vmcore: add API to collect hardware dump in second kernel

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@xmission.com>.
Signed-off-by: NRahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fs/proc/Kconfig

@@ -43,6 +43,21 @@ 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 n
+	help
+	  After kernel panic, device drivers can collect the device
+	  specific snapshot of their hardware or firmware before the
+	  underlying devices are initialized in crash recovery kernel.
+	  Note that the device driver must be present in the crash
+	  recovery kernel's initramfs to collect its underlying device
+	  snapshot.
+
+	  If you say Y here, the collected 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

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 +1150,115 @@ static int __init parse_crash_elf_headers(void)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+/**
+ * vmcoredd_write_header - Write vmcore device dump header at the
+ * beginning of the dump's buffer.
+ * @buf: Output buffer where the note is written
+ * @data: Dump info
+ * @size: Size of the dump
+ *
+ * Fills beginning of the dump's buffer with vmcore device dump header.
+ */
+static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data,
+				  u32 size)
+{
+	struct vmcoredd_header *vdd_hdr = (struct vmcoredd_header *)buf;
+
+	vdd_hdr->n_namesz = sizeof(vdd_hdr->name);
+	vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name);
+	vdd_hdr->n_type = NT_VMCOREDD;
+
+	strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME,
+		sizeof(vdd_hdr->name));
+	memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_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)
+{
+	struct vmcoredd_node *dump;
+	void *buf = NULL;
+	size_t data_size;
+	int ret;
+
+	if (!data || !strlen(data->dump_name) ||
+	    !data->vmcoredd_callback || !data->size)
+		return -EINVAL;
+
+	dump = vzalloc(sizeof(*dump));
+	if (!dump) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	/* Keep size of the buffer page aligned so that it can be mmaped */
+	data_size = roundup(sizeof(struct vmcoredd_header) + 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_header(buf, data, data_size -
+			      sizeof(struct vmcoredd_header));
+
+	/* Invoke the driver's dump collection routing */
+	ret = data->vmcoredd_callback(data, buf +
+				      sizeof(struct vmcoredd_header));
+	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;
+}
+EXPORT_SYMBOL(vmcore_add_device_dump);
+#endif /* CONFIG_PROC_VMCORE_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 +1306,7 @@ void vmcore_cleanup(void)
 		kfree(m);
 	}
 	free_elfcorebuf();
+
+	/* clear vmcore device dump list */
+	vmcore_free_device_dumps();
 }

include/linux/crash_dump.h

@@ -5,6 +5,7 @@
 #include <linux/kexec.h>
 #include <linux/proc_fs.h>
 #include <linux/elf.h>
+#include <uapi/linux/vmcore.h>
 
 #include <asm/pgtable.h> /* for pgprot_t */
 
@@ -93,4 +94,21 @@ 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 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */
+	unsigned int size;                       /* Size of the dump */
+	/* Driver's registered callback to be invoked to collect dump */
+	int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf);
+};
+
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+int vmcore_add_device_dump(struct vmcoredd_data *data);
+#else
+static inline int vmcore_add_device_dump(struct vmcoredd_data *data)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 #endif /* LINUX_CRASHDUMP_H */

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 int size;	/* Size of the buffer */
+};
+
 #ifdef CONFIG_PROC_KCORE
 extern void kclist_add(struct kcore_list *, void *, size_t, int type);
 #else

include/uapi/linux/elf.h

@@ -421,6 +421,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
 #define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #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 {

include/uapi/linux/vmcore.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI_VMCORE_H
+#define _UAPI_VMCORE_H
+
+#include <linux/types.h>
+
+#define VMCOREDD_NOTE_NAME "LINUX"
+#define VMCOREDD_MAX_NAME_BYTES 44
+
+struct vmcoredd_header {
+	__u32 n_namesz; /* Name size */
+	__u32 n_descsz; /* Content size */
+	__u32 n_type;   /* NT_VMCOREDD */
+	__u8 name[8];   /* LINUX\0\0\0 */
+	__u8 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Device dump's name */
+};
+
+#endif /* _UAPI_VMCORE_H */