openpower/linux/0004-powerpc-fadump-add-support-to-preserve-crash-data-on.patch

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Wed, 9 Oct 2019 10:45:34 +0530
Subject: [PATCH 4/8] powerpc/fadump: add support to preserve crash data on
 FADUMP disabled kernel

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.

As OPAL allows registering address with it in the first kernel and
retrieving it after MPIPL, use it to store the top of boot memory.
A kernel that intends to preserve crash data retrieves it and avoids
using memory beyond this address.

Move arch_reserved_kernel_pages() function as it is needed for both
FA_DUMP and PRESERVE_FA_DUMP configurations.

This is the backport of upstream commit bec53196adf4 ("powerpc/fadump:
add support to preserve crash data on FADUMP disabled kernel").

Also, OPAL FADump metadata definition from upstream commit 742a265accd3
("powerpc/fadump: register kernel metadata address with opal") is
backported here for completeness.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Joel Stanley <joel@jms.id.au>
---
 arch/powerpc/Kconfig              |   9 +++
 arch/powerpc/include/asm/fadump.h |  17 ++++-
 arch/powerpc/kernel/Makefile      |   4 +-
 arch/powerpc/kernel/fadump.c      | 123 ++++++++++++++++++++++++++++--
 arch/powerpc/kernel/prom.c        |   4 +-
 5 files changed, 146 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d8dcd8820369..a286c203e732 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -579,6 +579,15 @@ config FA_DUMP
 
 	  If unsure, say "N"
 
+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 17d9b6acaf63..0401a6ffde0c 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -193,9 +193,6 @@ struct fad_crash_memory_ranges {
 };
 
 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);
@@ -208,4 +205,18 @@ 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
+
+#ifdef CONFIG_PRESERVE_FA_DUMP
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	u64	boot_mem_top;
+	u64	dump_active;
+};
+#endif
+
+#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
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 56dfa7a2a6f2..ce70e7776cfd 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -78,7 +78,9 @@ 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
+ifneq ($(CONFIG_FA_DUMP)$(CONFIG_PRESERVE_FA_DUMP),)
+obj-y				+= 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 4dacce3fac72..1202dadf1d58 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -24,11 +24,13 @@
 #include <linux/slab.h>
 #include <linux/cma.h>
 #include <linux/hugetlb.h>
+#include <linux/libfdt.h>
 
 #include <asm/debugfs.h>
 #include <asm/page.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
+#include <asm/opal.h>
 #include <asm/fadump.h>
 #include <asm/setup.h>
 
@@ -36,6 +38,7 @@ static struct fw_dump fw_dump;
 
 static void __init fadump_reserve_crash_area(u64 base);
 
+#ifndef CONFIG_PRESERVE_FA_DUMP
 static struct fadump_mem_struct fdm;
 static const struct fadump_mem_struct *fdm_active;
 #ifdef CONFIG_CMA
@@ -542,11 +545,6 @@ int __init fadump_reserve_mem(void)
 	return 1;
 }
 
-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)
 {
@@ -1684,6 +1682,116 @@ int __init setup_fadump(void)
 	return 1;
 }
 subsys_initcall(setup_fadump);
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+
+/* Maximum number of memory regions kernel supports */
+#define OPAL_FADUMP_MAX_MEM_REGS		128
+
+/*
+ * OPAL FADump kernel metadata
+ *
+ * The address of this structure will be registered with f/w for retrieving
+ * and processing during crash dump.
+ */
+struct opal_fadump_mem_struct {
+	u8	version;
+	u8	reserved[3];
+	u16	region_cnt;             /* number of regions */
+	u16	registered_regions;     /* Regions registered for MPIPL */
+	u64	fadumphdr_addr;
+	struct opal_mpipl_region	rgn[OPAL_FADUMP_MAX_MEM_REGS];
+} __packed;
+
+
+/*
+ * 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.
+ */
+void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
+{
+	const struct opal_fadump_mem_struct *opal_fdm_active;
+	const __be32 *prop;
+	unsigned long dn;
+	u64 addr = 0;
+	s64 ret;
+
+	dn = of_get_flat_dt_subnode_by_name(node, "dump");
+	if (dn == -FDT_ERR_NOTFOUND)
+		return;
+
+	/*
+	 * Check if dump has been initiated on last reboot.
+	 */
+	prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL);
+	if (!prop)
+		return;
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_debug("Could not get Kernel metadata (%lld)\n", ret);
+		return;
+	}
+
+	/*
+	 * Preserve memory only if kernel memory regions are registered
+	 * with f/w for MPIPL.
+	 */
+	addr = be64_to_cpu(addr);
+	pr_debug("Kernel metadata addr: %llx\n", addr);
+	opal_fdm_active = (void *)addr;
+	if (opal_fdm_active->registered_regions == 0)
+		return;
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_BOOT_MEM, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_err("Failed to get boot memory tag (%lld)\n", ret);
+		return;
+	}
+
+	/*
+	 * Memory below this address can be used for booting a
+	 * capture kernel or petitboot kernel. Preserve everything
+	 * above this address for processing crashdump.
+	 */
+	fadump_conf->boot_mem_top = be64_to_cpu(addr);
+	pr_debug("Preserve everything above %llx\n", fadump_conf->boot_mem_top);
+
+	pr_info("Firmware-assisted dump is active.\n");
+	fadump_conf->dump_active = 1;
+}
+
+/* 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)
@@ -1708,3 +1816,8 @@ static void __init fadump_reserve_crash_area(u64 base)
 		memblock_reserve(mstart, msize);
 	}
 }
+
+unsigned long __init arch_reserved_kernel_pages(void)
+{
+	return memblock_reserved_size() / PAGE_SIZE;
+}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 7159e791a70d..9c3861bda216 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -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.