fadump: Register for firmware assisted dump.
On 2012-02-20 11:02:51 Mon, Paul Mackerras wrote:
> On Thu, Feb 16, 2012 at 04:44:30PM +0530, Mahesh J Salgaonkar wrote:
>
> If I have read the code correctly, we are going to get this printk on
> non-pSeries machines or on older pSeries machines, even if the user
> has not put the fadump=on option on the kernel command line. The
> printk will be annoying since there is no actual error condition. It
> seems to me that the condition for the printk should include
> fw_dump.fadump_enabled. In other words you should probably add
>
> if (!fw_dump.fadump_enabled)
> return 0;
>
> at the beginning of the function.
Hi Paul,
Thanks for pointing it out. Please find the updated patch below.
The existing patches above this (4/10 through 10/10) cleanly applies
on this update.
Thanks,
-Mahesh.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index deb276a..eb8f782 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -29,6 +29,9 @@
#include <linux/string.h>
#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -36,6 +39,10 @@
#include <asm/fadump.h>
static struct fw_dump fw_dump;
+static struct fadump_mem_struct fdm;
+static const struct fadump_mem_struct *fdm_active;
+
+static DEFINE_MUTEX(fadump_mutex);
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node,
@@ -64,7 +71,8 @@
* The 'ibm,kernel-dump' rtas node is present only if there is
* dump data waiting for us.
*/
- if (of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL))
+ fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+ if (fdm_active)
fw_dump.dump_active = 1;
/* Get the sizes required to store dump data for the firmware provided
@@ -98,6 +106,85 @@
return 1;
}
+int is_fadump_active(void)
+{
+ return fw_dump.dump_active;
+}
+
+/* Print firmware assisted dump configurations for debugging purpose. */
+static void fadump_show_config(void)
+{
+ pr_debug("Support for firmware-assisted dump (fadump): %s\n",
+ (fw_dump.fadump_supported ? "present" : "no support"));
+
+ if (!fw_dump.fadump_supported)
+ return;
+
+ pr_debug("Fadump enabled : %s\n",
+ (fw_dump.fadump_enabled ? "yes" : "no"));
+ pr_debug("Dump Active : %s\n",
+ (fw_dump.dump_active ? "yes" : "no"));
+ pr_debug("Dump section sizes:\n");
+ pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
+ pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
+ pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size);
+}
+
+static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
+ unsigned long addr)
+{
+ if (!fdm)
+ return 0;
+
+ memset(fdm, 0, sizeof(struct fadump_mem_struct));
+ addr = addr & PAGE_MASK;
+
+ fdm->header.dump_format_version = 0x00000001;
+ fdm->header.dump_num_sections = 3;
+ fdm->header.dump_status_flag = 0;
+ fdm->header.offset_first_dump_section =
+ (u32)offsetof(struct fadump_mem_struct, cpu_state_data);
+
+ /*
+ * Fields for disk dump option.
+ * We are not using disk dump option, hence set these fields to 0.
+ */
+ fdm->header.dd_block_size = 0;
+ fdm->header.dd_block_offset = 0;
+ fdm->header.dd_num_blocks = 0;
+ fdm->header.dd_offset_disk_path = 0;
+
+ /* set 0 to disable an automatic dump-reboot. */
+ fdm->header.max_time_auto = 0;
+
+ /* Kernel dump sections */
+ /* cpu state data section. */
+ fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA;
+ fdm->cpu_state_data.source_address = 0;
+ fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size;
+ fdm->cpu_state_data.destination_address = addr;
+ addr += fw_dump.cpu_state_data_size;
+
+ /* hpte region section */
+ fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION;
+ fdm->hpte_region.source_address = 0;
+ fdm->hpte_region.source_len = fw_dump.hpte_region_size;
+ fdm->hpte_region.destination_address = addr;
+ addr += fw_dump.hpte_region_size;
+
+ /* RMA region section */
+ fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION;
+ fdm->rmr_region.source_address = RMA_START;
+ fdm->rmr_region.source_len = fw_dump.boot_memory_size;
+ fdm->rmr_region.destination_address = addr;
+ addr += fw_dump.boot_memory_size;
+
+ return addr;
+}
+
/**
* fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
*
@@ -166,8 +253,15 @@
fw_dump.fadump_enabled = 0;
return 0;
}
- /* Initialize boot memory size */
- fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+ /*
+ * Initialize boot memory size
+ * If dump is active then we have already calculated the size during
+ * first kernel.
+ */
+ if (fdm_active)
+ fw_dump.boot_memory_size = fdm_active->rmr_region.source_len;
+ else
+ fw_dump.boot_memory_size = fadump_calculate_reserve_size();
/*
* Calculate the memory boundary.
@@ -244,3 +338,258 @@
return 0;
}
early_param("fadump_reserve_mem", early_fadump_reserve_mem);
+
+static void register_fw_dump(struct fadump_mem_struct *fdm)
+{
+ int rc;
+ unsigned int wait_time;
+
+ pr_debug("Registering for firmware-assisted kernel dump...\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_REGISTER, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+
+ } while (wait_time);
+
+ switch (rc) {
+ case -1:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Hardware Error(%d).\n", rc);
+ break;
+ case -3:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Parameter Error(%d).\n", rc);
+ break;
+ case -9:
+ printk(KERN_ERR "firmware-assisted kernel dump is already "
+ " registered.");
+ fw_dump.dump_registered = 1;
+ break;
+ case 0:
+ printk(KERN_INFO "firmware-assisted kernel dump registration"
+ " is successful\n");
+ fw_dump.dump_registered = 1;
+ break;
+ }
+}
+
+static void register_fadump(void)
+{
+ /*
+ * If no memory is reserved then we can not register for firmware-
+ * assisted dump.
+ */
+ if (!fw_dump.reserve_dump_area_size)
+ return;
+
+ /* register the future kernel dump with firmware. */
+ register_fw_dump(&fdm);
+}
+
+static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Un-register firmware-assisted dump\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_UNREGISTER, 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 un-register firmware-assisted dump."
+ " unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_registered = 0;
+ return 0;
+}
+
+static ssize_t fadump_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
+}
+
+static ssize_t fadump_register_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.dump_registered);
+}
+
+static ssize_t fadump_register_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret = 0;
+
+ if (!fw_dump.fadump_enabled || fdm_active)
+ return -EPERM;
+
+ mutex_lock(&fadump_mutex);
+
+ switch (buf[0]) {
+ case '0':
+ if (fw_dump.dump_registered == 0) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Un-register Firmware-assisted dump */
+ fadump_unregister_dump(&fdm);
+ break;
+ case '1':
+ if (fw_dump.dump_registered == 1) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Register Firmware-assisted dump */
+ register_fadump();
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+unlock_out:
+ mutex_unlock(&fadump_mutex);
+ return ret < 0 ? ret : count;
+}
+
+static int fadump_region_show(struct seq_file *m, void *private)
+{
+ const struct fadump_mem_struct *fdm_ptr;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else
+ fdm_ptr = &fdm;
+
+ seq_printf(m,
+ "CPU : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->cpu_state_data.destination_address,
+ fdm_ptr->cpu_state_data.destination_address +
+ fdm_ptr->cpu_state_data.source_len - 1,
+ fdm_ptr->cpu_state_data.source_len,
+ fdm_ptr->cpu_state_data.bytes_dumped);
+ seq_printf(m,
+ "HPTE: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->hpte_region.destination_address,
+ fdm_ptr->hpte_region.destination_address +
+ fdm_ptr->hpte_region.source_len - 1,
+ fdm_ptr->hpte_region.source_len,
+ fdm_ptr->hpte_region.bytes_dumped);
+ seq_printf(m,
+ "DUMP: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->rmr_region.destination_address,
+ fdm_ptr->rmr_region.destination_address +
+ fdm_ptr->rmr_region.source_len - 1,
+ fdm_ptr->rmr_region.source_len,
+ fdm_ptr->rmr_region.bytes_dumped);
+
+ if (!fdm_active ||
+ (fw_dump.reserve_dump_area_start ==
+ fdm_ptr->cpu_state_data.destination_address))
+ return 0;
+
+ /* Dump is active. Show reserved memory region. */
+ seq_printf(m,
+ " : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ (unsigned long long)fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address - 1,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start);
+ return 0;
+}
+
+static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
+ 0444, fadump_enabled_show,
+ NULL);
+static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
+ 0644, fadump_register_show,
+ fadump_register_store);
+
+static int fadump_region_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, fadump_region_show, inode->i_private);
+}
+
+static const struct file_operations fadump_region_fops = {
+ .open = fadump_region_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void fadump_init_files(void)
+{
+ struct dentry *debugfs_file;
+ int rc = 0;
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_enabled (%d)\n", rc);
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_registered (%d)\n", rc);
+
+ debugfs_file = debugfs_create_file("fadump_region", 0444,
+ powerpc_debugfs_root, NULL,
+ &fadump_region_fops);
+ if (!debugfs_file)
+ printk(KERN_ERR "fadump: unable to create debugfs file"
+ " fadump_region\n");
+ return;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_ERR "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ return 0;
+ }
+
+ fadump_show_config();
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ if (fw_dump.reserve_dump_area_size)
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ fadump_init_files();
+
+ return 1;
+}
+subsys_initcall(setup_fadump);