X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=crypto%2Fasync_tx%2Fasync_xor.c;h=3a0dddca5a1097e473d103a15797547da66e7bf1;hb=2052e8d40ad58b1d364f900e70edfda62caa0874;hp=2575f674dcd5ee226cb2a29f946e27ab9b9b7c1a;hpb=f79e3185dd0f8650022518d7624c876d8929061b;p=linux-2.6-omap-h63xx.git diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 2575f674dcd..3a0dddca5a1 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -30,35 +30,51 @@ #include #include -static void -do_async_xor(struct dma_async_tx_descriptor *tx, struct dma_device *device, +/* do_async_xor - dma map the pages and perform the xor with an engine. + * This routine is marked __always_inline so it can be compiled away + * when CONFIG_DMA_ENGINE=n + */ +static __always_inline struct dma_async_tx_descriptor * +do_async_xor(struct dma_device *device, struct dma_chan *chan, struct page *dest, struct page **src_list, unsigned int offset, unsigned int src_cnt, size_t len, enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx, dma_async_tx_callback cb_fn, void *cb_param) { - dma_addr_t dma_addr; - enum dma_data_direction dir; + dma_addr_t dma_dest; + dma_addr_t *dma_src = (dma_addr_t *) src_list; + struct dma_async_tx_descriptor *tx; int i; + unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0; - pr_debug("%s: len: %zu\n", __FUNCTION__, len); - - dir = (flags & ASYNC_TX_ASSUME_COHERENT) ? - DMA_NONE : DMA_FROM_DEVICE; - - dma_addr = dma_map_page(device->dev, dest, offset, len, dir); - tx->tx_set_dest(dma_addr, tx, 0); + pr_debug("%s: len: %zu\n", __func__, len); - dir = (flags & ASYNC_TX_ASSUME_COHERENT) ? - DMA_NONE : DMA_TO_DEVICE; + dma_dest = dma_map_page(device->dev, dest, offset, len, + DMA_FROM_DEVICE); - for (i = 0; i < src_cnt; i++) { - dma_addr = dma_map_page(device->dev, src_list[i], - offset, len, dir); - tx->tx_set_src(dma_addr, tx, i); + for (i = 0; i < src_cnt; i++) + dma_src[i] = dma_map_page(device->dev, src_list[i], offset, + len, DMA_TO_DEVICE); + + /* 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 + */ + tx = device->device_prep_dma_xor(chan, dma_dest, dma_src, src_cnt, len, + dma_prep_flags); + if (!tx) { + if (depend_tx) + dma_wait_for_async_tx(depend_tx); + + while (!tx) + tx = device->device_prep_dma_xor(chan, dma_dest, + dma_src, src_cnt, len, + dma_prep_flags); } async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); + + return tx; } static void @@ -70,7 +86,7 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, void *_dest; int i; - pr_debug("%s: len: %zu\n", __FUNCTION__, len); + pr_debug("%s: len: %zu\n", __func__, len); /* reuse the 'src_list' array to convert to buffer pointers */ for (i = 0; i < src_cnt; i++) @@ -102,7 +118,7 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, * @src_cnt: number of source pages * @len: length in bytes * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST, - * ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * ASYNC_TX_ACK, ASYNC_TX_DEP_ACK * @depend_tx: xor depends on the result of this transaction. * @cb_fn: function to call when the xor completes * @cb_param: parameter to pass to the callback routine @@ -113,14 +129,16 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, struct dma_async_tx_descriptor *depend_tx, dma_async_tx_callback cb_fn, void *cb_param) { - struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR); + struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR, + &dest, 1, src_list, + src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; dma_async_tx_callback _cb_fn; void *_cb_param; unsigned long local_flags; int xor_src_cnt; - int i = 0, src_off = 0, int_en; + int i = 0, src_off = 0; BUG_ON(src_cnt <= 1); @@ -140,20 +158,11 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, _cb_param = cb_param; } - int_en = _cb_fn ? 1 : 0; - - tx = device->device_prep_dma_xor( - chan, xor_src_cnt, len, int_en); - - if (tx) { - do_async_xor(tx, device, chan, dest, - &src_list[src_off], offset, xor_src_cnt, len, - local_flags, depend_tx, _cb_fn, - _cb_param); - } else /* fall through */ - goto xor_sync; + tx = do_async_xor(device, chan, dest, + &src_list[src_off], offset, + xor_src_cnt, len, local_flags, + depend_tx, _cb_fn, _cb_param); } else { /* run the xor synchronously */ -xor_sync: /* in the sync case the dest is an implied source * (assumes the dest is at the src_off index) */ @@ -182,12 +191,12 @@ xor_sync: /* if ack is already set then we cannot be sure * we are referring to the correct operation */ - BUG_ON(depend_tx->ack); + BUG_ON(async_tx_test_ack(depend_tx)); if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR) panic("%s: DMA_ERROR waiting for " "depend_tx\n", - __FUNCTION__); + __func__); } do_sync_xor(dest, &src_list[src_off], offset, @@ -242,7 +251,7 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) * @src_cnt: number of source pages * @len: length in bytes * @result: 0 if sum == 0 else non-zero - * @flags: ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK * @depend_tx: xor depends on the result of this transaction. * @cb_fn: function to call when the xor completes * @cb_param: parameter to pass to the callback routine @@ -254,36 +263,43 @@ async_xor_zero_sum(struct page *dest, struct page **src_list, struct dma_async_tx_descriptor *depend_tx, dma_async_tx_callback cb_fn, void *cb_param) { - struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_ZERO_SUM); + struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_ZERO_SUM, + &dest, 1, src_list, + src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; - int int_en = cb_fn ? 1 : 0; - struct dma_async_tx_descriptor *tx = device ? - device->device_prep_dma_zero_sum(chan, src_cnt, len, result, - int_en) : NULL; - int i; + struct dma_async_tx_descriptor *tx = NULL; BUG_ON(src_cnt <= 1); - if (tx) { - dma_addr_t dma_addr; - enum dma_data_direction dir; + if (device && src_cnt <= device->max_xor) { + dma_addr_t *dma_src = (dma_addr_t *) src_list; + unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0; + int i; + + pr_debug("%s: (async) len: %zu\n", __func__, len); - pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len); + for (i = 0; i < src_cnt; i++) + dma_src[i] = dma_map_page(device->dev, src_list[i], + offset, len, DMA_TO_DEVICE); - dir = (flags & ASYNC_TX_ASSUME_COHERENT) ? - DMA_NONE : DMA_TO_DEVICE; + tx = device->device_prep_dma_zero_sum(chan, dma_src, src_cnt, + len, result, + dma_prep_flags); + if (!tx) { + if (depend_tx) + dma_wait_for_async_tx(depend_tx); - for (i = 0; i < src_cnt; i++) { - dma_addr = dma_map_page(device->dev, src_list[i], - offset, len, dir); - tx->tx_set_src(dma_addr, tx, i); + while (!tx) + tx = device->device_prep_dma_zero_sum(chan, + dma_src, src_cnt, len, result, + dma_prep_flags); } async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); } else { unsigned long xor_flags = flags; - pr_debug("%s: (sync) len: %zu\n", __FUNCTION__, len); + pr_debug("%s: (sync) len: %zu\n", __func__, len); xor_flags |= ASYNC_TX_XOR_DROP_DST; xor_flags &= ~ASYNC_TX_ACK; @@ -294,7 +310,7 @@ async_xor_zero_sum(struct page *dest, struct page **src_list, if (tx) { if (dma_wait_for_async_tx(tx) == DMA_ERROR) panic("%s: DMA_ERROR waiting for tx\n", - __FUNCTION__); + __func__); async_tx_ack(tx); } @@ -311,6 +327,16 @@ EXPORT_SYMBOL_GPL(async_xor_zero_sum); static int __init async_xor_init(void) { + #ifdef CONFIG_DMA_ENGINE + /* To conserve stack space the input src_list (array of page pointers) + * is reused to hold the array of dma addresses passed to the driver. + * This conversion is only possible when dma_addr_t is less than the + * the size of a pointer. HIGHMEM64G is known to violate this + * assumption. + */ + BUILD_BUG_ON(sizeof(dma_addr_t) > sizeof(struct page *)); + #endif + return 0; }