LinuxPPC-Dev Archive on lore.kernel.org
 help / color / Atom feed
From: Hari Bathini <hbathini@linux.ibm.com>
To: linuxppc-dev <linuxppc-dev@ozlabs.org>
Cc: Ananth N Mavinakayanahalli <ananth@linux.ibm.com>,
	Mahesh J Salgaonkar <mahesh@linux.ibm.com>,
	Vasant Hegde <hegdevasant@linux.ibm.com>,
	Oliver <oohall@gmail.com>, Nicholas Piggin <npiggin@gmail.com>,
	Daniel Axtens <dja@axtens.net>
Subject: [PATCH v5 25/31] powernv/fadump: add support to preserve crash data on FADUMP disabled kernel
Date: Tue, 20 Aug 2019 17:37:12 +0530
Message-ID: <156630283293.8896.17685034018378110649.stgit@hbathini.in.ibm.com> (raw)
In-Reply-To: <156630261682.8896.3418665808003586786.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.

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.

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          |   11 ++++
 arch/powerpc/kernel/fadump.c                 |   43 +++++++++++++--
 arch/powerpc/kernel/prom.c                   |    4 +
 arch/powerpc/platforms/powernv/Makefile      |    1 
 arch/powerpc/platforms/powernv/opal-fadump.c |   76 ++++++++++++++++++++++++++
 8 files changed, 148 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fc4ecfe..2be9b96 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -580,6 +580,15 @@ 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 e608d34..fd990d8 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -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__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 439d548..6abaead 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -78,7 +78,11 @@ 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
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index d1ff5b2..ba8481b 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -12,6 +12,7 @@
 #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
@@ -157,6 +158,16 @@ void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
 int is_fadump_boot_mem_contiguous(struct fw_dump *fadump_conf);
 int is_fadump_reserved_mem_contiguous(struct fw_dump *fadump_conf);
 
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	unsigned long	boot_mem_top;
+	unsigned long	dump_active;
+};
+
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
 #ifdef CONFIG_PPC_PSERIES
 extern int rtas_fadump_dt_scan(struct fw_dump *fadump_config, ulong node);
 #else
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 665104a..43038f5 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -37,6 +37,7 @@ static struct fw_dump fw_dump;
 
 static void __init fadump_reserve_crash_area(unsigned long base);
 
+#ifndef CONFIG_PRESERVE_FA_DUMP
 static DEFINE_MUTEX(fadump_mutex);
 struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 };
 struct fadump_mrange_info reserved_mrange_info = { "reserved", NULL, 0, 0, 0 };
@@ -384,11 +385,6 @@ 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)
 {
@@ -1221,6 +1217,38 @@ int __init setup_fadump(void)
 	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;
+
+	return opal_fadump_dt_scan(&fw_dump, node);
+}
+
+/*
+ * 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(PAGE_ALIGN(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(unsigned long base)
@@ -1245,3 +1273,8 @@ static void __init fadump_reserve_crash_area(unsigned long 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 7159e79..9c3861bd 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.
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 43a6e1c..b4a8022 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 9a32a7f..85a89c0 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -22,6 +22,70 @@
 #include "../../kernel/fadump-common.h"
 #include "opal-fadump.h"
 
+
+#ifdef CONFIG_PRESERVE_FA_DUMP
+/*
+ * 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.
+ */
+int __init opal_fadump_dt_scan(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) {
+		u64 addr = 0;
+		s64 ret;
+		const struct opal_fadump_mem_struct *r_opal_fdm_active;
+
+		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 1;
+		}
+
+		/*
+		 * 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);
+		r_opal_fdm_active = (void *)addr;
+		if (r_opal_fdm_active->registered_regions == 0)
+			return 1;
+
+		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 1;
+		}
+
+		/*
+		 * Anything 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 %lx\n",
+			 fadump_conf->boot_mem_top);
+
+		pr_info("Firmware-assisted dump is active.\n");
+		fadump_conf->dump_active = 1;
+	}
+
+	return 1;
+}
+
+#else /* CONFIG_PRESERVE_FA_DUMP */
 static const struct opal_fadump_mem_struct *opal_fdm_active;
 static const struct opal_mpipl_fadump *opal_cpu_metadata;
 static struct opal_fadump_mem_struct *opal_fdm;
@@ -189,6 +253,17 @@ static int opal_fadump_setup_metadata(struct fw_dump *fadump_conf)
 		err = -EPERM;
 	}
 
+	/*
+	 * Register boot memory top address with f/w. Should be retrieved
+	 * by a kernel that intends to preserve crash'ed kernel's memory.
+	 */
+	ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_BOOT_MEM,
+				      fadump_conf->boot_memory_size);
+	if (ret != OPAL_SUCCESS) {
+		pr_err("Failed to set boot memory tag!\n");
+		err = -EPERM;
+	}
+
 	return err;
 }
 
@@ -654,3 +729,4 @@ int __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
 
 	return 1;
 }
+#endif /* !CONFIG_PRESERVE_FA_DUMP */


  parent reply index

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-20 12:04 [PATCH v5 00/31] Add FADump support on PowerNV platform Hari Bathini
2019-08-20 12:04 ` [PATCH v5 01/31] powerpc/fadump: move internal macros/definitions to a new header Hari Bathini
2019-09-03 11:09   ` Michael Ellerman
2019-09-03 16:05     ` Hari Bathini
2019-08-20 12:04 ` [PATCH v5 02/31] powerpc/fadump: move internal code to a new file Hari Bathini
2019-09-03 11:09   ` Michael Ellerman
2019-09-03 16:05     ` Hari Bathini
2019-09-04  9:02       ` Mahesh Jagannath Salgaonkar
2019-09-04 18:26         ` Hari Bathini
2019-08-20 12:04 ` [PATCH v5 03/31] powerpc/fadump: Improve fadump documentation Hari Bathini
2019-08-20 12:04 ` [PATCH v5 04/31] pseries/fadump: move rtas specific definitions to platform code Hari Bathini
2019-08-20 12:04 ` [PATCH v5 05/31] pseries/fadump: introduce callbacks for platform specific operations Hari Bathini
2019-09-03 11:10   ` Michael Ellerman
2019-09-03 16:06     ` Hari Bathini
2019-09-06  6:39       ` Hari Bathini
2019-08-20 12:04 ` [PATCH v5 06/31] pseries/fadump: define register/un-register callback functions Hari Bathini
2019-09-03 11:10   ` Michael Ellerman
2019-09-03 17:15     ` Hari Bathini
2019-08-20 12:04 ` [PATCH v5 07/31] powerpc/fadump: release all the memory above boot memory size Hari Bathini
2019-09-03 11:10   ` Michael Ellerman
2019-09-03 16:27     ` Hari Bathini
2019-08-20 12:05 ` [PATCH v5 08/31] pseries/fadump: move out platform specific support from generic code Hari Bathini
2019-08-20 12:05 ` [PATCH v5 09/31] powerpc/fadump: use FADump instead of fadump for how it is pronounced Hari Bathini
2019-08-20 12:05 ` [PATCH v5 10/31] opal: add MPIPL interface definitions Hari Bathini
2019-09-03 11:10   ` Michael Ellerman
2019-09-03 16:28     ` Hari Bathini
2019-09-04 11:03       ` Michael Ellerman
2019-09-04 11:05   ` Michael Ellerman
2019-08-20 12:05 ` [PATCH v5 11/31] powernv/fadump: add fadump support on powernv Hari Bathini
2019-09-03 11:10   ` Michael Ellerman
2019-09-03 16:31     ` Hari Bathini
2019-09-04 14:33       ` Hari Bathini
2019-09-05  3:11         ` Michael Ellerman
2019-08-20 12:05 ` [PATCH v5 12/31] powernv/fadump: register kernel metadata address with opal Hari Bathini
2019-09-04 11:25   ` Michael Ellerman
2019-08-20 12:05 ` [PATCH v5 13/31] powernv/fadump: reset metadata address during clean up Hari Bathini
2019-08-27 12:00   ` Hari Bathini
2019-08-20 12:05 ` [PATCH v5 14/31] powernv/fadump: define register/un-register callback functions Hari Bathini
2019-09-05  4:15   ` Michael Ellerman
2019-09-05  7:23   ` Michael Ellerman
2019-09-05  9:54     ` Hari Bathini
2019-08-20 12:05 ` [PATCH v5 15/31] powernv/fadump: support copying multiple kernel boot memory regions Hari Bathini
2019-09-04 11:30   ` Michael Ellerman
2019-09-04 20:20     ` Hari Bathini
2019-09-05  3:13       ` Michael Ellerman
2019-08-20 12:06 ` [PATCH v5 16/31] powernv/fadump: process the crashdump by exporting it as /proc/vmcore Hari Bathini
2019-09-04 11:42   ` Michael Ellerman
2019-09-04 21:01     ` Hari Bathini
2019-08-20 12:06 ` [PATCH v5 17/31] powernv/fadump: Warn before processing partial crashdump Hari Bathini
2019-09-04 11:48   ` Michael Ellerman
2019-08-20 12:06 ` [PATCH v5 18/31] powernv/fadump: handle invalidation of crashdump and re-registraion Hari Bathini
2019-08-20 12:06 ` [PATCH v5 19/31] powerpc/fadump: Update documentation about OPAL platform support Hari Bathini
2019-09-04 11:51   ` Michael Ellerman
2019-09-04 12:08     ` Oliver O'Halloran
2019-09-05  3:15       ` Michael Ellerman
2019-08-20 12:06 ` [PATCH v5 20/31] powerpc/fadump: use smaller offset while finding memory for reservation Hari Bathini
2019-09-04 11:54   ` Michael Ellerman
2019-08-20 12:06 ` [PATCH v5 21/31] powernv/fadump: process architected register state data provided by firmware Hari Bathini
2019-09-04 12:20   ` Michael Ellerman
2019-09-09 13:23     ` Hari Bathini
2019-09-09 15:33       ` Oliver O'Halloran
2019-09-10  8:48         ` Hari Bathini
2019-09-10 14:05           ` Michael Ellerman
2019-09-10 16:10             ` Hari Bathini
2019-08-20 12:06 ` [PATCH v5 22/31] powerpc/fadump: make crash memory ranges array allocation generic Hari Bathini
2019-08-20 12:06 ` [PATCH v5 23/31] powerpc/fadump: consider reserved ranges while releasing memory Hari Bathini
2019-08-20 12:07 ` [PATCH v5 24/31] powerpc/fadump: improve how crashed kernel's memory is reserved Hari Bathini
2019-08-20 12:07 ` Hari Bathini [this message]
2019-08-20 12:07 ` [PATCH v5 26/31] powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP Hari Bathini
2019-08-20 12:07 ` [PATCH v5 27/31] powernv/opalcore: export /sys/firmware/opal/core for analysing opal crashes Hari Bathini
2019-08-20 12:07 ` [PATCH v5 28/31] powernv/opalcore: provide an option to invalidate /sys/firmware/opal/core file Hari Bathini
2019-08-20 12:07 ` [PATCH v5 29/31] powerpc/fadump: consider f/w load area Hari Bathini
2019-08-20 12:07 ` [PATCH v5 30/31] powernv/fadump: update documentation about option to release opalcore Hari Bathini
2019-08-20 12:07 ` [PATCH v5 31/31] powernv/fadump: support holes in kernel boot memory area Hari Bathini

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=156630283293.8896.17685034018378110649.stgit@hbathini.in.ibm.com \
    --to=hbathini@linux.ibm.com \
    --cc=ananth@linux.ibm.com \
    --cc=dja@axtens.net \
    --cc=hegdevasant@linux.ibm.com \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=mahesh@linux.ibm.com \
    --cc=npiggin@gmail.com \
    --cc=oohall@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LinuxPPC-Dev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linuxppc-dev/0 linuxppc-dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linuxppc-dev linuxppc-dev/ https://lore.kernel.org/linuxppc-dev \
		linuxppc-dev@lists.ozlabs.org linuxppc-dev@ozlabs.org linuxppc-dev@archiver.kernel.org
	public-inbox-index linuxppc-dev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.ozlabs.lists.linuxppc-dev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox