diff options
Diffstat (limited to 'drivers/dma/ioat')
-rw-r--r-- | drivers/dma/ioat/dma.c | 52 | ||||
-rw-r--r-- | drivers/dma/ioat/dma.h | 1 | ||||
-rw-r--r-- | drivers/dma/ioat/dma_v2.c | 11 | ||||
-rw-r--r-- | drivers/dma/ioat/dma_v3.c | 49 |
4 files changed, 70 insertions, 43 deletions
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 17a2393b3e2..533e1874e1d 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -77,7 +77,8 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data) attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET); for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) { chan = ioat_chan_by_index(instance, bit); - tasklet_schedule(&chan->cleanup_task); + if (test_bit(IOAT_RUN, &chan->state)) + tasklet_schedule(&chan->cleanup_task); } writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET); @@ -93,7 +94,8 @@ static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data) { struct ioat_chan_common *chan = data; - tasklet_schedule(&chan->cleanup_task); + if (test_bit(IOAT_RUN, &chan->state)) + tasklet_schedule(&chan->cleanup_task); return IRQ_HANDLED; } @@ -116,7 +118,6 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c chan->timer.function = device->timer_fn; chan->timer.data = data; tasklet_init(&chan->cleanup_task, device->cleanup_fn, data); - tasklet_disable(&chan->cleanup_task); } /** @@ -354,13 +355,49 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c) writel(((u64) chan->completion_dma) >> 32, chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH); - tasklet_enable(&chan->cleanup_task); + set_bit(IOAT_RUN, &chan->state); ioat1_dma_start_null_desc(ioat); /* give chain to dma device */ dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n", __func__, ioat->desccount); return ioat->desccount; } +void ioat_stop(struct ioat_chan_common *chan) +{ + struct ioatdma_device *device = chan->device; + struct pci_dev *pdev = device->pdev; + int chan_id = chan_num(chan); + struct msix_entry *msix; + + /* 1/ stop irq from firing tasklets + * 2/ stop the tasklet from re-arming irqs + */ + clear_bit(IOAT_RUN, &chan->state); + + /* flush inflight interrupts */ + switch (device->irq_mode) { + case IOAT_MSIX: + msix = &device->msix_entries[chan_id]; + synchronize_irq(msix->vector); + break; + case IOAT_MSI: + case IOAT_INTX: + synchronize_irq(pdev->irq); + break; + default: + break; + } + + /* flush inflight timers */ + del_timer_sync(&chan->timer); + + /* flush inflight tasklet runs */ + tasklet_kill(&chan->cleanup_task); + + /* final cleanup now that everything is quiesced and can't re-arm */ + device->cleanup_fn((unsigned long) &chan->common); +} + /** * ioat1_dma_free_chan_resources - release all the descriptors * @chan: the channel to be cleaned @@ -379,9 +416,7 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c) if (ioat->desccount == 0) return; - tasklet_disable(&chan->cleanup_task); - del_timer_sync(&chan->timer); - ioat1_cleanup(ioat); + ioat_stop(chan); /* Delay 100ms after reset to allow internal DMA logic to quiesce * before removing DMA descriptor resources. @@ -526,8 +561,11 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest, static void ioat1_cleanup_event(unsigned long data) { struct ioat_dma_chan *ioat = to_ioat_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat1_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index 54fb7b9ff9a..a1d78847e5a 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -370,6 +370,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan, void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type); void ioat_kobject_del(struct ioatdma_device *device); int ioat_dma_setup_interrupts(struct ioatdma_device *device); +void ioat_stop(struct ioat_chan_common *chan); extern const struct sysfs_ops ioat_sysfs_ops; extern struct ioat_sysfs_entry ioat_version_attr; extern struct ioat_sysfs_entry ioat_cap_attr; diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index b925e1b1d13..1cd761026d8 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -190,8 +190,11 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat) void ioat2_cleanup_event(unsigned long data) { struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat2_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } @@ -553,10 +556,10 @@ int ioat2_alloc_chan_resources(struct dma_chan *c) ioat->issued = 0; ioat->tail = 0; ioat->alloc_order = order; + set_bit(IOAT_RUN, &chan->state); spin_unlock_bh(&ioat->prep_lock); spin_unlock_bh(&chan->cleanup_lock); - tasklet_enable(&chan->cleanup_task); ioat2_start_null_desc(ioat); /* check that we got off the ground */ @@ -566,7 +569,6 @@ int ioat2_alloc_chan_resources(struct dma_chan *c) } while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status)); if (is_ioat_active(status) || is_ioat_idle(status)) { - set_bit(IOAT_RUN, &chan->state); return 1 << ioat->alloc_order; } else { u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); @@ -809,11 +811,8 @@ void ioat2_free_chan_resources(struct dma_chan *c) if (!ioat->ring) return; - tasklet_disable(&chan->cleanup_task); - del_timer_sync(&chan->timer); - device->cleanup_fn((unsigned long) c); + ioat_stop(chan); device->reset_hw(chan); - clear_bit(IOAT_RUN, &chan->state); spin_lock_bh(&chan->cleanup_lock); spin_lock_bh(&ioat->prep_lock); diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index ca6ea9b3551..38b94b393c6 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -87,13 +87,6 @@ static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 }; static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7, 0, 1, 2, 3, 4, 5, 6 }; -/* - * technically sources 1 and 2 do not require SED, but the op will have - * at least 9 descriptors so that's irrelevant. - */ -static const u8 pq16_idx_to_sed[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, - 1, 1, 1, 1, 1, 1, 1 }; - static void ioat3_eh(struct ioat2_dma_chan *ioat); static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx) @@ -135,12 +128,6 @@ static void pq_set_src(struct ioat_raw_descriptor *descs[2], pq->coef[idx] = coef; } -static int sed_get_pq16_pool_idx(int src_cnt) -{ - - return pq16_idx_to_sed[src_cnt]; -} - static bool is_jf_ioat(struct pci_dev *pdev) { switch (pdev->device) { @@ -648,8 +635,11 @@ static void ioat3_cleanup(struct ioat2_dma_chan *ioat) static void ioat3_cleanup_event(unsigned long data) { struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat3_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } @@ -1182,9 +1172,6 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result, u8 op; int i, s, idx, num_descs; - /* this function only handles src_cnt 9 - 16 */ - BUG_ON(src_cnt < 9); - /* this function is only called with 9-16 sources */ op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S; @@ -1212,8 +1199,7 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result, descs[0] = (struct ioat_raw_descriptor *) pq; - desc->sed = ioat3_alloc_sed(device, - sed_get_pq16_pool_idx(src_cnt)); + desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3); if (!desc->sed) { dev_err(to_dev(chan), "%s: no free sed entries\n", __func__); @@ -1271,13 +1257,21 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result, return &desc->txd; } +static int src_cnt_flags(unsigned int src_cnt, unsigned long flags) +{ + if (dmaf_p_disabled_continue(flags)) + return src_cnt + 1; + else if (dmaf_continue(flags)) + return src_cnt + 3; + else + return src_cnt; +} + static struct dma_async_tx_descriptor * ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, unsigned long flags) { - struct dma_device *dma = chan->device; - /* specify valid address for disabled result */ if (flags & DMA_PREP_PQ_DISABLE_P) dst[0] = dst[1]; @@ -1297,7 +1291,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, single_source_coef[0] = scf[0]; single_source_coef[1] = 0; - return (src_cnt > 8) && (dma->max_pq > 8) ? + return src_cnt_flags(src_cnt, flags) > 8 ? __ioat3_prep_pq16_lock(chan, NULL, dst, single_source, 2, single_source_coef, len, flags) : @@ -1305,7 +1299,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, single_source_coef, len, flags); } else { - return (src_cnt > 8) && (dma->max_pq > 8) ? + return src_cnt_flags(src_cnt, flags) > 8 ? __ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt, scf, len, flags) : __ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt, @@ -1318,8 +1312,6 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, enum sum_check_flags *pqres, unsigned long flags) { - struct dma_device *dma = chan->device; - /* specify valid address for disabled result */ if (flags & DMA_PREP_PQ_DISABLE_P) pq[0] = pq[1]; @@ -1331,7 +1323,7 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, */ *pqres = 0; - return (src_cnt > 8) && (dma->max_pq > 8) ? + return src_cnt_flags(src_cnt, flags) > 8 ? __ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len, flags) : __ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len, @@ -1342,7 +1334,6 @@ static struct dma_async_tx_descriptor * ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags) { - struct dma_device *dma = chan->device; unsigned char scf[src_cnt]; dma_addr_t pq[2]; @@ -1351,7 +1342,7 @@ ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, flags |= DMA_PREP_PQ_DISABLE_Q; pq[1] = dst; /* specify valid address for disabled result */ - return (src_cnt > 8) && (dma->max_pq > 8) ? + return src_cnt_flags(src_cnt, flags) > 8 ? __ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len, flags) : __ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len, @@ -1363,7 +1354,6 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, size_t len, enum sum_check_flags *result, unsigned long flags) { - struct dma_device *dma = chan->device; unsigned char scf[src_cnt]; dma_addr_t pq[2]; @@ -1377,8 +1367,7 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src, flags |= DMA_PREP_PQ_DISABLE_Q; pq[1] = pq[0]; /* specify valid address for disabled result */ - - return (src_cnt > 8) && (dma->max_pq > 8) ? + return src_cnt_flags(src_cnt, flags) > 8 ? __ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1, scf, len, flags) : __ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1, |