump.reserve_dump_area_size)
init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists