2020-10-16 04:59:18

by Douglas Gilbert

[permalink] [raw]
Subject: [PATCH 0/4] scatterlist: add new capabilities

Scatter-gather lists (sgl_s) are frequently used as data
carriers in the block layer. For example the SCSI and NVMe
subsystems interchange data with the block layer using
sgl_s. The sgl API is declared in <linux/scatterlist.h>

The author has extended these transient sgl use cases to
a store (i.e. ramdisk) in the scsi_debug driver. Other new
potential uses of sgl_s could be for caches. When this extra
step is taken, the need to copy between sgl_s becomes apparent.
The patchset adds sgl_copy_sgl() and a few other sgl
operations.

The existing sgl_alloc_order() function can be seen as a
replacement for vmalloc() for large, long-term allocations.
For what seems like no good reason, sgl_alloc_order()
currently restricts its total allocation to less than or
equal to 4 GiB. vmalloc() has no such restriction.

This patchset is against lk 5.9.0

Douglas Gilbert (4):
sgl_alloc_order: remove 4 GiB limit, sgl_free() warning
scatterlist: add sgl_copy_sgl() function
scatterlist: add sgl_compare_sgl() function
scatterlist: add sgl_memset()

include/linux/scatterlist.h | 12 +++
lib/scatterlist.c | 204 +++++++++++++++++++++++++++++++++++-
2 files changed, 213 insertions(+), 3 deletions(-)

--
2.25.1


2020-10-16 05:02:50

by Douglas Gilbert

[permalink] [raw]
Subject: [PATCH 4/4] scatterlist: add sgl_memset()

The existing sg_zero_buffer() function is a bit restrictive.
For example protection information (PI) blocks are usually
initialized to 0xff bytes. As its name suggests sgl_memset()
is modelled on memset(). One difference is the type of the
val argument which is u8 rather than int.

Signed-off-by: Douglas Gilbert <[email protected]>
---
include/linux/scatterlist.h | 3 +++
lib/scatterlist.c | 39 +++++++++++++++++++++++++++++++++++--
2 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index ae260dc5fedb..e50dc9a6d887 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -329,6 +329,9 @@ bool sgl_compare_sgl(struct scatterlist *x_sgl, unsigned int x_nents, off_t x_sk
struct scatterlist *y_sgl, unsigned int y_nents, off_t y_skip,
size_t n_bytes);

+void sgl_memset(struct scatterlist *sgl, unsigned int nents, off_t skip,
+ u8 val, size_t n_bytes);
+
/*
* Maximum number of entries that will be allocated in one piece, if
* a list larger than this is required then chaining will be utilized.
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 344725990b9d..3ca66f0c949f 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -1083,8 +1083,8 @@ EXPORT_SYMBOL(sgl_copy_sgl);
*
**/
bool sgl_compare_sgl(struct scatterlist *x_sgl, unsigned int x_nents, off_t x_skip,
- struct scatterlist *y_sgl, unsigned int y_nents, off_t y_skip,
- size_t n_bytes)
+ struct scatterlist *y_sgl, unsigned int y_nents, off_t y_skip,
+ size_t n_bytes)
{
bool equ = true;
size_t x_off, y_off, len, x_len, y_len;
@@ -1140,3 +1140,38 @@ bool sgl_compare_sgl(struct scatterlist *x_sgl, unsigned int x_nents, off_t x_sk
return equ;
}
EXPORT_SYMBOL(sgl_compare_sgl);
+
+/**
+ * sgl_memset - set byte 'val' n_bytes times on SG list
+ * @sgl: The SG list
+ * @nents: Number of SG entries in sgl
+ * @skip: Number of bytes to skip before starting
+ * @val: byte value to write to sgl
+ * @n_bytes: The number of bytes to modify
+ *
+ * Notes:
+ * Writes val n_bytes times or until sgl is exhausted.
+ *
+ **/
+void sgl_memset(struct scatterlist *sgl, unsigned int nents, off_t skip,
+ u8 val, size_t n_bytes)
+{
+ size_t offset = 0;
+ size_t len;
+ struct sg_mapping_iter miter;
+ unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG;
+
+ if (n_bytes == 0)
+ return;
+ sg_miter_start(&miter, sgl, nents, sg_flags);
+ if (!sg_miter_skip(&miter, skip))
+ goto fini;
+
+ while ((offset < n_bytes) && sg_miter_next(&miter)) {
+ len = min(miter.length, n_bytes - offset);
+ memset(miter.addr, val, len);
+ offset += len;
+ }
+fini:
+ sg_miter_stop(&miter);
+}
--
2.25.1

2020-10-16 05:47:06

by Douglas Gilbert

[permalink] [raw]
Subject: [PATCH 2/4] scatterlist: add sgl_copy_sgl() function

Both the SCSI and NVMe subsystems receive user data from the block
layer in scatterlist_s (aka scatter gather lists (sgl) which are
often arrays). If drivers in those subsystems represent storage
(e.g. a ramdisk) or cache "hot" user data then they may also
choose to use scatterlist_s. Currently there are no sgl to sgl
operations in the kernel. Start with a copy.

Signed-off-by: Douglas Gilbert <[email protected]>
---
include/linux/scatterlist.h | 4 ++
lib/scatterlist.c | 86 +++++++++++++++++++++++++++++++++++++
2 files changed, 90 insertions(+)

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 80178afc2a4a..6649414c0749 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -321,6 +321,10 @@ size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
size_t buflen, off_t skip);

+size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_skip,
+ struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
+ size_t n_bytes);
+
/*
* Maximum number of entries that will be allocated in one piece, if
* a list larger than this is required then chaining will be utilized.
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index d5770e7f1030..1ec2c909c8d4 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -974,3 +974,89 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
return offset;
}
EXPORT_SYMBOL(sg_zero_buffer);
+
+/**
+ * sgl_copy_sgl - Copy over a destination sgl from a source sgl
+ * @d_sgl: Destination sgl
+ * @d_nents: Number of SG entries in destination sgl
+ * @d_skip: Number of bytes to skip in destination before copying
+ * @s_sgl: Source sgl
+ * @s_nents: Number of SG entries in source sgl
+ * @s_skip: Number of bytes to skip in source before copying
+ * @n_bytes: The number of bytes to copy
+ *
+ * Returns the number of copied bytes.
+ *
+ * Notes:
+ * Destination arguments appear before the source arguments, as with memcpy().
+ *
+ * Stops copying if the end of d_sgl or s_sgl is reached.
+ *
+ * Since memcpy() is used, overlapping copies (where d_sgl and s_sgl belong
+ * to the same sgl and the copy regions overlap) are not supported.
+ *
+ * If d_skip is large, potentially spanning multiple d_nents then some
+ * integer arithmetic to adjust d_sgl may improve performance. For example
+ * if d_sgl is built using sgl_alloc_order(chainable=false) then the sgl
+ * will be an array with equally sized segments facilitating that
+ * arithmetic. The suggestion applies to s_skip, s_sgl and s_nents as well.
+ *
+ **/
+size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_skip,
+ struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
+ size_t n_bytes)
+{
+ size_t d_off, s_off, len, d_len, s_len;
+ size_t offset = 0;
+ struct sg_mapping_iter d_iter;
+ struct sg_mapping_iter s_iter;
+
+ if (n_bytes == 0)
+ return 0;
+ sg_miter_start(&d_iter, d_sgl, d_nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
+ sg_miter_start(&s_iter, s_sgl, s_nents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
+ if (!sg_miter_skip(&d_iter, d_skip))
+ goto fini;
+ if (!sg_miter_skip(&s_iter, s_skip))
+ goto fini;
+
+ for (d_off = 0, s_off = 0; true ; ) {
+ /* Assume d_iter.length and s_iter.length can never be 0 */
+ if (d_off == 0) {
+ if (!sg_miter_next(&d_iter))
+ break;
+ d_len = d_iter.length;
+ } else {
+ d_len = d_iter.length - d_off;
+ }
+ if (s_off == 0) {
+ if (!sg_miter_next(&s_iter))
+ break;
+ s_len = s_iter.length;
+ } else {
+ s_len = s_iter.length - s_off;
+ }
+ len = min3(d_len, s_len, n_bytes - offset);
+
+ memcpy(d_iter.addr + d_off, s_iter.addr + s_off, len);
+ offset += len;
+ if (offset >= n_bytes)
+ break;
+ if (d_len == s_len) {
+ d_off = 0;
+ s_off = 0;
+ } else if (d_len < s_len) {
+ d_off = 0;
+ s_off += len;
+ } else {
+ d_off += len;
+ s_off = 0;
+ }
+ }
+fini:
+ sg_miter_stop(&d_iter);
+ sg_miter_stop(&s_iter);
+ return offset;
+}
+EXPORT_SYMBOL(sgl_copy_sgl);
+
--
2.25.1

2020-10-16 05:47:06

by Douglas Gilbert

[permalink] [raw]
Subject: [PATCH 3/4] scatterlist: add sgl_compare_sgl() function

After enabling copies between scatter gather lists (sgl_s),
another storage related operation is to compare two sgl_s.
This new function is modelled on NVMe's Compare command and
the SCSI VERIFY(BYTCHK=1) command. Like memcmp() this function
returns false on the first miscompare and stop comparing.

Signed-off-by: Douglas Gilbert <[email protected]>
---
include/linux/scatterlist.h | 4 ++
lib/scatterlist.c | 84 ++++++++++++++++++++++++++++++++++++-
2 files changed, 86 insertions(+), 2 deletions(-)

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 6649414c0749..ae260dc5fedb 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -325,6 +325,10 @@ size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_ski
struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
size_t n_bytes);

+bool sgl_compare_sgl(struct scatterlist *x_sgl, unsigned int x_nents, off_t x_skip,
+ struct scatterlist *y_sgl, unsigned int y_nents, off_t y_skip,
+ size_t n_bytes);
+
/*
* Maximum number of entries that will be allocated in one piece, if
* a list larger than this is required then chaining will be utilized.
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 1ec2c909c8d4..344725990b9d 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -979,10 +979,10 @@ EXPORT_SYMBOL(sg_zero_buffer);
* sgl_copy_sgl - Copy over a destination sgl from a source sgl
* @d_sgl: Destination sgl
* @d_nents: Number of SG entries in destination sgl
- * @d_skip: Number of bytes to skip in destination before copying
+ * @d_skip: Number of bytes to skip in destination before starting
* @s_sgl: Source sgl
* @s_nents: Number of SG entries in source sgl
- * @s_skip: Number of bytes to skip in source before copying
+ * @s_skip: Number of bytes to skip in source before starting
* @n_bytes: The number of bytes to copy
*
* Returns the number of copied bytes.
@@ -1060,3 +1060,83 @@ size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_ski
}
EXPORT_SYMBOL(sgl_copy_sgl);

+/**
+ * sgl_compare_sgl - Compare x and y (both sgl_s)
+ * @x_sgl: x (left) sgl
+ * @x_nents: Number of SG entries in x (left) sgl
+ * @x_skip: Number of bytes to skip in x (left) before starting
+ * @y_sgl: y (right) sgl
+ * @y_nents: Number of SG entries in y (right) sgl
+ * @y_skip: Number of bytes to skip in y (right) before starting
+ * @n_bytes: The number of bytes to compare
+ *
+ * Returns true if x and y compare equal before x, y or n_bytes is exhausted.
+ * Otherwise on a miscompare, returns false (and stops comparing).
+ *
+ * Notes:
+ * x and y are symmetrical: they can be swapped and the result is the same.
+ *
+ * Implementation is based on memcmp(). x and y segments may overlap.
+ *
+ * Same comment from sgl_copy_sgl() about large _skip arguments applies here
+ * as well.
+ *
+ **/
+bool sgl_compare_sgl(struct scatterlist *x_sgl, unsigned int x_nents, off_t x_skip,
+ struct scatterlist *y_sgl, unsigned int y_nents, off_t y_skip,
+ size_t n_bytes)
+{
+ bool equ = true;
+ size_t x_off, y_off, len, x_len, y_len;
+ size_t offset = 0;
+ struct sg_mapping_iter x_iter;
+ struct sg_mapping_iter y_iter;
+
+ if (n_bytes == 0)
+ return true;
+ sg_miter_start(&x_iter, x_sgl, x_nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
+ sg_miter_start(&y_iter, y_sgl, y_nents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
+ if (!sg_miter_skip(&x_iter, x_skip))
+ goto fini;
+ if (!sg_miter_skip(&y_iter, y_skip))
+ goto fini;
+
+ for (x_off = 0, y_off = 0; true ; ) {
+ /* Assume x_iter.length and y_iter.length can never be 0 */
+ if (x_off == 0) {
+ if (!sg_miter_next(&x_iter))
+ break;
+ x_len = x_iter.length;
+ } else {
+ x_len = x_iter.length - x_off;
+ }
+ if (y_off == 0) {
+ if (!sg_miter_next(&y_iter))
+ break;
+ y_len = y_iter.length;
+ } else {
+ y_len = y_iter.length - y_off;
+ }
+ len = min3(x_len, y_len, n_bytes - offset);
+
+ equ = memcmp(x_iter.addr + x_off, y_iter.addr + y_off, len) == 0;
+ offset += len;
+ if (!equ || offset >= n_bytes)
+ break;
+ if (x_len == y_len) {
+ x_off = 0;
+ y_off = 0;
+ } else if (x_len < y_len) {
+ x_off = 0;
+ y_off += len;
+ } else {
+ x_off += len;
+ y_off = 0;
+ }
+ }
+fini:
+ sg_miter_stop(&x_iter);
+ sg_miter_stop(&y_iter);
+ return equ;
+}
+EXPORT_SYMBOL(sgl_compare_sgl);
--
2.25.1

2020-10-16 13:09:57

by Bodo Stroesser

[permalink] [raw]
Subject: Re: [PATCH 2/4] scatterlist: add sgl_copy_sgl() function

Hi Douglas,

AFAICS this patch - and also patch 3 - are not correct.
When started with SG_MITER_ATOMIC, sg_miter_next and sg_miter_stop use
the k(un)map_atomic calls. But these have to be used strictly nested
according to docu and code.
The below code uses the atomic mappings in overlapping mode.

Regards,
Bodo

Am 16.10.20 um 06:52 schrieb Douglas Gilbert:
> Both the SCSI and NVMe subsystems receive user data from the block
> layer in scatterlist_s (aka scatter gather lists (sgl) which are
> often arrays). If drivers in those subsystems represent storage
> (e.g. a ramdisk) or cache "hot" user data then they may also
> choose to use scatterlist_s. Currently there are no sgl to sgl
> operations in the kernel. Start with a copy.
>
> Signed-off-by: Douglas Gilbert <[email protected]>
> ---
> include/linux/scatterlist.h | 4 ++
> lib/scatterlist.c | 86 +++++++++++++++++++++++++++++++++++++
> 2 files changed, 90 insertions(+)
>
> diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
> index 80178afc2a4a..6649414c0749 100644
> --- a/include/linux/scatterlist.h
> +++ b/include/linux/scatterlist.h
> @@ -321,6 +321,10 @@ size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
> size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
> size_t buflen, off_t skip);
>
> +size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_skip,
> + struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
> + size_t n_bytes);
> +
> /*
> * Maximum number of entries that will be allocated in one piece, if
> * a list larger than this is required then chaining will be utilized.
> diff --git a/lib/scatterlist.c b/lib/scatterlist.c
> index d5770e7f1030..1ec2c909c8d4 100644
> --- a/lib/scatterlist.c
> +++ b/lib/scatterlist.c
> @@ -974,3 +974,89 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
> return offset;
> }
> EXPORT_SYMBOL(sg_zero_buffer);
> +
> +/**
> + * sgl_copy_sgl - Copy over a destination sgl from a source sgl
> + * @d_sgl: Destination sgl
> + * @d_nents: Number of SG entries in destination sgl
> + * @d_skip: Number of bytes to skip in destination before copying
> + * @s_sgl: Source sgl
> + * @s_nents: Number of SG entries in source sgl
> + * @s_skip: Number of bytes to skip in source before copying
> + * @n_bytes: The number of bytes to copy
> + *
> + * Returns the number of copied bytes.
> + *
> + * Notes:
> + * Destination arguments appear before the source arguments, as with memcpy().
> + *
> + * Stops copying if the end of d_sgl or s_sgl is reached.
> + *
> + * Since memcpy() is used, overlapping copies (where d_sgl and s_sgl belong
> + * to the same sgl and the copy regions overlap) are not supported.
> + *
> + * If d_skip is large, potentially spanning multiple d_nents then some
> + * integer arithmetic to adjust d_sgl may improve performance. For example
> + * if d_sgl is built using sgl_alloc_order(chainable=false) then the sgl
> + * will be an array with equally sized segments facilitating that
> + * arithmetic. The suggestion applies to s_skip, s_sgl and s_nents as well.
> + *
> + **/
> +size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t d_skip,
> + struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
> + size_t n_bytes)
> +{
> + size_t d_off, s_off, len, d_len, s_len;
> + size_t offset = 0;
> + struct sg_mapping_iter d_iter;
> + struct sg_mapping_iter s_iter;
> +
> + if (n_bytes == 0)
> + return 0;
> + sg_miter_start(&d_iter, d_sgl, d_nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
> + sg_miter_start(&s_iter, s_sgl, s_nents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
> + if (!sg_miter_skip(&d_iter, d_skip))
> + goto fini;
> + if (!sg_miter_skip(&s_iter, s_skip))
> + goto fini;
> +
> + for (d_off = 0, s_off = 0; true ; ) {
> + /* Assume d_iter.length and s_iter.length can never be 0 */
> + if (d_off == 0) {
> + if (!sg_miter_next(&d_iter))
> + break;
> + d_len = d_iter.length;
> + } else {
> + d_len = d_iter.length - d_off;
> + }
> + if (s_off == 0) {
> + if (!sg_miter_next(&s_iter))
> + break;
> + s_len = s_iter.length;
> + } else {
> + s_len = s_iter.length - s_off;
> + }
> + len = min3(d_len, s_len, n_bytes - offset);
> +
> + memcpy(d_iter.addr + d_off, s_iter.addr + s_off, len);
> + offset += len;
> + if (offset >= n_bytes)
> + break;
> + if (d_len == s_len) {
> + d_off = 0;
> + s_off = 0;
> + } else if (d_len < s_len) {
> + d_off = 0;
> + s_off += len;
> + } else {
> + d_off += len;
> + s_off = 0;
> + }
> + }
> +fini:
> + sg_miter_stop(&d_iter);
> + sg_miter_stop(&s_iter);
> + return offset;
> +}
> +EXPORT_SYMBOL(sgl_copy_sgl);
> +
>

2020-10-16 18:47:18

by Douglas Gilbert

[permalink] [raw]
Subject: Re: [PATCH 2/4] scatterlist: add sgl_copy_sgl() function

On 2020-10-16 7:17 a.m., Bodo Stroesser wrote:
> Hi Douglas,
>
> AFAICS this patch - and also patch 3 - are not correct.
> When started with SG_MITER_ATOMIC, sg_miter_next and sg_miter_stop use
> the k(un)map_atomic calls. But these have to be used strictly nested
> according to docu and code.
> The below code uses the atomic mappings in overlapping mode.

That being the case, I'll add d_flags and s_flags arguments that are
expected to take either 0 or SG_MITER_ATOMIC and re-test. There probably
should be a warning in the notes not to set both d_flags and s_flags
to SG_MITER_ATOMIC.

My testing to date has not been in irq or soft interrupt state. I
should be able to rig a test for the latter.

Thanks
Doug Gilbert

> Am 16.10.20 um 06:52 schrieb Douglas Gilbert:
>> Both the SCSI and NVMe subsystems receive user data from the block
>> layer in scatterlist_s (aka scatter gather lists (sgl) which are
>> often arrays). If drivers in those subsystems represent storage
>> (e.g. a ramdisk) or cache "hot" user data then they may also
>> choose to use scatterlist_s. Currently there are no sgl to sgl
>> operations in the kernel. Start with a copy.
>>
>> Signed-off-by: Douglas Gilbert <[email protected]>
>> ---
>>   include/linux/scatterlist.h |  4 ++
>>   lib/scatterlist.c           | 86 +++++++++++++++++++++++++++++++++++++
>>   2 files changed, 90 insertions(+)
>>
>> diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
>> index 80178afc2a4a..6649414c0749 100644
>> --- a/include/linux/scatterlist.h
>> +++ b/include/linux/scatterlist.h
>> @@ -321,6 +321,10 @@ size_t sg_pcopy_to_buffer(struct scatterlist *sgl,
>> unsigned int nents,
>>   size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
>>                  size_t buflen, off_t skip);
>> +size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t
>> d_skip,
>> +            struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
>> +            size_t n_bytes);
>> +
>>   /*
>>    * Maximum number of entries that will be allocated in one piece, if
>>    * a list larger than this is required then chaining will be utilized.
>> diff --git a/lib/scatterlist.c b/lib/scatterlist.c
>> index d5770e7f1030..1ec2c909c8d4 100644
>> --- a/lib/scatterlist.c
>> +++ b/lib/scatterlist.c
>> @@ -974,3 +974,89 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned
>> int nents,
>>       return offset;
>>   }
>>   EXPORT_SYMBOL(sg_zero_buffer);
>> +
>> +/**
>> + * sgl_copy_sgl - Copy over a destination sgl from a source sgl
>> + * @d_sgl:         Destination sgl
>> + * @d_nents:         Number of SG entries in destination sgl
>> + * @d_skip:         Number of bytes to skip in destination before copying
>> + * @s_sgl:         Source sgl
>> + * @s_nents:         Number of SG entries in source sgl
>> + * @s_skip:         Number of bytes to skip in source before copying
>> + * @n_bytes:         The number of bytes to copy
>> + *
>> + * Returns the number of copied bytes.
>> + *
>> + * Notes:
>> + *   Destination arguments appear before the source arguments, as with memcpy().
>> + *
>> + *   Stops copying if the end of d_sgl or s_sgl is reached.
>> + *
>> + *   Since memcpy() is used, overlapping copies (where d_sgl and s_sgl belong
>> + *   to the same sgl and the copy regions overlap) are not supported.
>> + *
>> + *   If d_skip is large, potentially spanning multiple d_nents then some
>> + *   integer arithmetic to adjust d_sgl may improve performance. For example
>> + *   if d_sgl is built using sgl_alloc_order(chainable=false) then the sgl
>> + *   will be an array with equally sized segments facilitating that
>> + *   arithmetic. The suggestion applies to s_skip, s_sgl and s_nents as well.
>> + *
>> + **/
>> +size_t sgl_copy_sgl(struct scatterlist *d_sgl, unsigned int d_nents, off_t
>> d_skip,
>> +            struct scatterlist *s_sgl, unsigned int s_nents, off_t s_skip,
>> +            size_t n_bytes)
>> +{
>> +    size_t d_off, s_off, len, d_len, s_len;
>> +    size_t offset = 0;
>> +    struct sg_mapping_iter d_iter;
>> +    struct sg_mapping_iter s_iter;
>> +
>> +    if (n_bytes == 0)
>> +        return 0;
>> +    sg_miter_start(&d_iter, d_sgl, d_nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
>> +    sg_miter_start(&s_iter, s_sgl, s_nents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
>> +    if (!sg_miter_skip(&d_iter, d_skip))
>> +        goto fini;
>> +    if (!sg_miter_skip(&s_iter, s_skip))
>> +        goto fini;
>> +
>> +    for (d_off = 0, s_off = 0; true ; ) {
>> +        /* Assume d_iter.length and s_iter.length can never be 0 */
>> +        if (d_off == 0) {
>> +            if (!sg_miter_next(&d_iter))
>> +                break;
>> +            d_len = d_iter.length;
>> +        } else {
>> +            d_len = d_iter.length - d_off;
>> +        }
>> +        if (s_off == 0) {
>> +            if (!sg_miter_next(&s_iter))
>> +                break;
>> +            s_len = s_iter.length;
>> +        } else {
>> +            s_len = s_iter.length - s_off;
>> +        }
>> +        len = min3(d_len, s_len, n_bytes - offset);
>> +
>> +        memcpy(d_iter.addr + d_off, s_iter.addr + s_off, len);
>> +        offset += len;
>> +        if (offset >= n_bytes)
>> +            break;
>> +        if (d_len == s_len) {
>> +            d_off = 0;
>> +            s_off = 0;
>> +        } else if (d_len < s_len) {
>> +            d_off = 0;
>> +            s_off += len;
>> +        } else {
>> +            d_off += len;
>> +            s_off = 0;
>> +        }
>> +    }
>> +fini:
>> +    sg_miter_stop(&d_iter);
>> +    sg_miter_stop(&s_iter);
>> +    return offset;
>> +}
>> +EXPORT_SYMBOL(sgl_copy_sgl);
>> +
>>