* [PATCH 03/18] pseries/fadump: move out platform specific support from generic code
From: Hari Bathini @ 2019-02-21 17:35 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Introduce callbacks for platform specific operations like register,
unregister, invalidate & such, and move pseries specific code into
platform code.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 75 ---
arch/powerpc/kernel/fadump.c | 501 +--------------------
arch/powerpc/kernel/fadump_internal.h | 39 ++
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/pseries_fadump.c | 538 +++++++++++++++++++++++
arch/powerpc/platforms/pseries/pseries_fadump.h | 96 ++++
6 files changed, 711 insertions(+), 539 deletions(-)
create mode 100644 arch/powerpc/platforms/pseries/pseries_fadump.c
create mode 100644 arch/powerpc/platforms/pseries/pseries_fadump.h
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 028a8ef..d27cde7 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -24,79 +24,8 @@
#ifdef CONFIG_FA_DUMP
-/* Firmware provided dump sections */
-#define FADUMP_CPU_STATE_DATA 0x0001
-#define FADUMP_HPTE_REGION 0x0002
-#define FADUMP_REAL_MODE_REGION 0x0011
-
-/* Dump request flag */
-#define FADUMP_REQUEST_FLAG 0x00000001
-
-/* Dump status flag */
-#define FADUMP_ERROR_FLAG 0x2000
-
-/* Utility macros */
-#define SKIP_TO_NEXT_CPU(reg_entry) \
-({ \
- while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) \
- reg_entry++; \
- reg_entry++; \
-})
-
extern int crashing_cpu;
-/* Kernel Dump section info */
-struct fadump_section {
- __be32 request_flag;
- __be16 source_data_type;
- __be16 error_flags;
- __be64 source_address;
- __be64 source_len;
- __be64 bytes_dumped;
- __be64 destination_address;
-};
-
-/* ibm,configure-kernel-dump header. */
-struct fadump_section_header {
- __be32 dump_format_version;
- __be16 dump_num_sections;
- __be16 dump_status_flag;
- __be32 offset_first_dump_section;
-
- /* Fields for disk dump option. */
- __be32 dd_block_size;
- __be64 dd_block_offset;
- __be64 dd_num_blocks;
- __be32 dd_offset_disk_path;
-
- /* Maximum time allowed to prevent an automatic dump-reboot. */
- __be32 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;
-};
-
-#define REGSAVE_AREA_MAGIC STR_TO_HEX("REGSAVE")
-
-/* Register save area header. */
-struct fadump_reg_save_area_header {
- __be64 magic_number;
- __be32 version;
- __be32 num_cpu_offset;
-};
-
extern int is_fadump_memory_area(u64 addr, ulong size);
extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
int depth, void *data);
@@ -111,5 +40,5 @@ extern void fadump_cleanup(void);
static inline int is_fadump_active(void) { return 0; }
static inline int should_fadump_crash(void) { return 0; }
static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
-#endif
-#endif
+#endif /* !CONFIG_FA_DUMP */
+#endif /* __PPC64_FA_DUMP_H__ */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index fcd50bd..eb88447 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -40,15 +40,12 @@
#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_internal.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);
struct fad_crash_memory_ranges *crash_memory_ranges;
@@ -123,63 +120,13 @@ 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)
{
- const __be32 *sections;
- int i, num_sections;
- int size;
- const __be32 *token;
-
- if (depth != 1 || strcmp(uname, "rtas") != 0)
+ if (depth != 1)
return 0;
- /*
- * Check if Firmware Assisted dump is supported. if yes, check
- * if dump has been initiated on last reboot.
- */
- token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
- if (!token)
- return 1;
-
- fw_dump.fadump_supported = 1;
- fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
-
- /*
- * 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;
-
- /* 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
- * the ID of a supported section followed by two 32 bit cells which
- * gives teh size of the section in bytes.
- */
- sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
- &size);
-
- if (!sections)
- return 1;
-
- num_sections = size / (3 * sizeof(u32));
+ if (strcmp(uname, "rtas") == 0)
+ return pseries_dt_scan_fadump(&fw_dump, node);
- for (i = 0; i < num_sections; i++, sections += 3) {
- u32 type = (u32)of_read_number(sections, 1);
-
- switch (type) {
- case FADUMP_CPU_STATE_DATA:
- fw_dump.cpu_state_data_size =
- of_read_ulong(§ions[1], 2);
- break;
- case FADUMP_HPTE_REGION:
- fw_dump.hpte_region_size =
- of_read_ulong(§ions[1], 2);
- break;
- }
- }
-
- return 1;
+ return 0;
}
/*
@@ -231,61 +178,6 @@ static void fadump_show_config(void)
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 = cpu_to_be32(0x00000001);
- fdm->header.dump_num_sections = cpu_to_be16(3);
- fdm->header.dump_status_flag = 0;
- fdm->header.offset_first_dump_section =
- cpu_to_be32((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 = cpu_to_be32(FADUMP_REQUEST_FLAG);
- fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA);
- fdm->cpu_state_data.source_address = 0;
- fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size);
- fdm->cpu_state_data.destination_address = cpu_to_be64(addr);
- addr += fw_dump.cpu_state_data_size;
-
- /* hpte region section */
- fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
- fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION);
- fdm->hpte_region.source_address = 0;
- fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size);
- fdm->hpte_region.destination_address = cpu_to_be64(addr);
- addr += fw_dump.hpte_region_size;
-
- /* RMA region section */
- fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
- fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION);
- fdm->rmr_region.source_address = cpu_to_be64(RMA_START);
- fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size);
- fdm->rmr_region.destination_address = cpu_to_be64(addr);
- addr += fw_dump.boot_memory_size;
-
- return addr;
-}
-
/**
* fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
*
@@ -416,8 +308,8 @@ 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);
+ if (fw_dump.dump_active)
+ fw_dump.boot_memory_size = fw_dump.rmr_source_len;
else {
fw_dump.boot_memory_size = fadump_calculate_reserve_size();
#ifdef CONFIG_CMA
@@ -426,8 +318,11 @@ int __init fadump_reserve_mem(void)
ALIGN(fw_dump.boot_memory_size,
FADUMP_CMA_ALIGNMENT);
#endif
+ fw_dump.rmr_source_len = fw_dump.boot_memory_size;
}
+ size = get_fadump_area_size();
+
/*
* Calculate the memory boundary.
* If memory_limit is less than actual memory boundary then reserve
@@ -436,13 +331,11 @@ int __init fadump_reserve_mem(void)
* specified memory_limit.
*/
if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
- size = get_fadump_area_size();
if ((memory_limit + size) < memblock_end_of_DRAM())
memory_limit += size;
else
memory_limit = memblock_end_of_DRAM();
- printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
- " dump, now %#016llx\n", memory_limit);
+ pr_info("memory_limit adjusted to %#016llx\n", memory_limit);
}
if (memory_limit)
memory_boundary = memory_limit;
@@ -450,8 +343,6 @@ int __init fadump_reserve_mem(void)
memory_boundary = memblock_end_of_DRAM();
if (fw_dump.dump_active) {
- pr_info("Firmware-assisted dump is active.\n");
-
#ifdef CONFIG_HUGETLB_PAGE
/*
* FADump capture kernel doesn't care much about hugepages.
@@ -470,15 +361,11 @@ 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);
+ fw_dump.fadumphdr_addr = fw_dump.meta_area_start;
+ 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
@@ -548,61 +435,6 @@ static int __init early_fadump_reserve_mem(char *p)
}
early_param("fadump_reserve_mem", early_fadump_reserve_mem);
-static int register_fw_dump(struct fadump_mem_struct *fdm)
-{
- int rc, err;
- 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);
-
- err = -EIO;
- switch (rc) {
- default:
- pr_err("Failed to register. Unknown Error(%d).\n", rc);
- break;
- case -1:
- printk(KERN_ERR "Failed to register firmware-assisted kernel"
- " dump. Hardware Error(%d).\n", rc);
- break;
- case -3:
- if (!is_boot_memory_area_contiguous(&fw_dump))
- pr_err("Can't have holes in boot memory area while registering fadump\n");
- else if (!is_reserved_memory_area_contiguous(&fw_dump))
- pr_err("Can't have holes in reserved memory area while"
- " registering fadump\n");
-
- printk(KERN_ERR "Failed to register firmware-assisted kernel"
- " dump. Parameter Error(%d).\n", rc);
- err = -EINVAL;
- break;
- case -9:
- printk(KERN_ERR "firmware-assisted kernel dump is already "
- " registered.");
- fw_dump.dump_registered = 1;
- err = -EEXIST;
- break;
- case 0:
- printk(KERN_INFO "firmware-assisted kernel dump registration"
- " is successful\n");
- fw_dump.dump_registered = 1;
- err = 0;
- break;
- }
- return err;
-}
-
void crash_fadump(struct pt_regs *regs, const char *str)
{
struct fadump_crash_info_header *fdh = NULL;
@@ -645,173 +477,7 @@ void crash_fadump(struct pt_regs *regs, const char *str)
fdh->online_mask = *cpu_online_mask;
- /* Call ibm,os-term rtas call to trigger firmware assisted dump */
- rtas_os_term((char *)str);
-}
-
-static struct fadump_reg_entry*
-fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
-{
- memset(regs, 0, sizeof(struct pt_regs));
-
- while (be64_to_cpu(reg_entry->reg_id) != REG_ID("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 fadump_mem_struct *fdm)
-{
- struct fadump_reg_save_area_header *reg_header;
- struct 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) != REGSAVE_AREA_MAGIC) {
- 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 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) != REG_ID("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) & FADUMP_CPU_ID_MASK;
- if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
- 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);
- 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 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) == 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;
+ fw_dump.ops->crash_fadump(fdh, str);
}
static void free_crash_memory_ranges(void)
@@ -1008,7 +674,7 @@ static int fadump_setup_crash_memory_ranges(void)
static inline unsigned long fadump_relocate(unsigned long paddr)
{
if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
- return be64_to_cpu(fdm.rmr_region.destination_address) + paddr;
+ return fw_dump.rmr_destination_addr + paddr;
else
return paddr;
}
@@ -1081,7 +747,7 @@ static int fadump_create_elfcore_headers(char *bufp)
* to the specified destination_address. Hence set
* the correct offset.
*/
- phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address);
+ phdr->p_offset = fw_dump.rmr_destination_addr;
}
phdr->p_paddr = mbase;
@@ -1133,7 +799,8 @@ static int register_fadump(void)
if (ret)
return ret;
- addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
+ addr = fw_dump.meta_area_start;
+
/* Initialize fadump crash info header. */
addr = init_fadump_header(addr);
vaddr = __va(addr);
@@ -1142,72 +809,19 @@ static int register_fadump(void)
fadump_create_elfcore_headers(vaddr);
/* register the future kernel dump with firmware. */
- return 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 int fadump_invalidate_dump(const 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) {
- 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;
+ pr_debug("Registering for firmware-assisted kernel dump...\n");
+ return fw_dump.ops->register_fadump(&fw_dump);
}
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. */
- fadump_unregister_dump(&fdm);
+ fw_dump.ops->unregister_fadump(&fw_dump);
free_crash_memory_ranges();
}
}
@@ -1290,7 +904,7 @@ 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);
@@ -1316,8 +930,9 @@ 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. */
- init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ fw_dump.ops->init_fadump_mem_struct(&fw_dump);
}
static ssize_t fadump_release_memory_store(struct kobject *kobj,
@@ -1368,7 +983,7 @@ 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))
@@ -1381,13 +996,15 @@ static ssize_t fadump_register_store(struct kobject *kobj,
if (fw_dump.dump_registered == 0) {
goto unlock_out;
}
+
/* Un-register Firmware-assisted dump */
- fadump_unregister_dump(&fdm);
+ pr_debug("Un-register firmware-assisted dump\n");
+ fw_dump.ops->unregister_fadump(&fw_dump);
break;
case 1:
if (fw_dump.dump_registered == 1) {
/* Un-register Firmware-assisted dump */
- fadump_unregister_dump(&fdm);
+ fw_dump.ops->unregister_fadump(&fw_dump);
}
/* Register Firmware-assisted dump */
ret = register_fadump();
@@ -1404,62 +1021,13 @@ static ssize_t fadump_register_store(struct kobject *kobj,
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;
mutex_lock(&fadump_mutex);
- if (fdm_active)
- fdm_ptr = fdm_active;
- else {
- mutex_unlock(&fadump_mutex);
- fdm_ptr = &fdm;
- }
+ 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;
}
@@ -1530,12 +1098,13 @@ 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)
- init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ fw_dump.ops->init_fadump_mem_struct(&fw_dump);
+
fadump_init_files();
return 1;
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index 8ccd96d..f926145 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -47,6 +47,12 @@
#define FADUMP_UNREGISTER 2
#define FADUMP_INVALIDATE 3
+/* Firmware-Assited Dump platforms */
+enum fadump_platform_type {
+ FADUMP_PLATFORM_UNKNOWN = 0,
+ FADUMP_PLATFORM_PSERIES,
+};
+
#define FADUMP_CPU_ID_MASK ((1UL << 32) - 1)
#define CPU_UNKNOWN (~((u32)0))
@@ -91,6 +97,9 @@ struct fad_crash_memory_ranges {
unsigned long long size;
};
+/* Platform specific callback functions */
+struct fadump_ops;
+
/* Firmware-assisted dump configuration details. */
struct fw_dump {
unsigned long cpu_state_data_size;
@@ -98,6 +107,8 @@ struct fw_dump {
unsigned long boot_memory_size;
unsigned long reserve_dump_area_start;
unsigned long reserve_dump_area_size;
+ unsigned long meta_area_start;
+ unsigned long preserv_area_start;
/* cmd line option during boot */
unsigned long reserve_bootvar;
@@ -105,6 +116,9 @@ struct fw_dump {
unsigned long cpu_notes_buf;
unsigned long cpu_notes_buf_size;
+ unsigned long rmr_source_len;
+ unsigned long rmr_destination_addr;
+
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -112,6 +126,21 @@ struct fw_dump {
unsigned long dump_active:1;
unsigned long dump_registered:1;
unsigned long nocma:1;
+
+ enum fadump_platform_type fadump_platform;
+ struct fadump_ops *ops;
+};
+
+struct fadump_ops {
+ ulong (*init_fadump_mem_struct)(struct fw_dump *fadump_config);
+ int (*register_fadump)(struct fw_dump *fadump_config);
+ int (*unregister_fadump)(struct fw_dump *fadump_config);
+ 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,
+ struct seq_file *m);
+ void (*crash_fadump)(struct fadump_crash_info_header *fdh,
+ const char *msg);
};
/* Helper functions */
@@ -123,4 +152,14 @@ void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
int is_boot_memory_area_contiguous(struct fw_dump *fadump_conf);
int is_reserved_memory_area_contiguous(struct fw_dump *fadump_conf);
+#ifdef CONFIG_PPC_PSERIES
+extern int pseries_dt_scan_fadump(struct fw_dump *fadump_config, ulong node);
+#else
+static inline int
+pseries_dt_scan_fadump(struct fw_dump *fadump_config, ulong node)
+{
+ return 1;
+}
+#endif
+
#endif /* __PPC64_FA_DUMP_INTERNAL_H__ */
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index a43ec84..dace1a4 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_LPARCFG) += lparcfg.o
obj-$(CONFIG_IBMVIO) += vio.o
obj-$(CONFIG_IBMEBUS) += ibmebus.o
obj-$(CONFIG_PAPR_SCM) += papr_scm.o
+obj-$(CONFIG_FA_DUMP) += pseries_fadump.o
ifdef CONFIG_PPC_PSERIES
obj-$(CONFIG_SUSPEND) += suspend.o
diff --git a/arch/powerpc/platforms/pseries/pseries_fadump.c b/arch/powerpc/platforms/pseries/pseries_fadump.c
new file mode 100644
index 0000000..e93a7a4
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/pseries_fadump.c
@@ -0,0 +1,538 @@
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ *
+ * Copyright 2018-2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "pseries fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+
+#include "../../kernel/fadump_internal.h"
+#include "pseries_fadump.h"
+
+static struct pseries_fadump_mem_struct fdm;
+static const struct pseries_fadump_mem_struct *fdm_active;
+
+static void pseries_set_preserv_area_start(struct fw_dump *fadump_conf)
+{
+ const struct pseries_fadump_mem_struct *fdm_ptr;
+
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else
+ fdm_ptr = &fdm;
+
+ fadump_conf->preserv_area_start =
+ be64_to_cpu(fdm_ptr->cpu_state_data.destination_address);
+
+ pr_debug("Preserve area start address: 0x%lx\n",
+ fadump_conf->preserv_area_start);
+}
+
+static void pseries_set_meta_area_start(struct fw_dump *fadump_conf)
+{
+ fadump_conf->meta_area_start = (fadump_conf->rmr_destination_addr +
+ fadump_conf->rmr_source_len);
+
+ pr_debug("Meta area start address: 0x%lx\n",
+ fadump_conf->meta_area_start);
+}
+
+static void update_fadump_config(struct fw_dump *fadump_conf,
+ const struct pseries_fadump_mem_struct *fdm)
+{
+ fadump_conf->rmr_destination_addr =
+ be64_to_cpu(fdm->rmr_region.destination_address);
+
+ if (fadump_conf->dump_active) {
+ fadump_conf->rmr_source_len =
+ be64_to_cpu(fdm->rmr_region.source_len);
+ }
+
+ pseries_set_meta_area_start(fadump_conf);
+ pseries_set_preserv_area_start(fadump_conf);
+}
+
+static ulong pseries_init_fadump_mem_struct(struct fw_dump *fadump_conf)
+{
+ ulong addr = fadump_conf->reserve_dump_area_start;
+
+ memset(&fdm, 0, sizeof(struct pseries_fadump_mem_struct));
+ addr = addr & PAGE_MASK;
+
+ fdm.header.dump_format_version = cpu_to_be32(0x00000001);
+ fdm.header.dump_num_sections = cpu_to_be16(3);
+ fdm.header.dump_status_flag = 0;
+ fdm.header.offset_first_dump_section =
+ cpu_to_be32((u32)offsetof(struct pseries_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 =
+ cpu_to_be32(PSERIES_FADUMP_REQUEST_FLAG);
+ fdm.cpu_state_data.source_data_type =
+ cpu_to_be16(PSERIES_FADUMP_CPU_STATE_DATA);
+ fdm.cpu_state_data.source_address = 0;
+ fdm.cpu_state_data.source_len =
+ cpu_to_be64(fadump_conf->cpu_state_data_size);
+ fdm.cpu_state_data.destination_address = cpu_to_be64(addr);
+ addr += fadump_conf->cpu_state_data_size;
+
+ /* hpte region section */
+ fdm.hpte_region.request_flag = cpu_to_be32(PSERIES_FADUMP_REQUEST_FLAG);
+ fdm.hpte_region.source_data_type =
+ cpu_to_be16(PSERIES_FADUMP_HPTE_REGION);
+ fdm.hpte_region.source_address = 0;
+ fdm.hpte_region.source_len =
+ cpu_to_be64(fadump_conf->hpte_region_size);
+ fdm.hpte_region.destination_address = cpu_to_be64(addr);
+ addr += fadump_conf->hpte_region_size;
+
+ /* RMA region section */
+ fdm.rmr_region.request_flag = cpu_to_be32(PSERIES_FADUMP_REQUEST_FLAG);
+ fdm.rmr_region.source_data_type =
+ cpu_to_be16(PSERIES_FADUMP_REAL_MODE_REGION);
+ fdm.rmr_region.source_address = cpu_to_be64(RMA_START);
+ fdm.rmr_region.source_len =
+ cpu_to_be64(fadump_conf->boot_memory_size);
+ fdm.rmr_region.destination_address = cpu_to_be64(addr);
+ addr += fadump_conf->boot_memory_size;
+
+ update_fadump_config(fadump_conf, &fdm);
+
+ return addr;
+}
+
+static int pseries_register_fadump(struct fw_dump *fadump_conf)
+{
+ int rc, err;
+ 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_REGISTER, &fdm,
+ sizeof(struct pseries_fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+
+ } while (wait_time);
+
+ err = -EIO;
+ switch (rc) {
+ default:
+ pr_err("Failed to register. Unknown Error(%d).\n", rc);
+ break;
+ case -1:
+ pr_err("Failed to register. Hardware Error(%d).\n", rc);
+ break;
+ case -3:
+ if (!is_boot_memory_area_contiguous(fadump_conf))
+ pr_err("Can't hot-remove boot memory area.\n");
+ else if (!is_reserved_memory_area_contiguous(fadump_conf))
+ pr_err("Can't hot-remove reserved memory area.\n");
+
+ pr_err("Failed to register. Parameter Error(%d).\n", rc);
+ err = -EINVAL;
+ break;
+ case -9:
+ pr_err("Already registered!\n");
+ fadump_conf->dump_registered = 1;
+ err = -EEXIST;
+ break;
+ case 0:
+ pr_err("Registration is successful!\n");
+ fadump_conf->dump_registered = 1;
+ err = 0;
+ break;
+ }
+
+ return err;
+}
+
+static int pseries_unregister_fadump(struct fw_dump *fadump_conf)
+{
+ int rc = 0;
+ 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_UNREGISTER, &fdm,
+ sizeof(struct pseries_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 un-register - unexpected error(%d).\n", rc);
+ return rc;
+ }
+
+ fadump_conf->dump_registered = 0;
+ return 0;
+}
+
+static int pseries_invalidate_fadump(struct fw_dump *fadump_conf)
+{
+ int rc = 0;
+ 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 pseries_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 rc;
+ }
+
+ fadump_conf->dump_active = 0;
+ fdm_active = NULL;
+ return 0;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+{
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ while (be64_to_cpu(reg_entry->reg_id) != REG_ID("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(struct fw_dump *fadump_conf)
+{
+ struct fadump_reg_save_area_header *reg_header;
+ struct 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) != REGSAVE_AREA_MAGIC) {
+ 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 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) != REG_ID("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) & FADUMP_CPU_ID_MASK;
+ if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
+ 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);
+ 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) {
+ 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;
+
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init pseries_process_fadump(struct fw_dump *fadump_conf)
+{
+ 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) ==
+ PSERIES_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 = 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 pseries_fadump_region_show(struct fw_dump *fadump_conf,
+ struct seq_file *m)
+{
+ const struct pseries_fadump_mem_struct *fdm_ptr;
+ const struct pseries_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),
+ be64_to_cpu(cpu_data_section->destination_address) +
+ be64_to_cpu(cpu_data_section->source_len) - 1,
+ be64_to_cpu(cpu_data_section->source_len),
+ be64_to_cpu(cpu_data_section->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 ||
+ (fadump_conf->reserve_dump_area_start ==
+ be64_to_cpu(cpu_data_section->destination_address)))
+ return;
+
+ /* Dump is active. Show reserved memory region. */
+ seq_printf(m,
+ " :[%#016lx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+ fadump_conf->reserve_dump_area_start,
+ be64_to_cpu(cpu_data_section->destination_address) - 1,
+ be64_to_cpu(cpu_data_section->destination_address) -
+ fadump_conf->reserve_dump_area_start,
+ be64_to_cpu(cpu_data_section->destination_address) -
+ fadump_conf->reserve_dump_area_start);
+}
+
+static void pseries_crash_fadump(struct fadump_crash_info_header *fdh,
+ const char *msg)
+{
+ /* Call ibm,os-term rtas call to trigger firmware assisted dump */
+ rtas_os_term((char *)msg);
+}
+
+
+static struct fadump_ops pseries_fadump_ops = {
+ .init_fadump_mem_struct = pseries_init_fadump_mem_struct,
+ .register_fadump = pseries_register_fadump,
+ .unregister_fadump = pseries_unregister_fadump,
+ .invalidate_fadump = pseries_invalidate_fadump,
+ .process_fadump = pseries_process_fadump,
+ .fadump_region_show = pseries_fadump_region_show,
+ .crash_fadump = pseries_crash_fadump,
+};
+
+int __init pseries_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
+{
+ const __be32 *sections;
+ int i, num_sections;
+ int size;
+ const __be32 *token;
+
+ /*
+ * Check if Firmware Assisted dump is supported. if yes, check
+ * if dump has been initiated on last reboot.
+ */
+ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+ if (!token)
+ return 1;
+
+ fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
+
+ /*
+ * 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;
+ update_fadump_config(fadump_conf, 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
+ * the ID of a supported section followed by two 32 bit cells which
+ * gives the size of the section in bytes.
+ */
+ sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+ &size);
+
+ if (!sections)
+ return 1;
+
+ num_sections = size / (3 * sizeof(u32));
+
+ for (i = 0; i < num_sections; i++, sections += 3) {
+ u32 type = (u32)of_read_number(sections, 1);
+
+ switch (type) {
+ case PSERIES_FADUMP_CPU_STATE_DATA:
+ fadump_conf->cpu_state_data_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ case PSERIES_FADUMP_HPTE_REGION:
+ fadump_conf->hpte_region_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ }
+ }
+
+ fadump_conf->ops = &pseries_fadump_ops;
+ fadump_conf->fadump_platform = FADUMP_PLATFORM_PSERIES;
+ fadump_conf->fadump_supported = 1;
+
+ return 1;
+}
diff --git a/arch/powerpc/platforms/pseries/pseries_fadump.h b/arch/powerpc/platforms/pseries/pseries_fadump.h
new file mode 100644
index 0000000..d61e5d9
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/pseries_fadump.h
@@ -0,0 +1,96 @@
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2018-2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __PPC64_PSERIES_FA_DUMP_H__
+#define __PPC64_PSERIES_FA_DUMP_H__
+
+/* Firmware provided dump sections */
+#define PSERIES_FADUMP_CPU_STATE_DATA 0x0001
+#define PSERIES_FADUMP_HPTE_REGION 0x0002
+#define PSERIES_FADUMP_REAL_MODE_REGION 0x0011
+
+/* Dump request flag */
+#define PSERIES_FADUMP_REQUEST_FLAG 0x00000001
+
+/* Dump status flag */
+#define PSERIES_FADUMP_ERROR_FLAG 0x2000
+
+/* Utility macros */
+#define SKIP_TO_NEXT_CPU(reg_entry) \
+({ \
+ while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) \
+ reg_entry++; \
+ reg_entry++; \
+})
+
+/* Kernel Dump section info */
+struct pseries_fadump_section {
+ __be32 request_flag;
+ __be16 source_data_type;
+ __be16 error_flags;
+ __be64 source_address;
+ __be64 source_len;
+ __be64 bytes_dumped;
+ __be64 destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct pseries_fadump_section_header {
+ __be32 dump_format_version;
+ __be16 dump_num_sections;
+ __be16 dump_status_flag;
+ __be32 offset_first_dump_section;
+
+ /* Fields for disk dump option. */
+ __be32 dd_block_size;
+ __be64 dd_block_offset;
+ __be64 dd_num_blocks;
+ __be32 dd_offset_disk_path;
+
+ /* Maximum time allowed to prevent an automatic dump-reboot. */
+ __be32 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 pseries_fadump_mem_struct {
+ struct pseries_fadump_section_header header;
+
+ /* Kernel dump sections */
+ struct pseries_fadump_section cpu_state_data;
+ struct pseries_fadump_section hpte_region;
+ struct pseries_fadump_section rmr_region;
+};
+
+#define REGSAVE_AREA_MAGIC STR_TO_HEX("REGSAVE")
+
+/* The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. On pseries, each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct fadump_reg_save_area_header {
+ __be64 magic_number;
+ __be32 version;
+ __be32 num_cpu_offset;
+};
+
+#endif /* __PPC64_PSERIES_FA_DUMP_H__ */
^ permalink raw reply related
* [PATCH 04/18] powerpc/fadump: use FADump instead of fadump for how it is pronounced
From: Hari Bathini @ 2019-02-21 17:35 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 56 +++++++++++-----------
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index 059993b..62e75ef 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -8,18 +8,18 @@ a crashed system, and to do so from a fully-reset system, and
to minimize the total elapsed time until the system is back
in production use.
-- Firmware assisted dump (fadump) infrastructure is intended to replace
+- Firmware-Assisted Dump (FADump) infrastructure is intended to replace
the existing phyp assisted dump.
- Fadump uses the same firmware interfaces and memory reservation model
as phyp assisted dump.
-- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
+- Unlike phyp dump, FADump exports the memory dump through /proc/vmcore
in the ELF format in the same way as kdump. This helps us reuse the
kdump infrastructure for dump capture and filtering.
- Unlike phyp dump, userspace tool does not need to refer any sysfs
interface while reading /proc/vmcore.
-- Unlike phyp dump, fadump allows user to release all the memory reserved
+- Unlike phyp dump, FADump allows user to release all the memory reserved
for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
-- Once enabled through kernel boot parameter, fadump can be
+- Once enabled through kernel boot parameter, FADump can be
started/stopped through /sys/kernel/fadump_registered interface (see
sysfs files section below) and can be easily integrated with kdump
service start/stop init scripts.
@@ -33,7 +33,7 @@ dump offers several strong, practical advantages:
in a clean, consistent state.
-- Once the dump is copied out, the memory that held the dump
is immediately available to the running kernel. And therefore,
- unlike kdump, fadump doesn't need a 2nd reboot to get back
+ unlike kdump, FADump doesn't need a 2nd reboot to get back
the system to the production configuration.
The above can only be accomplished by coordination with,
@@ -61,7 +61,7 @@ as follows:
boot successfully. For syntax of crashkernel= parameter,
refer to Documentation/kdump/kdump.txt. If any offset is
provided in crashkernel= parameter, it will be ignored
- as fadump uses a predefined offset to reserve memory
+ as FADump uses a predefined offset to reserve memory
for boot memory dump preservation in case of a crash.
-- After the low memory (boot memory) area has been saved, the
@@ -120,7 +120,7 @@ blocking this significant chunk of memory from production kernel.
Hence, the implementation uses the Linux kernel's Contiguous Memory
Allocator (CMA) for memory reservation if CMA is configured for kernel.
With CMA reservation this memory will be available for applications to
-use it, while kernel is prevented from using it. With this fadump will
+use it, while kernel is prevented from using it. With this FADump will
still be able to capture all of the kernel memory and most of the user
space memory except the user pages that were present in CMA region.
@@ -170,14 +170,14 @@ KDump, as dump mechanism.
The tools to examine the dump will be same as the ones
used for kdump.
-How to enable firmware-assisted dump (fadump):
+How to enable firmware-assisted dump (FADump):
---------------------------------------------
1. Set config option CONFIG_FA_DUMP=y and build kernel.
-2. Boot into linux kernel with 'fadump=on' kernel cmdline option.
- By default, fadump reserved memory will be initialized as CMA area.
- Alternatively, user can boot linux kernel with 'fadump=nocma' to
- prevent fadump to use CMA.
+2. Boot into linux kernel with 'FADump=on' kernel cmdline option.
+ By default, FADump reserved memory will be initialized as CMA area.
+ Alternatively, user can boot linux kernel with 'FADump=nocma' to
+ prevent FADump to use CMA.
3. Optionally, user can also set 'crashkernel=' kernel cmdline
to specify size of the memory to reserve for boot memory dump
preservation.
@@ -190,7 +190,7 @@ NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead
option is set at kernel cmdline.
3. if user wants to capture all of user space memory and ok with
reserved memory not available to production system, then
- 'fadump=nocma' kernel parameter can be used to fallback to
+ 'FADump=nocma' kernel parameter can be used to fallback to
old behaviour.
Sysfs/debugfs files:
@@ -203,29 +203,29 @@ Here is the list of files under kernel sysfs:
/sys/kernel/fadump_enabled
- This is used to display the fadump status.
- 0 = fadump is disabled
- 1 = fadump is enabled
+ This is used to display the FADump status.
+ 0 = FADump is disabled
+ 1 = FADump is enabled
This interface can be used by kdump init scripts to identify if
- fadump is enabled in the kernel and act accordingly.
+ FADump is enabled in the kernel and act accordingly.
/sys/kernel/fadump_registered
- This is used to display the fadump registration status as well
- as to control (start/stop) the fadump registration.
- 0 = fadump is not registered.
- 1 = fadump is registered and ready to handle system crash.
+ This is used to display the FADump registration status as well
+ as to control (start/stop) the FADump registration.
+ 0 = FADump is not registered.
+ 1 = FADump is registered and ready to handle system crash.
- To register fadump echo 1 > /sys/kernel/fadump_registered and
+ To register FADump echo 1 > /sys/kernel/fadump_registered and
echo 0 > /sys/kernel/fadump_registered for un-register and stop the
- fadump. Once the fadump is un-registered, the system crash will not
+ FADump. Once the FADump is un-registered, the system crash will not
be handled and vmcore will not be captured. This interface can be
easily integrated with kdump service start/stop.
/sys/kernel/fadump_release_mem
- This file is available only when fadump is active during
+ This file is available only when FADump is active during
second kernel. This is used to release the reserved memory
region that are held for saving crash dump. To release the
reserved memory echo 1 to it:
@@ -244,20 +244,20 @@ Here is the list of files under powerpc debugfs:
/sys/kernel/debug/powerpc/fadump_region
- This file shows the reserved memory regions if fadump is
+ This file shows the reserved memory regions if FADump is
enabled otherwise this file is empty. The output format
is:
<region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size>
e.g.
- Contents when fadump is registered during first kernel
+ Contents when FADump is registered during first kernel
# cat /sys/kernel/debug/powerpc/fadump_region
CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0
HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0
DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0
- Contents when fadump is active during second kernel
+ Contents when FADump is active during second kernel
# cat /sys/kernel/debug/powerpc/fadump_region
CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020
@@ -274,7 +274,7 @@ TODO:
o Need to come up with the better approach to find out more
accurate boot memory size that is required for a kernel to
boot successfully when booted with restricted memory.
- o The fadump implementation introduces a fadump crash info structure
+ o The FADump implementation introduces a FADump crash info structure
in the scratch area before the ELF core header. The idea of introducing
this structure is to pass some important crash info data to the second
kernel which will help second kernel to populate ELF core header with
^ permalink raw reply related
* [PATCH 05/18] powerpc/fadump: enable fadump support on OPAL based POWER platform
From: Hari Bathini @ 2019-02-21 17:35 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Firmware-assisted dump support is enabled for OPAL based POWER platforms
in P9 firmware. Make the corresponding updates in kernel to enable fadump
support for such platforms.
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 5
arch/powerpc/include/asm/opal-api.h | 35 ++
arch/powerpc/include/asm/opal.h | 1
arch/powerpc/kernel/fadump.c | 259 ++++++++++++----
arch/powerpc/kernel/fadump_internal.c | 27 +-
arch/powerpc/kernel/fadump_internal.h | 44 ++-
arch/powerpc/platforms/powernv/Makefile | 1
arch/powerpc/platforms/powernv/opal-fadump.c | 375 +++++++++++++++++++++++
arch/powerpc/platforms/powernv/opal-fadump.h | 40 ++
arch/powerpc/platforms/powernv/opal-wrappers.S | 1
arch/powerpc/platforms/pseries/pseries_fadump.c | 18 -
11 files changed, 716 insertions(+), 90 deletions(-)
create mode 100644 arch/powerpc/platforms/powernv/opal-fadump.c
create mode 100644 arch/powerpc/platforms/powernv/opal-fadump.h
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2890d36..c667d07 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -568,7 +568,7 @@ config CRASH_DUMP
config FA_DUMP
bool "Firmware-assisted dump"
- depends on PPC64 && PPC_RTAS
+ depends on PPC64 && (PPC_RTAS || PPC_POWERNV)
select CRASH_CORE
select CRASH_DUMP
help
@@ -579,7 +579,8 @@ config FA_DUMP
is meant to be a kdump replacement offering robustness and
speed not possible without system firmware assistance.
- If unsure, say "N"
+ If unsure, say "y". Only special kernels like petitboot may
+ need to say "N" here.
config IRQ_ALL_CPUS
bool "Distribute interrupts on all CPUs by default"
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 870fb7b..6076e51 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -210,7 +210,8 @@
#define OPAL_PCI_GET_PBCQ_TUNNEL_BAR 164
#define OPAL_PCI_SET_PBCQ_TUNNEL_BAR 165
#define OPAL_NX_COPROC_INIT 167
-#define OPAL_LAST 167
+#define OPAL_CONFIGURE_FADUMP 170
+#define OPAL_LAST 170
#define QUIESCE_HOLD 1 /* Spin all calls at entry */
#define QUIESCE_REJECT 2 /* Fail all calls with OPAL_BUSY */
@@ -972,6 +973,37 @@ struct opal_sg_list {
};
/*
+ * Firmware-Assisted Dump (FADump)
+ */
+
+/* The maximum number of dump sections supported by OPAL */
+#define OPAL_FADUMP_NR_SECTIONS 64
+
+/* Kernel Dump section info */
+struct opal_fadump_section {
+ u8 src_type;
+ u8 reserved[7];
+ __be64 src_addr;
+ __be64 src_size;
+ __be64 dest_addr;
+ __be64 dest_size;
+};
+
+/*
+ * FADump memory structure for registering dump support with
+ * POWER f/w through opal call.
+ */
+struct opal_fadump_mem_struct {
+
+ __be16 section_size; /*sizeof(struct fadump_section) */
+ __be16 section_count; /* number of sections */
+ __be32 crashing_cpu; /* Thread on which OPAL crashed */
+ __be64 reserved;
+
+ struct opal_fadump_section section[OPAL_FADUMP_NR_SECTIONS];
+};
+
+/*
* Dump region ID range usable by the OS
*/
#define OPAL_DUMP_REGION_HOST_START 0x80
@@ -1051,6 +1083,7 @@ enum {
OPAL_REBOOT_NORMAL = 0,
OPAL_REBOOT_PLATFORM_ERROR = 1,
OPAL_REBOOT_FULL_IPL = 2,
+ OPAL_REBOOT_OS_ERROR = 3,
};
/* Argument to OPAL_PCI_TCE_KILL */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index a55b01c..2123b3f 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -43,6 +43,7 @@ int64_t opal_npu_spa_clear_cache(uint64_t phb_id, uint32_t bdfn,
uint64_t PE_handle);
int64_t opal_npu_tl_set(uint64_t phb_id, uint32_t bdfn, long cap,
uint64_t rate_phys, uint32_t size);
+int64_t opal_configure_fadump(uint64_t command, void *data, uint64_t data_size);
int64_t opal_console_write(int64_t term_number, __be64 *length,
const uint8_t *buffer);
int64_t opal_console_read(int64_t term_number, __be64 *length,
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index eb88447..6ff05046 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -48,7 +48,7 @@
static struct fw_dump fw_dump;
static DEFINE_MUTEX(fadump_mutex);
-struct fad_crash_memory_ranges *crash_memory_ranges;
+struct fadump_memory_range *crash_memory_ranges;
int crash_memory_ranges_size;
int crash_mem_ranges;
int max_crash_mem_ranges;
@@ -126,6 +126,9 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
if (strcmp(uname, "rtas") == 0)
return pseries_dt_scan_fadump(&fw_dump, node);
+ if (strcmp(uname, "ibm,opal") == 0)
+ return opal_dt_scan_fadump(&fw_dump, node);
+
return 0;
}
@@ -137,6 +140,7 @@ int is_fadump_memory_area(u64 addr, ulong size)
{
u64 d_start = fw_dump.reserve_dump_area_start;
u64 d_end = d_start + fw_dump.reserve_dump_area_size;
+ u64 b_end = fw_dump.boot_memory_size + fw_dump.boot_memory_hole_size;
if (!fw_dump.dump_registered)
return 0;
@@ -144,7 +148,7 @@ int is_fadump_memory_area(u64 addr, ulong size)
if (((addr + size) > d_start) && (addr <= d_end))
return 1;
- return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size;
+ return (((addr + size) > RMA_START) && (addr <= b_end));
}
int should_fadump_crash(void)
@@ -162,6 +166,8 @@ int is_fadump_active(void)
/* Print firmware assisted dump configurations for debugging purpose. */
static void fadump_show_config(void)
{
+ int i;
+
pr_debug("Support for firmware-assisted dump (fadump): %s\n",
(fw_dump.fadump_supported ? "present" : "no support"));
@@ -176,6 +182,13 @@ static void fadump_show_config(void)
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);
+ pr_debug("Real memory region hole size : %lx\n",
+ fw_dump.boot_memory_hole_size);
+ pr_debug("Real meory regions count : %lx\n", fw_dump.rmr_regions_cnt);
+ for (i = 0; i < fw_dump.rmr_regions_cnt; i++) {
+ pr_debug("%d. RMR base = %lx, size = %lx\n", (i+1),
+ fw_dump.rmr_src_addr[i], fw_dump.rmr_src_size[i]);
+ }
}
/**
@@ -270,39 +283,122 @@ static unsigned long get_fadump_area_size(void)
return size;
}
-static void __init fadump_reserve_crash_area(unsigned long base,
- unsigned long size)
+static int __init add_rmr_region(unsigned long rmr_start,
+ unsigned long rmr_size)
+{
+ int i = fw_dump.rmr_regions_cnt++;
+
+ if (fw_dump.rmr_regions_cnt > MAX_REAL_MEM_REGIONS)
+ return 0;
+
+ pr_debug("Added real memory range[%d] [%#016lx-%#016lx)\n",
+ i, rmr_start, (rmr_start + rmr_size));
+ fw_dump.rmr_src_addr[i] = rmr_start;
+ fw_dump.rmr_src_size[i] = rmr_size;
+ return 1;
+}
+
+/*
+ * Platforms like PowerNV have an upper limit on the size.
+ * If 'rmr_size' is bigger than that limit, split this memory range
+ * into multiple entries.
+ */
+static int __init add_rmr_regions(unsigned long rmr_start,
+ unsigned long rmr_size)
+{
+ unsigned long rstart, rsize, max_size;
+ int ret = 1;
+
+ rstart = rmr_start;
+ max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : rmr_size;
+ while (rmr_size) {
+ if (rmr_size > max_size)
+ rsize = max_size;
+ else
+ rsize = rmr_size;
+
+ ret = add_rmr_region(rstart, rsize);
+ if (!ret)
+ break;
+
+ rmr_size -= rsize;
+ rstart += rsize;
+ }
+
+ return ret;
+}
+
+static int __init fadump_get_rmr_regions(void)
+{
+ int ret = 1;
+ struct memblock_region *reg;
+ unsigned long base, size, cur_size, last_end;
+ unsigned long mem_size = fw_dump.boot_memory_size;
+
+ fw_dump.rmr_regions_cnt = 0;
+ fw_dump.boot_memory_hole_size = 0;
+
+ last_end = 0;
+ cur_size = 0;
+ for_each_memblock(memory, reg) {
+ base = reg->base;
+ size = reg->size;
+ fw_dump.boot_memory_hole_size += (base - last_end);
+
+ if ((cur_size + size) >= mem_size) {
+ size = (mem_size - cur_size);
+ ret = add_rmr_regions(base, size);
+ break;
+ }
+
+ mem_size -= size;
+ cur_size += size;
+ ret = add_rmr_regions(base, size);
+ if (!ret)
+ break;
+
+ last_end = base + size;
+ }
+
+ return ret;
+}
+
+/* Preserve everything above the base address */
+static void __init fadump_reserve_crash_area(unsigned long base)
{
struct memblock_region *reg;
- unsigned long mstart, mend, msize;
+ unsigned long mstart, msize;
for_each_memblock(memory, reg) {
- mstart = max_t(unsigned long, base, reg->base);
- mend = reg->base + reg->size;
- mend = min(base + size, mend);
-
- if (mstart < mend) {
- msize = mend - mstart;
- memblock_reserve(mstart, msize);
- pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n",
- (msize >> 20), mstart);
+ mstart = reg->base;
+ msize = reg->size;
+
+ if ((mstart + msize) < base)
+ continue;
+
+ if (mstart < base) {
+ msize -= (base - mstart);
+ mstart = base;
}
+ pr_info("Reserving %luMB of memory at %#016lx for saving crash dump",
+ (msize >> 20), mstart);
+ memblock_reserve(mstart, msize);
}
}
int __init fadump_reserve_mem(void)
{
+ int ret = 1;
unsigned long base, size, memory_boundary;
if (!fw_dump.fadump_enabled)
return 0;
if (!fw_dump.fadump_supported) {
- printk(KERN_INFO "Firmware-assisted dump is not supported on"
- " this hardware\n");
- fw_dump.fadump_enabled = 0;
- return 0;
+ pr_info("Firmware-Assisted Dump is not supported on this hardware\n");
+ goto error_out;
}
+
/*
* Initialize boot memory size
* If dump is active then we have already calculated the size during
@@ -319,9 +415,14 @@ int __init fadump_reserve_mem(void)
FADUMP_CMA_ALIGNMENT);
#endif
fw_dump.rmr_source_len = fw_dump.boot_memory_size;
+ if (!fadump_get_rmr_regions()) {
+ pr_err("Too many holes in boot memory area to enable fadump\n");
+ goto error_out;
+ }
}
size = get_fadump_area_size();
+ fw_dump.reserve_dump_area_size = size;
/*
* Calculate the memory boundary.
@@ -342,6 +443,8 @@ int __init fadump_reserve_mem(void)
else
memory_boundary = memblock_end_of_DRAM();
+ base = fw_dump.boot_memory_size + fw_dump.boot_memory_hole_size;
+ base = PAGE_ALIGN(base);
if (fw_dump.dump_active) {
#ifdef CONFIG_HUGETLB_PAGE
/*
@@ -353,18 +456,15 @@ int __init fadump_reserve_mem(void)
#endif
/*
* If last boot has crashed then reserve all the memory
- * above boot_memory_size so that we don't touch it until
+ * above boot memory size so that we don't touch it until
* dump is written to disk by userspace tool. This memory
- * will be released for general use once the dump is saved.
+ * can be released for general use by invalidating fadump.
*/
- base = fw_dump.boot_memory_size;
- size = memory_boundary - base;
- fadump_reserve_crash_area(base, size);
+ fadump_reserve_crash_area(base);
fw_dump.fadumphdr_addr = fw_dump.meta_area_start;
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 {
/*
* Reserve memory at an offset closer to bottom of the RAM to
@@ -372,30 +472,32 @@ int __init fadump_reserve_mem(void)
* use memblock_find_in_range() here since it doesn't allocate
* from bottom to top.
*/
- for (base = fw_dump.boot_memory_size;
- base <= (memory_boundary - size);
- base += size) {
+ while (base <= (memory_boundary - size)) {
if (memblock_is_region_memory(base, size) &&
!memblock_is_region_reserved(base, size))
break;
+
+ base += size;
}
+
if ((base > (memory_boundary - size)) ||
memblock_reserve(base, size)) {
pr_err("Failed to reserve memory\n");
- return 0;
+ goto error_out;
}
- pr_info("Reserved %ldMB of memory at %ldMB for firmware-"
- "assisted dump (System RAM: %ldMB)\n",
- (unsigned long)(size >> 20),
- (unsigned long)(base >> 20),
+ pr_info("Reserved %ldMB of memory at %#016lx (System RAM: %ldMB)\n",
+ (unsigned long)(size >> 20), base,
(unsigned long)(memblock_phys_mem_size() >> 20));
fw_dump.reserve_dump_area_start = base;
- fw_dump.reserve_dump_area_size = size;
- return fadump_cma_init();
+ ret = fadump_cma_init();
}
- return 1;
+
+ return ret;
+error_out:
+ fw_dump.fadump_enabled = 0;
+ return 0;
}
unsigned long __init arch_reserved_kernel_pages(void)
@@ -494,7 +596,7 @@ static void free_crash_memory_ranges(void)
*/
static int allocate_crash_memory_ranges(void)
{
- struct fad_crash_memory_ranges *new_array;
+ struct fadump_memory_range *new_array;
u64 new_size;
new_size = crash_memory_ranges_size + PAGE_SIZE;
@@ -511,7 +613,7 @@ static int allocate_crash_memory_ranges(void)
crash_memory_ranges = new_array;
crash_memory_ranges_size = new_size;
max_crash_mem_ranges = (new_size /
- sizeof(struct fad_crash_memory_ranges));
+ sizeof(struct fadump_memory_range));
return 0;
}
@@ -623,36 +725,40 @@ static int fadump_init_elfcore_header(char *bufp)
static int fadump_setup_crash_memory_ranges(void)
{
struct memblock_region *reg;
- unsigned long long start, end;
- int ret;
+ unsigned long long start, end, offset;
+ int i, ret;
pr_debug("Setup crash memory ranges.\n");
crash_mem_ranges = 0;
+ offset = fw_dump.boot_memory_size + fw_dump.boot_memory_hole_size;
/*
- * add the first memory chunk (RMA_START through boot_memory_size) as
- * a separate memory chunk. The reason is, at the time crash firmware
- * will move the content of this memory chunk to different location
- * specified during fadump registration. We need to create a separate
- * program header for this chunk with the correct offset.
+ * Add real memory region(s) whose content is going to be moved to
+ * a different location, specified during fadump registration, by
+ * firmware at the time of crash. We need to create separate program
+ * header(s) for this memory chunk with the correct offset.
*/
- ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
- if (ret)
- return ret;
+ for (i = 0; i < fw_dump.rmr_regions_cnt; i++) {
+ start = fw_dump.rmr_src_addr[i];
+ end = start + fw_dump.rmr_src_size[i];
+ ret = fadump_add_crash_memory(start, end);
+ if (ret)
+ return ret;
+ }
for_each_memblock(memory, reg) {
start = (unsigned long long)reg->base;
end = start + (unsigned long long)reg->size;
/*
- * skip the first memory chunk that is already added (RMA_START
+ * Skip the first memory chunk that is already added (RMA_START
* through boot_memory_size). This logic needs a relook if and
* when RMA_START changes to a non-zero value.
*/
BUILD_BUG_ON(RMA_START != 0);
- if (start < fw_dump.boot_memory_size) {
- if (end > fw_dump.boot_memory_size)
- start = fw_dump.boot_memory_size;
+ if (start < offset) {
+ if (end > offset)
+ start = offset;
else
continue;
}
@@ -673,17 +779,35 @@ static int fadump_setup_crash_memory_ranges(void)
*/
static inline unsigned long fadump_relocate(unsigned long paddr)
{
- if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
- return fw_dump.rmr_destination_addr + paddr;
- else
- return paddr;
+ unsigned long raddr, rstart, rend, rlast, hole_size;
+ int i;
+
+ hole_size = 0;
+ rlast = 0;
+ raddr = paddr;
+ for (i = 0; i < fw_dump.rmr_regions_cnt; i++) {
+ rstart = fw_dump.rmr_src_addr[i];
+ rend = rstart + fw_dump.rmr_src_size[i];
+ hole_size += (rstart - rlast);
+
+ if (paddr >= rstart && paddr < rend) {
+ raddr += fw_dump.rmr_destination_addr - hole_size;
+ break;
+ }
+
+ rlast = rend;
+ }
+
+ pr_debug("vmcoreinfo: paddr = 0x%lx, raddr = 0x%lx\n", paddr, raddr);
+ return raddr;
}
static int fadump_create_elfcore_headers(char *bufp)
{
struct elfhdr *elf;
struct elf_phdr *phdr;
- int i;
+ unsigned long long raddr, offset;
+ int i, j;
fadump_init_elfcore_header(bufp);
elf = (struct elfhdr *)bufp;
@@ -726,9 +850,12 @@ static int fadump_create_elfcore_headers(char *bufp)
(elf->e_phnum)++;
/* setup PT_LOAD sections. */
-
+ j = 0;
+ offset = 0;
+ raddr = fw_dump.rmr_src_addr[0];
for (i = 0; i < crash_mem_ranges; i++) {
unsigned long long mbase, msize;
+
mbase = crash_memory_ranges[i].base;
msize = crash_memory_ranges[i].size;
@@ -741,13 +868,17 @@ static int fadump_create_elfcore_headers(char *bufp)
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_offset = mbase;
- if (mbase == RMA_START) {
+ if (mbase == raddr) {
/*
* The entire RMA region will be moved by firmware
* to the specified destination_address. Hence set
* the correct offset.
*/
- phdr->p_offset = fw_dump.rmr_destination_addr;
+ phdr->p_offset = fw_dump.rmr_destination_addr + offset;
+ if (j < (fw_dump.rmr_regions_cnt - 1)) {
+ offset += fw_dump.rmr_src_size[j];
+ raddr = fw_dump.rmr_src_addr[++j];
+ }
}
phdr->p_paddr = mbase;
@@ -913,14 +1044,14 @@ static void fadump_invalidate_release_mem(void)
* 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;
+ reserved_area_end =
+ memory_limit ? memory_limit : memblock_end_of_DRAM();
+
/*
- * Setup reserve_dump_area_start and its size so that we can
- * reuse this reserved memory for Re-registration.
+ * Setup reserve_dump_area_start 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_fadump_area_size();
fadump_release_memory(reserved_area_start, reserved_area_end);
if (fw_dump.cpu_notes_buf) {
diff --git a/arch/powerpc/kernel/fadump_internal.c b/arch/powerpc/kernel/fadump_internal.c
index 570c357..b46c7da 100644
--- a/arch/powerpc/kernel/fadump_internal.c
+++ b/arch/powerpc/kernel/fadump_internal.c
@@ -10,6 +10,9 @@
* 2 of the License, or (at your option) any later version.
*/
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
#include <linux/memblock.h>
#include <linux/elf.h>
#include <linux/mm.h>
@@ -48,6 +51,15 @@ void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
__free_pages(page, order);
}
+void fadump_set_meta_area_start(struct fw_dump *fadump_conf)
+{
+ fadump_conf->meta_area_start = (fadump_conf->rmr_destination_addr +
+ fadump_conf->rmr_source_len);
+
+ pr_debug("Meta area start address: 0x%lx\n",
+ fadump_conf->meta_area_start);
+}
+
#define GPR_MASK 0xffffff0000000000
static inline int fadump_gpr_index(u64 id)
{
@@ -165,10 +177,19 @@ static int is_memory_area_contiguous(unsigned long d_start,
*/
int is_boot_memory_area_contiguous(struct fw_dump *fadump_conf)
{
- unsigned long d_start = RMA_START;
- unsigned long d_end = RMA_START + fadump_conf->boot_memory_size;
+ int i, ret = 0;
+ unsigned long d_start, d_end;
- return is_memory_area_contiguous(d_start, d_end);
+ for (i = 0; i < fadump_conf->rmr_regions_cnt; i++) {
+ d_start = fadump_conf->rmr_src_addr[i];
+ d_end = d_start + fadump_conf->rmr_src_size[i];
+
+ ret = is_memory_area_contiguous(d_start, d_end);
+ if (!ret)
+ break;
+ }
+
+ return ret;
}
/*
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index f926145..8ad98db 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -47,12 +47,6 @@
#define FADUMP_UNREGISTER 2
#define FADUMP_INVALIDATE 3
-/* Firmware-Assited Dump platforms */
-enum fadump_platform_type {
- FADUMP_PLATFORM_UNKNOWN = 0,
- FADUMP_PLATFORM_PSERIES,
-};
-
#define FADUMP_CPU_ID_MASK ((1UL << 32) - 1)
#define CPU_UNKNOWN (~((u32)0))
@@ -92,13 +86,23 @@ struct fadump_crash_info_header {
struct cpumask online_mask;
};
-struct fad_crash_memory_ranges {
+/* Platform specific callback functions */
+struct fadump_ops;
+
+/* Firmware-Assited Dump platforms */
+enum fadump_platform_type {
+ FADUMP_PLATFORM_UNKNOWN = 0,
+ FADUMP_PLATFORM_PSERIES,
+ FADUMP_PLATFORM_POWERNV,
+};
+
+struct fadump_memory_range {
unsigned long long base;
unsigned long long size;
};
-/* Platform specific callback functions */
-struct fadump_ops;
+/* Maximum no. of real memory regions supported by the kernel */
+#define MAX_REAL_MEM_REGIONS 8
/* Firmware-assisted dump configuration details. */
struct fw_dump {
@@ -119,6 +123,17 @@ struct fw_dump {
unsigned long rmr_source_len;
unsigned long rmr_destination_addr;
+ unsigned long boot_memory_hole_size;
+ unsigned long rmr_regions_cnt;
+ unsigned long rmr_src_addr[MAX_REAL_MEM_REGIONS];
+ unsigned long rmr_src_size[MAX_REAL_MEM_REGIONS];
+
+ /*
+ * Maximum size supported by firmware to copy from source to
+ * destination address per entry.
+ */
+ unsigned long max_copy_size;
+
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -146,6 +161,7 @@ struct fadump_ops {
/* Helper functions */
void *fadump_cpu_notes_buf_alloc(unsigned long size);
void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size);
+void fadump_set_meta_area_start(struct fw_dump *fadump_conf);
void fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val);
u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
@@ -162,4 +178,14 @@ pseries_dt_scan_fadump(struct fw_dump *fadump_config, ulong node)
}
#endif
+#ifdef CONFIG_PPC_POWERNV
+extern int opal_dt_scan_fadump(struct fw_dump *fadump_config, ulong node);
+#else
+static inline int
+opal_dt_scan_fadump(struct fw_dump *fadump_config, ulong node)
+{
+ return 1;
+}
+#endif
+
#endif /* __PPC64_FA_DUMP_INTERNAL_H__ */
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b540ce8e..adc0de6 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -6,6 +6,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o
+obj-$(CONFIG_FA_DUMP) += opal-fadump.o
obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
obj-$(CONFIG_CXL_BASE) += pci-cxl.o
obj-$(CONFIG_EEH) += eeh-powernv.o
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
new file mode 100644
index 0000000..3a83609
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -0,0 +1,375 @@
+/*
+ * Firmware-Assisted Dump support on POWER platform (OPAL).
+ *
+ * Copyright 2018-2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "opal fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/bug.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+#include <linux/libfdt.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/opal.h>
+#include <asm/fadump.h>
+
+#include "../../kernel/fadump_internal.h"
+#include "opal-fadump.h"
+
+static struct opal_fadump_mem_struct fdm;
+static const struct opal_fadump_mem_struct *fdm_active;
+unsigned long fdm_actual_size;
+
+static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
+{
+ fadump_conf->preserv_area_start = fadump_conf->rmr_destination_addr;
+
+ pr_debug("Preserve area start address: 0x%lx\n",
+ fadump_conf->preserv_area_start);
+}
+
+static void update_fadump_config(struct fw_dump *fadump_conf,
+ const struct opal_fadump_mem_struct *fdm)
+{
+ unsigned long base, size, last_end;
+ int section_cnt = be16_to_cpu(fdm->section_count);
+ int unused_sections = (OPAL_MAX_SECTIONS - section_cnt);
+ int i, j;
+
+ pr_debug("section_cnt: %d\n", section_cnt);
+ BUILD_BUG_ON(OPAL_MAX_SECTIONS > OPAL_FADUMP_NR_SECTIONS);
+ WARN_ON(unused_sections < 0);
+ fdm_actual_size = sizeof(*fdm) -
+ (unused_sections * sizeof(struct opal_fadump_section));
+
+ /*
+ * The first real memory region entry is the real memory
+ * regions destination address.
+ */
+ fadump_conf->rmr_destination_addr = 0;
+ for (i = 0; i < section_cnt; i++) {
+ if (fdm->section[i].src_type ==
+ OPAL_FADUMP_REAL_MODE_REGION) {
+ fadump_conf->rmr_destination_addr =
+ be64_to_cpu(fdm->section[i].dest_addr);
+ break;
+ }
+ }
+ pr_debug("Destination address of real memory regions: %#016lx\n",
+ fadump_conf->rmr_destination_addr);
+
+ if (fadump_conf->dump_active) {
+ j = 0;
+ last_end = 0;
+ fadump_conf->rmr_source_len = 0;
+ fadump_conf->boot_memory_hole_size = 0;
+ for (i = 0; i < section_cnt; i++) {
+ if (fdm->section[i].src_type ==
+ OPAL_FADUMP_REAL_MODE_REGION) {
+ base = be64_to_cpu(fdm->section[i].src_addr);
+ size = be64_to_cpu(fdm->section[i].src_size);
+ pr_debug("%d. RMR base: 0x%lx, size: 0x%lx\n",
+ (i + 1), base, size);
+
+ fadump_conf->rmr_src_addr[j] = base;
+ fadump_conf->rmr_src_size[j] = size;
+ fadump_conf->rmr_source_len += size;
+
+ if (base > last_end) {
+ fadump_conf->boot_memory_hole_size +=
+ (base - last_end);
+ }
+
+ last_end = base + size;
+ j++;
+ }
+ }
+ fadump_conf->rmr_regions_cnt = j;
+ pr_debug("Real memory regions count: %lu\n",
+ fadump_conf->rmr_regions_cnt);
+ }
+
+ fadump_set_meta_area_start(fadump_conf);
+ opal_set_preserv_area_start(fadump_conf);
+}
+
+static ulong opal_init_fadump_mem_struct(struct fw_dump *fadump_conf)
+{
+ ulong addr = fadump_conf->reserve_dump_area_start;
+ int i, section_cnt = 0;
+
+ fdm.section_size = cpu_to_be16(sizeof(struct opal_fadump_section));
+
+ /* RMA region sections */
+ for (i = 0; i < fadump_conf->rmr_regions_cnt; i++) {
+ fdm.section[RMR_REGION_INPUT_IDX + i].src_type =
+ OPAL_FADUMP_REAL_MODE_REGION;
+ fdm.section[RMR_REGION_INPUT_IDX + i].src_addr =
+ cpu_to_be64(fadump_conf->rmr_src_addr[i]);
+ fdm.section[RMR_REGION_INPUT_IDX + i].dest_addr =
+ cpu_to_be64(addr);
+ fdm.section[RMR_REGION_INPUT_IDX + i].src_size =
+ fdm.section[RMR_REGION_INPUT_IDX + i].dest_size =
+ cpu_to_be64(fadump_conf->rmr_src_size[i]);
+
+ section_cnt++;
+ addr += fadump_conf->rmr_src_size[i];
+ }
+
+ fdm.section_count = cpu_to_be16(section_cnt);
+ update_fadump_config(fadump_conf, &fdm);
+
+ return addr;
+}
+
+static int opal_register_fadump(struct fw_dump *fadump_conf)
+{
+ int rc, err = -EIO;
+
+ rc = opal_configure_fadump(FADUMP_REGISTER, &fdm, fdm_actual_size);
+ switch (rc) {
+ default:
+ pr_err("Failed to register. Unknown Error(%d).\n", rc);
+ break;
+ case OPAL_UNSUPPORTED:
+ pr_err("Support not available.\n");
+ fadump_conf->fadump_supported = 0;
+ fadump_conf->fadump_enabled = 0;
+ break;
+ case OPAL_INTERNAL_ERROR:
+ pr_err("Failed to register. Hardware Error(%d).\n", rc);
+ break;
+ case OPAL_PARAMETER:
+ pr_err("Failed to register. Parameter Error(%d).\n", rc);
+ break;
+ case OPAL_PERMISSION:
+ pr_err("Already registered!\n");
+ fadump_conf->dump_registered = 1;
+ err = -EEXIST;
+ break;
+ case OPAL_SUCCESS:
+ pr_err("Registration is successful!\n");
+ fadump_conf->dump_registered = 1;
+ err = 0;
+ break;
+ }
+
+ return err;
+}
+
+static int opal_unregister_fadump(struct fw_dump *fadump_conf)
+{
+ int rc;
+
+ rc = opal_configure_fadump(FADUMP_UNREGISTER, &fdm, fdm_actual_size);
+ if (rc) {
+ pr_err("Failed to un-register - unexpected Error(%d).\n", rc);
+ return -EIO;
+ }
+
+ fadump_conf->dump_registered = 0;
+ return 0;
+}
+
+static int opal_invalidate_fadump(struct fw_dump *fadump_conf)
+{
+ int rc;
+
+ rc = opal_configure_fadump(FADUMP_INVALIDATE, (void *)fdm_active,
+ fdm_actual_size);
+ if (rc) {
+ pr_err("Failed to invalidate - unexpected Error(%d).\n", rc);
+ return -EIO;
+ }
+
+ fadump_conf->dump_active = 0;
+ fdm_active = NULL;
+ return 0;
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ *
+ * Each register entry is of 16 bytes, A numerical identifier along with
+ * a GPR/SPR flag in the first 8 bytes and the register value in the next
+ * 8 bytes. For more details refer to F/W documentation.
+ */
+static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
+{
+ u32 num_cpus, *note_buf;
+ struct fadump_crash_info_header *fdh = NULL;
+
+ num_cpus = 1;
+ /* 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);
+
+ if (fdh && (fdh->crashing_cpu != CPU_UNKNOWN)) {
+ note_buf = fadump_regs_to_elf_notes(note_buf, &(fdh->regs));
+ final_note(note_buf);
+
+ 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;
+}
+
+static int __init opal_process_fadump(struct fw_dump *fadump_conf)
+{
+ struct fadump_crash_info_header *fdh;
+ int rc = 0;
+
+ if (!fdm_active || !fadump_conf->fadumphdr_addr)
+ 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;
+ }
+
+ /*
+ * 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;
+
+ /*
+ * 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 rc;
+}
+
+static void opal_fadump_region_show(struct fw_dump *fadump_conf,
+ struct seq_file *m)
+{
+ int i;
+ const struct opal_fadump_mem_struct *fdm_ptr;
+
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else
+ fdm_ptr = &fdm;
+
+ seq_puts(m, "-------------------------------------------------------");
+ seq_puts(m, "-----------------------------\n");
+ seq_puts(m, "| | Source | ");
+ seq_puts(m, " Destination |\n");
+ seq_puts(m, "- ------------------------------------------------");
+ seq_puts(m, "-----------------------------\n");
+ seq_puts(m, "| Type | Address | Size | ");
+ seq_puts(m, "Address | Size |\n");
+ seq_puts(m, "-------------------------------------------------------");
+ seq_puts(m, "-----------------------------\n");
+
+ for (i = 0; i < be16_to_cpu(fdm_ptr->section_count); i++) {
+ seq_printf(m, "|%5u | %016llx | %016llx | %016llx | %016llx |\n",
+ fdm_ptr->section[i].src_type,
+ be64_to_cpu(fdm_ptr->section[i].src_addr),
+ be64_to_cpu(fdm_ptr->section[i].src_size),
+ be64_to_cpu(fdm_ptr->section[i].dest_addr),
+ be64_to_cpu(fdm_ptr->section[i].dest_size));
+ seq_puts(m, "-----------------------------------------------");
+ seq_puts(m, "-------------------------------------\n");
+ }
+
+}
+
+static void opal_crash_fadump(struct fadump_crash_info_header *fdh,
+ const char *msg)
+{
+ int rc;
+
+ rc = opal_cec_reboot2(OPAL_REBOOT_OS_ERROR, msg);
+ if (rc == OPAL_UNSUPPORTED) {
+ pr_emerg("Reboot type %d not supported.\n",
+ OPAL_REBOOT_OS_ERROR);
+ } else if (rc == OPAL_HARDWARE)
+ pr_emerg("No backend support for MPIPL!\n");
+}
+
+static struct fadump_ops opal_fadump_ops = {
+ .init_fadump_mem_struct = opal_init_fadump_mem_struct,
+ .register_fadump = opal_register_fadump,
+ .unregister_fadump = opal_unregister_fadump,
+ .invalidate_fadump = opal_invalidate_fadump,
+ .process_fadump = opal_process_fadump,
+ .fadump_region_show = opal_fadump_region_show,
+ .crash_fadump = opal_crash_fadump,
+};
+
+int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
+{
+ unsigned long dn;
+
+ /*
+ * Check if Firmware-Assisted Dump is supported. if yes, check
+ * if dump has been initiated on last reboot.
+ */
+ dn = of_get_flat_dt_subnode_by_name(node, "dump");
+ if (dn == -FDT_ERR_NOTFOUND) {
+ pr_debug("FADump support is missing!\n");
+ return 1;
+ }
+
+ /*
+ * Firmware currently supports only 32-bit value for size,
+ * align it to 1MB size.
+ */
+ fadump_conf->max_copy_size = _ALIGN_DOWN(0xFFFFFFFF, (1 << 20));
+
+ /*
+ * Check if dump has been initiated on last reboot.
+ */
+ fdm_active = of_get_flat_dt_prop(dn, "result-table", NULL);
+ if (fdm_active) {
+ pr_info("Firmware-assisted dump is active.\n");
+ fadump_conf->dump_active = 1;
+ update_fadump_config(fadump_conf, (void *)__pa(fdm_active));
+ }
+
+ fadump_conf->ops = &opal_fadump_ops;
+ fadump_conf->fadump_platform = FADUMP_PLATFORM_POWERNV;
+ fadump_conf->fadump_supported = 1;
+
+ return 1;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
new file mode 100644
index 0000000..a5eeb2c
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -0,0 +1,40 @@
+/*
+ * Firmware-Assisted Dump support on POWER platform (OPAL).
+ *
+ * Copyright 2018-2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __PPC64_OPAL_FA_DUMP_H__
+#define __PPC64_OPAL_FA_DUMP_H__
+
+#define OPAL_FADUMP_CPU_STATE_DATA 0x0000
+/* OPAL : 0x01 – 0x39 */
+#define OPAL_FADUMP_OPAL_REGION 0x0001
+/* Firmware/SMF : 0x40 – 0x79 */
+#define OPAL_FADUMP_FW_REGION 0x0040
+/* Kernel memory region : 0x80 – 0xb9 */
+#define OPAL_FADUMP_REAL_MODE_REGION 0x0080
+/* Reserved for future use : 0xc0 – 0xff */
+#define OPAL_FADUMP_RESERVED_REGION 0x00c0
+
+enum opal_fadump_section_types {
+ CPU_STATE_TYPE = 0,
+ OPAL_REGION_TYPE,
+ FW_REGION_TYPE,
+ RMR_REGION_TYPE,
+ OPAL_SECTIONS
+};
+
+/* Starting index of RMR region in dump sections while registering */
+#define RMR_REGION_INPUT_IDX 0
+
+#define OPAL_MAX_SECTIONS (OPAL_SECTIONS + \
+ MAX_REAL_MEM_REGIONS - 1)
+
+#endif /* __PPC64_OPAL_FA_DUMP_H__ */
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index f4875fe..ecffee3 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -331,3 +331,4 @@ OPAL_CALL(opal_pci_set_pbcq_tunnel_bar, OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64);
OPAL_CALL(opal_sensor_group_enable, OPAL_SENSOR_GROUP_ENABLE);
OPAL_CALL(opal_nx_coproc_init, OPAL_NX_COPROC_INIT);
+OPAL_CALL(opal_configure_fadump, OPAL_CONFIGURE_FADUMP);
diff --git a/arch/powerpc/platforms/pseries/pseries_fadump.c b/arch/powerpc/platforms/pseries/pseries_fadump.c
index e93a7a4..2e2bd1e 100644
--- a/arch/powerpc/platforms/pseries/pseries_fadump.c
+++ b/arch/powerpc/platforms/pseries/pseries_fadump.c
@@ -49,15 +49,6 @@ static void pseries_set_preserv_area_start(struct fw_dump *fadump_conf)
fadump_conf->preserv_area_start);
}
-static void pseries_set_meta_area_start(struct fw_dump *fadump_conf)
-{
- fadump_conf->meta_area_start = (fadump_conf->rmr_destination_addr +
- fadump_conf->rmr_source_len);
-
- pr_debug("Meta area start address: 0x%lx\n",
- fadump_conf->meta_area_start);
-}
-
static void update_fadump_config(struct fw_dump *fadump_conf,
const struct pseries_fadump_mem_struct *fdm)
{
@@ -65,11 +56,16 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
be64_to_cpu(fdm->rmr_region.destination_address);
if (fadump_conf->dump_active) {
- fadump_conf->rmr_source_len =
+ fadump_conf->rmr_src_addr[0] =
+ be64_to_cpu(fdm->rmr_region.source_address);
+ fadump_conf->rmr_src_size[0] =
be64_to_cpu(fdm->rmr_region.source_len);
+ fadump_conf->rmr_regions_cnt = 1;
+ fadump_conf->rmr_source_len = fadump_conf->rmr_src_size[0];
+ fadump_conf->boot_memory_hole_size = 0;
}
- pseries_set_meta_area_start(fadump_conf);
+ fadump_set_meta_area_start(fadump_conf);
pseries_set_preserv_area_start(fadump_conf);
}
^ permalink raw reply related
* [PATCH 06/18] powerpc/fadump: Update documentation about OPAL platform support
From: Hari Bathini @ 2019-02-21 17:35 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
With FADump support now available on both pseries and OPAL platforms,
update FADump documentation with these details.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 90 ++++++++++++----------
1 file changed, 51 insertions(+), 39 deletions(-)
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index 62e75ef..844a229 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -70,7 +70,8 @@ as follows:
normal.
-- The freshly booted kernel will notice that there is a new
- node (ibm,dump-kernel) in the device tree, indicating that
+ node (ibm,dump-kernel on PSeries or ibm,opal/dump/result-table
+ on OPAL platform) in the device tree, indicating that
there is crash data available from a previous boot. During
the early boot OS will reserve rest of the memory above
boot memory size effectively booting with restricted memory
@@ -93,7 +94,9 @@ as follows:
Please note that the firmware-assisted dump feature
is only available on Power6 and above systems with recent
-firmware versions.
+firmware versions on PSeries (PowerVM) platform and Power9
+and above systems with recent firmware versions on PowerNV
+(OPAL) platform.
Implementation details:
----------------------
@@ -108,57 +111,66 @@ that are run. If there is dump data, then the
/sys/kernel/fadump_release_mem file is created, and the reserved
memory is held.
-If there is no waiting dump data, then only the memory required
-to hold CPU state, HPTE region, boot memory dump and elfcore
-header, is usually reserved at an offset greater than boot memory
-size (see Fig. 1). This area is *not* released: this region will
-be kept permanently reserved, so that it can act as a receptacle
-for a copy of the boot memory content in addition to CPU state
-and HPTE region, in the case a crash does occur. Since this reserved
-memory area is used only after the system crash, there is no point in
-blocking this significant chunk of memory from production kernel.
-Hence, the implementation uses the Linux kernel's Contiguous Memory
-Allocator (CMA) for memory reservation if CMA is configured for kernel.
-With CMA reservation this memory will be available for applications to
-use it, while kernel is prevented from using it. With this FADump will
-still be able to capture all of the kernel memory and most of the user
-space memory except the user pages that were present in CMA region.
+If there is no waiting dump data, then only the memory required to
+hold CPU state, HPTE region, boot memory dump, FADump header and
+elfcore header, is usually reserved at an offset greater than boot
+memory size (see Fig. 1). This area is *not* released: this region
+will be kept permanently reserved, so that it can act as a receptacle
+for a copy of the boot memory content in addition to CPU state and
+HPTE region, in the case a crash does occur.
+
+Since this reserved memory area is used only after the system crash,
+there is no point in blocking this significant chunk of memory from
+production kernel. Hence, the implementation uses the Linux kernel's
+Contiguous Memory Allocator (CMA) for memory reservation if CMA is
+configured for kernel. With CMA reservation this memory will be
+available for applications to use it, while kernel is prevented from
+using it. With this FADump will still be able to capture all of the
+kernel memory and most of the user space memory except the user pages
+that were present in CMA region.
o Memory Reservation during first kernel
- Low memory Top of memory
- 0 boot memory size |<--Reserved dump area --->| |
- | | | Permanent Reservation | |
- V V | (Preserve area) | V
- +-----------+----------/ /---+---+----+--------+---+----+------+
- | | |CPU|HPTE| DUMP |HDR|ELF | |
- +-----------+----------/ /---+---+----+--------+---+----+------+
- | ^ ^
- | | |
- \ / |
- ----------------------------------- FADump Header
- Boot memory content gets transferred (meta area)
- to reserved area by firmware at the
- time of crash
-
+ Low memory Top of memory
+ 0 boot memory size |<--- Reserved dump area --->| |
+ | | | Permanent Reservatio | |
+ V V | (Preserve area) | V
+ +-----------+--------/ /---+---+----+-------+-----+-----+-------+
+ | | |///|////| DUMP | HDR | ELF | |
+ +-----------+--------/ /---+---+----+-------+-----+-----+-------+
+ | ^ ^ ^ ^
+ | | | | |
+ \ CPU HPTE / |
+ --------------------------------- |
+ Boot memory content gets transferred |
+ to reserved area by firmware at the |
+ time of crash. |
+ FADump Header
+ (meta area)
Fig. 1
o Memory Reservation during second kernel after crash
- Low memory Top of memory
- 0 boot memory size |
- | |<------------- Reserved dump area --------------->|
- V V |<---- Preserve area ----->| V
- +-----------+----------/ /---+---+----+--------+---+----+------+
- | | |CPU|HPTE| DUMP |HDR|ELF | |
- +-----------+----------/ /---+---+----+--------+---+----+------+
+ Low memory Top of memory
+ 0 boot memory size |
+ | |<--------------- Reserved dump area -------------->|
+ V V |<---- Preserve area ------->| |
+ +-----------+--------/ /---+---+----+-------+-----+-----+-------+
+ | | |///|////| DUMP | HDR | ELF | |
+ +-----------+--------/ /---+---+----+-------+-----+-----+-------+
| |
V V
Used by second /proc/vmcore
kernel to boot
Fig. 2
+ +---+
+ |///| -> Regions (CPU & HPTE) marked like this in the above figures
+ +---+ are not always present. For example, OPAL platform does not
+ have CPU & HPTE regions.
+
+
Currently the dump will be copied from /proc/vmcore to a new file upon
user intervention. The dump data available through /proc/vmcore will be
in ELF format. Hence the existing kdump infrastructure (kdump scripts)
^ permalink raw reply related
* [PATCH 09/18] powernv/fadump: process architected register state data provided by firmware
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Firmware provides architected register state data at the time of crash.
Process this data and build CPU notes to append to ELF core.
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/opal-api.h | 23 +++
arch/powerpc/kernel/fadump_internal.h | 3
arch/powerpc/platforms/powernv/opal-fadump.c | 187 ++++++++++++++++++++++++--
arch/powerpc/platforms/powernv/opal-fadump.h | 4 +
4 files changed, 206 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 6076e51..f39a2b7 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -976,6 +976,29 @@ struct opal_sg_list {
* Firmware-Assisted Dump (FADump)
*/
+/* FADump thread header for register entries */
+struct opal_fadump_thread_hdr {
+ __be32 pir;
+ /* 0x00 - 0x0F - The corresponding stop state of the core */
+ u8 core_state;
+ u8 reserved[3];
+
+ __be32 offset; /* Offset to Register Entries array */
+ __be32 ecnt; /* Number of entries */
+ __be32 esize; /* Alloc size of each array entry in bytes */
+ __be32 eactsz; /* Actual size of each array entry in bytes */
+} __packed;
+
+#define OPAL_REG_TYPE_GPR 0
+#define OPAL_REG_TYPE_SPR 1
+
+/* FADump register entry. */
+struct opal_fadump_reg_entry {
+ __be32 reg_type;
+ __be32 reg_num;
+ __be64 reg_val;
+};
+
/* The maximum number of dump sections supported by OPAL */
#define OPAL_FADUMP_NR_SECTIONS 64
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index ff764d4..8d47382 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -117,6 +117,9 @@ struct fadump_memory_range {
/* 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 hpte_region_size;
unsigned long boot_memory_size;
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 3a83609..1b3a33f 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -94,6 +94,12 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
last_end = base + size;
j++;
+ } else if (fdm->section[i].src_type ==
+ OPAL_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;
@@ -199,6 +205,75 @@ static int opal_invalidate_fadump(struct fw_dump *fadump_conf)
return 0;
}
+static inline void fadump_set_regval_regnum(struct pt_regs *regs, u32 reg_type,
+ u32 reg_num, u64 reg_val)
+{
+ if (reg_type == OPAL_REG_TYPE_GPR) {
+ if (reg_num < 32)
+ regs->gpr[reg_num] = reg_val;
+ return;
+ }
+
+ switch (reg_num) {
+ case 2000:
+ regs->nip = reg_val;
+ break;
+ case 2001:
+ regs->msr = reg_val;
+ break;
+ case 9:
+ regs->ctr = reg_val;
+ break;
+ case 8:
+ regs->link = reg_val;
+ break;
+ case 1:
+ regs->xer = reg_val;
+ break;
+ case 2002:
+ regs->ccr = reg_val;
+ break;
+ case 19:
+ regs->dar = reg_val;
+ break;
+ case 18:
+ regs->dsisr = reg_val;
+ break;
+ }
+}
+
+static inline void fadump_read_registers(char *bufp, unsigned int regs_cnt,
+ unsigned int reg_entry_size,
+ struct pt_regs *regs)
+{
+ int i;
+ struct opal_fadump_reg_entry *reg_entry;
+
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) {
+ reg_entry = (struct opal_fadump_reg_entry *)bufp;
+ fadump_set_regval_regnum(regs,
+ be32_to_cpu(reg_entry->reg_type),
+ be32_to_cpu(reg_entry->reg_num),
+ be64_to_cpu(reg_entry->reg_val));
+ }
+}
+
+static inline bool __init is_thread_core_inactive(u8 core_state)
+{
+ bool is_inactive = false;
+
+ /*
+ * TODO: Check what each state value means and implement accordingly.
+ * Also, make sure F/W is updating this field appropriately.
+ */
+ if (core_state == CORE_STATE_INACTIVE)
+ is_inactive = true;
+
+ return is_inactive;
+}
+
/*
* Read CPU state dump data and convert it into ELF notes.
*
@@ -210,8 +285,32 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
{
u32 num_cpus, *note_buf;
struct fadump_crash_info_header *fdh = NULL;
+ struct opal_fadump_thread_hdr *thdr;
+ unsigned long addr;
+ u32 thread_pir;
+ char *bufp;
+ struct pt_regs regs;
+ unsigned int size_of_each_thread;
+ unsigned int regs_offset, regs_cnt, reg_esize;
+ int i;
+
+ size_of_each_thread = fadump_conf->cpu_state_entry_size;
+ num_cpus = (fadump_conf->cpu_state_data_size / size_of_each_thread);
+
+ addr = fadump_conf->cpu_state_destination_addr;
+ bufp = __va(addr);
+
+ /*
+ * Offset for register entries, entry size and registers count is
+ * duplicated in every thread header in keeping with HDAT format.
+ * Use these values from the first thread header.
+ */
+ thdr = (struct opal_fadump_thread_hdr *)bufp;
+ regs_offset = (offsetof(struct opal_fadump_thread_hdr, offset) +
+ be32_to_cpu(thdr->offset));
+ reg_esize = be32_to_cpu(thdr->esize);
+ regs_cnt = be32_to_cpu(thdr->ecnt);
- num_cpus = 1;
/* 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 =
@@ -230,10 +329,53 @@ 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");
+ pr_debug("NumCpus : %u\n", num_cpus);
+ pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n",
+ regs_offset, reg_esize, regs_cnt);
+
+ for (i = 0; i < num_cpus; i++, bufp += size_of_each_thread) {
+ thdr = (struct opal_fadump_thread_hdr *)bufp;
+
+ thread_pir = be32_to_cpu(thdr->pir);
+ pr_debug("%04d) PIR: 0x%x, core state: 0x%02x\n",
+ (i + 1), thread_pir, thdr->core_state);
+
+ /*
+ * Register state data of MAX cores is provided by firmware,
+ * but some of this cores may not be active. So, while
+ * processing register state data, check core state and
+ * skip threads that belong to inactive cores.
+ */
+ if (is_thread_core_inactive(thdr->core_state))
+ continue;
+
+ /*
+ * If this is kernel initiated crash, crashing_cpu would be set
+ * appropriately and register data of the crashing CPU saved by
+ * crashing kernel. Add this saved register data of crashing CPU
+ * to elf notes and populate the pt_regs for the remaining CPUs
+ * from register state data provided by firmware.
+ */
+ if (fdh && (fdh->crashing_cpu == thread_pir)) {
+ note_buf = fadump_regs_to_elf_notes(note_buf,
+ &fdh->regs);
+ pr_debug("Crashing CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n",
+ fdh->crashing_cpu, fdh->regs.gpr[1],
+ fdh->regs.nip);
+ continue;
+ }
+
+ fadump_read_registers((bufp + regs_offset), regs_cnt,
+ reg_esize, ®s);
+
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ pr_debug("CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n",
+ thread_pir, regs.gpr[1], regs.nip);
+ }
+ 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,
@@ -258,13 +400,6 @@ static int __init opal_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;
@@ -319,6 +454,14 @@ static void opal_crash_fadump(struct fadump_crash_info_header *fdh,
{
int rc;
+ /*
+ * Unlike on pseries platform, logical CPU number is not provided
+ * with architected register state data. So, store the crashing
+ * CPU's PIR instead to plug the appropriate register data for
+ * crashing CPU in the vmcore file.
+ */
+ fdh->crashing_cpu = (u32)mfspr(SPRN_PIR);
+
rc = opal_cec_reboot2(OPAL_REBOOT_OS_ERROR, msg);
if (rc == OPAL_UNSUPPORTED) {
pr_emerg("Reboot type %d not supported.\n",
@@ -340,6 +483,7 @@ static struct fadump_ops opal_fadump_ops = {
int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
{
unsigned long dn;
+ const __be32 *prop;
/*
* Check if Firmware-Assisted Dump is supported. if yes, check
@@ -351,6 +495,17 @@ int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
return 1;
}
+ prop = of_get_flat_dt_prop(dn, "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) {
+ pr_err("CPU state data format version mismatch!\n");
+ pr_err("Kernel: %u, OPAL: %lu\n", CPU_STATE_DATA_VERSION,
+ fadump_conf->cpu_state_data_version);
+ return 1;
+ }
+
/*
* Firmware currently supports only 32-bit value for size,
* align it to 1MB size.
@@ -365,6 +520,16 @@ int __init opal_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(dn, "cpu-data-size", NULL);
+ if (prop) {
+ fadump_conf->cpu_state_entry_size =
+ of_read_number(prop, 1);
+ }
}
fadump_conf->ops = &opal_fadump_ops;
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index a5eeb2c..80aee2d 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -13,6 +13,8 @@
#ifndef __PPC64_OPAL_FA_DUMP_H__
#define __PPC64_OPAL_FA_DUMP_H__
+#define CPU_STATE_DATA_VERSION 1
+
#define OPAL_FADUMP_CPU_STATE_DATA 0x0000
/* OPAL : 0x01 – 0x39 */
#define OPAL_FADUMP_OPAL_REGION 0x0001
@@ -37,4 +39,6 @@ enum opal_fadump_section_types {
#define OPAL_MAX_SECTIONS (OPAL_SECTIONS + \
MAX_REAL_MEM_REGIONS - 1)
+#define CORE_STATE_INACTIVE (0x0F)
+
#endif /* __PPC64_OPAL_FA_DUMP_H__ */
^ permalink raw reply related
* [PATCH 07/18] powerpc/fadump: consider reserved ranges while reserving memory
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Commit 0962e8004e97 ("powerpc/prom: Scan reserved-ranges node for
memory reservations") enabled support to parse reserved-ranges DT
node and reserve kernel memory falling in these ranges for F/W
purposes. Ensure memory in these ranges is not overlapped with
memory reserved for FADump.
Also, use a smaller offset, instead of the size of the memory to
be reserved, by which to skip memory before making another attempt
at reserving memory, after the previous attempt to reserve memory
for FADump failed due to memory holes and/or reserved ranges, to
reduce the likelihood of memory reservation failure.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump.c | 137 ++++++++++++++++++++++++++++++++-
arch/powerpc/kernel/fadump_internal.h | 11 +++
2 files changed, 145 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 6ff05046..a4510c91 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -53,6 +53,9 @@ int crash_memory_ranges_size;
int crash_mem_ranges;
int max_crash_mem_ranges;
+struct fadump_memory_range reserved_ranges[MAX_RESERVED_RANGES];
+int reserved_ranges_cnt;
+
#ifdef CONFIG_CMA
static struct cma *fadump_cma;
@@ -116,12 +119,116 @@ int __init fadump_cma_init(void)
static int __init fadump_cma_init(void) { return 1; }
#endif /* CONFIG_CMA */
+/*
+ * Sort the reserved ranges in-place and merge adjacent ranges
+ * to minimize the reserved ranges count.
+ */
+static void __init sort_and_merge_reserved_ranges(void)
+{
+ unsigned long long base, size;
+ struct fadump_memory_range tmp_range;
+ int i, j, idx;
+
+ if (!reserved_ranges_cnt)
+ return;
+
+ /* Sort the reserved ranges */
+ for (i = 0; i < reserved_ranges_cnt; i++) {
+ idx = i;
+ for (j = i + 1; j < reserved_ranges_cnt; j++) {
+ if (reserved_ranges[idx].base > reserved_ranges[j].base)
+ idx = j;
+ }
+ if (idx != i) {
+ tmp_range = reserved_ranges[idx];
+ reserved_ranges[idx] = reserved_ranges[i];
+ reserved_ranges[i] = tmp_range;
+ }
+ }
+
+ /* Merge adjacent reserved ranges */
+ idx = 0;
+ for (i = 1; i < reserved_ranges_cnt; i++) {
+ base = reserved_ranges[i-1].base;
+ size = reserved_ranges[i-1].size;
+ if (reserved_ranges[i].base == (base + size))
+ reserved_ranges[idx].size += reserved_ranges[i].size;
+ else {
+ idx++;
+ if (i == idx)
+ continue;
+
+ reserved_ranges[idx] = reserved_ranges[i];
+ }
+ }
+ reserved_ranges_cnt = idx + 1;
+}
+
+static int __init add_reserved_range(unsigned long base,
+ unsigned long size)
+{
+ int i;
+
+ if (reserved_ranges_cnt == MAX_RESERVED_RANGES) {
+ /* Compact reserved ranges and try again. */
+ sort_and_merge_reserved_ranges();
+ if (reserved_ranges_cnt == MAX_RESERVED_RANGES)
+ return 0;
+ }
+
+ i = reserved_ranges_cnt++;
+ reserved_ranges[i].base = base;
+ reserved_ranges[i].size = size;
+ return 1;
+}
+
+/*
+ * Scan reserved-ranges to consider them while reserving/releasing
+ * memory for FADump.
+ */
+static void __init early_init_dt_scan_reserved_ranges(unsigned long node)
+{
+ int len, ret;
+ unsigned long i;
+ const __be32 *prop;
+
+ /* reserved-ranges already scanned */
+ if (reserved_ranges_cnt != 0)
+ return;
+
+ prop = of_get_flat_dt_prop(node, "reserved-ranges", &len);
+
+ if (!prop)
+ return;
+
+ /*
+ * Each reserved range is an (address,size) pair, 2 cells each,
+ * totalling 4 cells per range.
+ */
+ for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+ u64 base, size;
+
+ base = of_read_number(prop + (i * 4) + 0, 2);
+ size = of_read_number(prop + (i * 4) + 2, 2);
+
+ if (size) {
+ ret = add_reserved_range(base, size);
+ if (ret == 0)
+ pr_warn("some reserved ranges are ignored!\n");
+ }
+ }
+}
+
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
int depth, void *data)
{
- if (depth != 1)
+ if (depth != 1) {
+ if (depth == 0)
+ early_init_dt_scan_reserved_ranges(node);
+
return 0;
+ }
if (strcmp(uname, "rtas") == 0)
return pseries_dt_scan_fadump(&fw_dump, node);
@@ -363,6 +470,26 @@ static int __init fadump_get_rmr_regions(void)
return ret;
}
+static bool overlaps_with_reserved_ranges(ulong base, ulong end)
+{
+ int i, ret = 0;
+
+ for (i = 0; i < reserved_ranges_cnt; i++) {
+ ulong rbase = (ulong)reserved_ranges[i].base;
+ ulong rend = rbase + (ulong)reserved_ranges[i].size;
+
+ if (end <= rbase)
+ break;
+
+ if ((end > rbase) && (base < rend)) {
+ ret = 1;
+ break;
+ }
+ }
+
+ return ret;
+}
+
/* Preserve everything above the base address */
static void __init fadump_reserve_crash_area(unsigned long base)
{
@@ -399,6 +526,9 @@ int __init fadump_reserve_mem(void)
goto error_out;
}
+ /* Compact reserved ranges */
+ sort_and_merge_reserved_ranges();
+
/*
* Initialize boot memory size
* If dump is active then we have already calculated the size during
@@ -474,10 +604,11 @@ int __init fadump_reserve_mem(void)
*/
while (base <= (memory_boundary - size)) {
if (memblock_is_region_memory(base, size) &&
- !memblock_is_region_reserved(base, size))
+ !memblock_is_region_reserved(base, size) &&
+ !overlaps_with_reserved_ranges(base, (base+size)))
break;
- base += size;
+ base += OFFSET_SIZE;
}
if ((base > (memory_boundary - size)) ||
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index 8ad98db..ff764d4 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -101,6 +101,17 @@ struct fadump_memory_range {
unsigned long long size;
};
+/*
+ * Amount of memory (1024MB) to skip before making another attempt at
+ * reserving memory (after the previous attempt to reserve memory for
+ * FADump failed due to memory holes and/or reserved ranges) to reduce
+ * the likelihood of memory reservation failure.
+ */
+#define OFFSET_SIZE 0x40000000U
+
+/* Maximum no. of reserved ranges supported for processing. */
+#define MAX_RESERVED_RANGES 128
+
/* Maximum no. of real memory regions supported by the kernel */
#define MAX_REAL_MEM_REGIONS 8
^ permalink raw reply related
* [PATCH 10/18] powernv/fadump: add support to preserve crash data on FADUMP disabled kernel
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Add a new kernel config option, CONFIG_PRESERVE_FA_DUMP that ensures
that crash data, from previously crash'ed kernel, is preserved. This
helps in cases where FADump is not enabled but the subsequent memory
preserving kernel boot is likely to process this crash data. One
typical usecase for this config option is petitboot kernel.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/Kconfig | 9 +++++
arch/powerpc/include/asm/fadump.h | 9 +++--
arch/powerpc/kernel/Makefile | 6 +++
arch/powerpc/kernel/fadump.c | 47 +++++++++++++++++++++++---
arch/powerpc/kernel/fadump_internal.h | 8 ++++
arch/powerpc/kernel/prom.c | 4 +-
arch/powerpc/platforms/powernv/Makefile | 1 +
arch/powerpc/platforms/powernv/opal-fadump.c | 37 +++++++++++++++++++-
8 files changed, 106 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c667d07..964a3ba 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -582,6 +582,15 @@ config FA_DUMP
If unsure, say "y". Only special kernels like petitboot may
need to say "N" here.
+config PRESERVE_FA_DUMP
+ bool "Preserve Firmware-assisted dump"
+ depends on PPC64 && PPC_POWERNV && !FA_DUMP
+ help
+ On a kernel with FA_DUMP disabled, this option helps to preserve
+ crash data from a previously crash'ed kernel. Useful when the next
+ memory preserving kernel boot would process this crash data.
+ Petitboot kernel is the typical usecase for this option.
+
config IRQ_ALL_CPUS
bool "Distribute interrupts on all CPUs by default"
depends on SMP
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index d27cde7..d09b77b 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -27,9 +27,6 @@
extern int crashing_cpu;
extern int is_fadump_memory_area(u64 addr, ulong size);
-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);
extern int should_fadump_crash(void);
@@ -41,4 +38,10 @@ static inline int is_fadump_active(void) { return 0; }
static inline int should_fadump_crash(void) { return 0; }
static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
#endif /* !CONFIG_FA_DUMP */
+
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
+ int depth, void *data);
+extern int fadump_reserve_mem(void);
+#endif
#endif /* __PPC64_FA_DUMP_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index eb50ac3..d091e56 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -65,7 +65,11 @@ obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
eeh_driver.o eeh_event.o eeh_sysfs.o
obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
-obj-$(CONFIG_FA_DUMP) += fadump.o fadump_internal.o
+ifeq ($(CONFIG_FA_DUMP),y)
+obj-y += fadump.o fadump_internal.o
+else
+obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o
+endif
ifdef CONFIG_PPC32
obj-$(CONFIG_E500) += idle_e500.o
endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 0332d7f..d343c4b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -47,6 +47,7 @@
static struct fw_dump fw_dump;
+#ifndef CONFIG_PRESERVE_FA_DUMP
static DEFINE_MUTEX(fadump_mutex);
struct fadump_memory_range *crash_memory_ranges;
int crash_memory_ranges_size;
@@ -217,6 +218,9 @@ static void __init early_init_dt_scan_reserved_ranges(unsigned long node)
}
}
}
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+static inline void early_init_dt_scan_reserved_ranges(unsigned long node) { }
+#endif /* CONFIG_PRESERVE_FA_DUMP */
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
@@ -238,6 +242,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
return 0;
}
+#ifndef CONFIG_PRESERVE_FA_DUMP
/*
* If fadump is registered, check if the memory provided
* falls within boot memory area and reserved memory area.
@@ -488,6 +493,7 @@ static bool overlaps_with_reserved_ranges(ulong base, ulong end)
return ret;
}
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
/* Preserve everything above the base address */
static void __init fadump_reserve_crash_area(unsigned long base)
@@ -506,12 +512,45 @@ static void __init fadump_reserve_crash_area(unsigned long base)
msize -= (base - mstart);
mstart = base;
}
- pr_info("Reserving %luMB of memory at %#016lx for saving crash dump",
+ pr_info("Reserving %luMB of memory at %#016lx for preserving crash data",
(msize >> 20), mstart);
memblock_reserve(mstart, msize);
}
}
+unsigned long __init arch_reserved_kernel_pages(void)
+{
+ return memblock_reserved_size() / PAGE_SIZE;
+}
+
+#ifdef CONFIG_PRESERVE_FA_DUMP
+/*
+ * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel,
+ * preserve crash data. The subsequent memory preserving kernel boot
+ * is likely to process this crash data.
+ */
+int __init fadump_reserve_mem(void)
+{
+ if (fw_dump.dump_active) {
+ unsigned long base;
+
+ pr_info("Preserving crash data for processing in next boot.\n");
+ fw_dump.boot_memory_size = fw_dump.rmr_source_len;
+ base = fw_dump.boot_memory_size + fw_dump.boot_memory_hole_size;
+ base = PAGE_ALIGN(base);
+
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot memory size to preserve crash data.
+ */
+ fadump_reserve_crash_area(base);
+ } else
+ pr_debug("FADump-aware kernel..\n");
+
+ return 1;
+}
+#else /* CONFIG_PRESERVE_FA_DUMP */
+
int __init fadump_reserve_mem(void)
{
int ret = 1;
@@ -630,11 +669,6 @@ int __init fadump_reserve_mem(void)
return 0;
}
-unsigned long __init arch_reserved_kernel_pages(void)
-{
- return memblock_reserved_size() / PAGE_SIZE;
-}
-
/* Look for fadump= cmdline option. */
static int __init early_fadump_param(char *p)
{
@@ -1395,3 +1429,4 @@ int __init setup_fadump(void)
return 1;
}
subsys_initcall(setup_fadump);
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index 8d47382..1bd3aeb 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -13,6 +13,7 @@
#ifndef __PPC64_FA_DUMP_INTERNAL_H__
#define __PPC64_FA_DUMP_INTERNAL_H__
+#ifndef CONFIG_PRESERVE_FA_DUMP
/*
* The RMA region will be saved for later dumping when kernel crashes.
* RMA is Real Mode Area, the first block of logical memory address owned
@@ -88,6 +89,7 @@ struct fadump_crash_info_header {
/* Platform specific callback functions */
struct fadump_ops;
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
/* Firmware-Assited Dump platforms */
enum fadump_platform_type {
@@ -157,9 +159,12 @@ struct fw_dump {
unsigned long nocma:1;
enum fadump_platform_type fadump_platform;
+#ifndef CONFIG_PRESERVE_FA_DUMP
struct fadump_ops *ops;
+#endif
};
+#ifndef CONFIG_PRESERVE_FA_DUMP
struct fadump_ops {
ulong (*init_fadump_mem_struct)(struct fw_dump *fadump_config);
int (*register_fadump)(struct fw_dump *fadump_config);
@@ -181,8 +186,9 @@ u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
int is_boot_memory_area_contiguous(struct fw_dump *fadump_conf);
int is_reserved_memory_area_contiguous(struct fw_dump *fadump_conf);
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
-#ifdef CONFIG_PPC_PSERIES
+#if !defined(CONFIG_PRESERVE_FA_DUMP) && defined(CONFIG_PPC_PSERIES)
extern int pseries_dt_scan_fadump(struct fw_dump *fadump_config, ulong node);
#else
static inline int
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 4181ec7..3de45a4 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -705,7 +705,7 @@ void __init early_init_devtree(void *params)
of_scan_flat_dt(early_init_dt_scan_opal, NULL);
#endif
-#ifdef CONFIG_FA_DUMP
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
/* scan tree to see if dump is active during last boot */
of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
#endif
@@ -732,7 +732,7 @@ void __init early_init_devtree(void *params)
if (PHYSICAL_START > MEMORY_START)
memblock_reserve(MEMORY_START, 0x8000);
reserve_kdump_trampoline();
-#ifdef CONFIG_FA_DUMP
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
/*
* If we fail to reserve memory for firmware-assisted dump then
* fallback to kexec based kdump.
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index adc0de6..f05a262 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -7,6 +7,7 @@ obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o
obj-$(CONFIG_FA_DUMP) += opal-fadump.o
+obj-$(CONFIG_PRESERVE_FA_DUMP) += opal-fadump.o
obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
obj-$(CONFIG_CXL_BASE) += pci-cxl.o
obj-$(CONFIG_EEH) += eeh-powernv.o
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 1b3a33f..f16f1aa 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -28,9 +28,10 @@
#include "../../kernel/fadump_internal.h"
#include "opal-fadump.h"
-static struct opal_fadump_mem_struct fdm;
-static const struct opal_fadump_mem_struct *fdm_active;
unsigned long fdm_actual_size;
+static const struct opal_fadump_mem_struct *fdm_active;
+#ifndef CONFIG_PRESERVE_FA_DUMP
+static struct opal_fadump_mem_struct fdm;
static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
{
@@ -39,6 +40,7 @@ static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
pr_debug("Preserve area start address: 0x%lx\n",
fadump_conf->preserv_area_start);
}
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
static void update_fadump_config(struct fw_dump *fadump_conf,
const struct opal_fadump_mem_struct *fdm)
@@ -107,10 +109,40 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
fadump_conf->rmr_regions_cnt);
}
+#ifndef CONFIG_PRESERVE_FA_DUMP
fadump_set_meta_area_start(fadump_conf);
opal_set_preserv_area_start(fadump_conf);
+#endif
+}
+
+/*
+ * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel,
+ * ensure crash data is preserved in hope that the subsequent memory
+ * preserving kernel boot is going to process this crash data.
+ */
+#ifdef CONFIG_PRESERVE_FA_DUMP
+int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
+{
+ unsigned long dn;
+
+ dn = of_get_flat_dt_subnode_by_name(node, "dump");
+ if (dn == -FDT_ERR_NOTFOUND)
+ return 1;
+
+ /*
+ * Check if dump has been initiated on last reboot.
+ */
+ fdm_active = of_get_flat_dt_prop(dn, "result-table", NULL);
+ if (fdm_active) {
+ pr_info("Firmware-assisted dump is active.\n");
+ fadump_conf->dump_active = 1;
+ update_fadump_config(fadump_conf, (void *)__pa(fdm_active));
+ }
+
+ return 1;
}
+#else /* CONFIG_PRESERVE_FA_DUMP */
static ulong opal_init_fadump_mem_struct(struct fw_dump *fadump_conf)
{
ulong addr = fadump_conf->reserve_dump_area_start;
@@ -538,3 +570,4 @@ int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
return 1;
}
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
^ permalink raw reply related
* [PATCH 11/18] powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Kernel config option CONFIG_PRESERVE_FA_DUMP is introduced to ensure
crash data, from previously crash'ed kernel, is preserved. Update
documentation with this details.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index 844a229..fa35593 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -98,6 +98,15 @@ firmware versions on PSeries (PowerVM) platform and Power9
and above systems with recent firmware versions on PowerNV
(OPAL) platform.
+On OPAL based machines, system first boots into an intermittent
+kernel (referred to as petitboot kernel) before booting into the
+capture kernel. This kernel would have minimal kernel and/or
+userspace support to process crash data. Such kernel needs to
+preserve previously crash'ed kernel's memory for the subsequent
+capture kernel boot to process this crash data. Kernel config
+option CONFIG_PRESERVE_FA_DUMP has to be enabled on such kernel
+to ensure that crash data is preserved to process later.
+
Implementation details:
----------------------
^ permalink raw reply related
* [PATCH 12/18] powerpc/powernv: export /proc/opalcore for analysing opal crashes
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Export /proc/opalcore file to analyze opal crashes. Since opalcore can
be generated independent of CONFIG_FA_DUMP support in kernel, add this
support under a new kernel config option CONFIG_OPAL_CORE. Also, avoid
code duplication by moving common code used for processing the register
state data to export /proc/vmcore and/or /proc/opalcore file(s).
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 9
arch/powerpc/platforms/powernv/Makefile | 1
arch/powerpc/platforms/powernv/opal-core.c | 563 ++++++++++++++++++++++++++
arch/powerpc/platforms/powernv/opal-fadump.c | 94 +---
arch/powerpc/platforms/powernv/opal-fadump.h | 72 +++
5 files changed, 669 insertions(+), 70 deletions(-)
create mode 100644 arch/powerpc/platforms/powernv/opal-core.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 964a3ba..2c08c3b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -591,6 +591,15 @@ config PRESERVE_FA_DUMP
memory preserving kernel boot would process this crash data.
Petitboot kernel is the typical usecase for this option.
+config OPAL_CORE
+ bool "Export OPAL memory as /proc/opalcore"
+ depends on PPC64 && PPC_POWERNV
+ help
+ This option uses the MPIPL support in firmware to provide
+ an ELF core of OPAL memory after a crash. The ELF core is
+ exported as /proc/opalcore file which is helpful in debugging
+ opal crashes using GDB.
+
config IRQ_ALL_CPUS
bool "Distribute interrupts on all CPUs by default"
depends on SMP
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index f05a262..05ba0c9 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -8,6 +8,7 @@ obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o
obj-$(CONFIG_FA_DUMP) += opal-fadump.o
obj-$(CONFIG_PRESERVE_FA_DUMP) += opal-fadump.o
+obj-$(CONFIG_OPAL_CORE) += opal-core.o
obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
obj-$(CONFIG_CXL_BASE) += pci-cxl.o
obj-$(CONFIG_EEH) += eeh-powernv.o
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
new file mode 100644
index 0000000..5355d95
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -0,0 +1,563 @@
+/*
+ * Interface for exporting the OPAL ELF core.
+ * Heavily inspired from fs/proc/vmcore.c
+ *
+ * Copyright 2018-2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "opalcore: " fmt
+
+#include <linux/memblock.h>
+#include <linux/uaccess.h>
+#include <linux/proc_fs.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/slab.h>
+#include <linux/crash_core.h>
+#include <linux/of.h>
+
+#include <asm/page.h>
+#include <asm/opal.h>
+
+#include "../../kernel/fadump_internal.h"
+#include "opal-fadump.h"
+
+#define MAX_PT_LOAD_CNT 8
+
+/* NT_AUXV note related info */
+#define AUXV_CNT 1
+#define AUXV_DESC_SZ (((2 * AUXV_CNT) + 1) * sizeof(Elf64_Off))
+
+struct opalcore_config {
+ unsigned int num_cpus;
+ /* PIR value of crashing CPU */
+ unsigned int crashing_cpu;
+
+ /* CPU state data info from F/W */
+ unsigned long cpu_state_destination_addr;
+ unsigned long cpu_state_data_size;
+ unsigned long cpu_state_entry_size;
+
+ /* OPAL memory to be exported as PT_LOAD segments */
+ unsigned long ptload_addr[MAX_PT_LOAD_CNT];
+ unsigned long ptload_size[MAX_PT_LOAD_CNT];
+ unsigned long ptload_cnt;
+
+ /* Pointer to the first PT_LOAD in the ELF core file */
+ Elf64_Phdr *ptload_phdr;
+
+ /* Total size of opalcore file. */
+ size_t opalcore_size;
+
+ struct proc_dir_entry *proc_opalcore;
+
+ /* Buffer for all the ELF core headers and the PT_NOTE */
+ size_t opalcorebuf_sz;
+ char *opalcorebuf;
+
+ /* NT_AUXV buffer */
+ char auxv_buf[AUXV_DESC_SZ];
+};
+
+struct opalcore {
+ struct list_head list;
+ unsigned long long paddr;
+ unsigned long long size;
+ loff_t offset;
+};
+
+static LIST_HEAD(opalcore_list);
+static struct opalcore_config *oc_conf;
+static const struct opal_fadump_mem_struct *fdm_active;
+
+/*
+ * Set crashing CPU's signal to SIGUSR1. if the kernel is triggered
+ * by kernel, SIGTERM otherwise.
+ */
+bool kernel_initiated;
+
+static struct opalcore * __init get_new_element(void)
+{
+ return kzalloc(sizeof(struct opalcore), GFP_KERNEL);
+}
+
+static inline int is_opalcore_usable(void)
+{
+ return (oc_conf && oc_conf->opalcorebuf != NULL) ? 1 : 0;
+}
+
+static Elf64_Word *append_elf64_note(Elf64_Word *buf, char *name,
+ unsigned int type, void *data,
+ size_t data_len)
+{
+ Elf64_Nhdr *note = (Elf64_Nhdr *)buf;
+ Elf64_Word namesz = strlen(name) + 1;
+
+ note->n_namesz = cpu_to_be32(namesz);
+ note->n_descsz = cpu_to_be32(data_len);
+ note->n_type = cpu_to_be32(type);
+ buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf64_Word));
+ memcpy(buf, name, namesz);
+ buf += DIV_ROUND_UP(namesz, sizeof(Elf64_Word));
+ memcpy(buf, data, data_len);
+ buf += DIV_ROUND_UP(data_len, sizeof(Elf64_Word));
+
+ return buf;
+}
+
+static void fill_prstatus(struct elf_prstatus *prstatus, int pir,
+ struct pt_regs *regs)
+{
+ memset(prstatus, 0, sizeof(struct elf_prstatus));
+ elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs);
+
+ /*
+ * Overload PID with PIR value.
+ * As a PIR value could also be '0', add an offset of '100'
+ * to every PIR to avoid misinterpretations in GDB.
+ */
+ prstatus->pr_pid = cpu_to_be32(100 + pir);
+ prstatus->pr_ppid = cpu_to_be32(1);
+
+ /*
+ * Indicate SIGUSR1 for crash initiated from kernel.
+ * SIGTERM otherwise.
+ */
+ if (pir == oc_conf->crashing_cpu) {
+ short sig;
+
+ sig = kernel_initiated ? SIGUSR1 : SIGTERM;
+ prstatus->pr_cursig = cpu_to_be16(sig);
+ }
+}
+
+static Elf64_Word *auxv_to_elf64_notes(Elf64_Word *buf,
+ uint64_t opal_boot_entry)
+{
+ int idx = 0;
+ Elf64_Off *bufp = (Elf64_Off *)oc_conf->auxv_buf;
+
+ memset(bufp, 0, AUXV_DESC_SZ);
+
+ /* Entry point of OPAL */
+ bufp[idx++] = cpu_to_be64(AT_ENTRY);
+ bufp[idx++] = cpu_to_be64(opal_boot_entry);
+
+ /* end of vector */
+ bufp[idx++] = cpu_to_be64(AT_NULL);
+
+ buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_AUXV,
+ oc_conf->auxv_buf, AUXV_DESC_SZ);
+ return buf;
+}
+
+/*
+ * Read from the ELF header and then the crash dump.
+ * Returns number of bytes read on success, -errno on failure.
+ */
+static ssize_t read_opalcore(struct file *file, char __user *buffer,
+ size_t buflen, loff_t *fpos)
+{
+ struct opalcore *m;
+ ssize_t tsz, acc = 0;
+
+ if (buflen == 0 || *fpos >= oc_conf->opalcore_size)
+ return 0;
+
+ /* Read ELF core header and/or PT_NOTE segment */
+ if (*fpos < oc_conf->opalcorebuf_sz) {
+ tsz = min(oc_conf->opalcorebuf_sz - (size_t)*fpos, buflen);
+ if (copy_to_user(buffer, oc_conf->opalcorebuf + *fpos, tsz))
+ return -EFAULT;
+ buflen -= tsz;
+ *fpos += tsz;
+ buffer += tsz;
+ acc += tsz;
+
+ /* leave now if filled buffer already */
+ if (buflen == 0)
+ return acc;
+ }
+
+ list_for_each_entry(m, &opalcore_list, list) {
+ if (*fpos < m->offset + m->size) {
+ void *addr;
+
+ tsz = (size_t)min_t(unsigned long long,
+ m->offset + m->size - *fpos,
+ buflen);
+ addr = (void *)(m->paddr + *fpos - m->offset);
+ if (copy_to_user(buffer, __va(addr), tsz))
+ return -EFAULT;
+ buflen -= tsz;
+ *fpos += tsz;
+ buffer += tsz;
+ acc += tsz;
+
+ /* leave now if filled buffer already */
+ if (buflen == 0)
+ return acc;
+ }
+ }
+
+ return acc;
+}
+
+static const struct file_operations proc_opalcore_operations = {
+ .read = read_opalcore,
+};
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ *
+ * Each register entry is of 16 bytes, A numerical identifier along with
+ * a GPR/SPR flag in the first 8 bytes and the register value in the next
+ * 8 bytes. For more details refer to F/W documentation.
+ */
+static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
+{
+ struct opal_fadump_thread_hdr *thdr;
+ unsigned long addr;
+ u32 thread_pir;
+ char *bufp;
+ Elf64_Word *first_cpu_note;
+ struct pt_regs regs;
+ struct elf_prstatus prstatus;
+ unsigned int size_of_each_thread;
+ unsigned int regs_offset, regs_cnt, reg_esize;
+ int i;
+
+ size_of_each_thread = oc_conf->cpu_state_entry_size;
+
+ addr = oc_conf->cpu_state_destination_addr;
+ bufp = __va(addr);
+
+ /*
+ * Offset for register entries, entry size and registers count is
+ * duplicated in every thread header in keeping with HDAT format.
+ * Use these values from the first thread header.
+ */
+ thdr = (struct opal_fadump_thread_hdr *)bufp;
+ regs_offset = (offsetof(struct opal_fadump_thread_hdr, offset) +
+ be32_to_cpu(thdr->offset));
+ reg_esize = be32_to_cpu(thdr->esize);
+ regs_cnt = be32_to_cpu(thdr->ecnt);
+
+ pr_debug("--------CPU State Data------------\n");
+ pr_debug("NumCpus : %u\n", oc_conf->num_cpus);
+ pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n",
+ regs_offset, reg_esize, regs_cnt);
+
+ /*
+ * Skip past the first CPU note. Fill this note with the
+ * crashing CPU's prstatus.
+ */
+ first_cpu_note = buf;
+ buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
+
+ for (i = 0; i < oc_conf->num_cpus; i++, bufp += size_of_each_thread) {
+ thdr = (struct opal_fadump_thread_hdr *)bufp;
+ thread_pir = be32_to_cpu(thdr->pir);
+
+ pr_debug("%04d) PIR: 0x%x, core state: 0x%02x\n",
+ (i + 1), thread_pir, thdr->core_state);
+
+ /*
+ * Register state data of MAX cores is provided by firmware,
+ * but some of this cores may not be active. So, while
+ * processing register state data, check core state and
+ * skip threads that belong to inactive cores.
+ */
+ if (is_thread_core_inactive(thdr->core_state))
+ continue;
+
+ fadump_read_registers((bufp + regs_offset), regs_cnt,
+ reg_esize, false, ®s);
+
+ pr_debug("PIR 0x%x - R1 : 0x%llx, NIP : 0x%llx\n", thread_pir,
+ be64_to_cpu(regs.gpr[1]), be64_to_cpu(regs.nip));
+ fill_prstatus(&prstatus, thread_pir, ®s);
+
+ if (thread_pir != oc_conf->crashing_cpu) {
+ buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME,
+ NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ } else {
+ /*
+ * Add crashing CPU as the first NT_PRSTATUS note for
+ * GDB to process the core file appropriately.
+ */
+ append_elf64_note(first_cpu_note, CRASH_CORE_NOTE_NAME,
+ NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ }
+ }
+
+ return buf;
+}
+
+static int __init create_opalcore(void)
+{
+ int hdr_size, cpu_notes_size, order, count;
+ int i, ret;
+ unsigned int numcpus;
+ unsigned long paddr;
+ Elf64_Ehdr *elf;
+ Elf64_Phdr *phdr;
+ loff_t opalcore_off;
+ struct opalcore *new;
+ struct page *page;
+ char *bufp;
+ struct device_node *dn;
+ uint64_t opal_base_addr;
+ uint64_t opal_boot_entry;
+
+
+ if ((oc_conf->ptload_cnt == 0) ||
+ (oc_conf->ptload_cnt > MAX_PT_LOAD_CNT))
+ return -EINVAL;
+
+ numcpus = oc_conf->num_cpus;
+ hdr_size = (sizeof(Elf64_Ehdr) +
+ ((oc_conf->ptload_cnt + 1) * sizeof(Elf64_Phdr)));
+ cpu_notes_size = ((numcpus * (CRASH_CORE_NOTE_HEAD_BYTES +
+ CRASH_CORE_NOTE_NAME_BYTES +
+ CRASH_CORE_NOTE_DESC_BYTES)) +
+ (CRASH_CORE_NOTE_HEAD_BYTES +
+ CRASH_CORE_NOTE_NAME_BYTES + AUXV_DESC_SZ));
+ oc_conf->opalcorebuf_sz = (hdr_size + cpu_notes_size);
+ order = get_order(oc_conf->opalcorebuf_sz);
+ oc_conf->opalcorebuf =
+ (char *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+ if (!oc_conf->opalcorebuf) {
+ pr_err("Not enough memory to setup opalcore (size: %lu)\n",
+ oc_conf->opalcorebuf_sz);
+ oc_conf->opalcorebuf_sz = 0;
+ return -ENOMEM;
+ }
+
+ pr_debug("opalcorebuf = 0x%lx\n", (unsigned long)oc_conf->opalcorebuf);
+
+ count = 1 << order;
+ page = virt_to_page(oc_conf->opalcorebuf);
+ for (i = 0; i < count; i++)
+ SetPageReserved(page + i);
+
+ /* Read OPAL related device-tree entries */
+ dn = of_find_node_by_name(NULL, "ibm,opal");
+ if (dn) {
+ ret = of_property_read_u64(dn, "opal-base-address",
+ &opal_base_addr);
+ ret |= of_property_read_u64(dn, "opal-boot-address",
+ &opal_boot_entry);
+ }
+ if (!dn || ret)
+ pr_warn("WARNING: Failed to read OPAL base & entry values\n");
+
+ /* Use count to keep track of the program headers */
+ count = 0;
+
+ bufp = oc_conf->opalcorebuf;
+ elf = (Elf64_Ehdr *)bufp;
+ bufp += sizeof(Elf64_Ehdr);
+ memcpy(elf->e_ident, ELFMAG, SELFMAG);
+ elf->e_ident[EI_CLASS] = ELF_CLASS;
+ elf->e_ident[EI_DATA] = ELFDATA2MSB;
+ elf->e_ident[EI_VERSION] = EV_CURRENT;
+ elf->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+ elf->e_type = cpu_to_be16(ET_CORE);
+ elf->e_machine = cpu_to_be16(ELF_ARCH);
+ elf->e_version = cpu_to_be32(EV_CURRENT);
+ elf->e_entry = 0;
+ elf->e_phoff = cpu_to_be64(sizeof(Elf64_Ehdr));
+ elf->e_shoff = 0;
+ elf->e_flags = 0;
+
+ elf->e_ehsize = cpu_to_be16(sizeof(Elf64_Ehdr));
+ elf->e_phentsize = cpu_to_be16(sizeof(Elf64_Phdr));
+ elf->e_phnum = 0;
+ elf->e_shentsize = 0;
+ elf->e_shnum = 0;
+ elf->e_shstrndx = 0;
+
+ phdr = (Elf64_Phdr *)bufp;
+ bufp += sizeof(Elf64_Phdr);
+ phdr->p_type = cpu_to_be32(PT_NOTE);
+ phdr->p_flags = 0;
+ phdr->p_align = 0;
+ phdr->p_paddr = phdr->p_vaddr = 0;
+ phdr->p_offset = cpu_to_be64(hdr_size);
+ phdr->p_filesz = phdr->p_memsz = cpu_to_be64(cpu_notes_size);
+ count++;
+
+ opalcore_off = oc_conf->opalcorebuf_sz;
+ oc_conf->ptload_phdr = (Elf64_Phdr *)bufp;
+ paddr = 0;
+ for (i = 0; i < oc_conf->ptload_cnt; i++) {
+ phdr = (Elf64_Phdr *)bufp;
+ bufp += sizeof(Elf64_Phdr);
+ phdr->p_type = cpu_to_be32(PT_LOAD);
+ phdr->p_flags = cpu_to_be32(PF_R|PF_W|PF_X);
+ phdr->p_align = 0;
+
+ new = get_new_element();
+ if (!new)
+ return -ENOMEM;
+ new->paddr = oc_conf->ptload_addr[i];
+ new->size = oc_conf->ptload_size[i];
+ new->offset = opalcore_off;
+ list_add_tail(&new->list, &opalcore_list);
+
+ phdr->p_paddr = cpu_to_be64(paddr);
+ phdr->p_vaddr = cpu_to_be64(opal_base_addr + paddr);
+ phdr->p_filesz = phdr->p_memsz =
+ cpu_to_be64(oc_conf->ptload_size[i]);
+ phdr->p_offset = cpu_to_be64(opalcore_off);
+
+ count++;
+ opalcore_off += oc_conf->ptload_size[i];
+ paddr += oc_conf->ptload_size[i];
+ }
+
+ elf->e_phnum = cpu_to_be16(count);
+
+ bufp = (char *)opalcore_append_cpu_notes((Elf64_Word *)bufp);
+ bufp = (char *)auxv_to_elf64_notes((Elf64_Word *)bufp, opal_boot_entry);
+
+ oc_conf->opalcore_size = opalcore_off;
+ return 0;
+}
+
+static void __init opalcore_config_init(void)
+{
+ struct device_node *np;
+ const __be32 *prop;
+ int i;
+
+ np = of_find_node_by_path("/ibm,opal/dump");
+ if (np == NULL)
+ return;
+
+ fdm_active = of_get_property(np, "result-table", NULL);
+ if (fdm_active == NULL)
+ goto out;
+
+ oc_conf = kzalloc(sizeof(struct opalcore_config), GFP_KERNEL);
+ if (oc_conf == NULL)
+ goto out;
+
+ prop = of_get_property(np, "cpu-data-size", NULL);
+ if (prop == NULL) {
+ pr_err("Failed to get CPU state entry size!");
+ kfree(oc_conf);
+ oc_conf = NULL;
+ goto out;
+ }
+ oc_conf->cpu_state_entry_size = of_read_number(prop, 1);
+
+ oc_conf->ptload_cnt = 0;
+ for (i = 0; i < be16_to_cpu(fdm_active->section_count); i++) {
+ u8 src_type = fdm_active->section[i].src_type;
+
+ if (src_type == OPAL_FADUMP_CPU_STATE_DATA) {
+ oc_conf->cpu_state_destination_addr =
+ be64_to_cpu(fdm_active->section[i].dest_addr);
+ oc_conf->cpu_state_data_size =
+ be64_to_cpu(fdm_active->section[i].dest_size);
+ continue;
+ }
+
+ if ((src_type < OPAL_FADUMP_OPAL_REGION) ||
+ (src_type >= OPAL_FADUMP_FW_REGION))
+ continue;
+
+ if (oc_conf->ptload_cnt >= MAX_PT_LOAD_CNT)
+ break;
+
+ oc_conf->ptload_addr[oc_conf->ptload_cnt] =
+ be64_to_cpu(fdm_active->section[i].dest_addr);
+ oc_conf->ptload_size[oc_conf->ptload_cnt++] =
+ be64_to_cpu(fdm_active->section[i].dest_size);
+ }
+
+ oc_conf->num_cpus = (oc_conf->cpu_state_data_size /
+ oc_conf->cpu_state_entry_size);
+ oc_conf->crashing_cpu = be32_to_cpu(fdm_active->crashing_cpu);
+
+out:
+ of_node_put(np);
+}
+
+/* Cleanup function for opalcore module. */
+static void opalcore_cleanup(void)
+{
+ unsigned long order, count, i;
+ struct page *page;
+
+ if (oc_conf == NULL)
+ return;
+
+ if (oc_conf->proc_opalcore) {
+ proc_remove(oc_conf->proc_opalcore);
+ oc_conf->proc_opalcore = NULL;
+ }
+
+ oc_conf->ptload_phdr = NULL;
+ oc_conf->ptload_cnt = 0;
+
+ /* free core buffer */
+ if ((oc_conf->opalcorebuf != NULL) && (oc_conf->opalcorebuf_sz != 0)) {
+ order = get_order(oc_conf->opalcorebuf_sz);
+ count = 1 << order;
+ page = virt_to_page(oc_conf->opalcorebuf);
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+
+ oc_conf->opalcorebuf = NULL;
+ oc_conf->opalcorebuf_sz = 0;
+ }
+
+ kfree(oc_conf);
+ oc_conf = NULL;
+}
+__exitcall(opalcore_cleanup);
+
+/* Init function for opalcore module. */
+static int __init opalcore_init(void)
+{
+ int rc = -1;
+
+ opalcore_config_init();
+
+ if (oc_conf == NULL)
+ return rc;
+
+ create_opalcore();
+
+ /*
+ * If oc_conf->opalcorebuf= is set in the 2nd kernel,
+ * then capture the dump.
+ */
+ if (!(is_opalcore_usable())) {
+ pr_err("Failed to export /proc/opalcore\n");
+ opalcore_cleanup();
+ return rc;
+ }
+
+ oc_conf->proc_opalcore = proc_create("opalcore", 0400, NULL,
+ &proc_opalcore_operations);
+ if (oc_conf->proc_opalcore)
+ proc_set_size(oc_conf->proc_opalcore, oc_conf->opalcore_size);
+ return 0;
+}
+fs_initcall(opalcore_init);
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index f16f1aa..2b36b5f 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -33,6 +33,10 @@ static const struct opal_fadump_mem_struct *fdm_active;
#ifndef CONFIG_PRESERVE_FA_DUMP
static struct opal_fadump_mem_struct fdm;
+#ifdef CONFIG_OPAL_CORE
+extern bool kernel_initiated;
+#endif
+
static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
{
fadump_conf->preserv_area_start = fadump_conf->rmr_destination_addr;
@@ -237,75 +241,6 @@ static int opal_invalidate_fadump(struct fw_dump *fadump_conf)
return 0;
}
-static inline void fadump_set_regval_regnum(struct pt_regs *regs, u32 reg_type,
- u32 reg_num, u64 reg_val)
-{
- if (reg_type == OPAL_REG_TYPE_GPR) {
- if (reg_num < 32)
- regs->gpr[reg_num] = reg_val;
- return;
- }
-
- switch (reg_num) {
- case 2000:
- regs->nip = reg_val;
- break;
- case 2001:
- regs->msr = reg_val;
- break;
- case 9:
- regs->ctr = reg_val;
- break;
- case 8:
- regs->link = reg_val;
- break;
- case 1:
- regs->xer = reg_val;
- break;
- case 2002:
- regs->ccr = reg_val;
- break;
- case 19:
- regs->dar = reg_val;
- break;
- case 18:
- regs->dsisr = reg_val;
- break;
- }
-}
-
-static inline void fadump_read_registers(char *bufp, unsigned int regs_cnt,
- unsigned int reg_entry_size,
- struct pt_regs *regs)
-{
- int i;
- struct opal_fadump_reg_entry *reg_entry;
-
- memset(regs, 0, sizeof(struct pt_regs));
-
- for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) {
- reg_entry = (struct opal_fadump_reg_entry *)bufp;
- fadump_set_regval_regnum(regs,
- be32_to_cpu(reg_entry->reg_type),
- be32_to_cpu(reg_entry->reg_num),
- be64_to_cpu(reg_entry->reg_val));
- }
-}
-
-static inline bool __init is_thread_core_inactive(u8 core_state)
-{
- bool is_inactive = false;
-
- /*
- * TODO: Check what each state value means and implement accordingly.
- * Also, make sure F/W is updating this field appropriately.
- */
- if (core_state == CORE_STATE_INACTIVE)
- is_inactive = true;
-
- return is_inactive;
-}
-
/*
* Read CPU state dump data and convert it into ELF notes.
*
@@ -399,7 +334,7 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
}
fadump_read_registers((bufp + regs_offset), regs_cnt,
- reg_esize, ®s);
+ reg_esize, true, ®s);
note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
pr_debug("CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n",
@@ -432,6 +367,25 @@ static int __init opal_process_fadump(struct fw_dump *fadump_conf)
return -EINVAL;
}
+#ifdef CONFIG_OPAL_CORE
+ /*
+ * If this is a kernel initiated crash, crashing_cpu would be set
+ * appropriately and register data of the crashing CPU saved by
+ * crashing kernel. Add this saved register data of crashing CPU
+ * to elf notes and populate the pt_regs for the remaining CPUs
+ * from register state data provided by firmware.
+ */
+ if (fdh->crashing_cpu != CPU_UNKNOWN) {
+ kernel_initiated = true;
+ if (fdh->crashing_cpu !=
+ be32_to_cpu(fdm_active->crashing_cpu)) {
+ pr_warn("Crashing CPU PIR logged by kernel (%u) and firmware (%u) don't match!\n",
+ fdh->crashing_cpu,
+ be32_to_cpu(fdm_active->crashing_cpu));
+ }
+ }
+#endif
+
rc = fadump_build_cpu_notes(fadump_conf);
if (rc)
return rc;
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index 80aee2d..ccddfec 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -41,4 +41,76 @@ enum opal_fadump_section_types {
#define CORE_STATE_INACTIVE (0x0F)
+static inline bool __init is_thread_core_inactive(u8 core_state)
+{
+ bool is_inactive = false;
+
+ /*
+ * TODO: Check what each state value means and implement accordingly.
+ * Also, make sure F/W is updating this field appropriately.
+ */
+ if (core_state == CORE_STATE_INACTIVE)
+ is_inactive = true;
+
+ return is_inactive;
+}
+
+static inline void fadump_set_regval_regnum(struct pt_regs *regs, u32 reg_type,
+ u32 reg_num, u64 reg_val)
+{
+ if (reg_type == OPAL_REG_TYPE_GPR) {
+ if (reg_num < 32)
+ regs->gpr[reg_num] = reg_val;
+ return;
+ }
+
+ switch (reg_num) {
+ case 2000:
+ regs->nip = reg_val;
+ break;
+ case 2001:
+ regs->msr = reg_val;
+ break;
+ case 9:
+ regs->ctr = reg_val;
+ break;
+ case 8:
+ regs->link = reg_val;
+ break;
+ case 1:
+ regs->xer = reg_val;
+ break;
+ case 2002:
+ regs->ccr = reg_val;
+ break;
+ case 19:
+ regs->dar = reg_val;
+ break;
+ case 18:
+ regs->dsisr = reg_val;
+ break;
+ }
+}
+
+static inline void fadump_read_registers(char *bufp, unsigned int regs_cnt,
+ unsigned int reg_entry_size,
+ bool cpu_endian,
+ struct pt_regs *regs)
+{
+ int i;
+ u64 val;
+ struct opal_fadump_reg_entry *reg_entry;
+
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) {
+ reg_entry = (struct opal_fadump_reg_entry *)bufp;
+ val = (cpu_endian ? be64_to_cpu(reg_entry->reg_val) :
+ reg_entry->reg_val);
+ fadump_set_regval_regnum(regs,
+ be32_to_cpu(reg_entry->reg_type),
+ be32_to_cpu(reg_entry->reg_num), val);
+ }
+}
+
#endif /* __PPC64_OPAL_FA_DUMP_H__ */
^ permalink raw reply related
* [PATCH 13/18] powernv/fadump: Skip processing /proc/vmcore when only OPAL core exists
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
If OPAL crashes when the kernel is not registered for FADump, F/W still
exports OPAL core through result-table DT node. Make sure '/proc/vmcore'
processing is skipped as only data relevant to OPAL core is exported in
such scenario.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/platforms/powernv/opal-fadump.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 2b36b5f..36077bd 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -108,6 +108,18 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
be64_to_cpu(fdm->section[i].dest_size);
}
}
+
+ /*
+ * If dump is active and no kernel memory region is found in
+ * result-table, it means OPAL crashed on system with MPIPL
+ * support and the kernel was not registered for FADump at the
+ * time of crash. Skip processing /proc/vmcore in that case.
+ */
+ if (j == 0) {
+ fadump_conf->dump_active = 0;
+ return;
+ }
+
fadump_conf->rmr_regions_cnt = j;
pr_debug("Real memory regions count: %lu\n",
fadump_conf->rmr_regions_cnt);
^ permalink raw reply related
* [PATCH 08/18] powerpc/fadump: consider reserved ranges while releasing memory
From: Hari Bathini @ 2019-02-21 17:36 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Commit 0962e8004e97 ("powerpc/prom: Scan reserved-ranges node for
memory reservations") enabled support to parse 'reserved-ranges' DT
node to reserve kernel memory falling in these ranges for firmware
purposes. Along with the preserved area memory, also ensure memory
in reserved ranges is not overlapped with memory released by capture
kernel aftering saving vmcore. Also, fix the off-by-one error in
fadump_release_reserved_area function while releasing memory.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump.c | 59 +++++++++++++++++++++++++++++-------------
1 file changed, 41 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index a4510c91..0332d7f 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -123,7 +123,7 @@ static int __init fadump_cma_init(void) { return 1; }
* Sort the reserved ranges in-place and merge adjacent ranges
* to minimize the reserved ranges count.
*/
-static void __init sort_and_merge_reserved_ranges(void)
+static void sort_and_merge_reserved_ranges(void)
{
unsigned long long base, size;
struct fadump_memory_range tmp_range;
@@ -164,8 +164,7 @@ static void __init sort_and_merge_reserved_ranges(void)
reserved_ranges_cnt = idx + 1;
}
-static int __init add_reserved_range(unsigned long base,
- unsigned long size)
+static int add_reserved_range(unsigned long base, unsigned long size)
{
int i;
@@ -1126,33 +1125,57 @@ static void fadump_release_reserved_area(unsigned long start, unsigned long end)
if (tend == end_pfn)
break;
- start_pfn = tend + 1;
+ start_pfn = tend;
}
}
}
/*
- * Release the memory that was reserved in early boot to preserve the memory
- * contents. The released memory will be available for general use.
+ * Release the memory that was reserved during early boot to preserve the
+ * crash'ed kernel's memory contents except reserved dump area (permanent
+ * reservation) and reserved ranges used by F/W. The released memory will
+ * be available for general use.
*/
static void fadump_release_memory(unsigned long begin, unsigned long end)
{
+ int i;
unsigned long ra_start, ra_end;
-
- ra_start = fw_dump.reserve_dump_area_start;
- ra_end = ra_start + fw_dump.reserve_dump_area_size;
+ unsigned long tstart;
/*
- * exclude the dump reserve area. Will reuse it for next
- * fadump registration.
+ * Add memory to permanently preserve to reserved ranges list
+ * and exclude all these ranges while releasing memory.
*/
- if (begin < ra_end && end > ra_start) {
- if (begin < ra_start)
- fadump_release_reserved_area(begin, ra_start);
- if (end > ra_end)
- fadump_release_reserved_area(ra_end, end);
- } else
- fadump_release_reserved_area(begin, end);
+ i = add_reserved_range(fw_dump.reserve_dump_area_start,
+ fw_dump.reserve_dump_area_size);
+ if (i == 0) {
+ /*
+ * Reached the MAX reserved ranges count. To ensure reserved
+ * dump area is excluded (as it will be reused for next
+ * FADump registration), ignore the last reserved range and
+ * add reserved dump area instead.
+ */
+ reserved_ranges_cnt--;
+ add_reserved_range(fw_dump.reserve_dump_area_start,
+ fw_dump.reserve_dump_area_size);
+ }
+ sort_and_merge_reserved_ranges();
+
+ tstart = begin;
+ for (i = 0; i < reserved_ranges_cnt; i++) {
+ ra_start = reserved_ranges[i].base;
+ ra_end = ra_start + reserved_ranges[i].size;
+
+ if (tstart >= ra_end)
+ continue;
+
+ if (tstart < ra_start)
+ fadump_release_reserved_area(tstart, ra_start);
+ tstart = ra_end;
+ }
+
+ if (tstart < end)
+ fadump_release_reserved_area(tstart, end);
}
static void fadump_invalidate_release_mem(void)
^ permalink raw reply related
* [PATCH 14/18] powernv/opalcore: provide an option to invalidate /proc/opalcore file
From: Hari Bathini @ 2019-02-21 17:37 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Writing '1' to /sys/kernel/fadump_release_opalcore would release the
memory held by kernel in exporting /proc/opalcore file.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/platforms/powernv/opal-core.c | 39 ++++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
index 5355d95..f9473b7 100644
--- a/arch/powerpc/platforms/powernv/opal-core.c
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -19,6 +19,8 @@
#include <linux/proc_fs.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/crash_core.h>
#include <linux/of.h>
@@ -532,6 +534,36 @@ static void opalcore_cleanup(void)
}
__exitcall(opalcore_cleanup);
+static ssize_t fadump_release_opalcore_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int input = -1;
+
+ if (kstrtoint(buf, 0, &input))
+ return -EINVAL;
+
+ if (input == 1) {
+ if (oc_conf == NULL) {
+ pr_err("'/proc/opalcore' file does not exist!\n");
+ return -EPERM;
+ }
+
+ /*
+ * Take away '/proc/opalcore' and release all memory
+ * used for exporting this file.
+ */
+ opalcore_cleanup();
+ } else
+ return -EINVAL;
+
+ return count;
+}
+
+static struct kobj_attribute opalcore_rel_attr = __ATTR(fadump_release_opalcore,
+ 0200, NULL,
+ fadump_release_opalcore_store);
+
/* Init function for opalcore module. */
static int __init opalcore_init(void)
{
@@ -558,6 +590,13 @@ static int __init opalcore_init(void)
&proc_opalcore_operations);
if (oc_conf->proc_opalcore)
proc_set_size(oc_conf->proc_opalcore, oc_conf->opalcore_size);
+
+ rc = sysfs_create_file(kernel_kobj, &opalcore_rel_attr.attr);
+ if (rc) {
+ pr_warn("unable to create sysfs file fadump_release_opalcore (%d)\n",
+ rc);
+ }
+
return 0;
}
fs_initcall(opalcore_init);
^ permalink raw reply related
* [PATCH 16/18] powernv/fadump: update documentation about option to release opalcore
From: Hari Bathini @ 2019-02-21 17:37 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
With /proc/opalcore support available on OPAL based machines and an
option to release memory used by kernel in exporting /proc/opalcore,
update FADump documentation with these details.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index fa35593..6411449 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -107,6 +107,16 @@ capture kernel boot to process this crash data. Kernel config
option CONFIG_PRESERVE_FA_DUMP has to be enabled on such kernel
to ensure that crash data is preserved to process later.
+-- On OPAL based machines (PowerNV), if the kernel is build with
+ CONFIG_OPAL_CORE=y, OPAL memory at the time of crash is also
+ exported as /proc/opalcore file. This procfs file is helpful
+ in debugging OPAL crashes with GDB. The kernel memory used
+ for exporting this procfs file can be released by echo'ing
+ '1' to /sys/kernel/fadump_release_opalcore node.
+
+ e.g.
+ # echo 1 > /sys/kernel/fadump_release_opalcore
+
Implementation details:
----------------------
@@ -260,6 +270,15 @@ Here is the list of files under kernel sysfs:
enhanced to use this interface to release the memory reserved for
dump and continue without 2nd reboot.
+ /sys/kernel/fadump_release_opalcore
+
+ This file is available only on OPAL based machines when FADump is
+ active during capture kernel. This is used to release the memory
+ used by the kernel to export /proc/opalcore file. To release this
+ memory, echo '1' to it:
+
+ echo 1 > /sys/kernel/fadump_release_opalcore
+
Here is the list of files under powerpc debugfs:
(Assuming debugfs is mounted on /sys/kernel/debug directory.)
^ permalink raw reply related
* [PATCH 17/18] powernv/fadump: use backup area to map PIR to logical CPUs
From: Hari Bathini @ 2019-02-21 17:37 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
Firmware provides architected register state data but it doesn't have
corresponding logical CPU number used in the kernel. So, populate a
backup area storing logical CPU number and PIR values while registering
FADump and use it to correlate the register state data to corresponding
logical CPU while processing this crash data.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump.c | 40 ++------
arch/powerpc/kernel/fadump_internal.c | 92 ++++++++++++++++++
arch/powerpc/kernel/fadump_internal.h | 28 ++++++
arch/powerpc/platforms/powernv/opal-fadump.c | 116 ++++++++++++++++++++++-
arch/powerpc/platforms/pseries/pseries_fadump.c | 1
5 files changed, 245 insertions(+), 32 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index c8eb166..30c555d 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -385,10 +385,10 @@ static unsigned long get_fadump_area_size(void)
size += fw_dump.hpte_region_size;
size += fw_dump.boot_memory_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 */
- /* Program headers for crash memory regions. */
- size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
+ /* To store the start address of backup area */
+ size += sizeof(unsigned long *);
+ size += get_fadump_elfcore_hdr_size();
+ size += fw_dump.backup_area_size;
size = PAGE_ALIGN(size);
return size;
@@ -1065,26 +1065,6 @@ static int fadump_create_elfcore_headers(char *bufp)
return 0;
}
-static unsigned long init_fadump_header(unsigned long addr)
-{
- struct fadump_crash_info_header *fdh;
-
- if (!addr)
- return 0;
-
- fw_dump.fadumphdr_addr = addr;
- fdh = __va(addr);
- addr += sizeof(struct fadump_crash_info_header);
-
- memset(fdh, 0, sizeof(struct fadump_crash_info_header));
- fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
- fdh->elfcorehdr_addr = addr;
- /* We will set the crashing cpu id in crash_fadump() during crash. */
- fdh->crashing_cpu = CPU_UNKNOWN;
-
- return addr;
-}
-
static int register_fadump(void)
{
unsigned long addr;
@@ -1102,15 +1082,15 @@ static int register_fadump(void)
if (ret)
return ret;
- addr = fw_dump.meta_area_start;
-
/* Initialize fadump crash info header. */
- addr = init_fadump_header(addr);
+ addr = fw_dump.ops->init_fadump_header(&fw_dump);
vaddr = __va(addr);
pr_debug("Creating ELF core headers at %#016lx\n", addr);
fadump_create_elfcore_headers(vaddr);
+ fadump_populate_backup_area(&fw_dump);
+
/* register the future kernel dump with firmware. */
pr_debug("Registering for firmware-assisted kernel dump...\n");
return fw_dump.ops->register_fadump(&fw_dump);
@@ -1429,8 +1409,12 @@ 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) {
fw_dump.ops->init_fadump_mem_struct(&fw_dump);
+ fw_dump.ops->init_fadump_header(&fw_dump);
+ init_fadump_backup_area(&fw_dump);
+ fadump_populate_backup_area(&fw_dump);
+ }
fadump_init_files();
diff --git a/arch/powerpc/kernel/fadump_internal.c b/arch/powerpc/kernel/fadump_internal.c
index b46c7da..8dac166 100644
--- a/arch/powerpc/kernel/fadump_internal.c
+++ b/arch/powerpc/kernel/fadump_internal.c
@@ -20,6 +20,34 @@
#include "fadump_internal.h"
+/*
+ * Initializes the legacy fadump header format.
+ * Platform specific code can reuse/overwrite this format.
+ * OPAL platform overrides this data to add backup area support.
+ *
+ * TODO: Extend backup area support to pseries to make it robust?
+ */
+unsigned long generic_init_fadump_header(struct fw_dump *fadump_conf)
+{
+ unsigned long addr = fadump_conf->meta_area_start;
+ struct fadump_crash_info_header *fdh;
+
+ if (!addr)
+ return 0;
+
+ fadump_conf->fadumphdr_addr = addr;
+ fdh = __va(addr);
+ addr += sizeof(struct fadump_crash_info_header);
+
+ memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+ fdh->elfcorehdr_addr = addr;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = CPU_UNKNOWN;
+
+ return addr;
+}
+
void *fadump_cpu_notes_buf_alloc(unsigned long size)
{
void *vaddr;
@@ -121,6 +149,19 @@ u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
return buf;
}
+unsigned long get_fadump_elfcore_hdr_size(void)
+{
+ unsigned long size = 0;
+
+ size = sizeof(struct elfhdr); /* ELF core header.*/
+ size += sizeof(struct elf_phdr); /* place holder for cpu notes */
+ size += sizeof(struct elf_phdr); /* vmcoreinfo notes program header */
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 1);
+
+ return size;
+}
+
void fadump_update_elfcore_header(struct fw_dump *fadump_conf, char *bufp)
{
struct elfhdr *elf;
@@ -203,3 +244,54 @@ int is_reserved_memory_area_contiguous(struct fw_dump *fadump_conf)
return is_memory_area_contiguous(d_start, d_end);
}
+
+void init_fadump_backup_area(struct fw_dump *fadump_conf)
+{
+ unsigned long addr = fadump_conf->backup_area_start;
+ struct fadump_backup_area *backup_info;
+
+ if (!addr)
+ return;
+
+ backup_info = __va(addr);
+ memset(backup_info, 0xFF, fadump_conf->backup_area_size);
+ backup_info->version = BACKUP_AREA_VERSION_V1;
+ backup_info->size = fadump_conf->backup_area_size;
+ backup_info->nr_threads = 0;
+}
+
+static inline void read_pir(void *val)
+{
+ *(unsigned long *)val = mfspr(SPRN_PIR);
+}
+
+unsigned long fadump_populate_backup_area(struct fw_dump *fadump_conf)
+{
+ unsigned long pir, addr;
+ struct fadump_backup_area *backup_info;
+ unsigned int i;
+
+ if (!fadump_conf->backup_area_start)
+ return 0;
+
+ addr = fadump_conf->backup_area_start;
+ backup_info = __va(addr);
+ addr += fadump_conf->backup_area_size;
+
+ backup_info->present_mask = *cpu_present_mask;
+ for_each_present_cpu(i) {
+ /*
+ * Skip if PIR is already read to avoid complex scenarios
+ * where the CPUs are offline'd after initial read.
+ */
+ if (backup_info->thread_pir[i] != 0xFFFFFFFFU)
+ continue;
+
+ smp_call_function_single(i, read_pir, &pir, 1);
+ pr_debug("Logical CPU: %d, PIR: 0x%lx\n", i, pir);
+ backup_info->thread_pir[i] = pir;
+ backup_info->nr_threads++;
+ }
+
+ return addr;
+}
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index f59fdc7..5f2b3f2 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -89,6 +89,9 @@ struct fadump_reg_entry {
#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF")
+/* Backup area support in this version */
+#define FADUMP_CRASH_INFO_MAGIC_V2 STR_TO_HEX("FADINFV2")
+
/* fadump crash info structure */
struct fadump_crash_info_header {
u64 magic_number;
@@ -100,6 +103,22 @@ struct fadump_crash_info_header {
/* Platform specific callback functions */
struct fadump_ops;
+
+#define BACKUP_AREA_VERSION_V1 1
+
+/* Backup area populated with data for processing in capture kernel */
+struct fadump_backup_area {
+ u32 size;
+ u32 version:4;
+ u32 nr_threads:28;
+ u32 thread_pir[NR_CPUS];
+ struct cpumask present_mask;
+ /*
+ * New backup data entries can be added here by bumping up
+ * the version field.
+ */
+};
+
#endif /* !CONFIG_PRESERVE_FA_DUMP */
/* Firmware-Assited Dump platforms */
@@ -140,6 +159,8 @@ struct fw_dump {
unsigned long reserve_dump_area_size;
unsigned long meta_area_start;
unsigned long preserv_area_start;
+ unsigned long backup_area_start;
+ unsigned long backup_area_size;
/* cmd line option during boot */
unsigned long reserve_bootvar;
@@ -178,6 +199,7 @@ struct fw_dump {
#ifndef CONFIG_PRESERVE_FA_DUMP
struct fadump_ops {
ulong (*init_fadump_mem_struct)(struct fw_dump *fadump_config);
+ ulong (*init_fadump_header)(struct fw_dump *fadump_config);
int (*register_fadump)(struct fw_dump *fadump_config);
int (*unregister_fadump)(struct fw_dump *fadump_config);
int (*invalidate_fadump)(struct fw_dump *fadump_config);
@@ -188,15 +210,21 @@ struct fadump_ops {
const char *msg);
};
+/* Generic version of fadump operations */
+unsigned long generic_init_fadump_header(struct fw_dump *fadump_conf);
+
/* Helper functions */
void *fadump_cpu_notes_buf_alloc(unsigned long size);
void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size);
void fadump_set_meta_area_start(struct fw_dump *fadump_conf);
void fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val);
u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
+unsigned long get_fadump_elfcore_hdr_size(void);
void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
int is_boot_memory_area_contiguous(struct fw_dump *fadump_conf);
int is_reserved_memory_area_contiguous(struct fw_dump *fadump_conf);
+void init_fadump_backup_area(struct fw_dump *fadump_conf);
+unsigned long fadump_populate_backup_area(struct fw_dump *fadump_conf);
#endif /* !CONFIG_PRESERVE_FA_DUMP */
#if !defined(CONFIG_PRESERVE_FA_DUMP) && defined(CONFIG_PPC_PSERIES)
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 06053fd..9ae1835 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -37,6 +37,39 @@ static struct opal_fadump_mem_struct fdm;
extern bool kernel_initiated;
#endif
+/*
+ * Backup area is not available in older format. In the newer fadump
+ * header format (v2), backup info is stored at the end of elfcorehdrs
+ * and pointer to this address is stored at the tail end of FADump
+ * crash info header.
+ */
+static void opal_set_backup_area_start(struct fw_dump *fadump_conf)
+{
+ unsigned long addr = fadump_conf->meta_area_start;
+
+ /*
+ * The start of meta area holds fadump_crash_info_header followed
+ * by a pointer to backup area start address, elfcore headers &
+ * backup info.
+ */
+ addr += sizeof(struct fadump_crash_info_header);
+
+ if (fadump_conf->dump_active) {
+ /* Pointer to backup area start address */
+ unsigned long *ptr = __va(addr);
+
+ addr = *ptr;
+ } else {
+ addr += sizeof(unsigned long *);
+ addr += get_fadump_elfcore_hdr_size();
+ }
+
+ fadump_conf->backup_area_start = addr;
+
+ pr_debug("Backup area start address: 0x%lx\n",
+ fadump_conf->backup_area_start);
+}
+
static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
{
fadump_conf->preserv_area_start = fadump_conf->rmr_destination_addr;
@@ -128,6 +161,7 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
#ifndef CONFIG_PRESERVE_FA_DUMP
fadump_set_meta_area_start(fadump_conf);
opal_set_preserv_area_start(fadump_conf);
+ opal_set_backup_area_start(fadump_conf);
#endif
}
@@ -188,6 +222,41 @@ static ulong opal_init_fadump_mem_struct(struct fw_dump *fadump_conf)
return addr;
}
+/*
+ * Newer fadump header version (v2) is used for process'ing OPAL FADump.
+ * In this version, PIR to Logical CPU map is backed up by crashing kernel
+ * for the capture kernel to make sense of the register state data provided
+ * by F/W. The start address of the area where this info is backed up is
+ * stored at the tail end of fadump crash info header.
+ */
+static ulong opal_init_fadump_header(struct fw_dump *fadump_conf)
+{
+ unsigned long addr = fadump_conf->meta_area_start;
+ struct fadump_crash_info_header *fdh;
+ unsigned long *backup_area_ptr;
+
+ if (!addr)
+ return 0;
+
+ fdh = __va(addr);
+ addr = generic_init_fadump_header(fadump_conf);
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC_V2;
+
+ /*
+ * This function returns the start address of elfcore headers.
+ * Earlier, elfcore headers sit right below crash info header but
+ * with V2, pointer to backup area start address (8 bytes) sits
+ * in-between. So, update the return value and elfcorehdr_addr
+ * in fadump crash info structure accordingly.
+ */
+ backup_area_ptr = __va(addr);
+ addr += sizeof(unsigned long *);
+ fdh->elfcorehdr_addr = addr;
+ *backup_area_ptr = fadump_conf->backup_area_start;
+
+ return addr;
+}
+
static int opal_register_fadump(struct fw_dump *fadump_conf)
{
int rc, err = -EIO;
@@ -253,6 +322,20 @@ static int opal_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;
+
+ for_each_cpu(i, &(ba->present_mask)) {
+ if (ba->thread_pir[i] == pir) {
+ cpu = i;
+ break;
+ }
+ }
+
+ return cpu;
+}
+
/*
* Read CPU state dump data and convert it into ELF notes.
*
@@ -260,7 +343,8 @@ static int opal_invalidate_fadump(struct fw_dump *fadump_conf)
* a GPR/SPR flag in the first 8 bytes and the register value in the next
* 8 bytes. For more details refer to F/W documentation.
*/
-static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
+static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf,
+ struct fadump_backup_area *backup_info)
{
u32 num_cpus, *note_buf;
struct fadump_crash_info_header *fdh = NULL;
@@ -271,7 +355,7 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
struct pt_regs regs;
unsigned int size_of_each_thread;
unsigned int regs_offset, regs_cnt, reg_esize;
- int i;
+ int i, cpu;
size_of_each_thread = fadump_conf->cpu_state_entry_size;
num_cpus = (fadump_conf->cpu_state_data_size / size_of_each_thread);
@@ -308,6 +392,11 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
if (fadump_conf->fadumphdr_addr)
fdh = __va(fadump_conf->fadumphdr_addr);
+ if (backup_info->nr_threads != num_cpus) {
+ pr_warn("Calculated numcpus (%d) not same as populated value (%d)!\n",
+ num_cpus, backup_info->nr_threads);
+ }
+
pr_debug("--------CPU State Data------------\n");
pr_debug("NumCpus : %u\n", num_cpus);
pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n",
@@ -345,6 +434,13 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
continue;
}
+ cpu = fadump_get_logical_cpu(backup_info, thread_pir);
+ if (cpu == CPU_UNKNOWN) {
+ pr_warn("Unable to get the logical CPU of PIR %d\n",
+ thread_pir);
+ continue;
+ }
+
fadump_read_registers((bufp + regs_offset), regs_cnt,
reg_esize, true, ®s);
@@ -367,6 +463,8 @@ static int __init fadump_build_cpu_notes(struct fw_dump *fadump_conf)
static int __init opal_process_fadump(struct fw_dump *fadump_conf)
{
struct fadump_crash_info_header *fdh;
+ struct fadump_backup_area *backup_info = NULL;
+ unsigned long addr;
int rc = 0;
if (!fdm_active || !fadump_conf->fadumphdr_addr)
@@ -374,7 +472,7 @@ static int __init opal_process_fadump(struct fw_dump *fadump_conf)
/* Validate the fadump crash info header */
fdh = __va(fadump_conf->fadumphdr_addr);
- if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+ if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC_V2) {
pr_err("Crash info header is not valid.\n");
return -EINVAL;
}
@@ -398,7 +496,14 @@ static int __init opal_process_fadump(struct fw_dump *fadump_conf)
}
#endif
- rc = fadump_build_cpu_notes(fadump_conf);
+ addr = fadump_conf->backup_area_start;
+ backup_info = __va(addr);
+ if (!addr || (backup_info->version != BACKUP_AREA_VERSION_V1)) {
+ pr_err("Backup data missing or unsupported!\n");
+ return -EINVAL;
+ }
+
+ rc = fadump_build_cpu_notes(fadump_conf, backup_info);
if (rc)
return rc;
@@ -470,6 +575,7 @@ static void opal_crash_fadump(struct fadump_crash_info_header *fdh,
static struct fadump_ops opal_fadump_ops = {
.init_fadump_mem_struct = opal_init_fadump_mem_struct,
+ .init_fadump_header = opal_init_fadump_header,
.register_fadump = opal_register_fadump,
.unregister_fadump = opal_unregister_fadump,
.invalidate_fadump = opal_invalidate_fadump,
@@ -553,6 +659,8 @@ int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
}
}
+ fadump_conf->backup_area_size = sizeof(struct fadump_backup_area);
+
fadump_conf->ops = &opal_fadump_ops;
fadump_conf->fadump_platform = FADUMP_PLATFORM_POWERNV;
fadump_conf->fadump_supported = 1;
diff --git a/arch/powerpc/platforms/pseries/pseries_fadump.c b/arch/powerpc/platforms/pseries/pseries_fadump.c
index 2e2bd1e..b52bd20 100644
--- a/arch/powerpc/platforms/pseries/pseries_fadump.c
+++ b/arch/powerpc/platforms/pseries/pseries_fadump.c
@@ -461,6 +461,7 @@ static void pseries_crash_fadump(struct fadump_crash_info_header *fdh,
static struct fadump_ops pseries_fadump_ops = {
.init_fadump_mem_struct = pseries_init_fadump_mem_struct,
+ .init_fadump_header = generic_init_fadump_header,
.register_fadump = pseries_register_fadump,
.unregister_fadump = pseries_unregister_fadump,
.invalidate_fadump = pseries_invalidate_fadump,
^ permalink raw reply related
* [PATCH 15/18] powernv/fadump: consider f/w load area
From: Hari Bathini @ 2019-02-21 17:37 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
OPAL loads kernel & initrd at 512MB offset (256MB size), also exported
as ibm,opal/dump/fw-load-area. So, if boot memory size of FADump is
less than 768MB, kernel memory to be exported as '/proc/vmcore' would
be overwritten by f/w while loading kernel & initrd. To avoid such a
scenario, enforce a minimum boot memory size of 768MB on OPAL platform.
Also, skip using FADump if a newer F/W version loads kernel & initrd
above 768MB.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump.c | 8 ++++++++
arch/powerpc/kernel/fadump_internal.h | 15 +++++++++++++--
arch/powerpc/platforms/powernv/opal-fadump.c | 23 +++++++++++++++++++++++
3 files changed, 44 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index d343c4b..c8eb166 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -582,6 +582,14 @@ int __init fadump_reserve_mem(void)
ALIGN(fw_dump.boot_memory_size,
FADUMP_CMA_ALIGNMENT);
#endif
+
+ if ((fw_dump.fadump_platform == FADUMP_PLATFORM_POWERNV) &&
+ (fw_dump.boot_memory_size < OPAL_MIN_BOOT_MEM)) {
+ pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%lx\n",
+ fw_dump.boot_memory_size, OPAL_MIN_BOOT_MEM);
+ goto error_out;
+ }
+
fw_dump.rmr_source_len = fw_dump.boot_memory_size;
if (!fadump_get_rmr_regions()) {
pr_err("Too many holes in boot memory area to enable fadump\n");
diff --git a/arch/powerpc/kernel/fadump_internal.h b/arch/powerpc/kernel/fadump_internal.h
index 1bd3aeb..f59fdc7 100644
--- a/arch/powerpc/kernel/fadump_internal.h
+++ b/arch/powerpc/kernel/fadump_internal.h
@@ -24,14 +24,25 @@
#define RMA_END (ppc64_rma_size)
/*
+ * With kernel & initrd loaded at 512MB (with 256MB size), enforce a minimum
+ * boot memory size of 768MB to ensure f/w loading kernel and initrd doesn't
+ * mess with crash'ed kernel's memory during MPIPL.
+ */
+#define OPAL_MIN_BOOT_MEM (0x30000000UL)
+
+/*
* On some Power systems where RMO is 128MB, it still requires minimum of
* 256MB for kernel to boot successfully. When kdump infrastructure is
* configured to save vmcore over network, we run into OOM issue while
* loading modules related to network setup. Hence we need additional 64M
* of memory to avoid OOM issue.
*/
-#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
- + (0x1UL << 26))
+#define PSERIES_MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : \
+ RMA_END) + (0x1UL << 26))
+
+#define MIN_BOOT_MEM ((fw_dump.fadump_platform == \
+ FADUMP_PLATFORM_POWERNV) ? OPAL_MIN_BOOT_MEM : \
+ PSERIES_MIN_BOOT_MEM)
/* The upper limit percentage for user specified boot memory size (25%) */
#define MAX_BOOT_MEM_RATIO 4
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 36077bd..06053fd 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -528,6 +528,29 @@ int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
fadump_conf->cpu_state_entry_size =
of_read_number(prop, 1);
}
+ } else {
+ int i, len;
+
+ prop = of_get_flat_dt_prop(dn, "fw-load-area", &len);
+ if (prop) {
+ /*
+ * Each f/w load area is an (address,size) pair,
+ * 2 cells each, totalling 4 cells per range.
+ */
+ for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+ u64 base, end;
+
+ base = of_read_number(prop + (i * 4) + 0, 2);
+ end = base;
+ end += of_read_number(prop + (i * 4) + 2, 2);
+ if (end > OPAL_MIN_BOOT_MEM) {
+ pr_err("F/W load area: 0x%llx-0x%llx\n",
+ base, end);
+ pr_err("F/W version not supported!\n");
+ return 1;
+ }
+ }
+ }
}
fadump_conf->ops = &opal_fadump_ops;
^ permalink raw reply related
* [PATCH 18/18] powerpc/fadump: Update documentation about backup area support
From: Hari Bathini @ 2019-02-21 17:37 UTC (permalink / raw)
To: Ananth N Mavinakayanahalli, Michael Ellerman, Mahesh J Salgaonkar,
Vasant Hegde, linuxppc-dev, Stewart Smith
In-Reply-To: <155077048463.21014.13936958730316555495.stgit@hbathini.in.ibm.com>
With backup area support available for FADump on PowerNV platform,
update FADump documentation with these details.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 71 +++++++++++++---------
1 file changed, 43 insertions(+), 28 deletions(-)
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index 6411449..42a0065 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -117,6 +117,17 @@ to ensure that crash data is preserved to process later.
e.g.
# echo 1 > /sys/kernel/fadump_release_opalcore
+To process dump on OPAL platform, additional meta data (PIR to
+Logical CPU map) from the crashing kernel is required. This info
+has to be backed up by the crashing kernel for capture kernel to
+use it in making sense of the register state data provided by the
+F/W. The start address of the area where this info is backed up
+is stored at the tail end of FADump crash info header. To indicate
+the presence of this additional meta data (backup info), the magic
+number field in FADump crash info header is overloaded as version
+identifier.
+
+
Implementation details:
----------------------
@@ -131,12 +142,12 @@ that are run. If there is dump data, then the
memory is held.
If there is no waiting dump data, then only the memory required to
-hold CPU state, HPTE region, boot memory dump, FADump header and
-elfcore header, is usually reserved at an offset greater than boot
-memory size (see Fig. 1). This area is *not* released: this region
+hold CPU state, HPTE region, boot memory dump, FADump header, elfcore
+header and backup area, is usually reserved at an offset greater than
+boot memory size (see Fig. 1). This area is *not* released: this region
will be kept permanently reserved, so that it can act as a receptacle
-for a copy of the boot memory content in addition to CPU state and
-HPTE region, in the case a crash does occur.
+for a copy of the boot memory content in addition to CPU state and HPTE
+region, in the case a crash does occur.
Since this reserved memory area is used only after the system crash,
there is no point in blocking this significant chunk of memory from
@@ -150,19 +161,19 @@ that were present in CMA region.
o Memory Reservation during first kernel
- Low memory Top of memory
- 0 boot memory size |<--- Reserved dump area --->| |
- | | | Permanent Reservatio | |
- V V | (Preserve area) | V
- +-----------+--------/ /---+---+----+-------+-----+-----+-------+
- | | |///|////| DUMP | HDR | ELF | |
- +-----------+--------/ /---+---+----+-------+-----+-----+-------+
- | ^ ^ ^ ^
- | | | | |
- \ CPU HPTE / |
- --------------------------------- |
- Boot memory content gets transferred |
- to reserved area by firmware at the |
+ Low memory Top of memory
+ 0 boot memory size |<---- Reserved dump area ---->| |
+ | | | Permanent Reservation | |
+ V V | (Preserve area) | V
+ +-----------+--------/ /---+---+----+-------+-----+----+--+-------+
+ | | |///|////| DUMP |HDR|/|ELF |//| |
+ +-----------+--------/ /---+---+----+-------+-----+----+--+-------+
+ | ^ ^ ^ ^ | ^^
+ | | | | | | ||
+ \ CPU HPTE / | \ / Backup Info
+ --------------------------------- | ----
+ Boot memory content gets transferred | Start address of
+ to reserved area by firmware at the | Backup Info.
time of crash. |
FADump Header
(meta area)
@@ -171,13 +182,13 @@ that were present in CMA region.
o Memory Reservation during second kernel after crash
- Low memory Top of memory
- 0 boot memory size |
- | |<--------------- Reserved dump area -------------->|
- V V |<---- Preserve area ------->| |
- +-----------+--------/ /---+---+----+-------+-----+-----+-------+
- | | |///|////| DUMP | HDR | ELF | |
- +-----------+--------/ /---+---+----+-------+-----+-----+-------+
+ Low memory Top of memory
+ 0 boot memory size |
+ | |<--------------- Reserved dump area ---------------->|
+ V V |<----- Preserve area -------->| |
+ +-----------+--------/ /---+---+----+-------+-----+----+--+-------+
+ | | |///|////| DUMP |HDR|/|ELF |//| |
+ +-----------+--------/ /---+---+----+-------+-----+----+--+-------+
| |
V V
Used by second /proc/vmcore
@@ -185,9 +196,10 @@ that were present in CMA region.
Fig. 2
+---+
- |///| -> Regions (CPU & HPTE) marked like this in the above figures
- +---+ are not always present. For example, OPAL platform does not
- have CPU & HPTE regions.
+ |///| -> Regions (CPU, HPTE, HDR extension & Backup area) marked
+ +---+ like this in the above figures are not always present.
+ For example, OPAL platform does not have CPU & HPTE regions
+ while PSeries platform doesn't use Backup area currently.
Currently the dump will be copied from /proc/vmcore to a new file upon
@@ -330,7 +342,10 @@ TODO:
2. Reserve the area of predefined size (say PAGE_SIZE) for this
structure and have unused area as reserved (initialized to zero)
for future field additions.
+
The advantage of approach 1 over 2 is we don't need to reserve extra space.
+ Using approach 1 to provide additional meta data on OPAL platform while
+ overloading magic number field as version identifier for version tracking.
---
Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This document is based on the original documentation written for phyp
^ permalink raw reply related
* Re: [PATCH v4 04/16] powerpc/mm/32s: use generic mmu_mapin_ram() for all blocks.
From: Christophe Leroy @ 2019-02-21 19:02 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <87o9755jy2.fsf@concordia.ellerman.id.au>
On 02/21/2019 01:51 PM, Michael Ellerman wrote:
> Christophe Leroy <christophe.leroy@c-s.fr> writes:
>
>> Now that mmu_mapin_ram() is able to handle other blocks
>> than the one starting at 0, the WII can use it for all
>> its blocks.
>>
>> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
>> ---
>> arch/powerpc/mm/pgtable_32.c | 27 +++++++++------------------
>> 1 file changed, 9 insertions(+), 18 deletions(-)
>>
>> diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
>> index b4858818523f..2bf9bf8867d4 100644
>> --- a/arch/powerpc/mm/pgtable_32.c
>> +++ b/arch/powerpc/mm/pgtable_32.c
>> @@ -254,26 +254,17 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
>>
>> void __init mapin_ram(void)
>> {
>> - unsigned long s, top;
>> -
>> -#ifndef CONFIG_WII
>> - top = total_lowmem;
>> - s = mmu_mapin_ram(0, top);
>> - __mapin_ram_chunk(s, top);
>> -#else
>> - if (!wii_hole_size) {
>> - s = mmu_mapin_ram(0, total_lowmem);
>> - __mapin_ram_chunk(s, total_lowmem);
>> - } else {
>> - top = wii_hole_start;
>> - s = mmu_mapin_ram(0, top);
>> - __mapin_ram_chunk(s, top);
>> + struct memblock_region *reg;
>> +
>> + for_each_memblock(memory, reg) {
>> + unsigned long base = reg->base;
>> + unsigned long top = min(base + reg->size, (unsigned long)total_lowmem);
>
> This gives me:
>
> In file included from ../arch/powerpc/mm/pgtable_32.c:22:
> ../arch/powerpc/mm/pgtable_32.c: In function ‘mapin_ram’:
> ../include/linux/kernel.h:846:29: error: comparison of distinct pointer types lacks a cast [-Werror]
> (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
> ^~
> ../include/linux/kernel.h:860:4: note: in expansion of macro ‘__typecheck’
> (__typecheck(x, y) && __no_side_effects(x, y))
> ^~~~~~~~~~~
> ../include/linux/kernel.h:870:24: note: in expansion of macro ‘__safe_cmp’
> __builtin_choose_expr(__safe_cmp(x, y), \
> ^~~~~~~~~~
> ../include/linux/kernel.h:879:19: note: in expansion of macro ‘__careful_cmp’
> #define min(x, y) __careful_cmp(x, y, <)
> ^~~~~~~~~~~~~
> ../arch/powerpc/mm/pgtable_32.c:261:23: note: in expansion of macro ‘min’
> unsigned long top = min(base + reg->size, (unsigned long)total_lowmem);
> ^~~
> cc1: all warnings being treated as errors
> ../scripts/Makefile.build:276: recipe for target 'arch/powerpc/mm/pgtable_32.o' failed
>
>
> For 44x/bamboo_defconfig.
>
The patch below should make it. Tested it on half a dozen of config.
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 2bf9bf8867d4..c4b0eb51f6d8 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -257,8 +257,8 @@ void __init mapin_ram(void)
struct memblock_region *reg;
for_each_memblock(memory, reg) {
- unsigned long base = reg->base;
- unsigned long top = min(base + reg->size, (unsigned long)total_lowmem);
+ phys_addr_t base = reg->base;
+ phys_addr_t top = min(base + reg->size, total_lowmem);
if (base >= top)
continue;
I'll send out v5, hope it'll be the last one :(
Christophe
^ permalink raw reply related
* [PATCH v5 01/16] powerpc/wii: properly disable use of BATs when requested.
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
'nobats' kernel parameter or some options like CONFIG_DEBUG_PAGEALLOC
deny the use of BATS for mapping memory.
This patch makes sure that the specific wii RAM mapping function
takes it into account as well.
Fixes: de32400dd26e ("wii: use both mem1 and mem2 as ram")
Cc: stable@vger.kernel.org
Reviewed-by: Jonathan Neuschafer <j.neuschaefer@gmx.net>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/platforms/embedded6xx/wii.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index ecf703ee3a76..ac4ee88efc80 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -83,6 +83,10 @@ unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
/* MEM2 64MB@0x10000000 */
delta = wii_hole_start + wii_hole_size;
size = top - delta;
+
+ if (__map_without_bats)
+ return delta;
+
for (bl = 128<<10; bl < max_size; bl <<= 1) {
if (bl * 2 > size)
break;
--
2.13.3
^ permalink raw reply related
* [PATCH v5 00/16] powerpc/32: Use BATs/LTLBs for STRICT_KERNEL_RWX
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
The purpose of this serie is to:
- use BATs with STRICT_KERNEL_RWX on book3s (See patch 13 for details.)
- use LTLBs with STRICT_KERNEL_RWX on 8xx (See patch 15 for a few details.)
v5:
- Changed var type from unsigned long to phys_addr_t in mapin_ram()
to fix build failure due to type mismatch in min() macro (patch 4).
v4:
- Fixed mapin_ram() to only map mem below total_lowmem (patch 4)
- Fixed sparse warning by making __mmu_mapin_ram static (patch 13)
v3:
- Reordered to avoid build failure due to setibat() not being used for several steps in the serie.
Now the patch using setibat() is next to the one adding setibat().
- Fixed mmu_mapin_ram() in patch 3 to return base in all cases, thanks Jonathan for the test
- Fixed build failure on 8xx when CONFIG_PERF_EVENTS is set due to too many instructions in Exception 0x1200
- Made 8M alignment for data the default on 8xx when STRICT_KERNEL_RWX is selected.
- Added patch 1 to not set additionnal bat on the wii when requesting nobats. The only purpose of this patch
is to be backported, as this function is removed later in the series.
v2:
- Fix patch 2 (was patch 3 in v1) based on feedback from Jonathan.
- Added support for 8xx with LTLBs.
- Added systematic population of pagetables for Abatron BDI.
Christophe Leroy (16):
powerpc/wii: properly disable use of BATs when requested.
powerpc/mm/32: add base address to mmu_mapin_ram()
powerpc/mm/32s: rework mmu_mapin_ram()
powerpc/mm/32s: use generic mmu_mapin_ram() for all blocks.
powerpc/32: always populate page tables for Abatron BDI.
powerpc/wii: remove wii_mmu_mapin_mem2()
powerpc/mm/32s: use _PAGE_EXEC in setbat()
powerpc/32: add helper to write into segment registers
powerpc/mmu: add is_strict_kernel_rwx() helper
powerpc/kconfig: define PAGE_SHIFT inside Kconfig
powerpc/kconfig: define CONFIG_DATA_SHIFT and CONFIG_ETEXT_SHIFT
powerpc/mm/32s: add setibat() clearibat() and update_bats()
powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX
powerpc/kconfig: make _etext and data areas alignment configurable on
Book3s 32
powerpc/8xx: don't disable large TLBs with CONFIG_STRICT_KERNEL_RWX
powerpc/kconfig: make _etext and data areas alignment configurable on
8xx
arch/powerpc/Kconfig | 60 +++++++++
arch/powerpc/include/asm/book3s/32/mmu-hash.h | 2 +
arch/powerpc/include/asm/book3s/32/pgtable.h | 11 ++
arch/powerpc/include/asm/mmu.h | 11 ++
arch/powerpc/include/asm/nohash/32/mmu-8xx.h | 3 +-
arch/powerpc/include/asm/page.h | 13 +-
arch/powerpc/include/asm/reg.h | 5 +
arch/powerpc/kernel/head_32.S | 35 +++++
arch/powerpc/kernel/head_8xx.S | 54 ++++++--
arch/powerpc/kernel/vmlinux.lds.S | 9 +-
arch/powerpc/mm/40x_mmu.c | 2 +-
arch/powerpc/mm/44x_mmu.c | 2 +-
arch/powerpc/mm/8xx_mmu.c | 33 ++++-
arch/powerpc/mm/fsl_booke_mmu.c | 2 +-
arch/powerpc/mm/init_32.c | 6 +-
arch/powerpc/mm/mmu_decl.h | 10 +-
arch/powerpc/mm/pgtable_32.c | 42 +++---
arch/powerpc/mm/ppc_mmu_32.c | 180 ++++++++++++++++++++++----
arch/powerpc/platforms/embedded6xx/wii.c | 24 ----
19 files changed, 393 insertions(+), 111 deletions(-)
--
2.13.3
^ permalink raw reply
* [PATCH v5 02/16] powerpc/mm/32: add base address to mmu_mapin_ram()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
At the time being, mmu_mapin_ram() always maps RAM from the beginning.
But some platforms like the WII have to map a second block of RAM.
This patch adds to mmu_mapin_ram() the base address of the block.
At the moment, only base address 0 is supported.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/40x_mmu.c | 2 +-
arch/powerpc/mm/44x_mmu.c | 2 +-
arch/powerpc/mm/8xx_mmu.c | 2 +-
arch/powerpc/mm/fsl_booke_mmu.c | 2 +-
arch/powerpc/mm/mmu_decl.h | 2 +-
arch/powerpc/mm/pgtable_32.c | 6 +++---
arch/powerpc/mm/ppc_mmu_32.c | 2 +-
7 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index 61ac468c87c6..b9cf6f8764b0 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -93,7 +93,7 @@ void __init MMU_init_hw(void)
#define LARGE_PAGE_SIZE_16M (1<<24)
#define LARGE_PAGE_SIZE_4M (1<<22)
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long v, s, mapped;
phys_addr_t p;
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index ea2b9af08a48..aad127acdbaa 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -170,7 +170,7 @@ void __init MMU_init_hw(void)
flush_instruction_cache();
}
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long addr;
unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index e2c32bdb6023..46bc26ef71e9 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -99,7 +99,7 @@ static void __init mmu_patch_cmp_limit(s32 *site, unsigned long mapped)
modify_instruction_site(site, 0xffff, (unsigned long)__va(mapped) >> 16);
}
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long mapped;
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 080d49b26c3a..210cbc1faf63 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -221,7 +221,7 @@ unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, bool dryrun)
#error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
#endif
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1;
}
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index c4a717da65eb..61730023dde3 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -130,7 +130,7 @@ extern void wii_memory_fixups(void);
*/
#ifdef CONFIG_PPC32
extern void MMU_init_hw(void);
-extern unsigned long mmu_mapin_ram(unsigned long top);
+unsigned long mmu_mapin_ram(unsigned long base, unsigned long top);
#endif
#ifdef CONFIG_PPC_FSL_BOOK3E
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index ded71126ce4c..b4858818523f 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -258,15 +258,15 @@ void __init mapin_ram(void)
#ifndef CONFIG_WII
top = total_lowmem;
- s = mmu_mapin_ram(top);
+ s = mmu_mapin_ram(0, top);
__mapin_ram_chunk(s, top);
#else
if (!wii_hole_size) {
- s = mmu_mapin_ram(total_lowmem);
+ s = mmu_mapin_ram(0, total_lowmem);
__mapin_ram_chunk(s, total_lowmem);
} else {
top = wii_hole_start;
- s = mmu_mapin_ram(top);
+ s = mmu_mapin_ram(0, top);
__mapin_ram_chunk(s, top);
top = memblock_end_of_DRAM();
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 3f4193201ee7..b260ced065b4 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -73,7 +73,7 @@ unsigned long p_block_mapped(phys_addr_t pa)
return 0;
}
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long tot, bl, done;
unsigned long max_size = (256<<20);
--
2.13.3
^ permalink raw reply related
* [PATCH v5 03/16] powerpc/mm/32s: rework mmu_mapin_ram()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
This patch reworks mmu_mapin_ram() to be more generic and map as much
blocks as possible. It now supports blocks not starting at address 0.
It scans DBATs array to find free ones instead of forcing the use of
BAT2 and BAT3.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/ppc_mmu_32.c | 63 ++++++++++++++++++++++++++++----------------
1 file changed, 41 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index b260ced065b4..5fc59b195fef 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -73,39 +73,58 @@ unsigned long p_block_mapped(phys_addr_t pa)
return 0;
}
+static int find_free_bat(void)
+{
+ int b;
+
+ if (cpu_has_feature(CPU_FTR_601)) {
+ for (b = 0; b < 4; b++) {
+ struct ppc_bat *bat = BATS[b];
+
+ if (!(bat[0].batl & 0x40))
+ return b;
+ }
+ } else {
+ int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+
+ for (b = 0; b < n; b++) {
+ struct ppc_bat *bat = BATS[b];
+
+ if (!(bat[1].batu & 3))
+ return b;
+ }
+ }
+ return -1;
+}
+
+static unsigned int block_size(unsigned long base, unsigned long top)
+{
+ unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
+ unsigned int base_shift = (fls(base) - 1) & 31;
+ unsigned int block_shift = (fls(top - base) - 1) & 31;
+
+ return min3(max_size, 1U << base_shift, 1U << block_shift);
+}
+
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
- unsigned long tot, bl, done;
- unsigned long max_size = (256<<20);
+ int idx;
if (__map_without_bats) {
printk(KERN_DEBUG "RAM mapped without BATs\n");
- return 0;
+ return base;
}
- /* Set up BAT2 and if necessary BAT3 to cover RAM. */
+ while ((idx = find_free_bat()) != -1 && base != top) {
+ unsigned int size = block_size(base, top);
- /* Make sure we don't map a block larger than the
- smallest alignment of the physical address. */
- tot = top;
- for (bl = 128<<10; bl < max_size; bl <<= 1) {
- if (bl * 2 > tot)
+ if (size < 128 << 10)
break;
+ setbat(idx, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
+ base += size;
}
- setbat(2, PAGE_OFFSET, 0, bl, PAGE_KERNEL_X);
- done = (unsigned long)bat_addrs[2].limit - PAGE_OFFSET + 1;
- if ((done < tot) && !bat_addrs[3].limit) {
- /* use BAT3 to cover a bit more */
- tot -= done;
- for (bl = 128<<10; bl < max_size; bl <<= 1)
- if (bl * 2 > tot)
- break;
- setbat(3, PAGE_OFFSET+done, done, bl, PAGE_KERNEL_X);
- done = (unsigned long)bat_addrs[3].limit - PAGE_OFFSET + 1;
- }
-
- return done;
+ return base;
}
/*
--
2.13.3
^ permalink raw reply related
* [PATCH v5 04/16] powerpc/mm/32s: use generic mmu_mapin_ram() for all blocks.
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Now that mmu_mapin_ram() is able to handle other blocks
than the one starting at 0, the WII can use it for all
its blocks.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/pgtable_32.c | 27 +++++++++------------------
1 file changed, 9 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index b4858818523f..c4b0eb51f6d8 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -254,26 +254,17 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
void __init mapin_ram(void)
{
- unsigned long s, top;
-
-#ifndef CONFIG_WII
- top = total_lowmem;
- s = mmu_mapin_ram(0, top);
- __mapin_ram_chunk(s, top);
-#else
- if (!wii_hole_size) {
- s = mmu_mapin_ram(0, total_lowmem);
- __mapin_ram_chunk(s, total_lowmem);
- } else {
- top = wii_hole_start;
- s = mmu_mapin_ram(0, top);
- __mapin_ram_chunk(s, top);
+ struct memblock_region *reg;
+
+ for_each_memblock(memory, reg) {
+ phys_addr_t base = reg->base;
+ phys_addr_t top = min(base + reg->size, total_lowmem);
- top = memblock_end_of_DRAM();
- s = wii_mmu_mapin_mem2(top);
- __mapin_ram_chunk(s, top);
+ if (base >= top)
+ continue;
+ base = mmu_mapin_ram(base, top);
+ __mapin_ram_chunk(base, top);
}
-#endif
}
/* Scan the real Linux page tables and return a PTE pointer for
--
2.13.3
^ permalink raw reply related
* [PATCH v5 05/16] powerpc/32: always populate page tables for Abatron BDI.
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
When CONFIG_BDI_SWITCH is set, the page tables have to be populated
allthough large TLBs are used, because the BDI switch knows nothing
about those large TLBs which are handled directly in TLB miss logic.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/pgtable_32.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index c4b0eb51f6d8..a000768a5cc9 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -263,7 +263,10 @@ void __init mapin_ram(void)
if (base >= top)
continue;
base = mmu_mapin_ram(base, top);
- __mapin_ram_chunk(base, top);
+ if (IS_ENABLED(CONFIG_BDI_SWITCH))
+ __mapin_ram_chunk(reg->base, top);
+ else
+ __mapin_ram_chunk(base, top);
}
}
--
2.13.3
^ permalink raw reply related
* [PATCH v5 06/16] powerpc/wii: remove wii_mmu_mapin_mem2()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
wii_mmu_mapin_mem2() is not used anymore, remove it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/platforms/embedded6xx/wii.c | 28 ----------------------------
1 file changed, 28 deletions(-)
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index ac4ee88efc80..235fe81aa2b1 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -54,10 +54,6 @@
static void __iomem *hw_ctrl;
static void __iomem *hw_gpio;
-unsigned long wii_hole_start;
-unsigned long wii_hole_size;
-
-
static int __init page_aligned(unsigned long x)
{
return !(x & (PAGE_SIZE-1));
@@ -69,30 +65,6 @@ void __init wii_memory_fixups(void)
BUG_ON(memblock.memory.cnt != 2);
BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base));
-
- /* determine hole */
- wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE);
- wii_hole_size = p[1].base - wii_hole_start;
-}
-
-unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
-{
- unsigned long delta, size, bl;
- unsigned long max_size = (256<<20);
-
- /* MEM2 64MB@0x10000000 */
- delta = wii_hole_start + wii_hole_size;
- size = top - delta;
-
- if (__map_without_bats)
- return delta;
-
- for (bl = 128<<10; bl < max_size; bl <<= 1) {
- if (bl * 2 > size)
- break;
- }
- setbat(4, PAGE_OFFSET+delta, delta, bl, PAGE_KERNEL_X);
- return delta + bl;
}
static void __noreturn wii_spin(void)
--
2.13.3
^ permalink raw reply related
* [PATCH v5 07/16] powerpc/mm/32s: use _PAGE_EXEC in setbat()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Do not set IBAT when setbat() is called without _PAGE_EXEC
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/ppc_mmu_32.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 5fc59b195fef..ff8580c6ab11 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -131,6 +131,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
* Set up one of the I/D BAT (block address translation) register pairs.
* The parameters are not checked; in particular size must be a power
* of 2 between 128k and 256M.
+ * On 603+, only set IBAT when _PAGE_EXEC is set
*/
void __init setbat(int index, unsigned long virt, phys_addr_t phys,
unsigned int size, pgprot_t prot)
@@ -157,11 +158,12 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
bat[1].batu |= 1; /* Vp = 1 */
if (flags & _PAGE_GUARDED) {
/* G bit must be zero in IBATs */
- bat[0].batu = bat[0].batl = 0;
- } else {
- /* make IBAT same as DBAT */
- bat[0] = bat[1];
+ flags &= ~_PAGE_EXEC;
}
+ if (flags & _PAGE_EXEC)
+ bat[0] = bat[1];
+ else
+ bat[0].batu = bat[0].batl = 0;
} else {
/* 601 cpu */
if (bl > BL_8M)
--
2.13.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox