diff mbox series

[v5,2/3] remoteproc: Add inline coredump functionality

Message ID 1592961854-634-3-git-send-email-rishabhb@codeaurora.org (mailing list archive)
State Superseded
Headers show
Series Extend coredump functionality | expand

Commit Message

Rishabh Bhatnagar June 24, 2020, 1:24 a.m. UTC
The current coredump implementation uses vmalloc area to copy
all the segments. But this might put strain on low memory targets
as the firmware size sometimes is in tens of MBs. The situation
becomes worse if there are multiple remote processors undergoing
recovery at the same time. This patch adds inline coredump
functionality that avoids extra memory usage. This requires
recovery to be halted until data is read by userspace and free
function is called.

Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
---
 drivers/remoteproc/qcom_q6v5_mss.c       |   9 +-
 drivers/remoteproc/remoteproc_coredump.c | 162 +++++++++++++++++++++++++++----
 include/linux/remoteproc.h               |  21 +++-
 3 files changed, 167 insertions(+), 25 deletions(-)

Comments

kernel test robot June 24, 2020, 6:26 a.m. UTC | #1
Hi Rishabh,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v5.8-rc2 next-20200623]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use  as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Rishabh-Bhatnagar/Extend-coredump-functionality/20200624-092759
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 5e857ce6eae7ca21b2055cca4885545e29228fe2
config: arc-allyesconfig (attached as .config)
compiler: arc-elf-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=arc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   In file included from include/linux/device.h:15,
                    from include/linux/devcoredump.h:8,
                    from drivers/remoteproc/remoteproc_coredump.c:9:
   drivers/remoteproc/remoteproc_coredump.c: In function 'rproc_copy_segment':
>> drivers/remoteproc/remoteproc_coredump.c:163:5: warning: format '%zu' expects argument of type 'size_t', but argument 3 has type 'dma_addr_t' {aka 'long long unsigned int'} [-Wformat=]
     163 |     "invalid copy request (%zu, %zu)\n",
         |     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   include/linux/dev_printk.h:19:22: note: in definition of macro 'dev_fmt'
      19 | #define dev_fmt(fmt) fmt
         |                      ^~~
>> drivers/remoteproc/remoteproc_coredump.c:162:4: note: in expansion of macro 'dev_err'
     162 |    dev_err(&rproc->dev,
         |    ^~~~~~~
   drivers/remoteproc/remoteproc_coredump.c:163:30: note: format string is defined here
     163 |     "invalid copy request (%zu, %zu)\n",
         |                            ~~^
         |                              |
         |                              unsigned int
         |                            %llu
   drivers/remoteproc/remoteproc_coredump.c: In function 'rproc_coredump_read':
>> drivers/remoteproc/remoteproc_coredump.c:186:15: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
     186 |   if (copy_sz < 0)
         |               ^

vim +163 drivers/remoteproc/remoteproc_coredump.c

   > 9	#include <linux/devcoredump.h>
    10	#include <linux/device.h>
    11	#include <linux/kernel.h>
    12	#include <linux/remoteproc.h>
    13	#include "remoteproc_internal.h"
    14	#include "remoteproc_elf_helpers.h"
    15	
    16	struct rproc_coredump_state {
    17		struct rproc *rproc;
    18		void *header;
    19		struct completion dump_done;
    20	};
    21	
    22	/**
    23	 * rproc_coredump_cleanup() - clean up dump_segments list
    24	 * @rproc: the remote processor handle
    25	 */
    26	void rproc_coredump_cleanup(struct rproc *rproc)
    27	{
    28		struct rproc_dump_segment *entry, *tmp;
    29	
    30		list_for_each_entry_safe(entry, tmp, &rproc->dump_segments, node) {
    31			list_del(&entry->node);
    32			kfree(entry);
    33		}
    34	}
    35	
    36	/**
    37	 * rproc_coredump_add_segment() - add segment of device memory to coredump
    38	 * @rproc:	handle of a remote processor
    39	 * @da:		device address
    40	 * @size:	size of segment
    41	 *
    42	 * Add device memory to the list of segments to be included in a coredump for
    43	 * the remoteproc.
    44	 *
    45	 * Return: 0 on success, negative errno on error.
    46	 */
    47	int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size)
    48	{
    49		struct rproc_dump_segment *segment;
    50	
    51		segment = kzalloc(sizeof(*segment), GFP_KERNEL);
    52		if (!segment)
    53			return -ENOMEM;
    54	
    55		segment->da = da;
    56		segment->size = size;
    57	
    58		list_add_tail(&segment->node, &rproc->dump_segments);
    59	
    60		return 0;
    61	}
    62	EXPORT_SYMBOL(rproc_coredump_add_segment);
    63	
    64	/**
    65	 * rproc_coredump_add_custom_segment() - add custom coredump segment
    66	 * @rproc:	handle of a remote processor
    67	 * @da:		device address
    68	 * @size:	size of segment
    69	 * @dumpfn:	custom dump function called for each segment during coredump
    70	 * @priv:	private data
    71	 *
    72	 * Add device memory to the list of segments to be included in the coredump
    73	 * and associate the segment with the given custom dump function and private
    74	 * data.
    75	 *
    76	 * Return: 0 on success, negative errno on error.
    77	 */
    78	int rproc_coredump_add_custom_segment(struct rproc *rproc,
    79					      dma_addr_t da, size_t size,
    80					      void (*dumpfn)(struct rproc *rproc,
    81							     struct rproc_dump_segment *segment,
    82							     void *dest, size_t offset,
    83							     size_t size),
    84					      void *priv)
    85	{
    86		struct rproc_dump_segment *segment;
    87	
    88		segment = kzalloc(sizeof(*segment), GFP_KERNEL);
    89		if (!segment)
    90			return -ENOMEM;
    91	
    92		segment->da = da;
    93		segment->size = size;
    94		segment->priv = priv;
    95		segment->dump = dumpfn;
    96	
    97		list_add_tail(&segment->node, &rproc->dump_segments);
    98	
    99		return 0;
   100	}
   101	EXPORT_SYMBOL(rproc_coredump_add_custom_segment);
   102	
   103	/**
   104	 * rproc_coredump_set_elf_info() - set coredump elf information
   105	 * @rproc:	handle of a remote processor
   106	 * @class:	elf class for coredump elf file
   107	 * @machine:	elf machine for coredump elf file
   108	 *
   109	 * Set elf information which will be used for coredump elf file.
   110	 *
   111	 * Return: 0 on success, negative errno on error.
   112	 */
   113	int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine)
   114	{
   115		if (class != ELFCLASS64 && class != ELFCLASS32)
   116			return -EINVAL;
   117	
   118		rproc->elf_class = class;
   119		rproc->elf_machine = machine;
   120	
   121		return 0;
   122	}
   123	EXPORT_SYMBOL(rproc_coredump_set_elf_info);
   124	
   125	static void rproc_coredump_free(void *data)
   126	{
   127		struct rproc_coredump_state *dump_state = data;
   128	
   129		complete(&dump_state->dump_done);
   130		vfree(dump_state->header);
   131	}
   132	
   133	static void *rproc_coredump_find_segment(loff_t user_offset,
   134						 struct list_head *segments,
   135						 size_t *data_left)
   136	{
   137		struct rproc_dump_segment *segment;
   138	
   139		list_for_each_entry(segment, segments, node) {
   140			if (user_offset < segment->size) {
   141				*data_left = segment->size - user_offset;
   142				return segment;
   143			}
   144			user_offset -= segment->size;
   145		}
   146	
   147		*data_left = 0;
   148		return NULL;
   149	}
   150	
   151	static void rproc_copy_segment(struct rproc *rproc, void *dest,
   152				       struct rproc_dump_segment *segment,
   153				       size_t offset, size_t size)
   154	{
   155		void *ptr;
   156	
   157		if (segment->dump) {
   158			segment->dump(rproc, segment, dest, offset, size);
   159		} else {
   160			ptr = rproc_da_to_va(rproc, segment->da + offset, size);
   161			if (!ptr) {
 > 162				dev_err(&rproc->dev,
 > 163					"invalid copy request (%zu, %zu)\n",
   164					segment->da + offset, size);
   165				memset(dest, 0xff, size);
   166			} else {
   167				memcpy(dest, ptr, size);
   168			}
   169		}
   170	}
   171	
   172	static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count,
   173					   void *data, size_t header_sz)
   174	{
   175		size_t seg_data;
   176		size_t copy_sz, bytes_left = count;
   177		struct rproc_dump_segment *seg;
   178		struct rproc_coredump_state *dump_state = data;
   179		struct rproc *rproc = dump_state->rproc;
   180		void *elfcore = dump_state->header;
   181	
   182		/* Copy the vmalloc'ed header first. */
   183		if (offset < header_sz) {
   184			copy_sz = memory_read_from_buffer(buffer, count, &offset,
   185							  elfcore, header_sz);
 > 186			if (copy_sz < 0)
   187				return -EINVAL;
   188	
   189			return copy_sz;
   190		}
   191	
   192		/*
   193		 * Find out the segment memory chunk to be copied based on offset.
   194		 * Keep copying data until count bytes are read.
   195		 */
   196		while (bytes_left) {
   197			seg = rproc_coredump_find_segment(offset - header_sz,
   198							  &rproc->dump_segments,
   199							  &seg_data);
   200			/* EOF check */
   201			if (!seg) {
   202				dev_info(&rproc->dev, "Ramdump done, %lld bytes read",
   203					 offset);
   204				break;
   205			}
   206	
   207			copy_sz = min_t(size_t, bytes_left, seg_data);
   208	
   209			rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data,
   210					   copy_sz);
   211	
   212			offset += copy_sz;
   213			buffer += copy_sz;
   214			bytes_left -= copy_sz;
   215		}
   216	
   217		return count - bytes_left;
   218	}
   219	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot June 24, 2020, 10:26 a.m. UTC | #2
Hi Rishabh,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v5.8-rc2 next-20200624]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use  as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Rishabh-Bhatnagar/Extend-coredump-functionality/20200624-092759
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 5e857ce6eae7ca21b2055cca4885545e29228fe2
config: i386-randconfig-a011-20200624 (attached as .config)
compiler: gcc-9 (Debian 9.3.0-13) 9.3.0
reproduce (this is a W=1 build):
        # save the attached .config to linux build tree
        make W=1 ARCH=i386 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   In file included from include/linux/export.h:43,
                    from include/linux/linkage.h:7,
                    from include/linux/kernel.h:8,
                    from include/linux/list.h:9,
                    from include/linux/swait.h:5,
                    from include/linux/completion.h:12,
                    from drivers/remoteproc/remoteproc_coredump.c:8:
   drivers/remoteproc/remoteproc_coredump.c: In function 'rproc_coredump_read':
   drivers/remoteproc/remoteproc_coredump.c:186:15: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
     186 |   if (copy_sz < 0)
         |               ^
   include/linux/compiler.h:58:52: note: in definition of macro '__trace_if_var'
      58 | #define __trace_if_var(cond) (__builtin_constant_p(cond) ? (cond) : __trace_if_value(cond))
         |                                                    ^~~~
>> drivers/remoteproc/remoteproc_coredump.c:186:3: note: in expansion of macro 'if'
     186 |   if (copy_sz < 0)
         |   ^~
   drivers/remoteproc/remoteproc_coredump.c:186:15: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
     186 |   if (copy_sz < 0)
         |               ^
   include/linux/compiler.h:58:61: note: in definition of macro '__trace_if_var'
      58 | #define __trace_if_var(cond) (__builtin_constant_p(cond) ? (cond) : __trace_if_value(cond))
         |                                                             ^~~~
>> drivers/remoteproc/remoteproc_coredump.c:186:3: note: in expansion of macro 'if'
     186 |   if (copy_sz < 0)
         |   ^~
   drivers/remoteproc/remoteproc_coredump.c:186:15: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
     186 |   if (copy_sz < 0)
         |               ^
   include/linux/compiler.h:69:3: note: in definition of macro '__trace_if_value'
      69 |  (cond) ?     \
         |   ^~~~
   include/linux/compiler.h:56:28: note: in expansion of macro '__trace_if_var'
      56 | #define if(cond, ...) if ( __trace_if_var( !!(cond , ## __VA_ARGS__) ) )
         |                            ^~~~~~~~~~~~~~
>> drivers/remoteproc/remoteproc_coredump.c:186:3: note: in expansion of macro 'if'
     186 |   if (copy_sz < 0)
         |   ^~

vim +/if +186 drivers/remoteproc/remoteproc_coredump.c

   171	
   172	static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count,
   173					   void *data, size_t header_sz)
   174	{
   175		size_t seg_data;
   176		size_t copy_sz, bytes_left = count;
   177		struct rproc_dump_segment *seg;
   178		struct rproc_coredump_state *dump_state = data;
   179		struct rproc *rproc = dump_state->rproc;
   180		void *elfcore = dump_state->header;
   181	
   182		/* Copy the vmalloc'ed header first. */
   183		if (offset < header_sz) {
   184			copy_sz = memory_read_from_buffer(buffer, count, &offset,
   185							  elfcore, header_sz);
 > 186			if (copy_sz < 0)
   187				return -EINVAL;
   188	
   189			return copy_sz;
   190		}
   191	
   192		/*
   193		 * Find out the segment memory chunk to be copied based on offset.
   194		 * Keep copying data until count bytes are read.
   195		 */
   196		while (bytes_left) {
   197			seg = rproc_coredump_find_segment(offset - header_sz,
   198							  &rproc->dump_segments,
   199							  &seg_data);
   200			/* EOF check */
   201			if (!seg) {
   202				dev_info(&rproc->dev, "Ramdump done, %lld bytes read",
   203					 offset);
   204				break;
   205			}
   206	
   207			copy_sz = min_t(size_t, bytes_left, seg_data);
   208	
   209			rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data,
   210					   copy_sz);
   211	
   212			offset += copy_sz;
   213			buffer += copy_sz;
   214			bytes_left -= copy_sz;
   215		}
   216	
   217		return count - bytes_left;
   218	}
   219	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot June 25, 2020, 6:33 p.m. UTC | #3
Hi Rishabh,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v5.8-rc2 next-20200625]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use  as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Rishabh-Bhatnagar/Extend-coredump-functionality/20200624-092759
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 5e857ce6eae7ca21b2055cca4885545e29228fe2
config: h8300-randconfig-m031-20200624 (attached as .config)
compiler: h8300-linux-gcc (GCC) 9.3.0

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

smatch warnings:
drivers/remoteproc/remoteproc_coredump.c:186 rproc_coredump_read() warn: unsigned 'copy_sz' is never less than zero.

vim +/copy_sz +186 drivers/remoteproc/remoteproc_coredump.c

   171	
   172	static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count,
   173					   void *data, size_t header_sz)
   174	{
   175		size_t seg_data;
   176		size_t copy_sz, bytes_left = count;
   177		struct rproc_dump_segment *seg;
   178		struct rproc_coredump_state *dump_state = data;
   179		struct rproc *rproc = dump_state->rproc;
   180		void *elfcore = dump_state->header;
   181	
   182		/* Copy the vmalloc'ed header first. */
   183		if (offset < header_sz) {
   184			copy_sz = memory_read_from_buffer(buffer, count, &offset,
   185							  elfcore, header_sz);
 > 186			if (copy_sz < 0)
   187				return -EINVAL;
   188	
   189			return copy_sz;
   190		}
   191	
   192		/*
   193		 * Find out the segment memory chunk to be copied based on offset.
   194		 * Keep copying data until count bytes are read.
   195		 */
   196		while (bytes_left) {
   197			seg = rproc_coredump_find_segment(offset - header_sz,
   198							  &rproc->dump_segments,
   199							  &seg_data);
   200			/* EOF check */
   201			if (!seg) {
   202				dev_info(&rproc->dev, "Ramdump done, %lld bytes read",
   203					 offset);
   204				break;
   205			}
   206	
   207			copy_sz = min_t(size_t, bytes_left, seg_data);
   208	
   209			rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data,
   210					   copy_sz);
   211	
   212			offset += copy_sz;
   213			buffer += copy_sz;
   214			bytes_left -= copy_sz;
   215		}
   216	
   217		return count - bytes_left;
   218	}
   219	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 903b2bb..d4ff9b8 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -1200,12 +1200,13 @@  static int q6v5_mpss_load(struct q6v5 *qproc)
 
 static void qcom_q6v5_dump_segment(struct rproc *rproc,
 				   struct rproc_dump_segment *segment,
-				   void *dest)
+				   void *dest, size_t cp_offset, size_t size)
 {
 	int ret = 0;
 	struct q6v5 *qproc = rproc->priv;
 	unsigned long mask = BIT((unsigned long)segment->priv);
 	int offset = segment->da - qproc->mpss_reloc;
+	size_t cp_size = size ? size : segment->size;
 	void *ptr = NULL;
 
 	/* Unlock mba before copying segments */
@@ -1221,13 +1222,13 @@  static void qcom_q6v5_dump_segment(struct rproc *rproc,
 	}
 
 	if (!ret)
-		ptr = ioremap_wc(qproc->mpss_phys + offset, segment->size);
+		ptr = ioremap_wc(qproc->mpss_phys + offset + cp_offset, cp_size);
 
 	if (ptr) {
-		memcpy(dest, ptr, segment->size);
+		memcpy(dest, ptr, cp_size);
 		iounmap(ptr);
 	} else {
-		memset(dest, 0xff, segment->size);
+		memset(dest, 0xff, cp_size);
 	}
 
 	qproc->dump_segment_mask |= mask;
diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index ded0244..e643a66 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -5,6 +5,7 @@ 
  * Copyright (c) 2020, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/completion.h>
 #include <linux/devcoredump.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -12,6 +13,12 @@ 
 #include "remoteproc_internal.h"
 #include "remoteproc_elf_helpers.h"
 
+struct rproc_coredump_state {
+	struct rproc *rproc;
+	void *header;
+	struct completion dump_done;
+};
+
 /**
  * rproc_coredump_cleanup() - clean up dump_segments list
  * @rproc: the remote processor handle
@@ -72,7 +79,8 @@  int rproc_coredump_add_custom_segment(struct rproc *rproc,
 				      dma_addr_t da, size_t size,
 				      void (*dumpfn)(struct rproc *rproc,
 						     struct rproc_dump_segment *segment,
-						     void *dest),
+						     void *dest, size_t offset,
+						     size_t size),
 				      void *priv)
 {
 	struct rproc_dump_segment *segment;
@@ -114,12 +122,112 @@  int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine)
 }
 EXPORT_SYMBOL(rproc_coredump_set_elf_info);
 
+static void rproc_coredump_free(void *data)
+{
+	struct rproc_coredump_state *dump_state = data;
+
+	complete(&dump_state->dump_done);
+	vfree(dump_state->header);
+}
+
+static void *rproc_coredump_find_segment(loff_t user_offset,
+					 struct list_head *segments,
+					 size_t *data_left)
+{
+	struct rproc_dump_segment *segment;
+
+	list_for_each_entry(segment, segments, node) {
+		if (user_offset < segment->size) {
+			*data_left = segment->size - user_offset;
+			return segment;
+		}
+		user_offset -= segment->size;
+	}
+
+	*data_left = 0;
+	return NULL;
+}
+
+static void rproc_copy_segment(struct rproc *rproc, void *dest,
+			       struct rproc_dump_segment *segment,
+			       size_t offset, size_t size)
+{
+	void *ptr;
+
+	if (segment->dump) {
+		segment->dump(rproc, segment, dest, offset, size);
+	} else {
+		ptr = rproc_da_to_va(rproc, segment->da + offset, size);
+		if (!ptr) {
+			dev_err(&rproc->dev,
+				"invalid copy request (%zu, %zu)\n",
+				segment->da + offset, size);
+			memset(dest, 0xff, size);
+		} else {
+			memcpy(dest, ptr, size);
+		}
+	}
+}
+
+static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count,
+				   void *data, size_t header_sz)
+{
+	size_t seg_data;
+	size_t copy_sz, bytes_left = count;
+	struct rproc_dump_segment *seg;
+	struct rproc_coredump_state *dump_state = data;
+	struct rproc *rproc = dump_state->rproc;
+	void *elfcore = dump_state->header;
+
+	/* Copy the vmalloc'ed header first. */
+	if (offset < header_sz) {
+		copy_sz = memory_read_from_buffer(buffer, count, &offset,
+						  elfcore, header_sz);
+		if (copy_sz < 0)
+			return -EINVAL;
+
+		return copy_sz;
+	}
+
+	/*
+	 * Find out the segment memory chunk to be copied based on offset.
+	 * Keep copying data until count bytes are read.
+	 */
+	while (bytes_left) {
+		seg = rproc_coredump_find_segment(offset - header_sz,
+						  &rproc->dump_segments,
+						  &seg_data);
+		/* EOF check */
+		if (!seg) {
+			dev_info(&rproc->dev, "Ramdump done, %lld bytes read",
+				 offset);
+			break;
+		}
+
+		copy_sz = min_t(size_t, bytes_left, seg_data);
+
+		rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data,
+				   copy_sz);
+
+		offset += copy_sz;
+		buffer += copy_sz;
+		bytes_left -= copy_sz;
+	}
+
+	return count - bytes_left;
+}
+
 /**
  * rproc_coredump() - perform coredump
  * @rproc:	rproc handle
  *
  * This function will generate an ELF header for the registered segments
- * and create a devcoredump device associated with rproc.
+ * and create a devcoredump device associated with rproc. Based on the
+ * coredump configuration this function will directly copy the segments
+ * from device memory to userspace or copy segments from device memory to
+ * a separate buffer, which can then be read by userspace.
+ * The first approach avoids using extra vmalloc memory. But it will stall
+ * recovery flow until dump is read by userspace.
  */
 void rproc_coredump(struct rproc *rproc)
 {
@@ -129,11 +237,13 @@  void rproc_coredump(struct rproc *rproc)
 	size_t data_size;
 	size_t offset;
 	void *data;
-	void *ptr;
 	u8 class = rproc->elf_class;
 	int phnum = 0;
+	struct rproc_coredump_state dump_state;
+	enum rproc_dump_mechanism dump_conf = rproc->dump_conf;
 
-	if (list_empty(&rproc->dump_segments))
+	if (list_empty(&rproc->dump_segments) ||
+	    dump_conf == RPROC_COREDUMP_DISABLED)
 		return;
 
 	if (class == ELFCLASSNONE) {
@@ -143,7 +253,14 @@  void rproc_coredump(struct rproc *rproc)
 
 	data_size = elf_size_of_hdr(class);
 	list_for_each_entry(segment, &rproc->dump_segments, node) {
-		data_size += elf_size_of_phdr(class) + segment->size;
+		/*
+		 * For default configuration buffer includes headers & segments.
+		 * For inline dump buffer just includes headers as segments are
+		 * directly read from device memory.
+		 */
+		data_size += elf_size_of_phdr(class);
+		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+			data_size += segment->size;
 
 		phnum++;
 	}
@@ -182,23 +299,30 @@  void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X);
 		elf_phdr_set_p_align(class, phdr, 0);
 
-		if (segment->dump) {
-			segment->dump(rproc, segment, data + offset);
-		} else {
-			ptr = rproc_da_to_va(rproc, segment->da, segment->size);
-			if (!ptr) {
-				dev_err(&rproc->dev,
-					"invalid coredump segment (%pad, %zu)\n",
-					&segment->da, segment->size);
-				memset(data + offset, 0xff, segment->size);
-			} else {
-				memcpy(data + offset, ptr, segment->size);
-			}
-		}
+		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+			rproc_copy_segment(rproc, data + offset, segment, 0,
+					   segment->size);
 
 		offset += elf_phdr_get_p_filesz(class, phdr);
 		phdr += elf_size_of_phdr(class);
 	}
 
-	dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
+	if (dump_conf == RPROC_COREDUMP_DEFAULT) {
+		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
+		return;
+	}
+
+	/* Initialize the dump state struct to be used by rproc_coredump_read */
+	dump_state.rproc = rproc;
+	dump_state.header = data;
+	init_completion(&dump_state.dump_done);
+
+	dev_coredumpm(&rproc->dev, NULL, &dump_state, data_size, GFP_KERNEL,
+		      rproc_coredump_read, rproc_coredump_free);
+
+	/*
+	 * Wait until the dump is read and free is called. Data is freed
+	 * by devcoredump framework automatically after 5 minutes.
+	 */
+	wait_for_completion(&dump_state.dump_done);
 }
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index e7b7bab..43e45a3 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -435,6 +435,20 @@  enum rproc_crash_type {
 };
 
 /**
+ * enum rproc_dump_mechanism - Coredump options for core
+ * @RPROC_COREDUMP_DEFAULT:	Copy dump to separate buffer and carry on with
+				recovery
+ * @RPROC_COREDUMP_INLINE:	Read segments directly from device memory. Stall
+				recovery until all segments are read
+ * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
+ */
+enum rproc_dump_mechanism {
+	RPROC_COREDUMP_DEFAULT,
+	RPROC_COREDUMP_INLINE,
+	RPROC_COREDUMP_DISABLED,
+};
+
+/**
  * struct rproc_dump_segment - segment info from ELF header
  * @node:	list node related to the rproc segment list
  * @da:		device address of the segment
@@ -451,7 +465,7 @@  struct rproc_dump_segment {
 
 	void *priv;
 	void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment,
-		     void *dest);
+		     void *dest, size_t offset, size_t size);
 	loff_t offset;
 };
 
@@ -466,6 +480,7 @@  struct rproc_dump_segment {
  * @dev: virtual device for refcounting and common remoteproc behavior
  * @power: refcount of users who need this rproc powered up
  * @state: state of the device
+ * @dump_conf: Currenlty selected coredump configuration
  * @lock: lock which protects concurrent manipulations of the rproc
  * @dbg_dir: debugfs directory of this rproc device
  * @traces: list of trace buffers
@@ -499,6 +514,7 @@  struct rproc {
 	struct device dev;
 	atomic_t power;
 	unsigned int state;
+	enum rproc_dump_mechanism dump_conf;
 	struct mutex lock;
 	struct dentry *dbg_dir;
 	struct list_head traces;
@@ -630,7 +646,8 @@  int rproc_coredump_add_custom_segment(struct rproc *rproc,
 				      dma_addr_t da, size_t size,
 				      void (*dumpfn)(struct rproc *rproc,
 						     struct rproc_dump_segment *segment,
-						     void *dest),
+						     void *dest, size_t offset,
+						     size_t size),
 				      void *priv);
 int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine);