}
for (i = q->read_ptr; i != q->write_ptr;
- i = iwl_queue_inc_wrap(i, q->n_bd)) {
- struct iwl_tx_cmd *tx_cmd =
- (struct iwl_tx_cmd *)txq->entries[i].cmd->payload;
+ i = iwl_queue_inc_wrap(i, q->n_bd))
IWL_ERR(trans, "scratch %d = 0x%08x\n", i,
- get_unaligned_le32(&tx_cmd->scratch));
- }
+ le32_to_cpu(txq->scratchbufs[i].scratch));
iwl_op_mode_nic_error(trans->op_mode);
}
}
static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
- struct iwl_cmd_meta *meta, struct iwl_tfd *tfd,
- enum dma_data_direction dma_dir)
+ struct iwl_cmd_meta *meta,
+ struct iwl_tfd *tfd)
{
int i;
int num_tbs;
return;
}
- /* Unmap tx_cmd */
- if (num_tbs)
- dma_unmap_single(trans->dev,
- dma_unmap_addr(meta, mapping),
- dma_unmap_len(meta, len),
- DMA_BIDIRECTIONAL);
+ /* first TB is never freed - it's the scratchbuf data */
- /* Unmap chunks, if any. */
for (i = 1; i < num_tbs; i++)
dma_unmap_single(trans->dev, iwl_pcie_tfd_tb_get_addr(tfd, i),
- iwl_pcie_tfd_tb_get_len(tfd, i), dma_dir);
+ iwl_pcie_tfd_tb_get_len(tfd, i),
+ DMA_TO_DEVICE);
tfd->num_tbs = 0;
}
* Does NOT advance any TFD circular buffer read/write indexes
* Does NOT free the TFD itself (which is within circular buffer)
*/
-static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
- enum dma_data_direction dma_dir)
+static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
{
struct iwl_tfd *tfd_tmp = txq->tfds;
lockdep_assert_held(&txq->lock);
/* We have only q->n_window txq->entries, but we use q->n_bd tfds */
- iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, &tfd_tmp[rd_ptr],
- dma_dir);
+ iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, &tfd_tmp[rd_ptr]);
/* free SKB */
if (txq->entries) {
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
size_t tfd_sz = sizeof(struct iwl_tfd) * TFD_QUEUE_SIZE_MAX;
+ size_t scratchbuf_sz;
int i;
if (WARN_ON(txq->entries || txq->tfds))
IWL_ERR(trans, "dma_alloc_coherent(%zd) failed\n", tfd_sz);
goto error;
}
+
+ BUILD_BUG_ON(IWL_HCMD_SCRATCHBUF_SIZE != sizeof(*txq->scratchbufs));
+ BUILD_BUG_ON(offsetof(struct iwl_pcie_txq_scratch_buf, scratch) !=
+ sizeof(struct iwl_cmd_header) +
+ offsetof(struct iwl_tx_cmd, scratch));
+
+ scratchbuf_sz = sizeof(*txq->scratchbufs) * slots_num;
+
+ txq->scratchbufs = dma_alloc_coherent(trans->dev, scratchbuf_sz,
+ &txq->scratchbufs_dma,
+ GFP_KERNEL);
+ if (!txq->scratchbufs)
+ goto err_free_tfds;
+
txq->q.id = txq_id;
return 0;
+err_free_tfds:
+ dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->q.dma_addr);
error:
if (txq->entries && txq_id == trans_pcie->cmd_queue)
for (i = 0; i < slots_num; i++)
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_txq *txq = &trans_pcie->txq[txq_id];
struct iwl_queue *q = &txq->q;
- enum dma_data_direction dma_dir;
if (!q->n_bd)
return;
- /* In the command queue, all the TBs are mapped as BIDI
- * so unmap them as such.
- */
- if (txq_id == trans_pcie->cmd_queue)
- dma_dir = DMA_BIDIRECTIONAL;
- else
- dma_dir = DMA_TO_DEVICE;
-
spin_lock_bh(&txq->lock);
while (q->write_ptr != q->read_ptr) {
- iwl_pcie_txq_free_tfd(trans, txq, dma_dir);
+ iwl_pcie_txq_free_tfd(trans, txq);
q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd);
}
spin_unlock_bh(&txq->lock);
if (txq_id == trans_pcie->cmd_queue)
for (i = 0; i < txq->q.n_window; i++) {
kfree(txq->entries[i].cmd);
- kfree(txq->entries[i].copy_cmd);
kfree(txq->entries[i].free_buf);
}
dma_free_coherent(dev, sizeof(struct iwl_tfd) *
txq->q.n_bd, txq->tfds, txq->q.dma_addr);
txq->q.dma_addr = 0;
+
+ dma_free_coherent(dev,
+ sizeof(*txq->scratchbufs) * txq->q.n_window,
+ txq->scratchbufs, txq->scratchbufs_dma);
}
kfree(txq->entries);
iwl_pcie_txq_inval_byte_cnt_tbl(trans, txq);
- iwl_pcie_txq_free_tfd(trans, txq, DMA_TO_DEVICE);
+ iwl_pcie_txq_free_tfd(trans, txq);
}
iwl_pcie_txq_progress(trans_pcie, txq);
iwl_set_bits_prph(trans, SCD_QUEUECHAIN_SEL, BIT(txq_id));
/* If this queue is mapped to a certain station: it is an AGG queue */
- if (sta_id != IWL_INVALID_STATION) {
+ if (sta_id >= 0) {
u16 ra_tid = BUILD_RAxTID(sta_id, tid);
/* Map receiver-address / traffic-ID to this queue */
void *dup_buf = NULL;
dma_addr_t phys_addr;
int idx;
- u16 copy_size, cmd_size;
+ u16 copy_size, cmd_size, scratch_size;
bool had_nocopy = false;
int i;
u32 cmd_pos;
+ const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
+ u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
copy_size = sizeof(out_cmd->hdr);
cmd_size = sizeof(out_cmd->hdr);
/* need one for the header if the first is NOCOPY */
- BUILD_BUG_ON(IWL_MAX_CMD_TFDS > IWL_NUM_OF_TBS - 1);
+ BUILD_BUG_ON(IWL_MAX_CMD_TBS_PER_TFD > IWL_NUM_OF_TBS - 1);
+
+ for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+ cmddata[i] = cmd->data[i];
+ cmdlen[i] = cmd->len[i];
- for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
if (!cmd->len[i])
continue;
+
+ /* need at least IWL_HCMD_SCRATCHBUF_SIZE copied */
+ if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
+ int copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
+
+ if (copy > cmdlen[i])
+ copy = cmdlen[i];
+ cmdlen[i] -= copy;
+ cmddata[i] += copy;
+ copy_size += copy;
+ }
+
if (cmd->dataflags[i] & IWL_HCMD_DFL_NOCOPY) {
had_nocopy = true;
if (WARN_ON(cmd->dataflags[i] & IWL_HCMD_DFL_DUP)) {
goto free_dup_buf;
}
- dup_buf = kmemdup(cmd->data[i], cmd->len[i],
+ dup_buf = kmemdup(cmddata[i], cmdlen[i],
GFP_ATOMIC);
if (!dup_buf)
return -ENOMEM;
idx = -EINVAL;
goto free_dup_buf;
}
- copy_size += cmd->len[i];
+ copy_size += cmdlen[i];
}
cmd_size += cmd->len[i];
}
/* and copy the data that needs to be copied */
cmd_pos = offsetof(struct iwl_device_cmd, payload);
- for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
- if (!cmd->len[i])
+ copy_size = sizeof(out_cmd->hdr);
+ for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+ int copy = 0;
+
+ if (!cmd->len)
continue;
- if (cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
- IWL_HCMD_DFL_DUP))
- break;
- memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], cmd->len[i]);
- cmd_pos += cmd->len[i];
- }
- WARN_ON_ONCE(txq->entries[idx].copy_cmd);
+ /* need at least IWL_HCMD_SCRATCHBUF_SIZE copied */
+ if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
+ copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
- /*
- * since out_cmd will be the source address of the FH, it will write
- * the retry count there. So when the user needs to receivce the HCMD
- * that corresponds to the response in the response handler, it needs
- * to set CMD_WANT_HCMD.
- */
- if (cmd->flags & CMD_WANT_HCMD) {
- txq->entries[idx].copy_cmd =
- kmemdup(out_cmd, cmd_pos, GFP_ATOMIC);
- if (unlikely(!txq->entries[idx].copy_cmd)) {
- idx = -ENOMEM;
- goto out;
+ if (copy > cmd->len[i])
+ copy = cmd->len[i];
+ }
+
+ /* copy everything if not nocopy/dup */
+ if (!(cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
+ IWL_HCMD_DFL_DUP)))
+ copy = cmd->len[i];
+
+ if (copy) {
+ memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], copy);
+ cmd_pos += copy;
+ copy_size += copy;
}
}
out_cmd->hdr.cmd, le16_to_cpu(out_cmd->hdr.sequence),
cmd_size, q->write_ptr, idx, trans_pcie->cmd_queue);
- phys_addr = dma_map_single(trans->dev, &out_cmd->hdr, copy_size,
- DMA_BIDIRECTIONAL);
- if (unlikely(dma_mapping_error(trans->dev, phys_addr))) {
- idx = -ENOMEM;
- goto out;
- }
-
- dma_unmap_addr_set(out_meta, mapping, phys_addr);
- dma_unmap_len_set(out_meta, len, copy_size);
+ /* start the TFD with the scratchbuf */
+ scratch_size = min_t(int, copy_size, IWL_HCMD_SCRATCHBUF_SIZE);
+ memcpy(&txq->scratchbufs[q->write_ptr], &out_cmd->hdr, scratch_size);
+ iwl_pcie_txq_build_tfd(trans, txq,
+ iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr),
+ scratch_size, 1);
+
+ /* map first command fragment, if any remains */
+ if (copy_size > scratch_size) {
+ phys_addr = dma_map_single(trans->dev,
+ ((u8 *)&out_cmd->hdr) + scratch_size,
+ copy_size - scratch_size,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(trans->dev, phys_addr)) {
+ iwl_pcie_tfd_unmap(trans, out_meta,
+ &txq->tfds[q->write_ptr]);
+ idx = -ENOMEM;
+ goto out;
+ }
- iwl_pcie_txq_build_tfd(trans, txq, phys_addr, copy_size, 1);
+ iwl_pcie_txq_build_tfd(trans, txq, phys_addr,
+ copy_size - scratch_size, 0);
+ }
- for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
- const void *data = cmd->data[i];
+ /* map the remaining (adjusted) nocopy/dup fragments */
+ for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+ const void *data = cmddata[i];
- if (!cmd->len[i])
+ if (!cmdlen[i])
continue;
if (!(cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
IWL_HCMD_DFL_DUP)))
if (cmd->dataflags[i] & IWL_HCMD_DFL_DUP)
data = dup_buf;
phys_addr = dma_map_single(trans->dev, (void *)data,
- cmd->len[i], DMA_BIDIRECTIONAL);
+ cmdlen[i], DMA_TO_DEVICE);
if (dma_mapping_error(trans->dev, phys_addr)) {
iwl_pcie_tfd_unmap(trans, out_meta,
- &txq->tfds[q->write_ptr],
- DMA_BIDIRECTIONAL);
+ &txq->tfds[q->write_ptr]);
idx = -ENOMEM;
goto out;
}
- iwl_pcie_txq_build_tfd(trans, txq, phys_addr, cmd->len[i], 0);
+ iwl_pcie_txq_build_tfd(trans, txq, phys_addr, cmdlen[i], 0);
}
out_meta->flags = cmd->flags;
txq->need_update = 1;
- trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size,
- &out_cmd->hdr, copy_size);
+ trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size, &out_cmd->hdr);
/* start timer if queue currently empty */
if (q->read_ptr == q->write_ptr && trans_pcie->wd_timeout)
cmd = txq->entries[cmd_index].cmd;
meta = &txq->entries[cmd_index].meta;
- iwl_pcie_tfd_unmap(trans, meta, &txq->tfds[index], DMA_BIDIRECTIONAL);
+ iwl_pcie_tfd_unmap(trans, meta, &txq->tfds[index]);
/* Input error checking is done when commands are added to queue. */
if (meta->flags & CMD_WANT_SKB) {
if (test_bit(STATUS_FW_ERROR, &trans_pcie->status))
return -EIO;
- if (test_bit(STATUS_RFKILL, &trans_pcie->status))
+ if (test_bit(STATUS_RFKILL, &trans_pcie->status)) {
+ IWL_DEBUG_RF_KILL(trans, "Dropping CMD 0x%x: RF KILL\n",
+ cmd->id);
return -ERFKILL;
+ }
if (cmd->flags & CMD_ASYNC)
return iwl_pcie_send_hcmd_async(trans, cmd);
struct iwl_cmd_meta *out_meta;
struct iwl_txq *txq;
struct iwl_queue *q;
- dma_addr_t phys_addr = 0;
- dma_addr_t txcmd_phys;
- dma_addr_t scratch_phys;
- u16 len, firstlen, secondlen;
+ dma_addr_t tb0_phys, tb1_phys, scratch_phys;
+ void *tb1_addr;
+ u16 len, tb1_len, tb2_len;
u8 wait_write_ptr = 0;
__le16 fc = hdr->frame_control;
u8 hdr_len = ieee80211_hdrlen(fc);
* Check here that the packets are in the right place on the ring.
*/
#ifdef CONFIG_IWLWIFI_DEBUG
- wifi_seq = SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
+ wifi_seq = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
WARN_ONCE((iwl_read_prph(trans, SCD_AGGR_SEL) & BIT(txq_id)) &&
((wifi_seq & 0xff) != q->write_ptr),
"Q: %d WiFi Seq %d tfdNum %d",
cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
INDEX_TO_SEQ(q->write_ptr)));
+ tb0_phys = iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr);
+ scratch_phys = tb0_phys + sizeof(struct iwl_cmd_header) +
+ offsetof(struct iwl_tx_cmd, scratch);
+
+ tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
+ tx_cmd->dram_msb_ptr = iwl_get_dma_hi_addr(scratch_phys);
+
/* Set up first empty entry in queue's array of Tx/cmd buffers */
out_meta = &txq->entries[q->write_ptr].meta;
/*
- * Use the first empty entry in this queue's command buffer array
- * to contain the Tx command and MAC header concatenated together
- * (payload data will be in another buffer).
- * Size of this varies, due to varying MAC header length.
- * If end is not dword aligned, we'll have 2 extra bytes at the end
- * of the MAC header (device reads on dword boundaries).
- * We'll tell device about this padding later.
+ * The second TB (tb1) points to the remainder of the TX command
+ * and the 802.11 header - dword aligned size
+ * (This calculation modifies the TX command, so do it before the
+ * setup of the first TB)
*/
- len = sizeof(struct iwl_tx_cmd) +
- sizeof(struct iwl_cmd_header) + hdr_len;
- firstlen = (len + 3) & ~3;
+ len = sizeof(struct iwl_tx_cmd) + sizeof(struct iwl_cmd_header) +
+ hdr_len - IWL_HCMD_SCRATCHBUF_SIZE;
+ tb1_len = (len + 3) & ~3;
/* Tell NIC about any 2-byte padding after MAC header */
- if (firstlen != len)
+ if (tb1_len != len)
tx_cmd->tx_flags |= TX_CMD_FLG_MH_PAD_MSK;
- /* Physical address of this Tx command's header (not MAC header!),
- * within command buffer array. */
- txcmd_phys = dma_map_single(trans->dev,
- &dev_cmd->hdr, firstlen,
- DMA_BIDIRECTIONAL);
- if (unlikely(dma_mapping_error(trans->dev, txcmd_phys)))
- goto out_err;
- dma_unmap_addr_set(out_meta, mapping, txcmd_phys);
- dma_unmap_len_set(out_meta, len, firstlen);
+ /* The first TB points to the scratchbuf data - min_copy bytes */
+ memcpy(&txq->scratchbufs[q->write_ptr], &dev_cmd->hdr,
+ IWL_HCMD_SCRATCHBUF_SIZE);
+ iwl_pcie_txq_build_tfd(trans, txq, tb0_phys,
+ IWL_HCMD_SCRATCHBUF_SIZE, 1);
- if (!ieee80211_has_morefrags(fc)) {
- txq->need_update = 1;
- } else {
- wait_write_ptr = 1;
- txq->need_update = 0;
- }
+ /* there must be data left over for TB1 or this code must be changed */
+ BUILD_BUG_ON(sizeof(struct iwl_tx_cmd) < IWL_HCMD_SCRATCHBUF_SIZE);
+
+ /* map the data for TB1 */
+ tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_HCMD_SCRATCHBUF_SIZE;
+ tb1_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(trans->dev, tb1_phys)))
+ goto out_err;
+ iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, 0);
- /* Set up TFD's 2nd entry to point directly to remainder of skb,
- * if any (802.11 null frames have no payload). */
- secondlen = skb->len - hdr_len;
- if (secondlen > 0) {
- phys_addr = dma_map_single(trans->dev, skb->data + hdr_len,
- secondlen, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(trans->dev, phys_addr))) {
- dma_unmap_single(trans->dev,
- dma_unmap_addr(out_meta, mapping),
- dma_unmap_len(out_meta, len),
- DMA_BIDIRECTIONAL);
+ /*
+ * Set up TFD's third entry to point directly to remainder
+ * of skb, if any (802.11 null frames have no payload).
+ */
+ tb2_len = skb->len - hdr_len;
+ if (tb2_len > 0) {
+ dma_addr_t tb2_phys = dma_map_single(trans->dev,
+ skb->data + hdr_len,
+ tb2_len, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(trans->dev, tb2_phys))) {
+ iwl_pcie_tfd_unmap(trans, out_meta,
+ &txq->tfds[q->write_ptr]);
goto out_err;
}
+ iwl_pcie_txq_build_tfd(trans, txq, tb2_phys, tb2_len, 0);
}
- /* Attach buffers to TFD */
- iwl_pcie_txq_build_tfd(trans, txq, txcmd_phys, firstlen, 1);
- if (secondlen > 0)
- iwl_pcie_txq_build_tfd(trans, txq, phys_addr, secondlen, 0);
-
- scratch_phys = txcmd_phys + sizeof(struct iwl_cmd_header) +
- offsetof(struct iwl_tx_cmd, scratch);
-
- /* take back ownership of DMA buffer to enable update */
- dma_sync_single_for_cpu(trans->dev, txcmd_phys, firstlen,
- DMA_BIDIRECTIONAL);
- tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
- tx_cmd->dram_msb_ptr = iwl_get_dma_hi_addr(scratch_phys);
-
/* Set up entry for this TFD in Tx byte-count array */
iwl_pcie_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len));
- dma_sync_single_for_device(trans->dev, txcmd_phys, firstlen,
- DMA_BIDIRECTIONAL);
-
trace_iwlwifi_dev_tx(trans->dev, skb,
&txq->tfds[txq->q.write_ptr],
sizeof(struct iwl_tfd),
- &dev_cmd->hdr, firstlen,
- skb->data + hdr_len, secondlen);
+ &dev_cmd->hdr, IWL_HCMD_SCRATCHBUF_SIZE + tb1_len,
+ skb->data + hdr_len, tb2_len);
trace_iwlwifi_dev_tx_data(trans->dev, skb,
- skb->data + hdr_len, secondlen);
+ skb->data + hdr_len, tb2_len);
+
+ if (!ieee80211_has_morefrags(fc)) {
+ txq->need_update = 1;
+ } else {
+ wait_write_ptr = 1;
+ txq->need_update = 0;
+ }
/* start timer if queue currently empty */
if (txq->need_update && q->read_ptr == q->write_ptr &&
projects / mirror_ubuntu-artful-kernel.git / blobdiff