@@ -571,6 +571,15 @@ 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
@@ -14,9 +14,6 @@
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);
@@ -29,4 +26,10 @@ static inline int should_fadump_crash(void) { return 0; }
static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
static inline void fadump_cleanup(void) { }
#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__ */
@@ -77,7 +77,11 @@ 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-common.o
+ifeq ($(CONFIG_FA_DUMP),y)
+obj-y += fadump.o fadump-common.o
+else
+obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o
+endif
ifdef CONFIG_PPC32
obj-$(CONFIG_E500) += idle_e500.o
endif
@@ -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);
ulong (*get_kernel_metadata_size)(void);
@@ -182,8 +187,9 @@ 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
@@ -35,6 +35,7 @@
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;
@@ -205,6 +206,9 @@ 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,
@@ -226,6 +230,7 @@ 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.
@@ -479,6 +484,7 @@ 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)
@@ -497,12 +503,45 @@ 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;
@@ -631,11 +670,6 @@ 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)
{
@@ -1396,3 +1430,4 @@ int __init setup_fadump(void)
return 1;
}
subsys_initcall(setup_fadump);
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
@@ -704,7 +704,7 @@ 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
@@ -731,7 +731,7 @@ 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.
@@ -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
@@ -29,8 +29,10 @@
#include "opal-fadump.h"
static const struct opal_fadump_mem_struct *opal_fdm_active;
+#ifndef CONFIG_PRESERVE_FA_DUMP
static const struct opal_mpipl_fadump *opal_cpu_metadata;
static struct opal_fadump_mem_struct *opal_fdm;
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
static void opal_set_preserv_area_start(struct fw_dump *fadump_conf)
{
@@ -89,6 +91,62 @@ static void update_fadump_config(struct fw_dump *fadump_conf,
opal_set_preserv_area_start(fadump_conf);
}
+/*
+ * 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;
+ const __be32 *prop;
+
+ 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.
+ */
+ prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL);
+ if (prop) {
+ u8 type;
+ u32 idx = 0;
+ u64 addr = 0;
+ s64 ret;
+
+ do {
+ ret = opal_mpipl_query_tag(idx, &addr);
+ if (ret != OPAL_SUCCESS)
+ break;
+
+ addr = be64_to_cpu(addr);
+ type = *((u8 *)addr);
+ switch (type) {
+ case MPIPL_FADUMP_TYPE_KERNEL:
+ opal_fdm_active = __va(addr);
+ break;
+ }
+
+ idx++;
+ } while (ret == OPAL_SUCCESS);
+
+ if (opal_fdm_active == NULL) {
+ pr_err("kernel metadata not found!\n");
+ return 1;
+ }
+
+ pr_info("Firmware-assisted dump is active.\n");
+ fadump_conf->dump_active = 1;
+ update_fadump_config(fadump_conf,
+ (void *)__pa(opal_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;
@@ -614,3 +672,4 @@ int __init opal_dt_scan_fadump(struct fw_dump *fadump_conf, ulong node)
return 1;
}
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
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-common.h | 8 +++- arch/powerpc/kernel/fadump.c | 47 ++++++++++++++++++--- arch/powerpc/kernel/prom.c | 4 +- arch/powerpc/platforms/powernv/Makefile | 1 arch/powerpc/platforms/powernv/opal-fadump.c | 59 ++++++++++++++++++++++++++ 8 files changed, 130 insertions(+), 13 deletions(-)