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>

4 files changed, 427 insertions, 4 deletions

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 7be25d3..bbaf278 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -48,6 +48,58 @@
 #define FADUMP_HPTE_REGION	0x0002
 #define FADUMP_REAL_MODE_REGION	0x0011
 
+/* Dump request flag */
+#define FADUMP_REQUEST_FLAG	0x00000001
+
+/* FAD commands */
+#define FADUMP_REGISTER		1
+#define FADUMP_UNREGISTER	2
+#define FADUMP_INVALIDATE	3
+
+/* Kernel Dump section info */
+struct fadump_section {
+	u32	request_flag;
+	u16	source_data_type;
+	u16	error_flags;
+	u64	source_address;
+	u64	source_len;
+	u64	bytes_dumped;
+	u64	destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct fadump_section_header {
+	u32	dump_format_version;
+	u16	dump_num_sections;
+	u16	dump_status_flag;
+	u32	offset_first_dump_section;
+
+	/* Fields for disk dump option. */
+	u32	dd_block_size;
+	u64	dd_block_offset;
+	u64	dd_num_blocks;
+	u32	dd_offset_disk_path;
+
+	/* Maximum time allowed to prevent an automatic dump-reboot. */
+	u32	max_time_auto;
+};
+
+/*
+ * Firmware Assisted dump memory structure. This structure is required for
+ * registering future kernel dump with power firmware through rtas call.
+ *
+ * No disk dump option. Hence disk dump path string section is not included.
+ */
+struct fadump_mem_struct {
+	struct fadump_section_header	header;
+
+	/* Kernel dump sections */
+	struct fadump_section		cpu_state_data;
+	struct fadump_section		hpte_region;
+	struct fadump_section		rmr_region;
+};
+
+/* Firmware-assisted dump configuration details. */
 struct fw_dump {
 	unsigned long	cpu_state_data_size;
 	unsigned long	hpte_region_size;
@@ -62,10 +114,15 @@ struct fw_dump {
 	unsigned long	fadump_enabled:1;
 	unsigned long	fadump_supported:1;
 	unsigned long	dump_active:1;
+	unsigned long	dump_registered:1;
 };
 
 extern int early_init_dt_scan_fw_dump(unsigned long node,
 		const char *uname, int depth, void *data);
 extern int fadump_reserve_mem(void);
+extern int setup_fadump(void);
+extern int is_fadump_active(void);
+#else	/* CONFIG_FA_DUMP */
+static inline int is_fadump_active(void) { return 0; }
 #endif
 #endif
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 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 	 * 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 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 	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 @@ int __init fadump_reserve_mem(void)
 		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 @@ static int __init early_fadump_reserve_mem(char *p)
 	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);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0cfcf98..359f078 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -39,6 +39,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/machdep.h>
 #include <asm/kdump.h>
+#include <asm/fadump.h>
 
 #define DBG(...)
 
@@ -445,7 +446,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 static void iommu_table_clear(struct iommu_table *tbl)
 {
-	if (!is_kdump_kernel()) {
+	/*
+	 * In case of firmware assisted dump system goes through clean
+	 * reboot process at the time of system crash. Hence it's safe to
+	 * clear the TCE entries if firmware assisted dump is active.
+	 */
+	if (!is_kdump_kernel() || is_fadump_active()) {
 		/* Clear the table in case firmware left allocations in it */
 		ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
 		return;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2d28218..b534bba 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -55,6 +55,7 @@
 #include <asm/spu.h>
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
+#include <asm/fadump.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -625,6 +626,16 @@ static void __init htab_initialize(void)
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
+#ifdef CONFIG_FA_DUMP
+		/*
+		 * If firmware assisted dump is active firmware preserves
+		 * the contents of htab along with entire partition memory.
+		 * Clear the htab if firmware assisted dump is active so
+		 * that we dont end up using old mappings.
+		 */
+		if (is_fadump_active() && ppc_md.hpte_clear_all)
+			ppc_md.hpte_clear_all();
+#endif
 	} else {
 		/* Find storage for the HPT.  Must be contiguous in
 		 * the absolute address space. On cell we want it to be