From: Hari Bathini <hbath...@linux.vnet.ibm.com>
Firmware provides architected register state data at the time of crash.
This data contains PIR value. Need to store the logical CPUs PIR values
to match the data provided by f/w with the corresponding logical CPU.
Signed-off-by: Hari Bathini <hbath...@linux.vnet.ibm.com>
---
arch/powerpc/kernel/fadump.c | 38 ++++++
arch/powerpc/kernel/fadump_internal.h | 12 ++
arch/powerpc/platforms/powernv/powernv_fadump.c | 146 +++++++++++++++++++++--
arch/powerpc/platforms/powernv/powernv_fadump.h | 13 ++
4 files changed, 195 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index a27e4af..8cafa2b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -421,6 +421,7 @@ static unsigned long get_fadump_area_size(void)
size += fw_dump.cpu_state_data_size;
size += fw_dump.hpte_region_size;
size += fw_dump.boot_memory_size;
+ size += fw_dump.backup_area_size;
size += sizeof(struct fadump_crash_info_header);
size += sizeof(struct elfhdr); /* ELF core header.*/
size += sizeof(struct elf_phdr); /* place holder for cpu notes */
@@ -985,6 +986,37 @@ static unsigned long init_fadump_header(unsigned long addr)
return addr;
}
+static inline void read_pir(void *val)
+{
+ *(unsigned long *)val = mfspr(SPRN_PIR);
+}
+
+static unsigned long fadump_populate_backup_area(void)
+{
+ struct fadump_backup_area *backup_info;
+ unsigned int i, size = sizeof(struct fadump_backup_area);
+ unsigned long addr;
+
+ if (fadump_ops->get_backup_area_start)
+ return 0;
+
+ addr = fadump_ops->get_backup_area_start(&fw_dump);
+ backup_info = __va(addr);
+ addr += fw_dump.backup_area_size;
+
+ memset(backup_info, 0, size);
+ backup_info->size = size;
+ backup_info->nr_threads = nr_cpu_ids;
+ for (i = 0; i < nr_cpu_ids; i++) {
+ smp_call_function_single(i, read_pir,
+ &(backup_info->thread_pir[i]), 1);
+ pr_debug("Logical CPU: %d, PIR: 0x%lx\n",
+ i, backup_info->thread_pir[i]);
+ }
+
+ return addr;
+}
+
static int register_fadump(void)
{
unsigned long addr;
@@ -1313,9 +1345,13 @@ int __init setup_fadump(void)
fadump_invalidate_release_mem();
}
/* Initialize the kernel dump memory structure for FAD registration. */
- else if (fw_dump.reserve_dump_area_size)
+ else if (fw_dump.reserve_dump_area_size) {
fadump_ops->init_fadump_mem_struct(&fw_dump,
fw_dump.reserve_dump_area_start);
+ /* TODO: Extend this to pseries too */
+ if (fw_dump.fadump_platform == FADUMP_PLATFORM_POWERNV)
+ fadump_populate_backup_area();
+ }
fadump_init_files();
return 1;
diff --git a/arch/powerpc/kernel/fadump_internal.h
b/arch/powerpc/kernel/fadump_internal.h
index eae4b55..f391405 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -101,9 +101,20 @@ struct fadump_memory_range {
/* Maximum no. of real memory regions supported by the kernel */
#define MAX_REAL_MEM_REGIONS 6
+/* Backup area populated with data for processing in capture kernel */
+struct fadump_backup_area {
+ unsigned int size;
+ unsigned int nr_threads;
+ unsigned long thread_pir[NR_CPUS];
+};
+
/* Firmware-assisted dump configuration details. */
struct fw_dump {
+ unsigned long cpu_state_destination_addr;
+ unsigned long cpu_state_data_version;
+ unsigned long cpu_state_entry_size;
unsigned long cpu_state_data_size;
+ unsigned long backup_area_size;
unsigned long hpte_region_size;
unsigned long boot_memory_size;
unsigned long reserve_dump_area_start;
@@ -145,6 +156,7 @@ struct fadump_ops_t {
int (*unregister_fadump)(struct fw_dump *fadump_config);
ulong (*get_preserv_area_start)(struct fw_dump *fadump_conf);
ulong (*get_meta_area_start)(struct fw_dump *fadump_conf);
+ ulong (*get_backup_area_start)(struct fw_dump *fadump_conf);
int (*invalidate_fadump)(struct fw_dump *fadump_config);
int (*process_fadump)(struct fw_dump *fadump_config);
void (*fadump_region_show)(struct fw_dump *fadump_config,
diff --git a/arch/powerpc/platforms/powernv/powernv_fadump.c
b/arch/powerpc/platforms/powernv/powernv_fadump.c
index 6d4b515..36f0360 100644
--- a/arch/powerpc/platforms/powernv/powernv_fadump.c
+++ b/arch/powerpc/platforms/powernv/powernv_fadump.c
@@ -39,6 +39,8 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
int unused_sections = (POWERNV_MAX_SECTIONS - section_cnt);
int i, j;
+ fadump_conf->backup_area_size = sizeof(struct fadump_backup_area);
+
pr_debug("section_cnt: %d\n", section_cnt);
WARN_ON(unused_sections < 0);
fdm_actual_size = sizeof(*fdm) -
@@ -84,6 +86,12 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
last_end = base + size;
j++;
+ } else if (fdm->section[i].src_type ==
+ POWERNV_FADUMP_CPU_STATE_DATA) {
+ fadump_conf->cpu_state_destination_addr =
+ be64_to_cpu(fdm->section[i].dest_addr);
+ fadump_conf->cpu_state_data_size =
+ be64_to_cpu(fdm->section[i].dest_size);
}
}
fadump_conf->rmr_regions_cnt = j;
@@ -178,6 +186,13 @@ static ulong powernv_get_preserv_area_start(struct fw_dump
*fadump_conf)
static ulong powernv_get_meta_area_start(struct fw_dump *fadump_conf)
{
return (fadump_conf->rmr_destination_addr +
+ fadump_conf->rmr_source_len +
+ fadump_conf->backup_area_size);
+}
+
+static ulong powernv_get_backup_area_start(struct fw_dump *fadump_conf)
+{
+ return (fadump_conf->rmr_destination_addr +
fadump_conf->rmr_source_len);
}
@@ -197,6 +212,38 @@ static int powernv_invalidate_fadump(struct fw_dump
*fadump_conf)
return 0;
}
+static inline int fadump_get_logical_cpu(struct fadump_backup_area *ba, u32
pir)
+{
+ int i = 0, cpu = CPU_UNKNOWN;
+
+ while (i < ba->nr_threads) {
+ if (ba->thread_pir[i] == pir) {
+ cpu = i;
+ break;
+ }
+ i++;
+ }
+
+ return cpu;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(unsigned int regs_per_thread,
+ struct fadump_reg_entry *reg_entry,
+ struct pt_regs *regs)
+{
+ int i;
+
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ for (i = 0; i < regs_per_thread; i++) {
+ fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
+ be64_to_cpu(reg_entry->reg_value));
+ reg_entry++;
+ }
+ return reg_entry;
+}
+
/*
* Read CPU state dump data and convert it into ELF notes.
* The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
@@ -213,8 +260,34 @@ static int powernv_invalidate_fadump(struct fw_dump
*fadump_conf)
*/
static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
{
- u32 num_cpus = 1, *note_buf;
+ struct powernv_thread_hdr *thdr;
+ struct fadump_reg_entry *reg_entry;
struct fadump_crash_info_header *fdh = NULL;
+ struct fadump_backup_area *backup_info = NULL;
+ char *bufp, *note_bufp;
+ u32 thread_pir;
+ unsigned long addr;
+ u32 num_cpus, *note_buf;
+ struct pt_regs regs;
+ int i, rc = 0, cpu = 0;
+ unsigned int size_of_each_thread, regs_per_thread;
+
+ addr = powernv_get_backup_area_start(fadump_conf);
+ if (!addr) {
+ pr_err("Unable to read CPU state data\n");
+ return -ENOENT;
+ }
+
+ backup_info = __va(addr);
+ num_cpus = backup_info->nr_threads;
+
+ size_of_each_thread = fadump_conf->cpu_state_entry_size;
+ regs_per_thread =
+ ((size_of_each_thread - CPU_REG_ENTRY_OFFSET) /
+ sizeof(struct fadump_reg_entry));
+
+ addr = fadump_conf->cpu_state_destination_addr;
+ bufp = __va(addr);
/* Allocate buffer to hold cpu crash notes. */
fadump_conf->cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
@@ -234,10 +307,41 @@ static int __init fadump_build_cpu_notes(struct fw_dump
*fadump_conf)
if (fadump_conf->fadumphdr_addr)
fdh = __va(fadump_conf->fadumphdr_addr);
- if (fdh && (fdh->crashing_cpu != CPU_UNKNOWN)) {
- note_buf = fadump_regs_to_elf_notes(note_buf, &(fdh->regs));
- final_note(note_buf);
+ pr_debug("--------CPU State Data------------\n");
+ num_cpus = fadump_conf->cpu_state_data_size / size_of_each_thread;
+ pr_debug("NumCpus : %u\n", num_cpus);
+
+ note_bufp = (char *)note_buf;
+ for (i = 0; i < num_cpus; i++, bufp += size_of_each_thread) {
+ thdr = (struct powernv_thread_hdr *)bufp;
+ thread_pir = be32_to_cpu(thdr->pir);
+ cpu = fadump_get_logical_cpu(backup_info, thread_pir);
+ if (cpu == CPU_UNKNOWN) {
+ pr_err("Unable to read CPU state data");
+ rc = -ENOENT;
+ goto error_out;
+ }
+
+ if (fdh) {
+ if (!cpumask_test_cpu(cpu, &fdh->online_mask))
+ continue;
+
+ if (fdh->crashing_cpu == cpu) {
+ regs = fdh->regs;
+ note_buf = fadump_regs_to_elf_notes(note_buf,
+ ®s);
+ continue;
+ }
+ }
+
+ reg_entry = (struct fadump_reg_entry *)(bufp +
+ CPU_REG_ENTRY_OFFSET);
+ fadump_read_registers(regs_per_thread, reg_entry, ®s);
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ }
+ final_note(note_buf);
+ if (fdh) {
pr_debug("Updating elfcore header (%llx) with cpu notes\n",
fdh->elfcorehdr_addr);
fadump_update_elfcore_header(fadump_conf,
@@ -245,6 +349,13 @@ static int __init fadump_build_cpu_notes(struct fw_dump
*fadump_conf)
}
return 0;
+
+error_out:
+ fadump_cpu_notes_buf_free((ulong)__va(fadump_conf->cpu_notes_buf),
+ fadump_conf->cpu_notes_buf_size);
+ fadump_conf->cpu_notes_buf = 0;
+ fadump_conf->cpu_notes_buf_size = 0;
+ return rc;
}
static int __init powernv_process_fadump(struct fw_dump *fadump_conf)
@@ -262,13 +373,6 @@ static int __init powernv_process_fadump(struct fw_dump
*fadump_conf)
return -EINVAL;
}
- /*
- * TODO: To build cpu notes, find a way to map PIR to logical id.
- * Also, we may need different method for pseries and powernv.
- * The currently booted kernel could have a different PIR to
- * logical id mapping. So, try saving info of previous kernel's
- * paca to get the right PIR to logical id mapping.
- */
rc = fadump_build_cpu_notes(fadump_conf);
if (rc)
return rc;
@@ -305,6 +409,7 @@ static struct fadump_ops_t powernv_fadump_ops = {
.unregister_fadump = powernv_unregister_fadump,
.get_preserv_area_start = powernv_get_preserv_area_start,
.get_meta_area_start = powernv_get_meta_area_start,
+ .get_backup_area_start = powernv_get_backup_area_start,
.invalidate_fadump = powernv_invalidate_fadump,
.process_fadump = powernv_process_fadump,
.fadump_region_show = powernv_fadump_region_show,
@@ -313,6 +418,15 @@ static struct fadump_ops_t powernv_fadump_ops = {
int __init powernv_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
{
+ const __be32 *prop;
+
+ prop = of_get_flat_dt_prop(node, "cpu-data-version", NULL);
+ if (prop)
+ fadump_conf->cpu_state_data_version = of_read_number(prop, 1);
+
+ if (fadump_conf->cpu_state_data_version != CPU_STATE_DATA_VERSION)
+ return 1;
+
/*
* Firmware currently supports only 32-bit value for size,
* align it to 1MB size.
@@ -327,6 +441,16 @@ int __init powernv_dt_scan_fadump(struct fw_dump
*fadump_conf, ulong node)
pr_info("Firmware-assisted dump is active.\n");
fadump_conf->dump_active = 1;
update_fadump_config(fadump_conf, (void *)__pa(fdm_active));
+
+ /*
+ * Doesn't need to populate these fields while registering dump
+ * as destination address and size are provided by F/W.
+ */
+ prop = of_get_flat_dt_prop(node, "cpu-data-size", NULL);
+ if (prop) {
+ fadump_conf->cpu_state_entry_size =
+ of_read_number(prop, 1);
+ }
}
fadump_ops = &powernv_fadump_ops;
diff --git a/arch/powerpc/platforms/powernv/powernv_fadump.h
b/arch/powerpc/platforms/powernv/powernv_fadump.h
index 224a142..33be534 100644
--- a/arch/powerpc/platforms/powernv/powernv_fadump.h
+++ b/arch/powerpc/platforms/powernv/powernv_fadump.h
@@ -13,6 +13,9 @@
#ifndef __PPC64_POWERNV_FA_DUMP_H__
#define __PPC64_POWERNV_FA_DUMP_H__
+#define CPU_STATE_DATA_VERSION 16
+#define CPU_REG_ENTRY_OFFSET 16
+
#define POWERNV_FADUMP_CPU_STATE_DATA 0x0000
/* OPAL : 0x01 – 0x39 */
#define POWERNV_FADUMP_OPAL_REGION 0x0001
@@ -37,6 +40,12 @@ enum powernv_fadump_section_types {
#define POWERNV_MAX_SECTIONS (POWERNV_SECTIONS + \
MAX_REAL_MEM_REGIONS - 1)
+struct powernv_thread_hdr {
+ __be32 pir;
+ u8 core_state;
+ u8 reserved[11];
+} __attribute__ ((packed));
+
/* Kernel Dump section info */
struct powernv_fadump_section {
u8 src_type;
@@ -45,7 +54,7 @@ struct powernv_fadump_section {
__be64 src_size;
__be64 dest_addr;
__be64 dest_size;
-};
+} __attribute__ ((packed));
/*
* Firmware Assisted dump memory structure. This structure is required for
@@ -58,6 +67,6 @@ struct powernv_fadump_mem_struct {
__be32 reserved;
struct powernv_fadump_section section[POWERNV_MAX_SECTIONS];
-};
+} __attribute__ ((packed));
#endif /* __PPC64_POWERNV_FA_DUMP_H__ */
