mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
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>
416 lines
12 KiB
C
416 lines
12 KiB
C
/*
|
|
* Copyright(c) 2007 Yuri Tikhonov <yur@emcraft.com>
|
|
* Copyright(c) 2009 Intel Corporation
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License as published by the Free
|
|
* Software Foundation; either version 2 of the License, or (at your option)
|
|
* any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc., 59
|
|
* Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
*
|
|
* The full GNU General Public License is included in this distribution in the
|
|
* file called COPYING.
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/dma-mapping.h>
|
|
#include <linux/raid/pq.h>
|
|
#include <linux/async_tx.h>
|
|
#include <linux/gfp.h>
|
|
|
|
/**
|
|
* pq_scribble_page - space to hold throwaway P or Q buffer for
|
|
* synchronous gen_syndrome
|
|
*/
|
|
static struct page *pq_scribble_page;
|
|
|
|
/* the struct page *blocks[] parameter passed to async_gen_syndrome()
|
|
* and async_syndrome_val() contains the 'P' destination address at
|
|
* blocks[disks-2] and the 'Q' destination address at blocks[disks-1]
|
|
*
|
|
* note: these are macros as they are used as lvalues
|
|
*/
|
|
#define P(b, d) (b[d-2])
|
|
#define Q(b, d) (b[d-1])
|
|
|
|
/**
|
|
* do_async_gen_syndrome - asynchronously calculate P and/or Q
|
|
*/
|
|
static __async_inline struct dma_async_tx_descriptor *
|
|
do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
|
|
const unsigned char *scfs, unsigned int offset, int disks,
|
|
size_t len, dma_addr_t *dma_src,
|
|
struct async_submit_ctl *submit)
|
|
{
|
|
struct dma_async_tx_descriptor *tx = NULL;
|
|
struct dma_device *dma = chan->device;
|
|
enum dma_ctrl_flags dma_flags = 0;
|
|
enum async_tx_flags flags_orig = submit->flags;
|
|
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
|
|
dma_async_tx_callback cb_param_orig = submit->cb_param;
|
|
int src_cnt = disks - 2;
|
|
unsigned char coefs[src_cnt];
|
|
unsigned short pq_src_cnt;
|
|
dma_addr_t dma_dest[2];
|
|
int src_off = 0;
|
|
int idx;
|
|
int i;
|
|
|
|
/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
|
|
if (P(blocks, disks))
|
|
dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
|
|
len, DMA_BIDIRECTIONAL);
|
|
else
|
|
dma_flags |= DMA_PREP_PQ_DISABLE_P;
|
|
if (Q(blocks, disks))
|
|
dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
|
|
len, DMA_BIDIRECTIONAL);
|
|
else
|
|
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
|
|
|
|
/* convert source addresses being careful to collapse 'empty'
|
|
* sources and update the coefficients accordingly
|
|
*/
|
|
for (i = 0, idx = 0; i < src_cnt; i++) {
|
|
if (blocks[i] == NULL)
|
|
continue;
|
|
dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
|
|
DMA_TO_DEVICE);
|
|
coefs[idx] = scfs[i];
|
|
idx++;
|
|
}
|
|
src_cnt = idx;
|
|
|
|
while (src_cnt > 0) {
|
|
submit->flags = flags_orig;
|
|
pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
|
|
/* if we are submitting additional pqs, leave the chain open,
|
|
* clear the callback parameters, and leave the destination
|
|
* buffers mapped
|
|
*/
|
|
if (src_cnt > pq_src_cnt) {
|
|
submit->flags &= ~ASYNC_TX_ACK;
|
|
submit->flags |= ASYNC_TX_FENCE;
|
|
dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
|
|
submit->cb_fn = NULL;
|
|
submit->cb_param = NULL;
|
|
} else {
|
|
dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
|
|
submit->cb_fn = cb_fn_orig;
|
|
submit->cb_param = cb_param_orig;
|
|
if (cb_fn_orig)
|
|
dma_flags |= DMA_PREP_INTERRUPT;
|
|
}
|
|
if (submit->flags & ASYNC_TX_FENCE)
|
|
dma_flags |= DMA_PREP_FENCE;
|
|
|
|
/* Since we have clobbered the src_list we are committed
|
|
* to doing this asynchronously. Drivers force forward
|
|
* progress in case they can not provide a descriptor
|
|
*/
|
|
for (;;) {
|
|
tx = dma->device_prep_dma_pq(chan, dma_dest,
|
|
&dma_src[src_off],
|
|
pq_src_cnt,
|
|
&coefs[src_off], len,
|
|
dma_flags);
|
|
if (likely(tx))
|
|
break;
|
|
async_tx_quiesce(&submit->depend_tx);
|
|
dma_async_issue_pending(chan);
|
|
}
|
|
|
|
async_tx_submit(chan, tx, submit);
|
|
submit->depend_tx = tx;
|
|
|
|
/* drop completed sources */
|
|
src_cnt -= pq_src_cnt;
|
|
src_off += pq_src_cnt;
|
|
|
|
dma_flags |= DMA_PREP_CONTINUE;
|
|
}
|
|
|
|
return tx;
|
|
}
|
|
|
|
/**
|
|
* do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
|
|
*/
|
|
static void
|
|
do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
|
|
size_t len, struct async_submit_ctl *submit)
|
|
{
|
|
void **srcs;
|
|
int i;
|
|
|
|
if (submit->scribble)
|
|
srcs = submit->scribble;
|
|
else
|
|
srcs = (void **) blocks;
|
|
|
|
for (i = 0; i < disks; i++) {
|
|
if (blocks[i] == NULL) {
|
|
BUG_ON(i > disks - 3); /* P or Q can't be zero */
|
|
srcs[i] = (void*)raid6_empty_zero_page;
|
|
} else
|
|
srcs[i] = page_address(blocks[i]) + offset;
|
|
}
|
|
raid6_call.gen_syndrome(disks, len, srcs);
|
|
async_tx_sync_epilog(submit);
|
|
}
|
|
|
|
/**
|
|
* async_gen_syndrome - asynchronously calculate a raid6 syndrome
|
|
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
|
|
* @offset: common offset into each block (src and dest) to start transaction
|
|
* @disks: number of blocks (including missing P or Q, see below)
|
|
* @len: length of operation in bytes
|
|
* @submit: submission/completion modifiers
|
|
*
|
|
* General note: This routine assumes a field of GF(2^8) with a
|
|
* primitive polynomial of 0x11d and a generator of {02}.
|
|
*
|
|
* 'disks' note: callers can optionally omit either P or Q (but not
|
|
* both) from the calculation by setting blocks[disks-2] or
|
|
* blocks[disks-1] to NULL. When P or Q is omitted 'len' must be <=
|
|
* PAGE_SIZE as a temporary buffer of this size is used in the
|
|
* synchronous path. 'disks' always accounts for both destination
|
|
* buffers. If any source buffers (blocks[i] where i < disks - 2) are
|
|
* set to NULL those buffers will be replaced with the raid6_zero_page
|
|
* in the synchronous path and omitted in the hardware-asynchronous
|
|
* path.
|
|
*
|
|
* 'blocks' note: if submit->scribble is NULL then the contents of
|
|
* 'blocks' may be overwritten to perform address conversions
|
|
* (dma_map_page() or page_address()).
|
|
*/
|
|
struct dma_async_tx_descriptor *
|
|
async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
|
|
size_t len, struct async_submit_ctl *submit)
|
|
{
|
|
int src_cnt = disks - 2;
|
|
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
|
|
&P(blocks, disks), 2,
|
|
blocks, src_cnt, len);
|
|
struct dma_device *device = chan ? chan->device : NULL;
|
|
dma_addr_t *dma_src = NULL;
|
|
|
|
BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
|
|
|
|
if (submit->scribble)
|
|
dma_src = submit->scribble;
|
|
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
|
|
dma_src = (dma_addr_t *) blocks;
|
|
|
|
if (dma_src && device &&
|
|
(src_cnt <= dma_maxpq(device, 0) ||
|
|
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
|
|
is_dma_pq_aligned(device, offset, 0, len)) {
|
|
/* run the p+q asynchronously */
|
|
pr_debug("%s: (async) disks: %d len: %zu\n",
|
|
__func__, disks, len);
|
|
return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
|
|
disks, len, dma_src, submit);
|
|
}
|
|
|
|
/* run the pq synchronously */
|
|
pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
|
|
|
|
/* wait for any prerequisite operations */
|
|
async_tx_quiesce(&submit->depend_tx);
|
|
|
|
if (!P(blocks, disks)) {
|
|
P(blocks, disks) = pq_scribble_page;
|
|
BUG_ON(len + offset > PAGE_SIZE);
|
|
}
|
|
if (!Q(blocks, disks)) {
|
|
Q(blocks, disks) = pq_scribble_page;
|
|
BUG_ON(len + offset > PAGE_SIZE);
|
|
}
|
|
do_sync_gen_syndrome(blocks, offset, disks, len, submit);
|
|
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(async_gen_syndrome);
|
|
|
|
static inline struct dma_chan *
|
|
pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, size_t len)
|
|
{
|
|
#ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA
|
|
return NULL;
|
|
#endif
|
|
return async_tx_find_channel(submit, DMA_PQ_VAL, NULL, 0, blocks,
|
|
disks, len);
|
|
}
|
|
|
|
/**
|
|
* async_syndrome_val - asynchronously validate a raid6 syndrome
|
|
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
|
|
* @offset: common offset into each block (src and dest) to start transaction
|
|
* @disks: number of blocks (including missing P or Q, see below)
|
|
* @len: length of operation in bytes
|
|
* @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
|
|
* @spare: temporary result buffer for the synchronous case
|
|
* @submit: submission / completion modifiers
|
|
*
|
|
* The same notes from async_gen_syndrome apply to the 'blocks',
|
|
* and 'disks' parameters of this routine. The synchronous path
|
|
* requires a temporary result buffer and submit->scribble to be
|
|
* specified.
|
|
*/
|
|
struct dma_async_tx_descriptor *
|
|
async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
|
|
size_t len, enum sum_check_flags *pqres, struct page *spare,
|
|
struct async_submit_ctl *submit)
|
|
{
|
|
struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
|
|
struct dma_device *device = chan ? chan->device : NULL;
|
|
struct dma_async_tx_descriptor *tx;
|
|
unsigned char coefs[disks-2];
|
|
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
|
|
dma_addr_t *dma_src = NULL;
|
|
int src_cnt = 0;
|
|
|
|
BUG_ON(disks < 4);
|
|
|
|
if (submit->scribble)
|
|
dma_src = submit->scribble;
|
|
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
|
|
dma_src = (dma_addr_t *) blocks;
|
|
|
|
if (dma_src && device && disks <= dma_maxpq(device, 0) &&
|
|
is_dma_pq_aligned(device, offset, 0, len)) {
|
|
struct device *dev = device->dev;
|
|
dma_addr_t *pq = &dma_src[disks-2];
|
|
int i;
|
|
|
|
pr_debug("%s: (async) disks: %d len: %zu\n",
|
|
__func__, disks, len);
|
|
if (!P(blocks, disks))
|
|
dma_flags |= DMA_PREP_PQ_DISABLE_P;
|
|
else
|
|
pq[0] = dma_map_page(dev, P(blocks, disks),
|
|
offset, len,
|
|
DMA_TO_DEVICE);
|
|
if (!Q(blocks, disks))
|
|
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
|
|
else
|
|
pq[1] = dma_map_page(dev, Q(blocks, disks),
|
|
offset, len,
|
|
DMA_TO_DEVICE);
|
|
|
|
if (submit->flags & ASYNC_TX_FENCE)
|
|
dma_flags |= DMA_PREP_FENCE;
|
|
for (i = 0; i < disks-2; i++)
|
|
if (likely(blocks[i])) {
|
|
dma_src[src_cnt] = dma_map_page(dev, blocks[i],
|
|
offset, len,
|
|
DMA_TO_DEVICE);
|
|
coefs[src_cnt] = raid6_gfexp[i];
|
|
src_cnt++;
|
|
}
|
|
|
|
for (;;) {
|
|
tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
|
|
src_cnt,
|
|
coefs,
|
|
len, pqres,
|
|
dma_flags);
|
|
if (likely(tx))
|
|
break;
|
|
async_tx_quiesce(&submit->depend_tx);
|
|
dma_async_issue_pending(chan);
|
|
}
|
|
async_tx_submit(chan, tx, submit);
|
|
|
|
return tx;
|
|
} else {
|
|
struct page *p_src = P(blocks, disks);
|
|
struct page *q_src = Q(blocks, disks);
|
|
enum async_tx_flags flags_orig = submit->flags;
|
|
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
|
|
void *scribble = submit->scribble;
|
|
void *cb_param_orig = submit->cb_param;
|
|
void *p, *q, *s;
|
|
|
|
pr_debug("%s: (sync) disks: %d len: %zu\n",
|
|
__func__, disks, len);
|
|
|
|
/* caller must provide a temporary result buffer and
|
|
* allow the input parameters to be preserved
|
|
*/
|
|
BUG_ON(!spare || !scribble);
|
|
|
|
/* wait for any prerequisite operations */
|
|
async_tx_quiesce(&submit->depend_tx);
|
|
|
|
/* recompute p and/or q into the temporary buffer and then
|
|
* check to see the result matches the current value
|
|
*/
|
|
tx = NULL;
|
|
*pqres = 0;
|
|
if (p_src) {
|
|
init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
|
|
NULL, NULL, scribble);
|
|
tx = async_xor(spare, blocks, offset, disks-2, len, submit);
|
|
async_tx_quiesce(&tx);
|
|
p = page_address(p_src) + offset;
|
|
s = page_address(spare) + offset;
|
|
*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
|
|
}
|
|
|
|
if (q_src) {
|
|
P(blocks, disks) = NULL;
|
|
Q(blocks, disks) = spare;
|
|
init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
|
|
tx = async_gen_syndrome(blocks, offset, disks, len, submit);
|
|
async_tx_quiesce(&tx);
|
|
q = page_address(q_src) + offset;
|
|
s = page_address(spare) + offset;
|
|
*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
|
|
}
|
|
|
|
/* restore P, Q and submit */
|
|
P(blocks, disks) = p_src;
|
|
Q(blocks, disks) = q_src;
|
|
|
|
submit->cb_fn = cb_fn_orig;
|
|
submit->cb_param = cb_param_orig;
|
|
submit->flags = flags_orig;
|
|
async_tx_sync_epilog(submit);
|
|
|
|
return NULL;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(async_syndrome_val);
|
|
|
|
static int __init async_pq_init(void)
|
|
{
|
|
pq_scribble_page = alloc_page(GFP_KERNEL);
|
|
|
|
if (pq_scribble_page)
|
|
return 0;
|
|
|
|
pr_err("%s: failed to allocate required spare page\n", __func__);
|
|
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void __exit async_pq_exit(void)
|
|
{
|
|
put_page(pq_scribble_page);
|
|
}
|
|
|
|
module_init(async_pq_init);
|
|
module_exit(async_pq_exit);
|
|
|
|
MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation");
|
|
MODULE_LICENSE("GPL");
|