Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

4 files changed, 419 insertions, 24 deletions

diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index e065bc0768e6..1faef56b12bd 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -310,6 +310,10 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 	case -ETIME:
 		_debug("no conn");
 		goto iterate_address;
+
+	case -ECONNRESET:
+		_debug("call reset");
+		goto failed;
 	}
 
 restart_from_beginning:
diff --git a/fs/exec.c b/fs/exec.c
index 183059c427b9..30a36c2a39bf 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1706,14 +1706,13 @@ static int exec_binprm(struct linux_binprm *bprm)
 /*
  * sys_execve() executes a new program.
  */
-static int do_execveat_common(int fd, struct filename *filename,
-			      struct user_arg_ptr argv,
-			      struct user_arg_ptr envp,
-			      int flags)
+static int __do_execve_file(int fd, struct filename *filename,
+			    struct user_arg_ptr argv,
+			    struct user_arg_ptr envp,
+			    int flags, struct file *file)
 {
 	char *pathbuf = NULL;
 	struct linux_binprm *bprm;
-	struct file *file;
 	struct files_struct *displaced;
 	int retval;
 
@@ -1752,7 +1751,8 @@ static int do_execveat_common(int fd, struct filename *filename,
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	file = do_open_execat(fd, filename, flags);
+	if (!file)
+		file = do_open_execat(fd, filename, flags);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1760,7 +1760,9 @@ static int do_execveat_common(int fd, struct filename *filename,
 	sched_exec();
 
 	bprm->file = file;
-	if (fd == AT_FDCWD || filename->name[0] == '/') {
+	if (!filename) {
+		bprm->filename = "none";
+	} else if (fd == AT_FDCWD || filename->name[0] == '/') {
 		bprm->filename = filename->name;
 	} else {
 		if (filename->name[0] == '\0')
@@ -1826,7 +1828,8 @@ static int do_execveat_common(int fd, struct filename *filename,
 	task_numa_free(current);
 	free_bprm(bprm);
 	kfree(pathbuf);
-	putname(filename);
+	if (filename)
+		putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
 	return retval;
@@ -1849,10 +1852,27 @@ out_files:
 	if (displaced)
 		reset_files_struct(displaced);
 out_ret:
-	putname(filename);
+	if (filename)
+		putname(filename);
 	return retval;
 }
 
+static int do_execveat_common(int fd, struct filename *filename,
+			      struct user_arg_ptr argv,
+			      struct user_arg_ptr envp,
+			      int flags)
+{
+	return __do_execve_file(fd, filename, argv, envp, flags, NULL);
+}
+
+int do_execve_file(struct file *file, void *__argv, void *__envp)
+{
+	struct user_arg_ptr argv = { .ptr.native = __argv };
+	struct user_arg_ptr envp = { .ptr.native = __envp };
+
+	return __do_execve_file(AT_FDCWD, NULL, argv, envp, 0, file);
+}
+
 int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
 	const char __user *const __user *__envp)
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 1ade1206bb89..0eaeb41453f5 100644
--- a/fs/proc/Kconfig
+++ b/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
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a45f0af22a60..cfb6674331fd 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>
@@ -38,12 +39,23 @@ static size_t elfcorebuf_sz_orig;
 
 static char *elfnotes_buf;
 static size_t elfnotes_sz;
+/* Size of all notes minus the device dump notes */
+static size_t elfnotes_orig_sz;
 
 /* Total size of vmcore file. */
 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 */
+
+/* Device Dump Size */
+static size_t vmcoredd_orig_sz;
+
 /*
  * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
  * The called function has to take care of module refcounting.
@@ -178,6 +190,77 @@ static int copy_to(void *target, void *src, size_t size, int userbuf)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf)
+{
+	struct vmcoredd_node *dump;
+	u64 offset = 0;
+	int ret = 0;
+	size_t tsz;
+	char *buf;
+
+	mutex_lock(&vmcoredd_mutex);
+	list_for_each_entry(dump, &vmcoredd_list, list) {
+		if (start < offset + dump->size) {
+			tsz = min(offset + (u64)dump->size - start, (u64)size);
+			buf = dump->buf + start - offset;
+			if (copy_to(dst, buf, tsz, userbuf)) {
+				ret = -EFAULT;
+				goto out_unlock;
+			}
+
+			size -= tsz;
+			start += tsz;
+			dst += tsz;
+
+			/* Leave now if buffer filled already */
+			if (!size)
+				goto out_unlock;
+		}
+		offset += dump->size;
+	}
+
+out_unlock:
+	mutex_unlock(&vmcoredd_mutex);
+	return ret;
+}
+
+static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
+			       u64 start, size_t size)
+{
+	struct vmcoredd_node *dump;
+	u64 offset = 0;
+	int ret = 0;
+	size_t tsz;
+	char *buf;
+
+	mutex_lock(&vmcoredd_mutex);
+	list_for_each_entry(dump, &vmcoredd_list, list) {
+		if (start < offset + dump->size) {
+			tsz = min(offset + (u64)dump->size - start, (u64)size);
+			buf = dump->buf + start - offset;
+			if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) {
+				ret = -EFAULT;
+				goto out_unlock;
+			}
+
+			size -= tsz;
+			start += tsz;
+			dst += tsz;
+
+			/* Leave now if buffer filled already */
+			if (!size)
+				goto out_unlock;
+		}
+		offset += dump->size;
+	}
+
+out_unlock:
+	mutex_unlock(&vmcoredd_mutex);
+	return ret;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
 /* Read from the ELF header and then the crash dump. On error, negative value is
  * returned otherwise number of bytes read are returned.
  */
@@ -215,10 +298,41 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
 	if (*fpos < elfcorebuf_sz + elfnotes_sz) {
 		void *kaddr;
 
+		/* We add device dumps before other elf notes because the
+		 * other elf notes may not fill the elf notes buffer
+		 * completely and we will end up with zero-filled data
+		 * between the elf notes and the device dumps. Tools will
+		 * then try to decode this zero-filled data as valid notes
+		 * and we don't want that. Hence, adding device dumps before
+		 * the other elf notes ensure that zero-filled data can be
+		 * avoided.
+		 */
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+		/* Read device dumps */
+		if (*fpos < elfcorebuf_sz + vmcoredd_orig_sz) {
+			tsz = min(elfcorebuf_sz + vmcoredd_orig_sz -
+				  (size_t)*fpos, buflen);
+			start = *fpos - elfcorebuf_sz;
+			if (vmcoredd_copy_dumps(buffer, start, tsz, userbuf))
+				return -EFAULT;
+
+			buflen -= tsz;
+			*fpos += tsz;
+			buffer += tsz;
+			acc += tsz;
+
+			/* leave now if filled buffer already */
+			if (!buflen)
+				return acc;
+		}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+		/* Read remaining elf notes */
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
-		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
+		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz - vmcoredd_orig_sz;
 		if (copy_to(buffer, kaddr, tsz, userbuf))
 			return -EFAULT;
+
 		buflen -= tsz;
 		*fpos += tsz;
 		buffer += tsz;
@@ -302,10 +416,8 @@ 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 +425,12 @@ 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
 }
 
@@ -446,11 +558,46 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 	if (start < elfcorebuf_sz + elfnotes_sz) {
 		void *kaddr;
 
+		/* We add device dumps before other elf notes because the
+		 * other elf notes may not fill the elf notes buffer
+		 * completely and we will end up with zero-filled data
+		 * between the elf notes and the device dumps. Tools will
+		 * then try to decode this zero-filled data as valid notes
+		 * and we don't want that. Hence, adding device dumps before
+		 * the other elf notes ensure that zero-filled data can be
+		 * avoided. This also ensures that the device dumps and
+		 * other elf notes can be properly mmaped at page aligned
+		 * address.
+		 */
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+		/* Read device dumps */
+		if (start < elfcorebuf_sz + vmcoredd_orig_sz) {
+			u64 start_off;
+
+			tsz = min(elfcorebuf_sz + vmcoredd_orig_sz -
+				  (size_t)start, size);
+			start_off = start - elfcorebuf_sz;
+			if (vmcoredd_mmap_dumps(vma, vma->vm_start + len,
+						start_off, tsz))
+				goto fail;
+
+			size -= tsz;
+			start += tsz;
+			len += tsz;
+
+			/* leave now if filled buffer already */
+			if (!size)
+				return 0;
+		}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+		/* Read remaining elf notes */
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
-		kaddr = elfnotes_buf + start - elfcorebuf_sz;
+		kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz;
 		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
 						kaddr, tsz))
 			goto fail;
+
 		size -= tsz;
 		start += tsz;
 		len += tsz;
@@ -502,8 +649,8 @@ static struct vmcore* __init get_new_element(void)
 	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
 }
 
-static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
-				  struct list_head *vc_list)
+static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
+			   struct list_head *vc_list)
 {
 	u64 size;
 	struct vmcore *m;
@@ -665,7 +812,7 @@ 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;
 
@@ -698,6 +845,11 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 	/* Modify e_phnum to reflect merged headers. */
 	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
 
+	/* Store the size of all notes.  We need this to update the note
+	 * header when the device dumps will be added.
+	 */
+	elfnotes_orig_sz = phdr.p_memsz;
+
 	return 0;
 }
 
@@ -851,7 +1003,7 @@ 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;
 
@@ -884,6 +1036,11 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 	/* Modify e_phnum to reflect merged headers. */
 	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
 
+	/* Store the size of all notes.  We need this to update the note
+	 * header when the device dumps will be added.
+	 */
+	elfnotes_orig_sz = phdr.p_memsz;
+
 	return 0;
 }
 
@@ -976,8 +1133,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
 }
 
 /* Sets offset fields of vmcore elements. */
-static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
-					   struct list_head *vc_list)
+static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
+				    struct list_head *vc_list)
 {
 	loff_t vmcore_off;
 	struct vmcore *m;
@@ -1145,6 +1302,202 @@ 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));
+}
+
+/**
+ * vmcoredd_update_program_headers - Update all Elf program headers
+ * @elfptr: Pointer to elf header
+ * @elfnotesz: Size of elf notes aligned to page size
+ * @vmcoreddsz: Size of device dumps to be added to elf note header
+ *
+ * Determine type of Elf header (Elf64 or Elf32) and update the elf note size.
+ * Also update the offsets of all the program headers after the elf note header.
+ */
+static void vmcoredd_update_program_headers(char *elfptr, size_t elfnotesz,
+					    size_t vmcoreddsz)
+{
+	unsigned char *e_ident = (unsigned char *)elfptr;
+	u64 start, end, size;
+	loff_t vmcore_off;
+	u32 i;
+
+	vmcore_off = elfcorebuf_sz + elfnotesz;
+
+	if (e_ident[EI_CLASS] == ELFCLASS64) {
+		Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfptr;
+		Elf64_Phdr *phdr = (Elf64_Phdr *)(elfptr + sizeof(Elf64_Ehdr));
+
+		/* Update all program headers */
+		for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+			if (phdr->p_type == PT_NOTE) {
+				/* Update note size */
+				phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz;
+				phdr->p_filesz = phdr->p_memsz;
+				continue;
+			}
+
+			start = rounddown(phdr->p_offset, PAGE_SIZE);
+			end = roundup(phdr->p_offset + phdr->p_memsz,
+				      PAGE_SIZE);
+			size = end - start;
+			phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+			vmcore_off += size;
+		}
+	} else {
+		Elf32_Ehdr *ehdr = (Elf32_Ehdr *)elfptr;
+		Elf32_Phdr *phdr = (Elf32_Phdr *)(elfptr + sizeof(Elf32_Ehdr));
+
+		/* Update all program headers */
+		for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+			if (phdr->p_type == PT_NOTE) {
+				/* Update note size */
+				phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz;
+				phdr->p_filesz = phdr->p_memsz;
+				continue;
+			}
+
+			start = rounddown(phdr->p_offset, PAGE_SIZE);
+			end = roundup(phdr->p_offset + phdr->p_memsz,
+				      PAGE_SIZE);
+			size = end - start;
+			phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+			vmcore_off += size;
+		}
+	}
+}
+
+/**
+ * vmcoredd_update_size - Update the total size of the device dumps and update
+ * Elf header
+ * @dump_size: Size of the current device dump to be added to total size
+ *
+ * Update the total size of all the device dumps and update the Elf program
+ * headers. Calculate the new offsets for the vmcore list and update the
+ * total vmcore size.
+ */
+static void vmcoredd_update_size(size_t dump_size)
+{
+	vmcoredd_orig_sz += dump_size;
+	elfnotes_sz = roundup(elfnotes_orig_sz, PAGE_SIZE) + vmcoredd_orig_sz;
+	vmcoredd_update_program_headers(elfcorebuf, elfnotes_sz,
+					vmcoredd_orig_sz);
+
+	/* Update vmcore list offsets */
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+
+	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+				      &vmcore_list);
+	proc_vmcore->size = vmcore_size;
+}
+
+/**
+ * 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);
+
+	vmcoredd_update_size(data_size);
+	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 +1545,7 @@ void vmcore_cleanup(void)
 		kfree(m);
 	}
 	free_elfcorebuf();
+
+	/* clear vmcore device dump list */
+	vmcore_free_device_dumps();
 }