OpenCloudOS-Kernel/lib/scatterlist.c

1093 lines
28 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2007 Jens Axboe <jens.axboe@oracle.com>
*
* Scatterlist handling helpers.
*/
#include <linux/export.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/scatterlist.h>
#include <linux/highmem.h>
#include <linux/kmemleak.h>
/**
* sg_next - return the next scatterlist entry in a list
* @sg: The current sg entry
*
* Description:
* Usually the next entry will be @sg@ + 1, but if this sg element is part
* of a chained scatterlist, it could jump to the start of a new
* scatterlist array.
*
**/
struct scatterlist *sg_next(struct scatterlist *sg)
{
if (sg_is_last(sg))
return NULL;
sg++;
if (unlikely(sg_is_chain(sg)))
sg = sg_chain_ptr(sg);
return sg;
}
EXPORT_SYMBOL(sg_next);
/**
* sg_nents - return total count of entries in scatterlist
* @sg: The scatterlist
*
* Description:
* Allows to know how many entries are in sg, taking into account
* chaining as well
*
**/
int sg_nents(struct scatterlist *sg)
{
int nents;
for (nents = 0; sg; sg = sg_next(sg))
nents++;
return nents;
}
EXPORT_SYMBOL(sg_nents);
/**
* sg_nents_for_len - return total count of entries in scatterlist
* needed to satisfy the supplied length
* @sg: The scatterlist
* @len: The total required length
*
* Description:
* Determines the number of entries in sg that are required to meet
* the supplied length, taking into account chaining as well
*
* Returns:
* the number of sg entries needed, negative error on failure
*
**/
int sg_nents_for_len(struct scatterlist *sg, u64 len)
{
int nents;
u64 total;
if (!len)
return 0;
for (nents = 0, total = 0; sg; sg = sg_next(sg)) {
nents++;
total += sg->length;
if (total >= len)
return nents;
}
return -EINVAL;
}
EXPORT_SYMBOL(sg_nents_for_len);
/**
* sg_last - return the last scatterlist entry in a list
* @sgl: First entry in the scatterlist
* @nents: Number of entries in the scatterlist
*
* Description:
* Should only be used casually, it (currently) scans the entire list
* to get the last entry.
*
* Note that the @sgl@ pointer passed in need not be the first one,
* the important bit is that @nents@ denotes the number of entries that
* exist from @sgl@.
*
**/
struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
{
struct scatterlist *sg, *ret = NULL;
unsigned int i;
for_each_sg(sgl, sg, nents, i)
ret = sg;
BUG_ON(!sg_is_last(ret));
return ret;
}
EXPORT_SYMBOL(sg_last);
/**
* sg_init_table - Initialize SG table
* @sgl: The SG table
* @nents: Number of entries in table
*
* Notes:
* If this is part of a chained sg table, sg_mark_end() should be
* used only on the last table part.
*
**/
void sg_init_table(struct scatterlist *sgl, unsigned int nents)
{
memset(sgl, 0, sizeof(*sgl) * nents);
sg_init_marker(sgl, nents);
}
EXPORT_SYMBOL(sg_init_table);
/**
* sg_init_one - Initialize a single entry sg list
* @sg: SG entry
* @buf: Virtual address for IO
* @buflen: IO length
*
**/
void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
{
sg_init_table(sg, 1);
sg_set_buf(sg, buf, buflen);
}
EXPORT_SYMBOL(sg_init_one);
/*
* The default behaviour of sg_alloc_table() is to use these kmalloc/kfree
* helpers.
*/
static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask)
{
if (nents == SG_MAX_SINGLE_ALLOC) {
/*
* Kmemleak doesn't track page allocations as they are not
* commonly used (in a raw form) for kernel data structures.
* As we chain together a list of pages and then a normal
* kmalloc (tracked by kmemleak), in order to for that last
* allocation not to become decoupled (and thus a
* false-positive) we need to inform kmemleak of all the
* intermediate allocations.
*/
void *ptr = (void *) __get_free_page(gfp_mask);
kmemleak_alloc(ptr, PAGE_SIZE, 1, gfp_mask);
return ptr;
} else
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
return kmalloc_array(nents, sizeof(struct scatterlist),
gfp_mask);
}
static void sg_kfree(struct scatterlist *sg, unsigned int nents)
{
if (nents == SG_MAX_SINGLE_ALLOC) {
kmemleak_free(sg);
free_page((unsigned long) sg);
} else
kfree(sg);
}
/**
* __sg_free_table - Free a previously mapped sg table
* @table: The sg table header to use
* @max_ents: The maximum number of entries per single scatterlist
* @nents_first_chunk: Number of entries int the (preallocated) first
* scatterlist chunk, 0 means no such preallocated first chunk
* @free_fn: Free function
* @num_ents: Number of entries in the table
*
* Description:
* Free an sg table previously allocated and setup with
* __sg_alloc_table(). The @max_ents value must be identical to
* that previously used with __sg_alloc_table().
*
**/
void __sg_free_table(struct sg_table *table, unsigned int max_ents,
unsigned int nents_first_chunk, sg_free_fn *free_fn,
unsigned int num_ents)
{
struct scatterlist *sgl, *next;
unsigned curr_max_ents = nents_first_chunk ?: max_ents;
if (unlikely(!table->sgl))
return;
sgl = table->sgl;
while (num_ents) {
unsigned int alloc_size = num_ents;
unsigned int sg_size;
/*
* If we have more than max_ents segments left,
* then assign 'next' to the sg table after the current one.
* sg_size is then one less than alloc size, since the last
* element is the chain pointer.
*/
if (alloc_size > curr_max_ents) {
next = sg_chain_ptr(&sgl[curr_max_ents - 1]);
alloc_size = curr_max_ents;
sg_size = alloc_size - 1;
} else {
sg_size = alloc_size;
next = NULL;
}
num_ents -= sg_size;
if (nents_first_chunk)
nents_first_chunk = 0;
else
free_fn(sgl, alloc_size);
sgl = next;
curr_max_ents = max_ents;
}
table->sgl = NULL;
}
EXPORT_SYMBOL(__sg_free_table);
/**
* sg_free_append_table - Free a previously allocated append sg table.
* @table: The mapped sg append table header
*
**/
void sg_free_append_table(struct sg_append_table *table)
{
__sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, 0, sg_kfree,
table->total_nents);
}
EXPORT_SYMBOL(sg_free_append_table);
/**
* sg_free_table - Free a previously allocated sg table
* @table: The mapped sg table header
*
**/
void sg_free_table(struct sg_table *table)
{
__sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree,
table->orig_nents);
}
EXPORT_SYMBOL(sg_free_table);
/**
* __sg_alloc_table - Allocate and initialize an sg table with given allocator
* @table: The sg table header to use
* @nents: Number of entries in sg list
* @max_ents: The maximum number of entries the allocator returns per call
* @nents_first_chunk: Number of entries int the (preallocated) first
* scatterlist chunk, 0 means no such preallocated chunk provided by user
* @gfp_mask: GFP allocation mask
* @alloc_fn: Allocator to use
*
* Description:
* This function returns a @table @nents long. The allocator is
* defined to return scatterlist chunks of maximum size @max_ents.
* Thus if @nents is bigger than @max_ents, the scatterlists will be
* chained in units of @max_ents.
*
* Notes:
* If this function returns non-0 (eg failure), the caller must call
* __sg_free_table() to cleanup any leftover allocations.
*
**/
int __sg_alloc_table(struct sg_table *table, unsigned int nents,
unsigned int max_ents, struct scatterlist *first_chunk,
unsigned int nents_first_chunk, gfp_t gfp_mask,
sg_alloc_fn *alloc_fn)
{
struct scatterlist *sg, *prv;
unsigned int left;
unsigned curr_max_ents = nents_first_chunk ?: max_ents;
unsigned prv_max_ents;
memset(table, 0, sizeof(*table));
if (nents == 0)
return -EINVAL;
#ifdef CONFIG_ARCH_NO_SG_CHAIN
if (WARN_ON_ONCE(nents > max_ents))
return -EINVAL;
#endif
left = nents;
prv = NULL;
do {
unsigned int sg_size, alloc_size = left;
if (alloc_size > curr_max_ents) {
alloc_size = curr_max_ents;
sg_size = alloc_size - 1;
} else
sg_size = alloc_size;
left -= sg_size;
if (first_chunk) {
sg = first_chunk;
first_chunk = NULL;
} else {
sg = alloc_fn(alloc_size, gfp_mask);
}
if (unlikely(!sg)) {
/*
* Adjust entry count to reflect that the last
* entry of the previous table won't be used for
* linkage. Without this, sg_kfree() may get
* confused.
*/
if (prv)
table->nents = ++table->orig_nents;
return -ENOMEM;
}
sg_init_table(sg, alloc_size);
table->nents = table->orig_nents += sg_size;
/*
* If this is the first mapping, assign the sg table header.
* If this is not the first mapping, chain previous part.
*/
if (prv)
sg_chain(prv, prv_max_ents, sg);
else
table->sgl = sg;
/*
* If no more entries after this one, mark the end
*/
if (!left)
sg_mark_end(&sg[sg_size - 1]);
prv = sg;
prv_max_ents = curr_max_ents;
curr_max_ents = max_ents;
} while (left);
return 0;
}
EXPORT_SYMBOL(__sg_alloc_table);
/**
* sg_alloc_table - Allocate and initialize an sg table
* @table: The sg table header to use
* @nents: Number of entries in sg list
* @gfp_mask: GFP allocation mask
*
* Description:
* Allocate and initialize an sg table. If @nents@ is larger than
* SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
*
**/
int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
{
int ret;
ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC,
NULL, 0, gfp_mask, sg_kmalloc);
if (unlikely(ret))
sg_free_table(table);
return ret;
}
EXPORT_SYMBOL(sg_alloc_table);
static struct scatterlist *get_next_sg(struct sg_append_table *table,
struct scatterlist *cur,
unsigned long needed_sges,
gfp_t gfp_mask)
{
struct scatterlist *new_sg, *next_sg;
unsigned int alloc_size;
if (cur) {
next_sg = sg_next(cur);
/* Check if last entry should be keeped for chainning */
if (!sg_is_last(next_sg) || needed_sges == 1)
return next_sg;
}
alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC);
new_sg = sg_kmalloc(alloc_size, gfp_mask);
if (!new_sg)
return ERR_PTR(-ENOMEM);
sg_init_table(new_sg, alloc_size);
if (cur) {
table->total_nents += alloc_size - 1;
__sg_chain(next_sg, new_sg);
} else {
table->sgt.sgl = new_sg;
table->total_nents = alloc_size;
}
return new_sg;
}
static bool pages_are_mergeable(struct page *a, struct page *b)
{
if (page_to_pfn(a) != page_to_pfn(b) + 1)
return false;
if (!zone_device_pages_have_same_pgmap(a, b))
return false;
return true;
}
/**
* sg_alloc_append_table_from_pages - Allocate and initialize an append sg
* table from an array of pages
* @sgt_append: The sg append table to use
* @pages: Pointer to an array of page pointers
* @n_pages: Number of pages in the pages array
* @offset: Offset from start of the first page to the start of a buffer
* @size: Number of valid bytes in the buffer (after offset)
* @max_segment: Maximum size of a scatterlist element in bytes
* @left_pages: Left pages caller have to set after this call
* @gfp_mask: GFP allocation mask
*
* Description:
* In the first call it allocate and initialize an sg table from a list of
* pages, else reuse the scatterlist from sgt_append. Contiguous ranges of
* the pages are squashed into a single scatterlist entry up to the maximum
* size specified in @max_segment. A user may provide an offset at a start
* and a size of valid data in a buffer specified by the page array. The
* returned sg table is released by sg_free_append_table
*
* Returns:
* 0 on success, negative error on failure
*
* Notes:
* If this function returns non-0 (eg failure), the caller must call
* sg_free_append_table() to cleanup any leftover allocations.
*
* In the fist call, sgt_append must by initialized.
*/
int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
struct page **pages, unsigned int n_pages, unsigned int offset,
unsigned long size, unsigned int max_segment,
unsigned int left_pages, gfp_t gfp_mask)
{
unsigned int chunks, cur_page, seg_len, i, prv_len = 0;
unsigned int added_nents = 0;
struct scatterlist *s = sgt_append->prv;
struct page *last_pg;
/*
* The algorithm below requires max_segment to be aligned to PAGE_SIZE
* otherwise it can overshoot.
*/
max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE);
if (WARN_ON(max_segment < PAGE_SIZE))
return -EINVAL;
if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv)
return -EOPNOTSUPP;
if (sgt_append->prv) {
if (WARN_ON(offset))
return -EINVAL;
/* Merge contiguous pages into the last SG */
prv_len = sgt_append->prv->length;
last_pg = sg_page(sgt_append->prv);
while (n_pages && pages_are_mergeable(last_pg, pages[0])) {
if (sgt_append->prv->length + PAGE_SIZE > max_segment)
break;
sgt_append->prv->length += PAGE_SIZE;
last_pg = pages[0];
pages++;
n_pages--;
}
if (!n_pages)
goto out;
}
/* compute number of contiguous chunks */
chunks = 1;
seg_len = 0;
for (i = 1; i < n_pages; i++) {
seg_len += PAGE_SIZE;
if (seg_len >= max_segment ||
!pages_are_mergeable(pages[i], pages[i - 1])) {
chunks++;
seg_len = 0;
}
}
/* merging chunks and putting them into the scatterlist */
cur_page = 0;
for (i = 0; i < chunks; i++) {
unsigned int j, chunk_size;
/* look for the end of the current chunk */
seg_len = 0;
for (j = cur_page + 1; j < n_pages; j++) {
seg_len += PAGE_SIZE;
if (seg_len >= max_segment ||
!pages_are_mergeable(pages[j], pages[j - 1]))
break;
}
/* Pass how many chunks might be left */
s = get_next_sg(sgt_append, s, chunks - i + left_pages,
gfp_mask);
if (IS_ERR(s)) {
/*
* Adjust entry length to be as before function was
* called.
*/
if (sgt_append->prv)
sgt_append->prv->length = prv_len;
return PTR_ERR(s);
}
chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
sg_set_page(s, pages[cur_page],
min_t(unsigned long, size, chunk_size), offset);
added_nents++;
size -= chunk_size;
offset = 0;
cur_page = j;
}
sgt_append->sgt.nents += added_nents;
sgt_append->sgt.orig_nents = sgt_append->sgt.nents;
sgt_append->prv = s;
out:
if (!left_pages)
sg_mark_end(s);
return 0;
}
EXPORT_SYMBOL(sg_alloc_append_table_from_pages);
/**
* sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from
* an array of pages and given maximum
* segment.
* @sgt: The sg table header to use
* @pages: Pointer to an array of page pointers
* @n_pages: Number of pages in the pages array
* @offset: Offset from start of the first page to the start of a buffer
* @size: Number of valid bytes in the buffer (after offset)
* @max_segment: Maximum size of a scatterlist element in bytes
* @gfp_mask: GFP allocation mask
*
* Description:
* Allocate and initialize an sg table from a list of pages. Contiguous
* ranges of the pages are squashed into a single scatterlist node up to the
* maximum size specified in @max_segment. A user may provide an offset at a
* start and a size of valid data in a buffer specified by the page array.
*
* The returned sg table is released by sg_free_table.
*
* Returns:
* 0 on success, negative error on failure
*/
int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages,
unsigned int n_pages, unsigned int offset,
unsigned long size, unsigned int max_segment,
gfp_t gfp_mask)
{
struct sg_append_table append = {};
int err;
err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset,
size, max_segment, 0, gfp_mask);
if (err) {
sg_free_append_table(&append);
return err;
}
memcpy(sgt, &append.sgt, sizeof(*sgt));
WARN_ON(append.total_nents != sgt->orig_nents);
return 0;
}
EXPORT_SYMBOL(sg_alloc_table_from_pages_segment);
#ifdef CONFIG_SGL_ALLOC
/**
* sgl_alloc_order - allocate a scatterlist and its pages
* @length: Length in bytes of the scatterlist. Must be at least one
* @order: Second argument for alloc_pages()
* @chainable: Whether or not to allocate an extra element in the scatterlist
* for scatterlist chaining purposes
* @gfp: Memory allocation flags
* @nent_p: [out] Number of entries in the scatterlist that have pages
*
* Returns: A pointer to an initialized scatterlist or %NULL upon failure.
*/
struct scatterlist *sgl_alloc_order(unsigned long long length,
unsigned int order, bool chainable,
gfp_t gfp, unsigned int *nent_p)
{
struct scatterlist *sgl, *sg;
struct page *page;
unsigned int nent, nalloc;
u32 elem_len;
nent = round_up(length, PAGE_SIZE << order) >> (PAGE_SHIFT + order);
/* Check for integer overflow */
if (length > (nent << (PAGE_SHIFT + order)))
return NULL;
nalloc = nent;
if (chainable) {
/* Check for integer overflow */
if (nalloc + 1 < nalloc)
return NULL;
nalloc++;
}
sgl = kmalloc_array(nalloc, sizeof(struct scatterlist),
gfp & ~GFP_DMA);
if (!sgl)
return NULL;
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
sg_init_table(sgl, nalloc);
sg = sgl;
while (length) {
elem_len = min_t(u64, length, PAGE_SIZE << order);
page = alloc_pages(gfp, order);
if (!page) {
sgl_free_order(sgl, order);
return NULL;
}
sg_set_page(sg, page, elem_len, 0);
length -= elem_len;
sg = sg_next(sg);
}
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
WARN_ONCE(length, "length = %lld\n", length);
if (nent_p)
*nent_p = nent;
return sgl;
}
EXPORT_SYMBOL(sgl_alloc_order);
/**
* sgl_alloc - allocate a scatterlist and its pages
* @length: Length in bytes of the scatterlist
* @gfp: Memory allocation flags
* @nent_p: [out] Number of entries in the scatterlist
*
* Returns: A pointer to an initialized scatterlist or %NULL upon failure.
*/
struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp,
unsigned int *nent_p)
{
return sgl_alloc_order(length, 0, false, gfp, nent_p);
}
EXPORT_SYMBOL(sgl_alloc);
/**
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
* sgl_free_n_order - free a scatterlist and its pages
* @sgl: Scatterlist with one or more elements
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
* @nents: Maximum number of elements to free
* @order: Second argument for __free_pages()
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
*
* Notes:
* - If several scatterlists have been chained and each chain element is
* freed separately then it's essential to set nents correctly to avoid that a
* page would get freed twice.
* - All pages in a chained scatterlist can be freed at once by setting @nents
* to a high number.
*/
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
void sgl_free_n_order(struct scatterlist *sgl, int nents, int order)
{
struct scatterlist *sg;
struct page *page;
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
int i;
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
for_each_sg(sgl, sg, nents, i) {
if (!sg)
break;
page = sg_page(sg);
if (page)
__free_pages(page, order);
}
kfree(sgl);
}
lib/scatterlist: Fix chaining support in sgl_alloc_order() This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com> Cc: Nicholas A. Bellinger <nab@linux-iscsi.org> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-20 03:00:54 +08:00
EXPORT_SYMBOL(sgl_free_n_order);
/**
* sgl_free_order - free a scatterlist and its pages
* @sgl: Scatterlist with one or more elements
* @order: Second argument for __free_pages()
*/
void sgl_free_order(struct scatterlist *sgl, int order)
{
sgl_free_n_order(sgl, INT_MAX, order);
}
EXPORT_SYMBOL(sgl_free_order);
/**
* sgl_free - free a scatterlist and its pages
* @sgl: Scatterlist with one or more elements
*/
void sgl_free(struct scatterlist *sgl)
{
sgl_free_order(sgl, 0);
}
EXPORT_SYMBOL(sgl_free);
#endif /* CONFIG_SGL_ALLOC */
void __sg_page_iter_start(struct sg_page_iter *piter,
struct scatterlist *sglist, unsigned int nents,
unsigned long pgoffset)
{
piter->__pg_advance = 0;
piter->__nents = nents;
piter->sg = sglist;
piter->sg_pgoffset = pgoffset;
}
EXPORT_SYMBOL(__sg_page_iter_start);
static int sg_page_count(struct scatterlist *sg)
{
return PAGE_ALIGN(sg->offset + sg->length) >> PAGE_SHIFT;
}
bool __sg_page_iter_next(struct sg_page_iter *piter)
{
if (!piter->__nents || !piter->sg)
return false;
piter->sg_pgoffset += piter->__pg_advance;
piter->__pg_advance = 1;
while (piter->sg_pgoffset >= sg_page_count(piter->sg)) {
piter->sg_pgoffset -= sg_page_count(piter->sg);
piter->sg = sg_next(piter->sg);
if (!--piter->__nents || !piter->sg)
return false;
}
return true;
}
EXPORT_SYMBOL(__sg_page_iter_next);
static int sg_dma_page_count(struct scatterlist *sg)
{
return PAGE_ALIGN(sg->offset + sg_dma_len(sg)) >> PAGE_SHIFT;
}
bool __sg_page_iter_dma_next(struct sg_dma_page_iter *dma_iter)
{
struct sg_page_iter *piter = &dma_iter->base;
if (!piter->__nents || !piter->sg)
return false;
piter->sg_pgoffset += piter->__pg_advance;
piter->__pg_advance = 1;
while (piter->sg_pgoffset >= sg_dma_page_count(piter->sg)) {
piter->sg_pgoffset -= sg_dma_page_count(piter->sg);
piter->sg = sg_next(piter->sg);
if (!--piter->__nents || !piter->sg)
return false;
}
return true;
}
EXPORT_SYMBOL(__sg_page_iter_dma_next);
/**
* sg_miter_start - start mapping iteration over a sg list
* @miter: sg mapping iter to be started
* @sgl: sg list to iterate over
* @nents: number of sg entries
*
* Description:
* Starts mapping iterator @miter.
*
* Context:
* Don't care.
*/
void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl,
unsigned int nents, unsigned int flags)
{
memset(miter, 0, sizeof(struct sg_mapping_iter));
__sg_page_iter_start(&miter->piter, sgl, nents, 0);
WARN_ON(!(flags & (SG_MITER_TO_SG | SG_MITER_FROM_SG)));
miter->__flags = flags;
}
EXPORT_SYMBOL(sg_miter_start);
static bool sg_miter_get_next_page(struct sg_mapping_iter *miter)
{
if (!miter->__remaining) {
struct scatterlist *sg;
if (!__sg_page_iter_next(&miter->piter))
return false;
sg = miter->piter.sg;
miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset;
miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT;
miter->__offset &= PAGE_SIZE - 1;
miter->__remaining = sg->offset + sg->length -
(miter->piter.sg_pgoffset << PAGE_SHIFT) -
miter->__offset;
miter->__remaining = min_t(unsigned long, miter->__remaining,
PAGE_SIZE - miter->__offset);
}
return true;
}
/**
* sg_miter_skip - reposition mapping iterator
* @miter: sg mapping iter to be skipped
* @offset: number of bytes to plus the current location
*
* Description:
* Sets the offset of @miter to its current location plus @offset bytes.
* If mapping iterator @miter has been proceeded by sg_miter_next(), this
* stops @miter.
*
* Context:
mm/scatterlist: replace the !preemptible warning in sg_miter_stop() sg_miter_stop() checks for disabled preemption before unmapping a page via kunmap_atomic(). The kernel doc mentions under context that preemption must be disabled if SG_MITER_ATOMIC is set. There is no active requirement for the caller to have preemption disabled before invoking sg_mitter_stop(). The sg_mitter_*() implementation itself has no such requirement. In fact, preemption is disabled by kmap_atomic() as part of sg_miter_next() and remains disabled as long as there is an active SG_MITER_ATOMIC mapping. This is a consequence of kmap_atomic() and not a requirement for sg_mitter_*() itself. The user chooses SG_MITER_ATOMIC because it uses the API in a context where blocking is not possible or blocking is possible but he chooses a lower weight mapping which is not available on all CPUs and so it might need less overhead to setup at a price that now preemption will be disabled. The kmap_atomic() implementation on PREEMPT_RT does not disable preemption. It simply disables CPU migration to ensure that the task remains on the same CPU while the caller remains preemptible. This in turn triggers the warning in sg_miter_stop() because preemption is allowed. The PREEMPT_RT and !PREEMPT_RT implementation of kmap_atomic() disable pagefaults as a requirement. It is sufficient to check for this instead of disabled preemption. Check for disabled pagefault handler in the SG_MITER_ATOMIC case. Remove the "preemption disabled" part from the kernel doc as the sg_milter*() implementation does not care. [bigeasy@linutronix.de: commit description] Link: https://lkml.kernel.org/r/20211015211409.cqopacv3pxdwn2ty@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 10:33:25 +08:00
* Don't care.
*
* Returns:
* true if @miter contains the valid mapping. false if end of sg
* list is reached.
*/
bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset)
{
sg_miter_stop(miter);
while (offset) {
off_t consumed;
if (!sg_miter_get_next_page(miter))
return false;
consumed = min_t(off_t, offset, miter->__remaining);
miter->__offset += consumed;
miter->__remaining -= consumed;
offset -= consumed;
}
return true;
}
EXPORT_SYMBOL(sg_miter_skip);
/**
* sg_miter_next - proceed mapping iterator to the next mapping
* @miter: sg mapping iter to proceed
*
* Description:
* Proceeds @miter to the next mapping. @miter should have been started
* using sg_miter_start(). On successful return, @miter->page,
* @miter->addr and @miter->length point to the current mapping.
*
* Context:
mm/scatterlist: replace the !preemptible warning in sg_miter_stop() sg_miter_stop() checks for disabled preemption before unmapping a page via kunmap_atomic(). The kernel doc mentions under context that preemption must be disabled if SG_MITER_ATOMIC is set. There is no active requirement for the caller to have preemption disabled before invoking sg_mitter_stop(). The sg_mitter_*() implementation itself has no such requirement. In fact, preemption is disabled by kmap_atomic() as part of sg_miter_next() and remains disabled as long as there is an active SG_MITER_ATOMIC mapping. This is a consequence of kmap_atomic() and not a requirement for sg_mitter_*() itself. The user chooses SG_MITER_ATOMIC because it uses the API in a context where blocking is not possible or blocking is possible but he chooses a lower weight mapping which is not available on all CPUs and so it might need less overhead to setup at a price that now preemption will be disabled. The kmap_atomic() implementation on PREEMPT_RT does not disable preemption. It simply disables CPU migration to ensure that the task remains on the same CPU while the caller remains preemptible. This in turn triggers the warning in sg_miter_stop() because preemption is allowed. The PREEMPT_RT and !PREEMPT_RT implementation of kmap_atomic() disable pagefaults as a requirement. It is sufficient to check for this instead of disabled preemption. Check for disabled pagefault handler in the SG_MITER_ATOMIC case. Remove the "preemption disabled" part from the kernel doc as the sg_milter*() implementation does not care. [bigeasy@linutronix.de: commit description] Link: https://lkml.kernel.org/r/20211015211409.cqopacv3pxdwn2ty@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 10:33:25 +08:00
* May sleep if !SG_MITER_ATOMIC.
*
* Returns:
* true if @miter contains the next mapping. false if end of sg
* list is reached.
*/
bool sg_miter_next(struct sg_mapping_iter *miter)
{
sg_miter_stop(miter);
/*
* Get to the next page if necessary.
* __remaining, __offset is adjusted by sg_miter_stop
*/
if (!sg_miter_get_next_page(miter))
return false;
miter->page = sg_page_iter_page(&miter->piter);
miter->consumed = miter->length = miter->__remaining;
if (miter->__flags & SG_MITER_ATOMIC)
miter->addr = kmap_atomic(miter->page) + miter->__offset;
else
miter->addr = kmap(miter->page) + miter->__offset;
return true;
}
EXPORT_SYMBOL(sg_miter_next);
/**
* sg_miter_stop - stop mapping iteration
* @miter: sg mapping iter to be stopped
*
* Description:
* Stops mapping iterator @miter. @miter should have been started
* using sg_miter_start(). A stopped iteration can be resumed by
* calling sg_miter_next() on it. This is useful when resources (kmap)
* need to be released during iteration.
*
* Context:
mm/scatterlist: replace the !preemptible warning in sg_miter_stop() sg_miter_stop() checks for disabled preemption before unmapping a page via kunmap_atomic(). The kernel doc mentions under context that preemption must be disabled if SG_MITER_ATOMIC is set. There is no active requirement for the caller to have preemption disabled before invoking sg_mitter_stop(). The sg_mitter_*() implementation itself has no such requirement. In fact, preemption is disabled by kmap_atomic() as part of sg_miter_next() and remains disabled as long as there is an active SG_MITER_ATOMIC mapping. This is a consequence of kmap_atomic() and not a requirement for sg_mitter_*() itself. The user chooses SG_MITER_ATOMIC because it uses the API in a context where blocking is not possible or blocking is possible but he chooses a lower weight mapping which is not available on all CPUs and so it might need less overhead to setup at a price that now preemption will be disabled. The kmap_atomic() implementation on PREEMPT_RT does not disable preemption. It simply disables CPU migration to ensure that the task remains on the same CPU while the caller remains preemptible. This in turn triggers the warning in sg_miter_stop() because preemption is allowed. The PREEMPT_RT and !PREEMPT_RT implementation of kmap_atomic() disable pagefaults as a requirement. It is sufficient to check for this instead of disabled preemption. Check for disabled pagefault handler in the SG_MITER_ATOMIC case. Remove the "preemption disabled" part from the kernel doc as the sg_milter*() implementation does not care. [bigeasy@linutronix.de: commit description] Link: https://lkml.kernel.org/r/20211015211409.cqopacv3pxdwn2ty@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 10:33:25 +08:00
* Don't care otherwise.
*/
void sg_miter_stop(struct sg_mapping_iter *miter)
{
WARN_ON(miter->consumed > miter->length);
/* drop resources from the last iteration */
if (miter->addr) {
miter->__offset += miter->consumed;
miter->__remaining -= miter->consumed;
if (miter->__flags & SG_MITER_TO_SG)
flush_dcache_page(miter->page);
if (miter->__flags & SG_MITER_ATOMIC) {
mm/scatterlist: replace the !preemptible warning in sg_miter_stop() sg_miter_stop() checks for disabled preemption before unmapping a page via kunmap_atomic(). The kernel doc mentions under context that preemption must be disabled if SG_MITER_ATOMIC is set. There is no active requirement for the caller to have preemption disabled before invoking sg_mitter_stop(). The sg_mitter_*() implementation itself has no such requirement. In fact, preemption is disabled by kmap_atomic() as part of sg_miter_next() and remains disabled as long as there is an active SG_MITER_ATOMIC mapping. This is a consequence of kmap_atomic() and not a requirement for sg_mitter_*() itself. The user chooses SG_MITER_ATOMIC because it uses the API in a context where blocking is not possible or blocking is possible but he chooses a lower weight mapping which is not available on all CPUs and so it might need less overhead to setup at a price that now preemption will be disabled. The kmap_atomic() implementation on PREEMPT_RT does not disable preemption. It simply disables CPU migration to ensure that the task remains on the same CPU while the caller remains preemptible. This in turn triggers the warning in sg_miter_stop() because preemption is allowed. The PREEMPT_RT and !PREEMPT_RT implementation of kmap_atomic() disable pagefaults as a requirement. It is sufficient to check for this instead of disabled preemption. Check for disabled pagefault handler in the SG_MITER_ATOMIC case. Remove the "preemption disabled" part from the kernel doc as the sg_milter*() implementation does not care. [bigeasy@linutronix.de: commit description] Link: https://lkml.kernel.org/r/20211015211409.cqopacv3pxdwn2ty@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 10:33:25 +08:00
WARN_ON_ONCE(!pagefault_disabled());
kunmap_atomic(miter->addr);
} else
kunmap(miter->page);
miter->page = NULL;
miter->addr = NULL;
miter->length = 0;
miter->consumed = 0;
}
}
EXPORT_SYMBOL(sg_miter_stop);
/**
* sg_copy_buffer - Copy data between a linear buffer and an SG list
* @sgl: The SG list
* @nents: Number of SG entries
* @buf: Where to copy from
* @buflen: The number of bytes to copy
* @skip: Number of bytes to skip before copying
* @to_buffer: transfer direction (true == from an sg list to a
* buffer, false == from a buffer to an sg list)
*
* Returns the number of copied bytes.
*
**/
size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
size_t buflen, off_t skip, bool to_buffer)
{
unsigned int offset = 0;
struct sg_mapping_iter miter;
unsigned int sg_flags = SG_MITER_ATOMIC;
if (to_buffer)
sg_flags |= SG_MITER_FROM_SG;
else
sg_flags |= SG_MITER_TO_SG;
sg_miter_start(&miter, sgl, nents, sg_flags);
if (!sg_miter_skip(&miter, skip))
return 0;
while ((offset < buflen) && sg_miter_next(&miter)) {
unsigned int len;
len = min(miter.length, buflen - offset);
if (to_buffer)
memcpy(buf + offset, miter.addr, len);
else
memcpy(miter.addr, buf + offset, len);
offset += len;
}
sg_miter_stop(&miter);
return offset;
}
EXPORT_SYMBOL(sg_copy_buffer);
/**
* sg_copy_from_buffer - Copy from a linear buffer to an SG list
* @sgl: The SG list
* @nents: Number of SG entries
* @buf: Where to copy from
* @buflen: The number of bytes to copy
*
* Returns the number of copied bytes.
*
**/
size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
const void *buf, size_t buflen)
{
return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false);
}
EXPORT_SYMBOL(sg_copy_from_buffer);
/**
* sg_copy_to_buffer - Copy from an SG list to a linear buffer
* @sgl: The SG list
* @nents: Number of SG entries
* @buf: Where to copy to
* @buflen: The number of bytes to copy
*
* Returns the number of copied bytes.
*
**/
size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
void *buf, size_t buflen)
{
return sg_copy_buffer(sgl, nents, buf, buflen, 0, true);
}
EXPORT_SYMBOL(sg_copy_to_buffer);
/**
* sg_pcopy_from_buffer - Copy from a linear buffer to an SG list
* @sgl: The SG list
* @nents: Number of SG entries
* @buf: Where to copy from
* @buflen: The number of bytes to copy
* @skip: Number of bytes to skip before copying
*
* Returns the number of copied bytes.
*
**/
size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
const void *buf, size_t buflen, off_t skip)
{
return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false);
}
EXPORT_SYMBOL(sg_pcopy_from_buffer);
/**
* sg_pcopy_to_buffer - Copy from an SG list to a linear buffer
* @sgl: The SG list
* @nents: Number of SG entries
* @buf: Where to copy to
* @buflen: The number of bytes to copy
* @skip: Number of bytes to skip before copying
*
* Returns the number of copied bytes.
*
**/
size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
void *buf, size_t buflen, off_t skip)
{
return sg_copy_buffer(sgl, nents, buf, buflen, skip, true);
}
EXPORT_SYMBOL(sg_pcopy_to_buffer);
/**
* sg_zero_buffer - Zero-out a part of a SG list
* @sgl: The SG list
* @nents: Number of SG entries
* @buflen: The number of bytes to zero out
* @skip: Number of bytes to skip before zeroing
*
* Returns the number of bytes zeroed.
**/
size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
size_t buflen, off_t skip)
{
unsigned int offset = 0;
struct sg_mapping_iter miter;
unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG;
sg_miter_start(&miter, sgl, nents, sg_flags);
if (!sg_miter_skip(&miter, skip))
return false;
while (offset < buflen && sg_miter_next(&miter)) {
unsigned int len;
len = min(miter.length, buflen - offset);
memset(miter.addr, 0, len);
offset += len;
}
sg_miter_stop(&miter);
return offset;
}
EXPORT_SYMBOL(sg_zero_buffer);