[RFC PATCH v7 08/10] fadump: Invalidate registration and release reserved memory for general use.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]


From: Mahesh Salgaonkar <mahesh@xxxxxxxxxxxxxxxxxx>

This patch introduces an sysfs interface '/sys/kernel/fadump_release_mem' to
invalidate the last fadump registration, invalidate '/proc/vmcore', release
the reserved memory for general use and re-register for future kernel dump.
Once the dump is copied to the disk, unlike phyp dump, the userspace tool
can release all the memory reserved for dump with one single operation of
echo 1 to '/sys/kernel/fadump_release_mem'.

Release the reserved memory region excluding the size of the memory required
for future kernel dump registration. And therefore, unlike kdump, Fadump
doesn't need a 2nd reboot to get back the system to the production
configuration.

Signed-off-by: Mahesh Salgaonkar <mahesh@xxxxxxxxxxxxxxxxxx>
---
 arch/powerpc/include/asm/fadump.h |    3 +
 arch/powerpc/kernel/fadump.c      |  158 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 157 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 6768195..88dbf96 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -208,6 +208,9 @@ extern int fadump_reserve_mem(void);
 extern int setup_fadump(void);
 extern int is_fadump_active(void);
 extern void crash_fadump(struct pt_regs *, const char *);
+extern void fadump_cleanup(void);
+
+extern void vmcore_cleanup(void);
 #else	/* CONFIG_FA_DUMP */
 static inline int is_fadump_active(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 5689954..8874d6b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,8 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
 
 #include <asm/page.h>
 #include <asm/prom.h>
@@ -984,6 +986,132 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
 	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) {
+		printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
+			"rgistration. unexpected error(%d).\n", rc);
+		return rc;
+	}
+	fw_dump.dump_active = 0;
+	fdm_active = NULL;
+	return 0;
+}
+
+void fadump_cleanup(void)
+{
+	/* Invalidate the registration only if dump is active. */
+	if (fw_dump.dump_active) {
+		init_fadump_mem_struct(&fdm,
+			fdm_active->cpu_state_data.destination_address);
+		fadump_invalidate_dump(&fdm);
+	}
+}
+
+/*
+ * Release the memory that was reserved in early boot to preserve the memory
+ * contents. The released memory will be available for general use.
+ */
+static void fadump_release_memory(unsigned long begin, unsigned long end)
+{
+	unsigned long addr;
+	unsigned long ra_start, ra_end;
+
+	ra_start = fw_dump.reserve_dump_area_start;
+	ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
+		/*
+		 * exclude the dump reserve area. Will reuse it for next
+		 * fadump registration.
+		 */
+		if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
+			continue;
+
+		ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+		init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+		free_page((unsigned long)__va(addr));
+		totalram_pages++;
+	}
+}
+
+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 = 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(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);
+}
+
+static ssize_t fadump_release_memory_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count)
+{
+	if (!fw_dump.dump_active)
+		return -EPERM;
+
+	if (buf[0] == '1') {
+		/*
+		 * Take away the '/proc/vmcore'. We are releasing the dump
+		 * memory, hence it will not be valid anymore.
+		 */
+		vmcore_cleanup();
+		fadump_invalidate_release_mem();
+
+	} else
+		return -EINVAL;
+	return count;
+}
+
 static ssize_t fadump_enabled_show(struct kobject *kobj,
 					struct kobj_attribute *attr,
 					char *buf)
@@ -1043,10 +1171,13 @@ static int fadump_region_show(struct seq_file *m, void *private)
 	if (!fw_dump.fadump_enabled)
 		return 0;
 
+	mutex_lock(&fadump_mutex);
 	if (fdm_active)
 		fdm_ptr = fdm_active;
-	else
+	else {
+		mutex_unlock(&fadump_mutex);
 		fdm_ptr = &fdm;
+	}
 
 	seq_printf(m,
 			"CPU : [%#016llx-%#016llx] %#llx bytes, "
@@ -1076,7 +1207,7 @@ static int fadump_region_show(struct seq_file *m, void *private)
 	if (!fdm_active ||
 		(fw_dump.reserve_dump_area_start ==
 		fdm_ptr->cpu_state_data.destination_address))
-		return 0;
+		goto out;
 
 	/* Dump is active. Show reserved memory region. */
 	seq_printf(m,
@@ -1088,9 +1219,15 @@ static int fadump_region_show(struct seq_file *m, void *private)
 			fw_dump.reserve_dump_area_start,
 			fdm_ptr->cpu_state_data.destination_address -
 			fw_dump.reserve_dump_area_start);
+out:
+	if (fdm_active)
+		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);
@@ -1131,6 +1268,13 @@ static void fadump_init_files(void)
 	if (!debugfs_file)
 		printk(KERN_ERR "fadump: unable to create debugfs file"
 				" fadump_region\n");
+
+	if (fw_dump.dump_active) {
+		rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+		if (rc)
+			printk(KERN_ERR "fadump: unable to create sysfs file"
+				" fadump_release_mem (%d)\n", rc);
+	}
 	return;
 }
 
@@ -1150,8 +1294,14 @@ int __init setup_fadump(void)
 	 * If dump data is available then see if it is valid and prepare for
 	 * saving it to the disk.
 	 */
-	if (fw_dump.dump_active)
-		process_fadump(fdm_active);
+	if (fw_dump.dump_active) {
+		/*
+		 * if dump process fails then invalidate the registration
+		 * and release memory before proceeding for re-registration.
+		 */
+		if (process_fadump(fdm_active) < 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);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/


[Other Archives]     [Linux Kernel Newbies]     [Linux Driver Development]     [Fedora Kernel]     [Linux Kernel Testers]     [Linux SH]     [Linux Omap]     [Linux Kbuild]     [Linux Tape]     [Linux Input]     [Linux Kernel Janitors]     [Linux Kernel Packagers]     [Linux Doc]     [Linux Man Pages]     [Linux API]     [Linux Memory Management]     [Linux Modules]     [Linux Standards]     [Kernel Announce]     [Netdev]     [Git]     [Linux PCI]     Linux CAN Development     [Linux I2C]     [Linux RDMA]     [Linux NUMA]     [Netfilter]     [Netfilter Devel]     [SELinux]     [Bugtraq]     [FIO]     [Linux Perf Users]     [Linux Serial]     [Linux PPP]     [Linux ISDN]     [Linux Next]     [Kernel Stable Commits]     [Linux Tip Commits]     [Kernel MM Commits]     [Linux Security Module]     [Filesystem Development]     [Ext3 Filesystem]     [Linux bcache]     [Ext4 Filesystem]     [Linux BTRFS]     [Linux CEPH Filesystem]     [Linux XFS]     [XFS]     [Linux NFS]     [Linux CIFS]     [Ecryptfs]     [Linux NILFS]     [Linux Cachefs]     [Reiser FS]     [Initramfs]     [Linux FB Devel]     [Linux OpenGL]     [DRI Devel]     [Fastboot]     [Linux RT Users]     [Linux RT Stable]     [eCos]     [Corosync]     [Linux Clusters]     [LVS Devel]     [Hot Plug]     [Linux Virtualization]     [KVM]     [KVM PPC]     [KVM ia64]     [Linux Containers]     [Linux Hexagon]     [Linux Cgroups]     [Util Linux]     [Wireless]     [Linux Bluetooth]     [Bluez Devel]     [Ethernet Bridging]     [Embedded Linux]     [Barebox]     [Linux MMC]     [Linux IIO]     [Sparse]     [Smatch]     [Linux Arch]     [x86 Platform Driver]     [Linux ACPI]     [Linux IBM ACPI]     [LM Sensors]     [CPU Freq]     [Linux Power Management]     [Linmodems]     [Linux DCCP]     [Linux SCTP]     [ALSA Devel]     [Linux USB]     [Linux PA RISC]     [Linux Samsung SOC]     [MIPS Linux]     [IBM S/390 Linux]     [ARM Linux]     [ARM Kernel]     [ARM MSM]     [Tegra Devel]     [Sparc Linux]     [Linux Security]     [Linux Sound]     [Linux Media]     [Video 4 Linux]     [Linux IRDA Users]     [Linux for the blind]     [Linux RAID]     [Linux ATA RAID]     [Device Mapper]     [Linux SCSI]     [SCSI Target Devel]     [Linux SCSI Target Infrastructure]     [Linux IDE]     [Linux SMP]     [Linux AXP]     [Linux Alpha]     [Linux M68K]     [Linux ia64]     [Linux 8086]     [Linux x86_64]     [Linux Config]     [Linux Apps]     [Linux MSDOS]     [Linux X.25]     [Linux Crypto]     [DM Crypt]     [Linux Trace Users]     [Linux Btrace]     [Linux Watchdog]     [Utrace Devel]     [Linux C Programming]     [Linux Assembly]     [Dash]     [DWARVES]     [Hail Devel]     [Linux Kernel Debugger]     [Linux gcc]     [Gcc Help]     [X.Org]     [Wine]

Add to Google Powered by Linux

[Older Kernel Discussion]     [Yosemite National Park Forum]     [Large Format Photos]     [Gimp]     [Yosemite Photos]     [Stuff]