From 9d77db3c730780c8ef5ccd4b66403ff5675cfe4e Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 13 May 2024 10:30:14 +0000
Subject: [PATCH] modify sin led gpio
---
kernel/arch/powerpc/kernel/fadump.c | 1692 ++++++++++++++++++++++++++++++---------------------------
1 files changed, 897 insertions(+), 795 deletions(-)
diff --git a/kernel/arch/powerpc/kernel/fadump.c b/kernel/arch/powerpc/kernel/fadump.c
index c02c952..935ce1b 100644
--- a/kernel/arch/powerpc/kernel/fadump.c
+++ b/kernel/arch/powerpc/kernel/fadump.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Firmware Assisted dump: A robust mechanism to get reliable kernel crash
* dump with assistance from firmware. This approach does not use kexec,
@@ -5,20 +6,6 @@
* memory contents. The most of the code implementation has been adapted
* from phyp assisted dump implementation written by Linas Vepstas and
* Manish Ahuja
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright 2011 IBM Corporation
* Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
@@ -35,103 +22,155 @@
#include <linux/kobject.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
+#include <linux/cma.h>
+#include <linux/hugetlb.h>
#include <asm/debugfs.h>
#include <asm/page.h>
#include <asm/prom.h>
-#include <asm/rtas.h>
#include <asm/fadump.h>
+#include <asm/fadump-internal.h>
#include <asm/setup.h>
+/*
+ * The CPU who acquired the lock to trigger the fadump crash should
+ * wait for other CPUs to enter.
+ *
+ * The timeout is in milliseconds.
+ */
+#define CRASH_TIMEOUT 500
+
static struct fw_dump fw_dump;
-static struct fadump_mem_struct fdm;
-static const struct fadump_mem_struct *fdm_active;
+static void __init fadump_reserve_crash_area(u64 base);
+
+struct kobject *fadump_kobj;
+
+#ifndef CONFIG_PRESERVE_FA_DUMP
+
+static atomic_t cpus_in_fadump;
static DEFINE_MUTEX(fadump_mutex);
-struct fad_crash_memory_ranges *crash_memory_ranges;
-int crash_memory_ranges_size;
-int crash_mem_ranges;
-int max_crash_mem_ranges;
-/* 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)
+struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false };
+
+#define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */
+#define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \
+ sizeof(struct fadump_memory_range))
+static struct fadump_memory_range rngs[RESERVED_RNGS_CNT];
+struct fadump_mrange_info reserved_mrange_info = { "reserved", rngs,
+ RESERVED_RNGS_SZ, 0,
+ RESERVED_RNGS_CNT, true };
+
+static void __init early_init_dt_scan_reserved_ranges(unsigned long node);
+
+#ifdef CONFIG_CMA
+static struct cma *fadump_cma;
+
+/*
+ * fadump_cma_init() - Initialize CMA area from a fadump reserved memory
+ *
+ * This function initializes CMA area from fadump reserved memory.
+ * The total size of fadump reserved memory covers for boot memory size
+ * + cpu data size + hpte size and metadata.
+ * Initialize only the area equivalent to boot memory size for CMA use.
+ * The reamining portion of fadump reserved memory will be not given
+ * to CMA and pages for thoes will stay reserved. boot memory size is
+ * aligned per CMA requirement to satisy cma_init_reserved_mem() call.
+ * But for some reason even if it fails we still have the memory reservation
+ * with us and we can still continue doing fadump.
+ */
+int __init fadump_cma_init(void)
{
- const __be32 *sections;
- int i, num_sections;
- int size;
- const __be32 *token;
+ unsigned long long base, size;
+ int rc;
- if (depth != 1 || strcmp(uname, "rtas") != 0)
+ if (!fw_dump.fadump_enabled)
return 0;
/*
- * Check if Firmware Assisted dump is supported. if yes, check
- * if dump has been initiated on last reboot.
+ * Do not use CMA if user has provided fadump=nocma kernel parameter.
+ * Return 1 to continue with fadump old behaviour.
*/
- token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
- if (!token)
+ if (fw_dump.nocma)
return 1;
- fw_dump.fadump_supported = 1;
- fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
+ base = fw_dump.reserve_dump_area_start;
+ size = fw_dump.boot_memory_size;
- /*
- * 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;
+ if (!size)
+ return 0;
- /* 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)
+ rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
+ if (rc) {
+ pr_err("Failed to init cma area for firmware-assisted dump,%d\n", rc);
+ /*
+ * Though the CMA init has failed we still have memory
+ * reservation with us. The reserved memory will be
+ * blocked from production system usage. Hence return 1,
+ * so that we can continue with fadump.
+ */
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 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;
- }
}
+ /*
+ * So we now have successfully initialized cma area for fadump.
+ */
+ pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
+ "bytes of memory reserved for firmware-assisted dump\n",
+ cma_get_size(fadump_cma),
+ (unsigned long)cma_get_base(fadump_cma) >> 20,
+ fw_dump.reserve_dump_area_size);
return 1;
+}
+#else
+static int __init fadump_cma_init(void) { return 1; }
+#endif /* CONFIG_CMA */
+
+/* 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 == 0) {
+ early_init_dt_scan_reserved_ranges(node);
+ return 0;
+ }
+
+ if (depth != 1)
+ return 0;
+
+ if (strcmp(uname, "rtas") == 0) {
+ rtas_fadump_dt_scan(&fw_dump, node);
+ return 1;
+ }
+
+ if (strcmp(uname, "ibm,opal") == 0) {
+ opal_fadump_dt_scan(&fw_dump, node);
+ return 1;
+ }
+
+ return 0;
}
/*
* If fadump is registered, check if the memory provided
* falls within boot memory area and reserved memory area.
*/
-int is_fadump_memory_area(u64 addr, ulong size)
+int is_fadump_memory_area(u64 addr, unsigned long size)
{
- u64 d_start = fw_dump.reserve_dump_area_start;
- u64 d_end = d_start + fw_dump.reserve_dump_area_size;
+ u64 d_start, d_end;
if (!fw_dump.dump_registered)
return 0;
+ if (!size)
+ return 0;
+
+ d_start = fw_dump.reserve_dump_area_start;
+ d_end = d_start + fw_dump.reserve_dump_area_size;
if (((addr + size) > d_start) && (addr <= d_end))
return 1;
- return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size;
+ return (addr <= fw_dump.boot_mem_top);
}
int should_fadump_crash(void)
@@ -147,40 +186,75 @@
}
/*
- * Returns 1, if there are no holes in boot memory area,
- * 0 otherwise.
+ * Returns true, if there are no holes in memory area between d_start to d_end,
+ * false otherwise.
*/
-static int is_boot_memory_area_contiguous(void)
+static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
{
- struct memblock_region *reg;
- unsigned long tstart, tend;
- unsigned long start_pfn = PHYS_PFN(RMA_START);
- unsigned long end_pfn = PHYS_PFN(RMA_START + fw_dump.boot_memory_size);
- unsigned int ret = 0;
+ phys_addr_t reg_start, reg_end;
+ bool ret = false;
+ u64 i, start, end;
- for_each_memblock(memory, reg) {
- tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
- tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
- if (tstart < tend) {
- /* Memory hole from start_pfn to tstart */
- if (tstart > start_pfn)
+ for_each_mem_range(i, ®_start, ®_end) {
+ start = max_t(u64, d_start, reg_start);
+ end = min_t(u64, d_end, reg_end);
+ if (d_start < end) {
+ /* Memory hole from d_start to start */
+ if (start > d_start)
break;
- if (tend == end_pfn) {
- ret = 1;
+ if (end == d_end) {
+ ret = true;
break;
}
- start_pfn = tend + 1;
+ d_start = end + 1;
}
}
return ret;
}
+/*
+ * Returns true, if there are no holes in boot memory area,
+ * false otherwise.
+ */
+bool is_fadump_boot_mem_contiguous(void)
+{
+ unsigned long d_start, d_end;
+ bool ret = false;
+ int i;
+
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ d_start = fw_dump.boot_mem_addr[i];
+ d_end = d_start + fw_dump.boot_mem_sz[i];
+
+ ret = is_fadump_mem_area_contiguous(d_start, d_end);
+ if (!ret)
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Returns true, if there are no holes in reserved memory area,
+ * false otherwise.
+ */
+bool is_fadump_reserved_mem_contiguous(void)
+{
+ u64 d_start, d_end;
+
+ d_start = fw_dump.reserve_dump_area_start;
+ d_end = d_start + fw_dump.reserve_dump_area_size;
+ return is_fadump_mem_area_contiguous(d_start, d_end);
+}
+
/* 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"));
@@ -194,62 +268,13 @@
pr_debug("Dump section sizes:\n");
pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
- pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size);
-}
-
-static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
- unsigned long addr)
-{
- if (!fdm)
- return 0;
-
- memset(fdm, 0, sizeof(struct fadump_mem_struct));
- addr = addr & PAGE_MASK;
-
- fdm->header.dump_format_version = 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;
+ pr_debug(" Boot memory size : %lx\n", fw_dump.boot_memory_size);
+ pr_debug(" Boot memory top : %llx\n", fw_dump.boot_mem_top);
+ pr_debug("Boot memory regions cnt: %llx\n", fw_dump.boot_mem_regs_cnt);
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ pr_debug("[%03d] base = %llx, size = %llx\n", i,
+ fw_dump.boot_mem_addr[i], fw_dump.boot_mem_sz[i]);
+ }
}
/**
@@ -267,10 +292,10 @@
* that is required for a kernel to boot successfully.
*
*/
-static inline unsigned long fadump_calculate_reserve_size(void)
+static __init u64 fadump_calculate_reserve_size(void)
{
+ u64 base, size, bootmem_min;
int ret;
- unsigned long long base, size;
if (fw_dump.reserve_bootvar)
pr_warn("'fadump_reserve_mem=' parameter is deprecated in favor of 'crashkernel=' parameter.\n");
@@ -320,7 +345,8 @@
if (memory_limit && size > memory_limit)
size = memory_limit;
- return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+ bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+ return (size > bootmem_min ? size : bootmem_min);
}
/*
@@ -341,51 +367,199 @@
size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
size = PAGE_ALIGN(size);
+
+ /* This is to hold kernel metadata on platforms that support it */
+ size += (fw_dump.ops->fadump_get_metadata_size ?
+ fw_dump.ops->fadump_get_metadata_size() : 0);
return size;
}
-static void __init fadump_reserve_crash_area(unsigned long base,
- unsigned long size)
+static int __init add_boot_mem_region(unsigned long rstart,
+ unsigned long rsize)
{
- struct memblock_region *reg;
- unsigned long mstart, mend, msize;
+ int i = fw_dump.boot_mem_regs_cnt++;
- for_each_memblock(memory, reg) {
- mstart = max_t(unsigned long, base, reg->base);
- mend = reg->base + reg->size;
- mend = min(base + size, mend);
+ if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
+ fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+ return 0;
+ }
- 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);
+ pr_debug("Added boot memory range[%d] [%#016lx-%#016lx)\n",
+ i, rstart, (rstart + rsize));
+ fw_dump.boot_mem_addr[i] = rstart;
+ fw_dump.boot_mem_sz[i] = rsize;
+ return 1;
+}
+
+/*
+ * Firmware usually has a hard limit on the data it can copy per region.
+ * Honour that by splitting a memory range into multiple regions.
+ */
+static int __init add_boot_mem_regions(unsigned long mstart,
+ unsigned long msize)
+{
+ unsigned long rstart, rsize, max_size;
+ int ret = 1;
+
+ rstart = mstart;
+ max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : msize;
+ while (msize) {
+ if (msize > max_size)
+ rsize = max_size;
+ else
+ rsize = msize;
+
+ ret = add_boot_mem_region(rstart, rsize);
+ if (!ret)
+ break;
+
+ msize -= rsize;
+ rstart += rsize;
+ }
+
+ return ret;
+}
+
+static int __init fadump_get_boot_mem_regions(void)
+{
+ unsigned long size, cur_size, hole_size, last_end;
+ unsigned long mem_size = fw_dump.boot_memory_size;
+ phys_addr_t reg_start, reg_end;
+ int ret = 1;
+ u64 i;
+
+ fw_dump.boot_mem_regs_cnt = 0;
+
+ last_end = 0;
+ hole_size = 0;
+ cur_size = 0;
+ for_each_mem_range(i, ®_start, ®_end) {
+ size = reg_end - reg_start;
+ hole_size += (reg_start - last_end);
+
+ if ((cur_size + size) >= mem_size) {
+ size = (mem_size - cur_size);
+ ret = add_boot_mem_regions(reg_start, size);
+ break;
+ }
+
+ mem_size -= size;
+ cur_size += size;
+ ret = add_boot_mem_regions(reg_start, size);
+ if (!ret)
+ break;
+
+ last_end = reg_end;
+ }
+ fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size);
+
+ return ret;
+}
+
+/*
+ * Returns true, if the given range overlaps with reserved memory ranges
+ * starting at idx. Also, updates idx to index of overlapping memory range
+ * with the given memory range.
+ * False, otherwise.
+ */
+static bool overlaps_reserved_ranges(u64 base, u64 end, int *idx)
+{
+ bool ret = false;
+ int i;
+
+ for (i = *idx; i < reserved_mrange_info.mem_range_cnt; i++) {
+ u64 rbase = reserved_mrange_info.mem_ranges[i].base;
+ u64 rend = rbase + reserved_mrange_info.mem_ranges[i].size;
+
+ if (end <= rbase)
+ break;
+
+ if ((end > rbase) && (base < rend)) {
+ *idx = i;
+ ret = true;
+ break;
}
}
+
+ return ret;
+}
+
+/*
+ * Locate a suitable memory area to reserve memory for FADump. While at it,
+ * lookup reserved-ranges & avoid overlap with them, as they are used by F/W.
+ */
+static u64 __init fadump_locate_reserve_mem(u64 base, u64 size)
+{
+ struct fadump_memory_range *mrngs;
+ phys_addr_t mstart, mend;
+ int idx = 0;
+ u64 i, ret = 0;
+
+ mrngs = reserved_mrange_info.mem_ranges;
+ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ pr_debug("%llu) mstart: %llx, mend: %llx, base: %llx\n",
+ i, mstart, mend, base);
+
+ if (mstart > base)
+ base = PAGE_ALIGN(mstart);
+
+ while ((mend > base) && ((mend - base) >= size)) {
+ if (!overlaps_reserved_ranges(base, base+size, &idx)) {
+ ret = base;
+ goto out;
+ }
+
+ base = mrngs[idx].base + mrngs[idx].size;
+ base = PAGE_ALIGN(base);
+ }
+ }
+
+out:
+ return ret;
}
int __init fadump_reserve_mem(void)
{
- unsigned long base, size, memory_boundary;
+ u64 base, size, mem_boundary, bootmem_min;
+ int ret = 1;
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
* first kernel.
*/
- if (fdm_active)
- fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len);
- else
- fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+ if (!fw_dump.dump_active) {
+ fw_dump.boot_memory_size =
+ PAGE_ALIGN(fadump_calculate_reserve_size());
+#ifdef CONFIG_CMA
+ if (!fw_dump.nocma) {
+ fw_dump.boot_memory_size =
+ ALIGN(fw_dump.boot_memory_size,
+ FADUMP_CMA_ALIGNMENT);
+ }
+#endif
+
+ bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+ if (fw_dump.boot_memory_size < bootmem_min) {
+ pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%llx\n",
+ fw_dump.boot_memory_size, bootmem_min);
+ goto error_out;
+ }
+
+ if (!fadump_get_boot_mem_regions()) {
+ pr_err("Too many holes in boot memory area to enable fadump\n");
+ goto error_out;
+ }
+ }
/*
* Calculate the memory boundary.
@@ -404,10 +578,13 @@
" dump, now %#016llx\n", memory_limit);
}
if (memory_limit)
- memory_boundary = memory_limit;
+ mem_boundary = memory_limit;
else
- memory_boundary = memblock_end_of_DRAM();
+ mem_boundary = memblock_end_of_DRAM();
+ base = fw_dump.boot_mem_top;
+ size = get_fadump_area_size();
+ fw_dump.reserve_dump_area_size = size;
if (fw_dump.dump_active) {
pr_info("Firmware-assisted dump is active.\n");
@@ -421,56 +598,52 @@
#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 =
- be64_to_cpu(fdm_active->rmr_region.destination_address) +
- be64_to_cpu(fdm_active->rmr_region.source_len);
- pr_debug("fadumphdr_addr = %p\n",
- (void *) fw_dump.fadumphdr_addr);
+ pr_debug("fadumphdr_addr = %#016lx\n", fw_dump.fadumphdr_addr);
+ pr_debug("Reserve dump area start address: 0x%lx\n",
+ fw_dump.reserve_dump_area_start);
} 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
- * use memblock_find_in_range() here since it doesn't allocate
- * from bottom to top.
+ * minimize the impact of memory hot-remove operation.
*/
- for (base = fw_dump.boot_memory_size;
- base <= (memory_boundary - size);
- base += size) {
- if (memblock_is_region_memory(base, size) &&
- !memblock_is_region_reserved(base, size))
- break;
+ base = fadump_locate_reserve_mem(base, size);
+
+ if (!base || (base + size > mem_boundary)) {
+ pr_err("Failed to find memory chunk for reservation!\n");
+ goto error_out;
}
- if ((base > (memory_boundary - size)) ||
- memblock_reserve(base, size)) {
- pr_err("Failed to reserve memory\n");
- return 0;
+ fw_dump.reserve_dump_area_start = base;
+
+ /*
+ * Calculate the kernel metadata address and register it with
+ * f/w if the platform supports.
+ */
+ if (fw_dump.ops->fadump_setup_metadata &&
+ (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+ goto error_out;
+
+ if (memblock_reserve(base, size)) {
+ pr_err("Failed to reserve memory!\n");
+ 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),
- (unsigned long)(memblock_phys_mem_size() >> 20));
+ pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n",
+ (size >> 20), base, (memblock_phys_mem_size() >> 20));
+
+ ret = fadump_cma_init();
}
- fw_dump.reserve_dump_area_start = base;
- fw_dump.reserve_dump_area_size = size;
- return 1;
-}
-
-unsigned long __init arch_reserved_kernel_pages(void)
-{
- return memblock_reserved_size() / PAGE_SIZE;
+ return ret;
+error_out:
+ fw_dump.fadump_enabled = 0;
+ fw_dump.reserve_dump_area_size = 0;
+ return 0;
}
/* Look for fadump= cmdline option. */
@@ -483,6 +656,10 @@
fw_dump.fadump_enabled = 1;
else if (strncmp(p, "off", 3) == 0)
fw_dump.fadump_enabled = 0;
+ else if (strncmp(p, "nocma", 5) == 0) {
+ fw_dump.fadump_enabled = 1;
+ fw_dump.nocma = 1;
+ }
return 0;
}
@@ -501,63 +678,13 @@
}
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())
- pr_err("Can't have holes in boot 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)
{
+ unsigned int msecs;
struct fadump_crash_info_header *fdh = NULL;
int old_cpu, this_cpu;
+ /* Do not include first CPU */
+ unsigned int ncpus = num_online_cpus() - 1;
if (!should_fadump_crash())
return;
@@ -573,6 +700,8 @@
old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu);
if (old_cpu != -1) {
+ atomic_inc(&cpus_in_fadump);
+
/*
* We can't loop here indefinitely. Wait as long as fadump
* is in force. If we race with fadump un-registration this
@@ -596,71 +725,20 @@
fdh->online_mask = *cpu_online_mask;
- /* Call ibm,os-term rtas call to trigger firmware assisted dump */
- rtas_os_term((char *)str);
-}
-
-#define GPR_MASK 0xffffff0000000000
-static inline int fadump_gpr_index(u64 id)
-{
- int i = -1;
- char str[3];
-
- if ((id & GPR_MASK) == REG_ID("GPR")) {
- /* get the digits at the end */
- id &= ~GPR_MASK;
- id >>= 24;
- str[2] = '\0';
- str[1] = id & 0xff;
- str[0] = (id >> 8) & 0xff;
- sscanf(str, "%d", &i);
- if (i > 31)
- i = -1;
+ /*
+ * If we came in via system reset, wait a while for the secondary
+ * CPUs to enter.
+ */
+ if (TRAP(&(fdh->regs)) == 0x100) {
+ msecs = CRASH_TIMEOUT;
+ while ((atomic_read(&cpus_in_fadump) < ncpus) && (--msecs > 0))
+ mdelay(1);
}
- return i;
+
+ fw_dump.ops->fadump_trigger(fdh, str);
}
-static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
- u64 reg_val)
-{
- int i;
-
- i = fadump_gpr_index(reg_id);
- if (i >= 0)
- regs->gpr[i] = (unsigned long)reg_val;
- else if (reg_id == REG_ID("NIA"))
- regs->nip = (unsigned long)reg_val;
- else if (reg_id == REG_ID("MSR"))
- regs->msr = (unsigned long)reg_val;
- else if (reg_id == REG_ID("CTR"))
- regs->ctr = (unsigned long)reg_val;
- else if (reg_id == REG_ID("LR"))
- regs->link = (unsigned long)reg_val;
- else if (reg_id == REG_ID("XER"))
- regs->xer = (unsigned long)reg_val;
- else if (reg_id == REG_ID("CR"))
- regs->ccr = (unsigned long)reg_val;
- else if (reg_id == REG_ID("DAR"))
- regs->dar = (unsigned long)reg_val;
- else if (reg_id == REG_ID("DSISR"))
- regs->dsisr = (unsigned long)reg_val;
-}
-
-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;
-}
-
-static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
{
struct elf_prstatus prstatus;
@@ -675,19 +753,17 @@
return buf;
}
-static void fadump_update_elfcore_header(char *bufp)
+void fadump_update_elfcore_header(char *bufp)
{
- struct elfhdr *elf;
struct elf_phdr *phdr;
- elf = (struct elfhdr *)bufp;
bufp += sizeof(struct elfhdr);
/* First note is a place holder for cpu notes info. */
phdr = (struct elf_phdr *)bufp;
if (phdr->p_type == PT_NOTE) {
- phdr->p_paddr = fw_dump.cpu_notes_buf;
+ phdr->p_paddr = __pa(fw_dump.cpu_notes_buf_vaddr);
phdr->p_offset = phdr->p_paddr;
phdr->p_filesz = fw_dump.cpu_notes_buf_size;
phdr->p_memsz = fw_dump.cpu_notes_buf_size;
@@ -695,228 +771,103 @@
return;
}
-static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+static void *fadump_alloc_buffer(unsigned long size)
{
- void *vaddr;
+ unsigned long count, i;
struct page *page;
- unsigned long order, count, i;
+ void *vaddr;
- order = get_order(size);
- vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+ vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
if (!vaddr)
return NULL;
- count = 1 << order;
+ count = PAGE_ALIGN(size) / PAGE_SIZE;
page = virt_to_page(vaddr);
for (i = 0; i < count; i++)
- SetPageReserved(page + i);
+ mark_page_reserved(page + i);
return vaddr;
}
-static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+static void fadump_free_buffer(unsigned long vaddr, unsigned long size)
{
- struct page *page;
- unsigned long order, count, i;
-
- order = get_order(size);
- count = 1 << order;
- page = virt_to_page(vaddr);
- for (i = 0; i < count; i++)
- ClearPageReserved(page + i);
- __free_pages(page, order);
+ free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL);
}
-/*
- * 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)
+s32 fadump_setup_cpu_notes_buf(u32 num_cpus)
{
- 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);
+ fw_dump.cpu_notes_buf_vaddr =
+ (unsigned long)fadump_alloc_buffer(fw_dump.cpu_notes_buf_size);
+ if (!fw_dump.cpu_notes_buf_vaddr) {
+ pr_err("Failed to allocate %ld 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) {
- pr_debug("Updating elfcore header (%llx) with cpu notes\n",
- fdh->elfcorehdr_addr);
- fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
- }
+ pr_debug("Allocated buffer for cpu notes of size %ld at 0x%lx\n",
+ fw_dump.cpu_notes_buf_size,
+ fw_dump.cpu_notes_buf_vaddr);
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;
+void fadump_free_cpu_notes_buf(void)
+{
+ if (!fw_dump.cpu_notes_buf_vaddr)
+ return;
+
+ fadump_free_buffer(fw_dump.cpu_notes_buf_vaddr,
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf_vaddr = 0;
fw_dump.cpu_notes_buf_size = 0;
- return rc;
+}
+static void fadump_free_mem_ranges(struct fadump_mrange_info *mrange_info)
+{
+ if (mrange_info->is_static) {
+ mrange_info->mem_range_cnt = 0;
+ return;
+ }
+
+ kfree(mrange_info->mem_ranges);
+ memset((void *)((u64)mrange_info + RNG_NAME_SZ), 0,
+ (sizeof(struct fadump_mrange_info) - RNG_NAME_SZ));
}
/*
- * 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;
-}
-
-static void free_crash_memory_ranges(void)
-{
- kfree(crash_memory_ranges);
- crash_memory_ranges = NULL;
- crash_memory_ranges_size = 0;
- max_crash_mem_ranges = 0;
-}
-
-/*
- * Allocate or reallocate crash memory ranges array in incremental units
+ * Allocate or reallocate mem_ranges array in incremental units
* of PAGE_SIZE.
*/
-static int allocate_crash_memory_ranges(void)
+static int fadump_alloc_mem_ranges(struct fadump_mrange_info *mrange_info)
{
- struct fad_crash_memory_ranges *new_array;
+ struct fadump_memory_range *new_array;
u64 new_size;
- new_size = crash_memory_ranges_size + PAGE_SIZE;
- pr_debug("Allocating %llu bytes of memory for crash memory ranges\n",
- new_size);
+ new_size = mrange_info->mem_ranges_sz + PAGE_SIZE;
+ pr_debug("Allocating %llu bytes of memory for %s memory ranges\n",
+ new_size, mrange_info->name);
- new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL);
+ new_array = krealloc(mrange_info->mem_ranges, new_size, GFP_KERNEL);
if (new_array == NULL) {
- pr_err("Insufficient memory for setting up crash memory ranges\n");
- free_crash_memory_ranges();
+ pr_err("Insufficient memory for setting up %s memory ranges\n",
+ mrange_info->name);
+ fadump_free_mem_ranges(mrange_info);
return -ENOMEM;
}
- crash_memory_ranges = new_array;
- crash_memory_ranges_size = new_size;
- max_crash_mem_ranges = (new_size /
- sizeof(struct fad_crash_memory_ranges));
+ mrange_info->mem_ranges = new_array;
+ mrange_info->mem_ranges_sz = new_size;
+ mrange_info->max_mem_ranges = (new_size /
+ sizeof(struct fadump_memory_range));
return 0;
}
-
-static inline int fadump_add_crash_memory(unsigned long long base,
- unsigned long long end)
+static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info,
+ u64 base, u64 end)
{
- u64 start, size;
+ struct fadump_memory_range *mem_ranges = mrange_info->mem_ranges;
bool is_adjacent = false;
+ u64 start, size;
if (base == end)
return 0;
@@ -925,38 +876,52 @@
* Fold adjacent memory ranges to bring down the memory ranges/
* PT_LOAD segments count.
*/
- if (crash_mem_ranges) {
- start = crash_memory_ranges[crash_mem_ranges - 1].base;
- size = crash_memory_ranges[crash_mem_ranges - 1].size;
+ if (mrange_info->mem_range_cnt) {
+ start = mem_ranges[mrange_info->mem_range_cnt - 1].base;
+ size = mem_ranges[mrange_info->mem_range_cnt - 1].size;
- if ((start + size) == base)
+ /*
+ * Boot memory area needs separate PT_LOAD segment(s) as it
+ * is moved to a different location at the time of crash.
+ * So, fold only if the region is not boot memory area.
+ */
+ if ((start + size) == base && start >= fw_dump.boot_mem_top)
is_adjacent = true;
}
if (!is_adjacent) {
/* resize the array on reaching the limit */
- if (crash_mem_ranges == max_crash_mem_ranges) {
+ if (mrange_info->mem_range_cnt == mrange_info->max_mem_ranges) {
int ret;
- ret = allocate_crash_memory_ranges();
+ if (mrange_info->is_static) {
+ pr_err("Reached array size limit for %s memory ranges\n",
+ mrange_info->name);
+ return -ENOSPC;
+ }
+
+ ret = fadump_alloc_mem_ranges(mrange_info);
if (ret)
return ret;
+
+ /* Update to the new resized array */
+ mem_ranges = mrange_info->mem_ranges;
}
start = base;
- crash_memory_ranges[crash_mem_ranges].base = start;
- crash_mem_ranges++;
+ mem_ranges[mrange_info->mem_range_cnt].base = start;
+ mrange_info->mem_range_cnt++;
}
- crash_memory_ranges[crash_mem_ranges - 1].size = (end - start);
- pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
- (crash_mem_ranges - 1), start, end - 1, (end - start));
+ mem_ranges[mrange_info->mem_range_cnt - 1].size = (end - start);
+ pr_debug("%s_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+ mrange_info->name, (mrange_info->mem_range_cnt - 1),
+ start, end - 1, (end - start));
return 0;
}
-static int fadump_exclude_reserved_area(unsigned long long start,
- unsigned long long end)
+static int fadump_exclude_reserved_area(u64 start, u64 end)
{
- unsigned long long ra_start, ra_end;
+ u64 ra_start, ra_end;
int ret = 0;
ra_start = fw_dump.reserve_dump_area_start;
@@ -964,18 +929,22 @@
if ((ra_start < end) && (ra_end > start)) {
if ((start < ra_start) && (end > ra_end)) {
- ret = fadump_add_crash_memory(start, ra_start);
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ start, ra_start);
if (ret)
return ret;
- ret = fadump_add_crash_memory(ra_end, end);
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ ra_end, end);
} else if (start < ra_start) {
- ret = fadump_add_crash_memory(start, ra_start);
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ start, ra_start);
} else if (ra_end < end) {
- ret = fadump_add_crash_memory(ra_end, end);
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ ra_end, end);
}
} else
- ret = fadump_add_crash_memory(start, end);
+ ret = fadump_add_mem_range(&crash_mrange_info, start, end);
return ret;
}
@@ -1019,37 +988,33 @@
*/
static int fadump_setup_crash_memory_ranges(void)
{
- struct memblock_region *reg;
- unsigned long long start, end;
+ u64 i, start, end;
int ret;
pr_debug("Setup crash memory ranges.\n");
- crash_mem_ranges = 0;
+ crash_mrange_info.mem_range_cnt = 0;
/*
- * 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.
+ * Boot memory region(s) registered with firmware are moved to
+ * different location at the time of crash. Create separate program
+ * header(s) for this memory chunk(s) 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.boot_mem_regs_cnt; i++) {
+ start = fw_dump.boot_mem_addr[i];
+ end = start + fw_dump.boot_mem_sz[i];
+ ret = fadump_add_mem_range(&crash_mrange_info, start, end);
+ if (ret)
+ return ret;
+ }
- for_each_memblock(memory, reg) {
- start = (unsigned long long)reg->base;
- end = start + (unsigned long long)reg->size;
-
+ for_each_mem_range(i, &start, &end) {
/*
- * 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.
+ * skip the memory chunk that is already added
+ * (0 through boot_memory_top).
*/
- 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 < fw_dump.boot_mem_top) {
+ if (end > fw_dump.boot_mem_top)
+ start = fw_dump.boot_mem_top;
else
continue;
}
@@ -1070,17 +1035,35 @@
*/
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;
- 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.boot_mem_regs_cnt; i++) {
+ rstart = fw_dump.boot_mem_addr[i];
+ rend = rstart + fw_dump.boot_mem_sz[i];
+ hole_size += (rstart - rlast);
+
+ if (paddr >= rstart && paddr < rend) {
+ raddr += fw_dump.boot_mem_dest_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;
+ unsigned long long raddr, offset;
struct elf_phdr *phdr;
- int i;
+ struct elfhdr *elf;
+ int i, j;
fadump_init_elfcore_header(bufp);
elf = (struct elfhdr *)bufp;
@@ -1123,12 +1106,14 @@
(elf->e_phnum)++;
/* setup PT_LOAD sections. */
+ j = 0;
+ offset = 0;
+ raddr = fw_dump.boot_mem_addr[0];
+ for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) {
+ u64 mbase, msize;
- 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;
-
+ mbase = crash_mrange_info.mem_ranges[i].base;
+ msize = crash_mrange_info.mem_ranges[i].size;
if (!msize)
continue;
@@ -1138,13 +1123,17 @@
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.
+ * The entire real memory region will be moved by
+ * firmware 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.boot_mem_dest_addr + offset;
+ if (j < (fw_dump.boot_mem_regs_cnt - 1)) {
+ offset += fw_dump.boot_mem_sz[j];
+ raddr = fw_dump.boot_mem_addr[++j];
+ }
}
phdr->p_paddr = mbase;
@@ -1166,7 +1155,6 @@
if (!addr)
return 0;
- fw_dump.fadumphdr_addr = addr;
fdh = __va(addr);
addr += sizeof(struct fadump_crash_info_header);
@@ -1174,7 +1162,7 @@
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;
+ fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
return addr;
}
@@ -1196,7 +1184,8 @@
if (ret)
return ret;
- addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
+ addr = fw_dump.fadumphdr_addr;
+
/* Initialize fadump crash info header. */
addr = init_fadump_header(addr);
vaddr = __va(addr);
@@ -1205,75 +1194,27 @@
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(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->fadump_register(&fw_dump);
}
void fadump_cleanup(void)
{
+ if (!fw_dump.fadump_supported)
+ return;
+
/* Invalidate the registration only if dump is active. */
if (fw_dump.dump_active) {
- init_fadump_mem_struct(&fdm,
- be64_to_cpu(fdm_active->cpu_state_data.destination_address));
- fadump_invalidate_dump(&fdm);
+ pr_debug("Invalidating firmware-assisted dump registration\n");
+ fw_dump.ops->fadump_invalidate(&fw_dump);
} else if (fw_dump.dump_registered) {
/* Un-register Firmware-assisted dump if it was registered. */
- fadump_unregister_dump(&fdm);
- free_crash_memory_ranges();
+ fw_dump.ops->fadump_unregister(&fw_dump);
+ fadump_free_mem_ranges(&crash_mrange_info);
}
+
+ if (fw_dump.ops->fadump_cleanup)
+ fw_dump.ops->fadump_cleanup(&fw_dump);
}
static void fadump_free_reserved_memory(unsigned long start_pfn,
@@ -1298,95 +1239,194 @@
/*
* Skip memory holes and free memory that was actually reserved.
*/
-static void fadump_release_reserved_area(unsigned long start, unsigned long end)
+static void fadump_release_reserved_area(u64 start, u64 end)
{
- struct memblock_region *reg;
- unsigned long tstart, tend;
- unsigned long start_pfn = PHYS_PFN(start);
- unsigned long end_pfn = PHYS_PFN(end);
+ unsigned long reg_spfn, reg_epfn;
+ u64 tstart, tend, spfn, epfn;
+ int i;
- for_each_memblock(memory, reg) {
- tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
- tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+ spfn = PHYS_PFN(start);
+ epfn = PHYS_PFN(end);
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, ®_spfn, ®_epfn, NULL) {
+ tstart = max_t(u64, spfn, reg_spfn);
+ tend = min_t(u64, epfn, reg_epfn);
+
if (tstart < tend) {
fadump_free_reserved_memory(tstart, tend);
- if (tend == end_pfn)
+ if (tend == epfn)
break;
- start_pfn = tend + 1;
+ spfn = tend;
}
}
}
/*
- * Release the memory that was reserved in early boot to preserve the memory
- * contents. The released memory will be available for general use.
+ * Sort the mem ranges in-place and merge adjacent ranges
+ * to minimize the memory ranges count.
*/
-static void fadump_release_memory(unsigned long begin, unsigned long end)
+static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info)
{
- unsigned long ra_start, ra_end;
+ struct fadump_memory_range *mem_ranges;
+ struct fadump_memory_range tmp_range;
+ u64 base, size;
+ int i, j, idx;
+
+ if (!reserved_mrange_info.mem_range_cnt)
+ return;
+
+ /* Sort the memory ranges */
+ mem_ranges = mrange_info->mem_ranges;
+ for (i = 0; i < mrange_info->mem_range_cnt; i++) {
+ idx = i;
+ for (j = (i + 1); j < mrange_info->mem_range_cnt; j++) {
+ if (mem_ranges[idx].base > mem_ranges[j].base)
+ idx = j;
+ }
+ if (idx != i) {
+ tmp_range = mem_ranges[idx];
+ mem_ranges[idx] = mem_ranges[i];
+ mem_ranges[i] = tmp_range;
+ }
+ }
+
+ /* Merge adjacent reserved ranges */
+ idx = 0;
+ for (i = 1; i < mrange_info->mem_range_cnt; i++) {
+ base = mem_ranges[i-1].base;
+ size = mem_ranges[i-1].size;
+ if (mem_ranges[i].base == (base + size))
+ mem_ranges[idx].size += mem_ranges[i].size;
+ else {
+ idx++;
+ if (i == idx)
+ continue;
+
+ mem_ranges[idx] = mem_ranges[i];
+ }
+ }
+ mrange_info->mem_range_cnt = idx + 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)
+{
+ const __be32 *prop;
+ int len, ret = -1;
+ unsigned long i;
+
+ /* reserved-ranges already scanned */
+ if (reserved_mrange_info.mem_range_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 = fadump_add_mem_range(&reserved_mrange_info,
+ base, base + size);
+ if (ret < 0) {
+ pr_warn("some reserved ranges are ignored!\n");
+ break;
+ }
+ }
+ }
+
+ /* Compact reserved ranges */
+ sort_and_merge_mem_ranges(&reserved_mrange_info);
+}
+
+/*
+ * 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(u64 begin, u64 end)
+{
+ u64 ra_start, ra_end, tstart;
+ int i, ret;
ra_start = fw_dump.reserve_dump_area_start;
ra_end = ra_start + fw_dump.reserve_dump_area_size;
/*
- * exclude the dump reserve area. Will reuse it for next
- * fadump registration.
+ * If reserved ranges array limit is hit, overwrite the last reserved
+ * memory range with reserved dump area to ensure it is excluded from
+ * the memory being released (reused for next FADump registration).
*/
- 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);
+ if (reserved_mrange_info.mem_range_cnt ==
+ reserved_mrange_info.max_mem_ranges)
+ reserved_mrange_info.mem_range_cnt--;
+
+ ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end);
+ if (ret != 0)
+ return;
+
+ /* Get the reserved ranges list in order first. */
+ sort_and_merge_mem_ranges(&reserved_mrange_info);
+
+ /* Exclude reserved ranges and release remaining memory */
+ tstart = begin;
+ for (i = 0; i < reserved_mrange_info.mem_range_cnt; i++) {
+ ra_start = reserved_mrange_info.mem_ranges[i].base;
+ ra_end = ra_start + reserved_mrange_info.mem_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)
{
- unsigned long reserved_area_start, reserved_area_end;
- unsigned long destination_address;
-
mutex_lock(&fadump_mutex);
if (!fw_dump.dump_active) {
mutex_unlock(&fadump_mutex);
return;
}
- destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
fadump_cleanup();
mutex_unlock(&fadump_mutex);
- /*
- * Save the current reserved memory bounds we will require them
- * 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;
- /*
- * Setup reserve_dump_area_start and its size 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(fw_dump.boot_mem_top, memblock_end_of_DRAM());
+ fadump_free_cpu_notes_buf();
- fadump_release_memory(reserved_area_start, reserved_area_end);
- if (fw_dump.cpu_notes_buf) {
- 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;
- }
- /* Initialize the kernel dump memory structure for FAD registration. */
- init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ /*
+ * Setup kernel metadata and initialize the kernel dump
+ * memory structure for FADump re-registration.
+ */
+ if (fw_dump.ops->fadump_setup_metadata &&
+ (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+ pr_warn("Failed to setup kernel metadata!\n");
+ fw_dump.ops->fadump_init_mem_struct(&fw_dump);
}
-static ssize_t fadump_release_memory_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
+static ssize_t release_mem_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
int input = -1;
@@ -1411,28 +1451,45 @@
return count;
}
-static ssize_t fadump_enabled_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
+/* Release the reserved memory and disable the FADump */
+static void unregister_fadump(void)
+{
+ fadump_cleanup();
+ fadump_release_memory(fw_dump.reserve_dump_area_start,
+ fw_dump.reserve_dump_area_size);
+ fw_dump.fadump_enabled = 0;
+ kobject_put(fadump_kobj);
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
}
-static ssize_t fadump_register_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
+static ssize_t mem_reserved_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%ld\n", fw_dump.reserve_dump_area_size);
+}
+
+static ssize_t registered_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", fw_dump.dump_registered);
}
-static ssize_t fadump_register_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
+static ssize_t registered_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
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))
@@ -1445,13 +1502,15 @@
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->fadump_unregister(&fw_dump);
break;
case 1:
if (fw_dump.dump_registered == 1) {
- ret = -EEXIST;
- goto unlock_out;
+ /* Un-register Firmware-assisted dump */
+ fw_dump.ops->fadump_unregister(&fw_dump);
}
/* Register Firmware-assisted dump */
ret = register_fadump();
@@ -1468,114 +1527,91 @@
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;
- }
-
- 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);
+ fw_dump.ops->fadump_region_show(&fw_dump, m);
+ mutex_unlock(&fadump_mutex);
return 0;
}
-static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
- 0200, NULL,
- fadump_release_memory_store);
-static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
- 0444, fadump_enabled_show,
- NULL);
-static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
- 0644, fadump_register_show,
- fadump_register_store);
+static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
+static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
+static struct kobj_attribute register_attr = __ATTR_RW(registered);
+static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
-static int fadump_region_open(struct inode *inode, struct file *file)
-{
- return single_open(file, fadump_region_show, inode->i_private);
-}
-
-static const struct file_operations fadump_region_fops = {
- .open = fadump_region_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
+static struct attribute *fadump_attrs[] = {
+ &enable_attr.attr,
+ ®ister_attr.attr,
+ &mem_reserved_attr.attr,
+ NULL,
};
+
+ATTRIBUTE_GROUPS(fadump);
+
+DEFINE_SHOW_ATTRIBUTE(fadump_region);
static void fadump_init_files(void)
{
- struct dentry *debugfs_file;
int rc = 0;
- rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
- if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_enabled (%d)\n", rc);
+ fadump_kobj = kobject_create_and_add("fadump", kernel_kobj);
+ if (!fadump_kobj) {
+ pr_err("failed to create fadump kobject\n");
+ return;
+ }
- rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
- if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_registered (%d)\n", rc);
-
- debugfs_file = debugfs_create_file("fadump_region", 0444,
- powerpc_debugfs_root, NULL,
- &fadump_region_fops);
- if (!debugfs_file)
- printk(KERN_ERR "fadump: unable to create debugfs file"
- " fadump_region\n");
+ debugfs_create_file("fadump_region", 0444, powerpc_debugfs_root, NULL,
+ &fadump_region_fops);
if (fw_dump.dump_active) {
- rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+ rc = sysfs_create_file(fadump_kobj, &release_attr.attr);
if (rc)
- printk(KERN_ERR "fadump: unable to create sysfs file"
- " fadump_release_mem (%d)\n", rc);
+ pr_err("unable to create release_mem sysfs file (%d)\n",
+ rc);
+ }
+
+ rc = sysfs_create_groups(fadump_kobj, fadump_groups);
+ if (rc) {
+ pr_err("sysfs group creation failed (%d), unregistering FADump",
+ rc);
+ unregister_fadump();
+ return;
+ }
+
+ /*
+ * The FADump sysfs are moved from kernel_kobj to fadump_kobj need to
+ * create symlink at old location to maintain backward compatibility.
+ *
+ * - fadump_enabled -> fadump/enabled
+ * - fadump_registered -> fadump/registered
+ * - fadump_release_mem -> fadump/release_mem
+ */
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "enabled", "fadump_enabled");
+ if (rc) {
+ pr_err("unable to create fadump_enabled symlink (%d)", rc);
+ return;
+ }
+
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "registered",
+ "fadump_registered");
+ if (rc) {
+ pr_err("unable to create fadump_registered symlink (%d)", rc);
+ sysfs_remove_link(kernel_kobj, "fadump_enabled");
+ return;
+ }
+
+ if (fw_dump.dump_active) {
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj,
+ fadump_kobj,
+ "release_mem",
+ "fadump_release_mem");
+ if (rc)
+ pr_err("unable to create fadump_release_mem symlink (%d)",
+ rc);
}
return;
}
@@ -1585,16 +1621,15 @@
*/
int __init setup_fadump(void)
{
- if (!fw_dump.fadump_enabled)
+ if (!fw_dump.fadump_supported)
return 0;
- if (!fw_dump.fadump_supported) {
- printk(KERN_ERR "Firmware-assisted dump is not supported on"
- " this hardware\n");
- return 0;
- }
-
+ fadump_init_files();
fadump_show_config();
+
+ if (!fw_dump.fadump_enabled)
+ return 1;
+
/*
* If dump data is available then see if it is valid and prepare for
* saving it to the disk.
@@ -1604,14 +1639,81 @@
* 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->fadump_process(&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);
- fadump_init_files();
+ fw_dump.ops->fadump_init_mem_struct(&fw_dump);
+
+ /*
+ * In case of panic, fadump is triggered via ppc_panic_event()
+ * panic notifier. Setting crash_kexec_post_notifiers to 'true'
+ * lets panic() function take crash friendly path before panic
+ * notifiers are invoked.
+ */
+ crash_kexec_post_notifiers = true;
return 1;
}
subsys_initcall(setup_fadump);
+#else /* !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,
+ int depth, void *data)
+{
+ if ((depth != 1) || (strcmp(uname, "ibm,opal") != 0))
+ return 0;
+
+ opal_fadump_dt_scan(&fw_dump, node);
+ return 1;
+}
+
+/*
+ * 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) {
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot memory to preserve crash data.
+ */
+ pr_info("Preserving crash data for processing in next boot.\n");
+ fadump_reserve_crash_area(fw_dump.boot_mem_top);
+ } else
+ pr_debug("FADump-aware kernel..\n");
+
+ return 1;
+}
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
+/* Preserve everything above the base address */
+static void __init fadump_reserve_crash_area(u64 base)
+{
+ u64 i, mstart, mend, msize;
+
+ for_each_mem_range(i, &mstart, &mend) {
+ msize = mend - mstart;
+
+ if ((mstart + msize) < base)
+ continue;
+
+ if (mstart < base) {
+ msize -= (base - mstart);
+ mstart = base;
+ }
+
+ pr_info("Reserving %lluMB of memory at %#016llx 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;
+}
--
Gitblit v1.6.2