On 2019-07-16 17:02:45 Tue, Hari Bathini wrote:
> Move code that supports processing the crash'ed kernel's memory
> preserved by firmware to platform specific callback functions.
>
> Signed-off-by: Hari Bathini <hbath...@linux.ibm.com>
> ---
> arch/powerpc/kernel/fadump-common.h | 6
> arch/powerpc/kernel/fadump.c | 340
> +-------------------------
> arch/powerpc/platforms/pseries/rtas-fadump.c | 278 +++++++++++++++++++++
> 3 files changed, 299 insertions(+), 325 deletions(-)
>
Reviewed-by: Mahesh Salgaonkar <mah...@linux.vnet.ibm.com>
Thanks,
-Mahesh.
> diff --git a/arch/powerpc/kernel/fadump-common.h
> b/arch/powerpc/kernel/fadump-common.h
> index 273247d..0231a0b 100644
> --- a/arch/powerpc/kernel/fadump-common.h
> +++ b/arch/powerpc/kernel/fadump-common.h
> @@ -100,6 +100,12 @@ struct fw_dump {
> /* cmd line option during boot */
> unsigned long reserve_bootvar;
>
> + /*
> + * Start address of preserve area. This memory is reserved
> + * permanently (production or capture kernel) for FADump.
> + */
> + unsigned long preserv_area_start;
> +
> unsigned long cpu_state_data_size;
> unsigned long hpte_region_size;
> unsigned long boot_memory_size;
> diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
> index 650ebf8..e995db1 100644
> --- a/arch/powerpc/kernel/fadump.c
> +++ b/arch/powerpc/kernel/fadump.c
> @@ -28,15 +28,12 @@
> #include <asm/debugfs.h>
> #include <asm/page.h>
> #include <asm/prom.h>
> -#include <asm/rtas.h>
> #include <asm/fadump.h>
> #include <asm/setup.h>
>
> #include "fadump-common.h"
> -#include "../platforms/pseries/rtas-fadump.h"
>
> static struct fw_dump fw_dump;
> -static const struct rtas_fadump_mem_struct *fdm_active;
>
> static DEFINE_MUTEX(fadump_mutex);
> struct fad_crash_memory_ranges *crash_memory_ranges;
> @@ -111,22 +108,13 @@ static int __init fadump_cma_init(void) { return 1; }
> int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
> int depth, void *data)
> {
> - int ret;
> -
> - if (depth != 1 || strcmp(uname, "rtas") != 0)
> + if (depth != 1)
> return 0;
>
> - ret = rtas_fadump_dt_scan(&fw_dump, node);
> + if (strcmp(uname, "rtas") == 0)
> + return rtas_fadump_dt_scan(&fw_dump, node);
>
> - /*
> - * The 'ibm,kernel-dump' rtas node is present only if there is
> - * dump data waiting for us.
> - */
> - fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
> - if (fdm_active)
> - fw_dump.dump_active = 1;
> -
> - return ret;
> + return 0;
> }
>
> /*
> @@ -308,9 +296,7 @@ int __init fadump_reserve_mem(void)
> * If dump is active then we have already calculated the size during
> * first kernel.
> */
> - if (fdm_active)
> - fw_dump.boot_memory_size =
> be64_to_cpu(fdm_active->rmr_region.source_len);
> - else {
> + if (!fw_dump.dump_active) {
> fw_dump.boot_memory_size = fadump_calculate_reserve_size();
> #ifdef CONFIG_CMA
> if (!fw_dump.nocma)
> @@ -320,6 +306,7 @@ int __init fadump_reserve_mem(void)
> #endif
> }
>
> + size = get_fadump_area_size();
> if (memory_limit)
> memory_boundary = memory_limit;
> else
> @@ -346,15 +333,10 @@ int __init fadump_reserve_mem(void)
> size = memory_boundary - base;
> fadump_reserve_crash_area(base, size);
>
> - fw_dump.fadumphdr_addr =
> -
> be64_to_cpu(fdm_active->rmr_region.destination_address) +
> - be64_to_cpu(fdm_active->rmr_region.source_len);
> - pr_debug("fadumphdr_addr = %pa\n", &fw_dump.fadumphdr_addr);
> + pr_debug("fadumphdr_addr = %#016lx\n", fw_dump.fadumphdr_addr);
> fw_dump.reserve_dump_area_start = base;
> fw_dump.reserve_dump_area_size = size;
> } else {
> - size = get_fadump_area_size();
> -
> /*
> * Reserve memory at an offset closer to bottom of the RAM to
> * minimize the impact of memory hot-remove operation. We can't
> @@ -469,218 +451,6 @@ void crash_fadump(struct pt_regs *regs, const char *str)
> fw_dump.ops->fadump_trigger(fdh, str);
> }
>
> -#define GPR_MASK 0xffffff0000000000
> -static inline int fadump_gpr_index(u64 id)
> -{
> - int i = -1;
> - char str[3];
> -
> - if ((id & GPR_MASK) == fadump_str_to_u64("GPR")) {
> - /* get the digits at the end */
> - id &= ~GPR_MASK;
> - id >>= 24;
> - str[2] = '\0';
> - str[1] = id & 0xff;
> - str[0] = (id >> 8) & 0xff;
> - sscanf(str, "%d", &i);
> - if (i > 31)
> - i = -1;
> - }
> - return i;
> -}
> -
> -static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
> - u64 reg_val)
> -{
> - int i;
> -
> - i = fadump_gpr_index(reg_id);
> - if (i >= 0)
> - regs->gpr[i] = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("NIA"))
> - regs->nip = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("MSR"))
> - regs->msr = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("CTR"))
> - regs->ctr = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("LR"))
> - regs->link = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("XER"))
> - regs->xer = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("CR"))
> - regs->ccr = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("DAR"))
> - regs->dar = (unsigned long)reg_val;
> - else if (reg_id == fadump_str_to_u64("DSISR"))
> - regs->dsisr = (unsigned long)reg_val;
> -}
> -
> -static struct rtas_fadump_reg_entry*
> -fadump_read_registers(struct rtas_fadump_reg_entry *reg_entry, struct
> pt_regs *regs)
> -{
> - memset(regs, 0, sizeof(struct pt_regs));
> -
> - while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) {
> - fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
> - be64_to_cpu(reg_entry->reg_value));
> - reg_entry++;
> - }
> - 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
> - * used to access the data to allow for additional fields to be added without
> - * affecting compatibility. Each list of registers for a CPU starts with
> - * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
> - * 8 Byte ASCII identifier and 8 Byte register value. The register entry
> - * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
> - * of register value. For more details refer to PAPR document.
> - *
> - * Only for the crashing cpu we ignore the CPU dump data and get exact
> - * state from fadump crash info structure populated by first kernel at the
> - * time of crash.
> - */
> -static int __init fadump_build_cpu_notes(const struct rtas_fadump_mem_struct
> *fdm)
> -{
> - struct rtas_fadump_reg_save_area_header *reg_header;
> - struct rtas_fadump_reg_entry *reg_entry;
> - struct fadump_crash_info_header *fdh = NULL;
> - void *vaddr;
> - unsigned long addr;
> - u32 num_cpus, *note_buf;
> - struct pt_regs regs;
> - int i, rc = 0, cpu = 0;
> -
> - if (!fdm->cpu_state_data.bytes_dumped)
> - return -EINVAL;
> -
> - addr = be64_to_cpu(fdm->cpu_state_data.destination_address);
> - vaddr = __va(addr);
> -
> - reg_header = vaddr;
> - if (be64_to_cpu(reg_header->magic_number) !=
> - fadump_str_to_u64("REGSAVE")) {
> - printk(KERN_ERR "Unable to read register save area.\n");
> - return -ENOENT;
> - }
> - pr_debug("--------CPU State Data------------\n");
> - pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
> - pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
> -
> - vaddr += be32_to_cpu(reg_header->num_cpu_offset);
> - num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
> - pr_debug("NumCpus : %u\n", num_cpus);
> - vaddr += sizeof(u32);
> - reg_entry = (struct rtas_fadump_reg_entry *)vaddr;
> -
> - /* Allocate buffer to hold cpu crash notes. */
> - fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
> - fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
> - note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
> - if (!note_buf) {
> - printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
> - "cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
> - return -ENOMEM;
> - }
> - fw_dump.cpu_notes_buf = __pa(note_buf);
> -
> - pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
> - (num_cpus * sizeof(note_buf_t)), note_buf);
> -
> - if (fw_dump.fadumphdr_addr)
> - fdh = __va(fw_dump.fadumphdr_addr);
> -
> - for (i = 0; i < num_cpus; i++) {
> - if (be64_to_cpu(reg_entry->reg_id) !=
> fadump_str_to_u64("CPUSTRT")) {
> - printk(KERN_ERR "Unable to read CPU state data\n");
> - rc = -ENOENT;
> - goto error_out;
> - }
> - /* Lower 4 bytes of reg_value contains logical cpu id */
> - cpu = be64_to_cpu(reg_entry->reg_value) &
> RTAS_FADUMP_CPU_ID_MASK;
> - if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
> - RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
> - continue;
> - }
> - pr_debug("Reading register data for cpu %d...\n", cpu);
> - if (fdh && fdh->crashing_cpu == cpu) {
> - regs = fdh->regs;
> - note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
> - RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
> - } else {
> - reg_entry++;
> - reg_entry = fadump_read_registers(reg_entry, ®s);
> - note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
> - }
> - }
> - final_note(note_buf);
> -
> - if (fdh) {
> - addr = fdh->elfcorehdr_addr;
> - pr_debug("Updating elfcore header(%lx) with cpu notes\n", addr);
> - fadump_update_elfcore_header(&fw_dump, (char *)__va(addr));
> - }
> - return 0;
> -
> -error_out:
> - fadump_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;
> - return rc;
> -
> -}
> -
> -/*
> - * Validate and process the dump data stored by firmware before exporting
> - * it through '/proc/vmcore'.
> - */
> -static int __init process_fadump(const struct rtas_fadump_mem_struct
> *fdm_active)
> -{
> - struct fadump_crash_info_header *fdh;
> - int rc = 0;
> -
> - if (!fdm_active || !fw_dump.fadumphdr_addr)
> - return -EINVAL;
> -
> - /* Check if the dump data is valid. */
> - if ((be16_to_cpu(fdm_active->header.dump_status_flag) ==
> RTAS_FADUMP_ERROR_FLAG) ||
> - (fdm_active->cpu_state_data.error_flags != 0) ||
> - (fdm_active->rmr_region.error_flags != 0)) {
> - printk(KERN_ERR "Dump taken by platform is not valid\n");
> - return -EINVAL;
> - }
> - if ((fdm_active->rmr_region.bytes_dumped !=
> - fdm_active->rmr_region.source_len) ||
> - !fdm_active->cpu_state_data.bytes_dumped) {
> - printk(KERN_ERR "Dump taken by platform is incomplete\n");
> - return -EINVAL;
> - }
> -
> - /* Validate the fadump crash info header */
> - fdh = __va(fw_dump.fadumphdr_addr);
> - if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
> - printk(KERN_ERR "Crash info header is not valid.\n");
> - return -EINVAL;
> - }
> -
> - rc = fadump_build_cpu_notes(fdm_active);
> - if (rc)
> - return rc;
> -
> - /*
> - * We are done validating dump info and elfcore header is now ready
> - * to be exported. set elfcorehdr_addr so that vmcore module will
> - * export the elfcore header through '/proc/vmcore'.
> - */
> - elfcorehdr_addr = fdh->elfcorehdr_addr;
> -
> - return 0;
> -}
> -
> static void free_crash_memory_ranges(void)
> {
> kfree(crash_memory_ranges);
> @@ -970,7 +740,6 @@ static unsigned long init_fadump_header(unsigned long
> addr)
> if (!addr)
> return 0;
>
> - fw_dump.fadumphdr_addr = addr;
> fdh = __va(addr);
> addr += sizeof(struct fadump_crash_info_header);
>
> @@ -1014,39 +783,12 @@ static int register_fadump(void)
> return fw_dump.ops->register_fadump(&fw_dump);
> }
>
> -static int fadump_invalidate_dump(const struct rtas_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 rtas_fadump_mem_struct));
> -
> - wait_time = rtas_busy_delay_time(rc);
> - if (wait_time)
> - mdelay(wait_time);
> - } while (wait_time);
> -
> - if (rc) {
> - pr_err("Failed to invalidate firmware-assisted dump
> registration. 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) {
> - /* pass the same memory dump structure provided by platform */
> - fadump_invalidate_dump(fdm_active);
> + pr_debug("Invalidating firmware-assisted dump registration\n");
> + fw_dump.ops->invalidate_fadump(&fw_dump);
> } else if (fw_dump.dump_registered) {
> /* Un-register Firmware-assisted dump if it was registered. */
> fw_dump.ops->unregister_fadump(&fw_dump);
> @@ -1132,7 +874,7 @@ static void fadump_invalidate_release_mem(void)
> return;
> }
>
> - destination_address =
> be64_to_cpu(fdm_active->cpu_state_data.destination_address);
> + destination_address = fw_dump.preserv_area_start;
> fadump_cleanup();
> mutex_unlock(&fadump_mutex);
>
> @@ -1158,6 +900,7 @@ static void fadump_invalidate_release_mem(void)
> fw_dump.cpu_notes_buf = 0;
> fw_dump.cpu_notes_buf_size = 0;
> }
> +
> /* Initialize the kernel dump memory structure for FAD registration. */
> fw_dump.ops->init_fadump_mem_struct(&fw_dump);
> }
> @@ -1210,7 +953,7 @@ static ssize_t fadump_register_store(struct kobject
> *kobj,
> int ret = 0;
> int input = -1;
>
> - if (!fw_dump.fadump_enabled || fdm_active)
> + if (!fw_dump.fadump_enabled || fw_dump.dump_active)
> return -EPERM;
>
> if (kstrtoint(buf, 0, &input))
> @@ -1223,7 +966,9 @@ static ssize_t fadump_register_store(struct kobject
> *kobj,
> if (fw_dump.dump_registered == 0) {
> goto unlock_out;
> }
> +
> /* Un-register Firmware-assisted dump */
> + pr_debug("Un-register firmware-assisted dump\n");
> fw_dump.ops->unregister_fadump(&fw_dump);
> break;
> case 1:
> @@ -1246,63 +991,13 @@ static ssize_t fadump_register_store(struct kobject
> *kobj,
>
> static int fadump_region_show(struct seq_file *m, void *private)
> {
> - const struct rtas_fadump_mem_struct *fdm_ptr;
> -
> if (!fw_dump.fadump_enabled)
> return 0;
>
> mutex_lock(&fadump_mutex);
> - if (fdm_active)
> - fdm_ptr = fdm_active;
> - else {
> - mutex_unlock(&fadump_mutex);
> - fw_dump.ops->fadump_region_show(&fw_dump, m);
> - return 0;
> - }
> + fw_dump.ops->fadump_region_show(&fw_dump, m);
> + mutex_unlock(&fadump_mutex);
>
> - seq_printf(m,
> - "CPU : [%#016llx-%#016llx] %#llx bytes, "
> - "Dumped: %#llx\n",
> -
> be64_to_cpu(fdm_ptr->cpu_state_data.destination_address),
> -
> be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) +
> - be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1,
> - be64_to_cpu(fdm_ptr->cpu_state_data.source_len),
> - be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped));
> - seq_printf(m,
> - "HPTE: [%#016llx-%#016llx] %#llx bytes, "
> - "Dumped: %#llx\n",
> - be64_to_cpu(fdm_ptr->hpte_region.destination_address),
> - be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
> - be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
> - be64_to_cpu(fdm_ptr->hpte_region.source_len),
> - be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
> - seq_printf(m,
> - "DUMP: [%#016llx-%#016llx] %#llx bytes, "
> - "Dumped: %#llx\n",
> - be64_to_cpu(fdm_ptr->rmr_region.destination_address),
> - be64_to_cpu(fdm_ptr->rmr_region.destination_address) +
> - be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1,
> - be64_to_cpu(fdm_ptr->rmr_region.source_len),
> - be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
> -
> - if (!fdm_active ||
> - (fw_dump.reserve_dump_area_start ==
> - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address)))
> - goto out;
> -
> - /* 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,
> -
> be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1,
> -
> be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
> - fw_dump.reserve_dump_area_start,
> -
> be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
> - fw_dump.reserve_dump_area_start);
> -out:
> - if (fdm_active)
> - mutex_unlock(&fadump_mutex);
> return 0;
> }
>
> @@ -1373,12 +1068,13 @@ int __init setup_fadump(void)
> * if dump process fails then invalidate the registration
> * and release memory before proceeding for re-registration.
> */
> - if (process_fadump(fdm_active) < 0)
> + if (fw_dump.ops->process_fadump(&fw_dump) < 0)
> fadump_invalidate_release_mem();
> }
> /* Initialize the kernel dump memory structure for FAD registration. */
> else if (fw_dump.reserve_dump_area_size)
> fw_dump.ops->init_fadump_mem_struct(&fw_dump);
> +
> fadump_init_files();
>
> return 1;
> diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c
> b/arch/powerpc/platforms/pseries/rtas-fadump.c
> index 790a37d..7ce84f8 100644
> --- a/arch/powerpc/platforms/pseries/rtas-fadump.c
> +++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
> @@ -31,6 +31,7 @@
> #include "rtas-fadump.h"
>
> static struct rtas_fadump_mem_struct fdm;
> +static const struct rtas_fadump_mem_struct *fdm_active;
>
> static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
> const struct rtas_fadump_mem_struct *fdm)
> @@ -40,6 +41,23 @@ static void rtas_fadump_update_config(struct fw_dump
> *fadump_conf,
>
> fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr +
> fadump_conf->boot_memory_size);
> +
> + /* Start address of preserve area (permanent reservation) */
> + fadump_conf->preserv_area_start =
> + be64_to_cpu(fdm->cpu_state_data.destination_address);
> + pr_debug("Preserve area start address: 0x%lx\n",
> + fadump_conf->preserv_area_start);
> +}
> +
> +/*
> + * This function is called in the capture kernel to get configuration details
> + * setup in the first kernel and passed to the f/w.
> + */
> +static void rtas_fadump_get_config(struct fw_dump *fadump_conf,
> + const struct rtas_fadump_mem_struct *fdm)
> +{
> + fadump_conf->boot_memory_size = be64_to_cpu(fdm->rmr_region.source_len);
> + rtas_fadump_update_config(fadump_conf, fdm);
> }
>
> static ulong rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
> @@ -180,7 +198,196 @@ static int rtas_fadump_unregister_fadump(struct fw_dump
> *fadump_conf)
>
> static int rtas_fadump_invalidate_fadump(struct fw_dump *fadump_conf)
> {
> - return -EIO;
> + int rc;
> + unsigned int wait_time;
> +
> + /* TODO: Add upper time limit for the delay */
> + do {
> + rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
> + NULL, FADUMP_INVALIDATE, fdm_active,
> + sizeof(struct rtas_fadump_mem_struct));
> +
> + wait_time = rtas_busy_delay_time(rc);
> + if (wait_time)
> + mdelay(wait_time);
> + } while (wait_time);
> +
> + if (rc) {
> + pr_err("Failed to invalidate - unexpected error (%d).\n", rc);
> + return -EIO;
> + }
> +
> + fadump_conf->dump_active = 0;
> + fdm_active = NULL;
> + return 0;
> +}
> +
> +#define RTAS_FADUMP_GPR_MASK 0xffffff0000000000
> +static inline int rtas_fadump_gpr_index(u64 id)
> +{
> + int i = -1;
> + char str[3];
> +
> + if ((id & RTAS_FADUMP_GPR_MASK) == fadump_str_to_u64("GPR")) {
> + /* get the digits at the end */
> + id &= ~RTAS_FADUMP_GPR_MASK;
> + id >>= 24;
> + str[2] = '\0';
> + str[1] = id & 0xff;
> + str[0] = (id >> 8) & 0xff;
> + if (kstrtoint(str, 10, &i))
> + i = -EINVAL;
> + if (i > 31)
> + i = -1;
> + }
> + return i;
> +}
> +
> +void rtas_fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val)
> +{
> + int i;
> +
> + i = rtas_fadump_gpr_index(reg_id);
> + if (i >= 0)
> + regs->gpr[i] = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("NIA"))
> + regs->nip = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("MSR"))
> + regs->msr = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("CTR"))
> + regs->ctr = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("LR"))
> + regs->link = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("XER"))
> + regs->xer = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("CR"))
> + regs->ccr = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("DAR"))
> + regs->dar = (unsigned long)reg_val;
> + else if (reg_id == fadump_str_to_u64("DSISR"))
> + regs->dsisr = (unsigned long)reg_val;
> +}
> +
> +static struct rtas_fadump_reg_entry*
> +rtas_fadump_read_regs(struct rtas_fadump_reg_entry *reg_entry,
> + struct pt_regs *regs)
> +{
> + memset(regs, 0, sizeof(struct pt_regs));
> +
> + while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) {
> + rtas_fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
> + be64_to_cpu(reg_entry->reg_value));
> + reg_entry++;
> + }
> + 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
> + * used to access the data to allow for additional fields to be added without
> + * affecting compatibility. Each list of registers for a CPU starts with
> + * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
> + * 8 Byte ASCII identifier and 8 Byte register value. The register entry
> + * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
> + * of register value. For more details refer to PAPR document.
> + *
> + * Only for the crashing cpu we ignore the CPU dump data and get exact
> + * state from fadump crash info structure populated by first kernel at the
> + * time of crash.
> + */
> +static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
> +{
> + struct rtas_fadump_reg_save_area_header *reg_header;
> + struct rtas_fadump_reg_entry *reg_entry;
> + struct fadump_crash_info_header *fdh = NULL;
> + void *vaddr;
> + unsigned long addr;
> + u32 num_cpus, *note_buf;
> + struct pt_regs regs;
> + int i, rc = 0, cpu = 0;
> +
> + addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
> + vaddr = __va(addr);
> +
> + reg_header = vaddr;
> + if (be64_to_cpu(reg_header->magic_number) !=
> + fadump_str_to_u64("REGSAVE")) {
> + pr_err("Unable to read register save area.\n");
> + return -ENOENT;
> + }
> +
> + pr_debug("--------CPU State Data------------\n");
> + pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
> + pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
> +
> + vaddr += be32_to_cpu(reg_header->num_cpu_offset);
> + num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
> + pr_debug("NumCpus : %u\n", num_cpus);
> + vaddr += sizeof(u32);
> + reg_entry = (struct rtas_fadump_reg_entry *)vaddr;
> +
> + /* Allocate buffer to hold cpu crash notes. */
> + fadump_conf->cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
> + fadump_conf->cpu_notes_buf_size =
> + PAGE_ALIGN(fadump_conf->cpu_notes_buf_size);
> + note_buf = fadump_cpu_notes_buf_alloc(fadump_conf->cpu_notes_buf_size);
> + if (!note_buf) {
> + pr_err("Failed to allocate 0x%lx bytes for cpu notes buffer\n",
> + fadump_conf->cpu_notes_buf_size);
> + return -ENOMEM;
> + }
> + fadump_conf->cpu_notes_buf = __pa(note_buf);
> +
> + pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
> + (num_cpus * sizeof(note_buf_t)), note_buf);
> +
> + if (fadump_conf->fadumphdr_addr)
> + fdh = __va(fadump_conf->fadumphdr_addr);
> +
> + for (i = 0; i < num_cpus; i++) {
> + if (be64_to_cpu(reg_entry->reg_id) !=
> + fadump_str_to_u64("CPUSTRT")) {
> + pr_err("Unable to read CPU state data\n");
> + rc = -ENOENT;
> + goto error_out;
> + }
> + /* Lower 4 bytes of reg_value contains logical cpu id */
> + cpu = (be64_to_cpu(reg_entry->reg_value) &
> + RTAS_FADUMP_CPU_ID_MASK);
> + if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
> + RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
> + continue;
> + }
> + pr_debug("Reading register data for cpu %d...\n", cpu);
> + if (fdh && fdh->crashing_cpu == cpu) {
> + regs = fdh->regs;
> + note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
> + RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
> + } else {
> + reg_entry++;
> + reg_entry = rtas_fadump_read_regs(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,
> + __va(fdh->elfcorehdr_addr));
> + }
> + 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;
> +
> }
>
> /*
> @@ -189,15 +396,62 @@ static int rtas_fadump_invalidate_fadump(struct fw_dump
> *fadump_conf)
> */
> static int __init rtas_fadump_process_fadump(struct fw_dump *fadump_conf)
> {
> - return -EINVAL;
> + struct fadump_crash_info_header *fdh;
> + int rc = 0;
> +
> + if (!fdm_active || !fadump_conf->fadumphdr_addr)
> + return -EINVAL;
> +
> + /* Check if the dump data is valid. */
> + if ((be16_to_cpu(fdm_active->header.dump_status_flag) ==
> + RTAS_FADUMP_ERROR_FLAG) ||
> + (fdm_active->cpu_state_data.error_flags != 0) ||
> + (fdm_active->rmr_region.error_flags != 0)) {
> + pr_err("Dump taken by platform is not valid\n");
> + return -EINVAL;
> + }
> + if ((fdm_active->rmr_region.bytes_dumped !=
> + fdm_active->rmr_region.source_len) ||
> + !fdm_active->cpu_state_data.bytes_dumped) {
> + pr_err("Dump taken by platform is incomplete\n");
> + return -EINVAL;
> + }
> +
> + /* Validate the fadump crash info header */
> + fdh = __va(fadump_conf->fadumphdr_addr);
> + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
> + pr_err("Crash info header is not valid.\n");
> + return -EINVAL;
> + }
> +
> + if (!fdm_active->cpu_state_data.bytes_dumped)
> + return -EINVAL;
> +
> + rc = rtas_fadump_build_cpu_notes(fadump_conf);
> + if (rc)
> + return rc;
> +
> + /*
> + * We are done validating dump info and elfcore header is now ready
> + * to be exported. set elfcorehdr_addr so that vmcore module will
> + * export the elfcore header through '/proc/vmcore'.
> + */
> + elfcorehdr_addr = fdh->elfcorehdr_addr;
> +
> + return 0;
> }
>
> static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
> struct seq_file *m)
> {
> - const struct rtas_fadump_mem_struct *fdm_ptr = &fdm;
> + const struct rtas_fadump_mem_struct *fdm_ptr;
> const struct rtas_fadump_section *cpu_data_section;
>
> + if (fdm_active)
> + fdm_ptr = fdm_active;
> + else
> + fdm_ptr = &fdm;
> +
> cpu_data_section = &(fdm_ptr->cpu_state_data);
> seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
> be64_to_cpu(cpu_data_section->destination_address),
> @@ -219,6 +473,12 @@ static void rtas_fadump_region_show(struct fw_dump
> *fadump_conf,
> seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
> be64_to_cpu(fdm_ptr->rmr_region.source_len),
> be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
> +
> + /* Dump is active. Show reserved area start address. */
> + if (fdm_active) {
> + seq_printf(m, "\nMemory above %#016lx is reserved for saving
> crash dump\n",
> + fadump_conf->reserve_dump_area_start);
> + }
> }
>
> static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
> @@ -228,6 +488,7 @@ static void rtas_fadump_trigger(struct
> fadump_crash_info_header *fdh,
> rtas_os_term((char *)msg);
> }
>
> +
> static struct fadump_ops rtas_fadump_ops = {
> .init_fadump_mem_struct = rtas_fadump_init_mem_struct,
> .register_fadump = rtas_fadump_register_fadump,
> @@ -258,6 +519,17 @@ int __init rtas_fadump_dt_scan(struct fw_dump
> *fadump_conf, ulong node)
> fadump_conf->fadump_platform = FADUMP_PLATFORM_PSERIES;
> fadump_conf->fadump_supported = 1;
>
> + /*
> + * The 'ibm,kernel-dump' rtas node is present only if there is
> + * dump data waiting for us.
> + */
> + fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
> + if (fdm_active) {
> + pr_info("Firmware-assisted dump is active.\n");
> + fadump_conf->dump_active = 1;
> + rtas_fadump_get_config(fadump_conf, (void *)__pa(fdm_active));
> + }
> +
> /* Get the sizes required to store dump data for the firmware provided
> * dump sections.
> * For each dump section type supported, a 32bit cell which defines
>
--
Mahesh J Salgaonkar
