[PATCH net-next v3 1/3] vmcore: add API to collect hardware dump in second kernel

[Rahul Lakkireddy]

The sequence of actions done by device drivers to append their device
specific hardware/firmware logs to /proc/vmcore are as follows:

1. During probe (before hardware is initialized), device drivers
register to the vmcore module (via vmcore_add_device_dump()), with
callback function, along with buffer size and log name needed for
firmware/hardware log collection.

2. vmcore module allocates the buffer with requested size. It adds
an Elf note and invokes the device driver's registered callback
function.

3. Device driver collects all hardware/firmware logs into the buffer
and returns control back to vmcore module.

Ensure that the device dump buffer size is always aligned to page size
so that it can be mmaped.

Also, rename alloc_elfnotes_buf() to vmcore_alloc_buf() to make it more
generic and reserve NT_VMCOREDD note type to indicate vmcore device
dump.

Suggested-by: Eric Biederman <ebiederm@xxxxxxxxxxxx>.
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@xxxxxxxxxxx>
Signed-off-by: Ganesh Goudar <ganeshgr@xxxxxxxxxxx>
---
v3:
- Dropped sysfs crashdd module.
- Added CONFIG_PROC_VMCORE_DEVICE_DUMP to allow configuring device
  dump support.
- Moved logic related to adding dumps from crashdd to vmcore module.
- Rename all crashdd* to vmcoredd*.

v2:
- Added ABI Documentation for crashdd.
- Directly use octal permission instead of macro.

Changes since rfc v2:
- Moved exporting crashdd from procfs to sysfs.  Suggested by
  Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx>
- Moved code from fs/proc/crashdd.c to fs/crashdd/ directory.
- Replaced all proc API with sysfs API and updated comments.
- Calling driver callback before creating the binary file under
  crashdd sysfs.
- Changed binary dump file permission from S_IRUSR to S_IRUGO.
- Changed module name from CRASH_DRIVER_DUMP to CRASH_DEVICE_DUMP.

rfc v2:
- Collecting logs in 2nd kernel instead of during kernel panic.
  Suggested by Eric Biederman <ebiederm@xxxxxxxxxxxx>.
- Patch added in this series.

 fs/proc/Kconfig            |  10 +++
 fs/proc/vmcore.c           | 156 ++++++++++++++++++++++++++++++++++++++++++---
 include/linux/crash_core.h |   4 ++
 include/linux/crash_dump.h |  10 +++
 include/linux/kcore.h      |   6 ++
 include/uapi/linux/elf.h   |   1 +
 6 files changed, 178 insertions(+), 9 deletions(-)

diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 1ade1206bb89..c31e8944592e 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -43,6 +43,16 @@ config PROC_VMCORE
         help
         Exports the dump image of crashed kernel in ELF format.
 
+config PROC_VMCORE_DEVICE_DUMP
+	bool "Device Hardware/Firmware Log Collection"
+	depends on PROC_VMCORE
+	default y
+	---help---
+	  Device drivers can collect the device specific snapshot of
+	  their hardware or firmware before they are initialized in
+	  crash recovery kernel. If you say Y here, the device dumps
+	  will be added as ELF notes to /proc/vmcore
+
 config PROC_SYSCTL
 	bool "Sysctl support (/proc/sys)" if EXPERT
 	depends on PROC_FS
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a45f0af22a60..b53698f22362 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/crash_dump.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
@@ -44,6 +45,12 @@ static u64 vmcore_size;
 
 static struct proc_dir_entry *proc_vmcore;
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+/* Device Dump list and mutex to synchronize access to list */
+static LIST_HEAD(vmcoredd_list);
+static DEFINE_MUTEX(vmcoredd_mutex);
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
 /*
  * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
  * The called function has to take care of module refcounting.
@@ -302,10 +309,8 @@ static const struct vm_operations_struct vmcore_mmap_ops = {
 };
 
 /**
- * alloc_elfnotes_buf - allocate buffer for ELF note segment in
- *                      vmalloc memory
- *
- * @notes_sz: size of buffer
+ * vmcore_alloc_buf - allocate buffer in vmalloc memory
+ * @sizez: size of buffer
  *
  * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
  * the buffer to user-space by means of remap_vmalloc_range().
@@ -313,12 +318,12 @@ static const struct vm_operations_struct vmcore_mmap_ops = {
  * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
  * disabled and there's no need to allow users to mmap the buffer.
  */
-static inline char *alloc_elfnotes_buf(size_t notes_sz)
+static inline char *vmcore_alloc_buf(size_t size)
 {
 #ifdef CONFIG_MMU
-	return vmalloc_user(notes_sz);
+	return vmalloc_user(size);
 #else
-	return vzalloc(notes_sz);
+	return vzalloc(size);
 #endif
 }
 
@@ -665,7 +670,7 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 		return rc;
 
 	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
-	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	*notes_buf = vmcore_alloc_buf(*notes_sz);
 	if (!*notes_buf)
 		return -ENOMEM;
 
@@ -851,7 +856,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 		return rc;
 
 	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
-	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	*notes_buf = vmcore_alloc_buf(*notes_sz);
 	if (!*notes_buf)
 		return -ENOMEM;
 
@@ -1145,6 +1150,136 @@ static int __init parse_crash_elf_headers(void)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+/**
+ * vmcoredd_get_note_size - Get size of the note that will be inserted at
+ * beginning of the dump's buffer.
+ * @name: Note's name
+ *
+ * Gets the overall size of the note that will be inserted at the beginning
+ * of the dump's buffer.  It also adds padding, if necessary to meet
+ * alignment requirements.
+ */
+static inline size_t vmcoredd_get_note_size(const char *name)
+{
+	return CRASH_CORE_NOTE_HEAD_BYTES +
+	       ALIGN(VMCOREDD_NOTE_NAME_BYTES + strlen(name), sizeof(Elf_Word));
+}
+
+/**
+ * vmcoredd_write_note - Write note at the beginning of the dump's buffer
+ * @name: Dump's name
+ * @buf: Output buffer where the note is written
+ * @size: Size of the dump
+ *
+ * Fills beginning of the dump's data with elf note.
+ */
+static void vmcoredd_write_note(const char *name, void *buf, size_t size)
+{
+	struct elf_note *note = (struct elf_note *)buf;
+	Elf_Word *word = (Elf_Word *)note;
+
+	note->n_namesz = ALIGN(VMCOREDD_NOTE_NAME_BYTES + strlen(name),
+			       sizeof(Elf_Word));
+	note->n_descsz = size;
+	note->n_type = NT_VMCOREDD;
+	word += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word));
+	snprintf((char *)word, note->n_namesz, "%s_%s", VMCOREDD_NOTE_NAME,
+		 name);
+}
+
+/**
+ * vmcore_add_device_dump - Add a buffer containing device dump to vmcore
+ * @data: dump info.
+ *
+ * Allocate a buffer and invoke the calling driver's dump collect routine.
+ * Write Elf note at the beginning of the buffer to indicate vmcore device
+ * dump and add the dump to global list.
+ */
+int __vmcore_add_device_dump(struct vmcoredd_data *data)
+{
+	size_t note_size, data_size;
+	struct vmcoredd_node *dump;
+	void *buf = NULL;
+	int ret;
+
+	if (!data || !strlen(data->name) ||
+	    !data->vmcoredd_callback || !data->size)
+		return -EINVAL;
+
+	dump = vzalloc(sizeof(*dump));
+	if (!dump) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	note_size = vmcoredd_get_note_size(data->name);
+	/* Keep size of the buffer page aligned so that it can be mmaped */
+	data_size = roundup(note_size + data->size, PAGE_SIZE);
+
+	/* Allocate buffer for driver's to write their dumps */
+	buf = vmcore_alloc_buf(data_size);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	vmcoredd_write_note(data->name, buf, data_size - note_size);
+
+	/* Invoke the driver's dump collection routing */
+	ret = data->vmcoredd_callback(data, buf + note_size);
+	if (ret)
+		goto out_err;
+
+	dump->buf = buf;
+	dump->size = data_size;
+
+	/* Add the dump to driver sysfs list */
+	mutex_lock(&vmcoredd_mutex);
+	list_add_tail(&dump->list, &vmcoredd_list);
+	mutex_unlock(&vmcoredd_mutex);
+
+	return 0;
+
+out_err:
+	if (buf)
+		vfree(buf);
+
+	if (dump)
+		vfree(dump);
+
+	return ret;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+int vmcore_add_device_dump(struct vmcoredd_data *data)
+{
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+	return __vmcore_add_device_dump(data);
+#else
+	return -EOPNOTSUPP;
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+}
+EXPORT_SYMBOL(vmcore_add_device_dump);
+
+/* Free all dumps in vmcore device dump list */
+static void vmcore_free_device_dumps(void)
+{
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+	mutex_lock(&vmcoredd_mutex);
+	while (!list_empty(&vmcoredd_list)) {
+		struct vmcoredd_node *dump;
+
+		dump = list_first_entry(&vmcoredd_list, struct vmcoredd_node,
+					list);
+		list_del(&dump->list);
+		vfree(dump->buf);
+		vfree(dump);
+	}
+	mutex_unlock(&vmcoredd_mutex);
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+}
+
 /* Init function for vmcore module. */
 static int __init vmcore_init(void)
 {
@@ -1192,4 +1327,7 @@ void vmcore_cleanup(void)
 		kfree(m);
 	}
 	free_elfcorebuf();
+
+	/* clear vmcore device dump list */
+	vmcore_free_device_dumps();
 }
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index b511f6d24b42..3b6b041d84c8 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -27,6 +27,10 @@
 				     VMCOREINFO_NOTE_NAME_BYTES +	\
 				     VMCOREINFO_BYTES)
 
+#define VMCOREDD_MAX_NAME_BYTES  32
+#define VMCOREDD_NOTE_NAME	 "VMCOREDD"
+#define VMCOREDD_NOTE_NAME_BYTES sizeof(VMCOREDD_NOTE_NAME)
+
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
 
 void crash_update_vmcoreinfo_safecopy(void *ptr);
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index f7ac2aa93269..4e617da654a3 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -93,4 +93,14 @@ static inline bool is_kdump_kernel(void) { return 0; }
 #endif /* CONFIG_CRASH_DUMP */
 
 extern unsigned long saved_max_pfn;
+
+/* Device Dump information to be filled by drivers */
+struct vmcoredd_data {
+	char name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */
+	unsigned long size;                 /* Size of the dump */
+	/* Driver's registered callback to be invoked to collect dump */
+	int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf);
+};
+
+int vmcore_add_device_dump(struct vmcoredd_data *data);
 #endif /* LINUX_CRASHDUMP_H */
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index 80db19d3a505..aa26e7199060 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -28,6 +28,12 @@ struct vmcore {
 	loff_t offset;
 };
 
+struct vmcoredd_node {
+	struct list_head list;	/* List of dumps */
+	void *buf;		/* Buffer containing device's dump */
+	unsigned long size;	/* Size of the buffer */
+};
+
 #ifdef CONFIG_PROC_KCORE
 extern void kclist_add(struct kcore_list *, void *, size_t, int type);
 #else
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 3bf73fb58045..05015d29ad8e 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -424,6 +424,7 @@ typedef struct elf64_shdr {
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
+#define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
-- 
2.14.1