diff options
Diffstat (limited to 'drivers/dma')
-rw-r--r-- | drivers/dma/Kconfig | 4 | ||||
-rw-r--r-- | drivers/dma/dmaengine.c | 93 | ||||
-rw-r--r-- | drivers/dma/dmatest.c | 40 | ||||
-rw-r--r-- | drivers/dma/ioat/Makefile | 2 | ||||
-rw-r--r-- | drivers/dma/ioat/dma.c | 136 | ||||
-rw-r--r-- | drivers/dma/ioat/dma.h | 34 | ||||
-rw-r--r-- | drivers/dma/ioat/dma_v2.c | 129 | ||||
-rw-r--r-- | drivers/dma/ioat/dma_v2.h | 45 | ||||
-rw-r--r-- | drivers/dma/ioat/dma_v3.c | 1220 | ||||
-rw-r--r-- | drivers/dma/ioat/hw.h | 142 | ||||
-rw-r--r-- | drivers/dma/ioat/pci.c | 45 | ||||
-rw-r--r-- | drivers/dma/ioat/registers.h | 20 | ||||
-rw-r--r-- | drivers/dma/iop-adma.c | 482 |
13 files changed, 2179 insertions, 213 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 81e1020fb514..fe1f3717b1ff 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -17,11 +17,15 @@ if DMADEVICES comment "DMA Devices" +config ASYNC_TX_DISABLE_CHANNEL_SWITCH + bool + config INTEL_IOATDMA tristate "Intel I/OAT DMA support" depends on PCI && X86 select DMA_ENGINE select DCA + select ASYNC_TX_DISABLE_CHANNEL_SWITCH help Enable support for the Intel(R) I/OAT DMA engine present in recent Intel Xeon chipsets. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 562d182eae66..bd0b248de2cf 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -608,6 +608,40 @@ void dmaengine_put(void) } EXPORT_SYMBOL(dmaengine_put); +static bool device_has_all_tx_types(struct dma_device *device) +{ + /* A device that satisfies this test has channels that will never cause + * an async_tx channel switch event as all possible operation types can + * be handled. + */ + #ifdef CONFIG_ASYNC_TX_DMA + if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE) + if (!dma_has_cap(DMA_MEMCPY, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_MEMSET) || defined(CONFIG_ASYNC_MEMSET_MODULE) + if (!dma_has_cap(DMA_MEMSET, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE) + if (!dma_has_cap(DMA_XOR, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE) + if (!dma_has_cap(DMA_PQ, device->cap_mask)) + return false; + #endif + + return true; +} + static int get_dma_id(struct dma_device *device) { int rc; @@ -644,8 +678,12 @@ int dma_async_device_register(struct dma_device *device) !device->device_prep_dma_memcpy); BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor); - BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) && - !device->device_prep_dma_zero_sum); + BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) && + !device->device_prep_dma_xor_val); + BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) && + !device->device_prep_dma_pq); + BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) && + !device->device_prep_dma_pq_val); BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) && !device->device_prep_dma_memset); BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) && @@ -661,6 +699,12 @@ int dma_async_device_register(struct dma_device *device) BUG_ON(!device->device_issue_pending); BUG_ON(!device->dev); + /* note: this only matters in the + * CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH=y case + */ + if (device_has_all_tx_types(device)) + dma_cap_set(DMA_ASYNC_TX, device->cap_mask); + idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL); if (!idr_ref) return -ENOMEM; @@ -938,49 +982,24 @@ EXPORT_SYMBOL(dma_async_tx_descriptor_init); /* dma_wait_for_async_tx - spin wait for a transaction to complete * @tx: in-flight transaction to wait on - * - * This routine assumes that tx was obtained from a call to async_memcpy, - * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped - * and submitted). Walking the parent chain is only meant to cover for DMA - * drivers that do not implement the DMA_INTERRUPT capability and may race with - * the driver's descriptor cleanup routine. */ enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { - enum dma_status status; - struct dma_async_tx_descriptor *iter; - struct dma_async_tx_descriptor *parent; + unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000); if (!tx) return DMA_SUCCESS; - WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for" - " %s\n", __func__, dma_chan_name(tx->chan)); - - /* poll through the dependency chain, return when tx is complete */ - do { - iter = tx; - - /* find the root of the unsubmitted dependency chain */ - do { - parent = iter->parent; - if (!parent) - break; - else - iter = parent; - } while (parent); - - /* there is a small window for ->parent == NULL and - * ->cookie == -EBUSY - */ - while (iter->cookie == -EBUSY) - cpu_relax(); - - status = dma_sync_wait(iter->chan, iter->cookie); - } while (status == DMA_IN_PROGRESS || (iter != tx)); - - return status; + while (tx->cookie == -EBUSY) { + if (time_after_eq(jiffies, dma_sync_wait_timeout)) { + pr_err("%s timeout waiting for descriptor submission\n", + __func__); + return DMA_ERROR; + } + cpu_relax(); + } + return dma_sync_wait(tx->chan, tx->cookie); } EXPORT_SYMBOL_GPL(dma_wait_for_async_tx); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index d93017fc7872..a32a4cf7b1e0 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -48,6 +48,11 @@ module_param(xor_sources, uint, S_IRUGO); MODULE_PARM_DESC(xor_sources, "Number of xor source buffers (default: 3)"); +static unsigned int pq_sources = 3; +module_param(pq_sources, uint, S_IRUGO); +MODULE_PARM_DESC(pq_sources, + "Number of p+q source buffers (default: 3)"); + /* * Initialization patterns. All bytes in the source buffer has bit 7 * set, all bytes in the destination buffer has bit 7 cleared. @@ -232,6 +237,7 @@ static int dmatest_func(void *data) dma_cookie_t cookie; enum dma_status status; enum dma_ctrl_flags flags; + u8 pq_coefs[pq_sources]; int ret; int src_cnt; int dst_cnt; @@ -248,6 +254,11 @@ static int dmatest_func(void *data) else if (thread->type == DMA_XOR) { src_cnt = xor_sources | 1; /* force odd to ensure dst = src */ dst_cnt = 1; + } else if (thread->type == DMA_PQ) { + src_cnt = pq_sources | 1; /* force odd to ensure dst = src */ + dst_cnt = 2; + for (i = 0; i < pq_sources; i++) + pq_coefs[i] = 1; } else goto err_srcs; @@ -283,6 +294,7 @@ static int dmatest_func(void *data) dma_addr_t dma_dsts[dst_cnt]; struct completion cmp; unsigned long tmo = msecs_to_jiffies(3000); + u8 align = 0; total_tests++; @@ -290,6 +302,18 @@ static int dmatest_func(void *data) src_off = dmatest_random() % (test_buf_size - len + 1); dst_off = dmatest_random() % (test_buf_size - len + 1); + /* honor alignment restrictions */ + if (thread->type == DMA_MEMCPY) + align = dev->copy_align; + else if (thread->type == DMA_XOR) + align = dev->xor_align; + else if (thread->type == DMA_PQ) + align = dev->pq_align; + + len = (len >> align) << align; + src_off = (src_off >> align) << align; + dst_off = (dst_off >> align) << align; + dmatest_init_srcs(thread->srcs, src_off, len); dmatest_init_dsts(thread->dsts, dst_off, len); @@ -306,6 +330,7 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); } + if (thread->type == DMA_MEMCPY) tx = dev->device_prep_dma_memcpy(chan, dma_dsts[0] + dst_off, @@ -316,6 +341,15 @@ static int dmatest_func(void *data) dma_dsts[0] + dst_off, dma_srcs, xor_sources, len, flags); + else if (thread->type == DMA_PQ) { + dma_addr_t dma_pq[dst_cnt]; + + for (i = 0; i < dst_cnt; i++) + dma_pq[i] = dma_dsts[i] + dst_off; + tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs, + pq_sources, pq_coefs, + len, flags); + } if (!tx) { for (i = 0; i < src_cnt; i++) @@ -459,6 +493,8 @@ static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_ty op = "copy"; else if (type == DMA_XOR) op = "xor"; + else if (type == DMA_PQ) + op = "pq"; else return -EINVAL; @@ -514,6 +550,10 @@ static int dmatest_add_channel(struct dma_chan *chan) cnt = dmatest_add_threads(dtc, DMA_XOR); thread_count += cnt > 0 ? cnt : 0; } + if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) { + cnt = dmatest_add_threads(dtc, DMA_PQ); + thread_count += cnt > 0 ?: 0; + } pr_info("dmatest: Started %u threads using %s\n", thread_count, dma_chan_name(chan)); diff --git a/drivers/dma/ioat/Makefile b/drivers/dma/ioat/Makefile index 205a639e84df..8997d3fb9051 100644 --- a/drivers/dma/ioat/Makefile +++ b/drivers/dma/ioat/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o -ioatdma-objs := pci.o dma.o dma_v2.o dca.o +ioatdma-objs := pci.o dma.o dma_v2.o dma_v3.o dca.o diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 21527b89590c..c524d36d3c2e 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -263,6 +263,7 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx) if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state)) mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT); + ioat->active += desc->hw->tx_cnt; ioat->pending += desc->hw->tx_cnt; if (ioat->pending >= ioat_pending_level) __ioat1_dma_memcpy_issue_pending(ioat); @@ -539,17 +540,6 @@ static void ioat1_cleanup_tasklet(unsigned long data) writew(IOAT_CHANCTRL_RUN, chan->base.reg_base + IOAT_CHANCTRL_OFFSET); } -static void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len, - int direction, enum dma_ctrl_flags flags, bool dst) -{ - if ((dst && (flags & DMA_COMPL_DEST_UNMAP_SINGLE)) || - (!dst && (flags & DMA_COMPL_SRC_UNMAP_SINGLE))) - pci_unmap_single(pdev, addr, len, direction); - else - pci_unmap_page(pdev, addr, len, direction); -} - - void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags, size_t len, struct ioat_dma_descriptor *hw) { @@ -623,6 +613,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete) chan->completed_cookie = tx->cookie; tx->cookie = 0; ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw); + ioat->active -= desc->hw->tx_cnt; if (tx->callback) { tx->callback(tx->callback_param); tx->callback = NULL; @@ -809,7 +800,7 @@ static void __devinit ioat_dma_test_callback(void *dma_async_param) * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works. * @device: device to be tested */ -static int __devinit ioat_dma_self_test(struct ioatdma_device *device) +int __devinit ioat_dma_self_test(struct ioatdma_device *device) { int i; u8 *src; @@ -1040,13 +1031,8 @@ int __devinit ioat_probe(struct ioatdma_device *device) dma_cap_set(DMA_MEMCPY, dma->cap_mask); dma->dev = &pdev->dev; - dev_err(dev, "Intel(R) I/OAT DMA Engine found," - " %d channels, device version 0x%02x, driver version %s\n", - dma->chancnt, device->version, IOAT_DMA_VERSION); - if (!dma->chancnt) { - dev_err(dev, "Intel(R) I/OAT DMA Engine problem found: " - "zero channels detected\n"); + dev_err(dev, "zero channels detected\n"); goto err_setup_interrupts; } @@ -1054,7 +1040,7 @@ int __devinit ioat_probe(struct ioatdma_device *device) if (err) goto err_setup_interrupts; - err = ioat_dma_self_test(device); + err = device->self_test(device); if (err) goto err_self_test; @@ -1097,6 +1083,113 @@ static void ioat1_intr_quirk(struct ioatdma_device *device) pci_write_config_dword(pdev, IOAT_PCI_DMACTRL_OFFSET, dmactrl); } +static ssize_t ring_size_show(struct dma_chan *c, char *page) +{ + struct ioat_dma_chan *ioat = to_ioat_chan(c); + + return sprintf(page, "%d\n", ioat->desccount); +} +static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size); + +static ssize_t ring_active_show(struct dma_chan *c, char *page) +{ + struct ioat_dma_chan *ioat = to_ioat_chan(c); + + return sprintf(page, "%d\n", ioat->active); +} +static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active); + +static ssize_t cap_show(struct dma_chan *c, char *page) +{ + struct dma_device *dma = c->device; + + return sprintf(page, "copy%s%s%s%s%s%s\n", + dma_has_cap(DMA_PQ, dma->cap_mask) ? " pq" : "", + dma_has_cap(DMA_PQ_VAL, dma->cap_mask) ? " pq_val" : "", + dma_has_cap(DMA_XOR, dma->cap_mask) ? " xor" : "", + dma_has_cap(DMA_XOR_VAL, dma->cap_mask) ? " xor_val" : "", + dma_has_cap(DMA_MEMSET, dma->cap_mask) ? " fill" : "", + dma_has_cap(DMA_INTERRUPT, dma->cap_mask) ? " intr" : ""); + +} +struct ioat_sysfs_entry ioat_cap_attr = __ATTR_RO(cap); + +static ssize_t version_show(struct dma_chan *c, char *page) +{ + struct dma_device *dma = c->device; + struct ioatdma_device *device = to_ioatdma_device(dma); + + return sprintf(page, "%d.%d\n", + device->version >> 4, device->version & 0xf); +} +struct ioat_sysfs_entry ioat_version_attr = __ATTR_RO(version); + +static struct attribute *ioat1_attrs[] = { + &ring_size_attr.attr, + &ring_active_attr.attr, + &ioat_cap_attr.attr, + &ioat_version_attr.attr, + NULL, +}; + +static ssize_t +ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page) +{ + struct ioat_sysfs_entry *entry; + struct ioat_chan_common *chan; + + entry = container_of(attr, struct ioat_sysfs_entry, attr); + chan = container_of(kobj, struct ioat_chan_common, kobj); + + if (!entry->show) + return -EIO; + return entry->show(&chan->common, page); +} + +struct sysfs_ops ioat_sysfs_ops = { + .show = ioat_attr_show, +}; + +static struct kobj_type ioat1_ktype = { + .sysfs_ops = &ioat_sysfs_ops, + .default_attrs = ioat1_attrs, +}; + +void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type) +{ + struct dma_device *dma = &device->common; + struct dma_chan *c; + + list_for_each_entry(c, &dma->channels, device_node) { + struct ioat_chan_common *chan = to_chan_common(c); + struct kobject *parent = &c->dev->device.kobj; + int err; + + err = kobject_init_and_add(&chan->kobj, type, parent, "quickdata"); + if (err) { + dev_warn(to_dev(chan), + "sysfs init error (%d), continuing...\n", err); + kobject_put(&chan->kobj); + set_bit(IOAT_KOBJ_INIT_FAIL, &chan->state); + } + } +} + +void ioat_kobject_del(struct ioatdma_device *device) +{ + struct dma_device *dma = &device->common; + struct dma_chan *c; + + list_for_each_entry(c, &dma->channels, device_node) { + struct ioat_chan_common *chan = to_chan_common(c); + + if (!test_bit(IOAT_KOBJ_INIT_FAIL, &chan->state)) { + kobject_del(&chan->kobj); + kobject_put(&chan->kobj); + } + } +} + int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca) { struct pci_dev *pdev = device->pdev; @@ -1105,6 +1198,7 @@ int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca) device->intr_quirk = ioat1_intr_quirk; device->enumerate_channels = ioat1_enumerate_channels; + device->self_test = ioat_dma_self_test; dma = &device->common; dma->device_prep_dma_memcpy = ioat1_dma_prep_memcpy; dma->device_issue_pending = ioat1_dma_memcpy_issue_pending; @@ -1119,6 +1213,8 @@ int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca) err = ioat_register(device); if (err) return err; + ioat_kobject_add(device, &ioat1_ktype); + if (dca) device->dca = ioat_dca_init(pdev, device->reg_base); @@ -1131,6 +1227,8 @@ void __devexit ioat_dma_remove(struct ioatdma_device *device) ioat_disable_interrupts(device); + ioat_kobject_del(device); + dma_async_device_unregister(dma); pci_pool_destroy(device->dma_pool); diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index 8966fa5453a7..6a675a2a2d1c 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -60,8 +60,12 @@ * @dca: direct cache access context * @intr_quirk: interrupt setup quirk (for ioat_v1 devices) * @enumerate_channels: hw version specific channel enumeration + * @cleanup_tasklet: select between the v2 and v3 cleanup routines + * @timer_fn: select between the v2 and v3 timer watchdog routines + * @self_test: hardware version specific self test for each supported op type + * + * Note: the v3 cleanup routine supports raid operations */ - struct ioatdma_device { struct pci_dev *pdev; void __iomem *reg_base; @@ -74,6 +78,9 @@ struct ioatdma_device { struct dca_provider *dca; void (*intr_quirk)(struct ioatdma_device *device); int (*enumerate_channels)(struct ioatdma_device *device); + void (*cleanup_tasklet)(unsigned long data); + void (*timer_fn)(unsigned long data); + int (*self_test)(struct ioatdma_device *device); }; struct ioat_chan_common { @@ -86,6 +93,7 @@ struct ioat_chan_common { #define IOAT_COMPLETION_PENDING 0 #define IOAT_COMPLETION_ACK 1 #define IOAT_RESET_PENDING 2 + #define IOAT_KOBJ_INIT_FAIL 3 struct timer_list timer; #define COMPLETION_TIMEOUT msecs_to_jiffies(100) #define IDLE_TIMEOUT msecs_to_jiffies(2000) @@ -94,8 +102,13 @@ struct ioat_chan_common { dma_addr_t completion_dma; u64 *completion; struct tasklet_struct cleanup_task; + struct kobject kobj; }; +struct ioat_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct dma_chan *, char *); +}; /** * struct ioat_dma_chan - internal representation of a DMA channel @@ -111,6 +124,7 @@ struct ioat_dma_chan { int pending; u16 desccount; + u16 active; }; static inline struct ioat_chan_common *to_chan_common(struct dma_chan *c) @@ -155,7 +169,7 @@ ioat_is_complete(struct dma_chan *c, dma_cookie_t cookie, /** * struct ioat_desc_sw - wrapper around hardware descriptor - * @hw: hardware DMA descriptor + * @hw: hardware DMA descriptor (for memcpy) * @node: this descriptor will either be on the free list, * or attached to a transaction list (tx_list) * @txd: the generic software descriptor for all engines @@ -288,9 +302,20 @@ static inline bool is_ioat_bug(unsigned long err) IOAT_CHANERR_LENGTH_ERR)); } +static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len, + int direction, enum dma_ctrl_flags flags, bool dst) +{ + if ((dst && (flags & DMA_COMPL_DEST_UNMAP_SINGLE)) || + (!dst && (flags & DMA_COMPL_SRC_UNMAP_SINGLE))) + pci_unmap_single(pdev, addr, len, direction); + else + pci_unmap_page(pdev, addr, len, direction); +} + int __devinit ioat_probe(struct ioatdma_device *device); int __devinit ioat_register(struct ioatdma_device *device); int __devinit ioat1_dma_probe(struct ioatdma_device *dev, int dca); +int __devinit ioat_dma_self_test(struct ioatdma_device *device); void __devexit ioat_dma_remove(struct ioatdma_device *device); struct dca_provider * __devinit ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase); @@ -304,4 +329,9 @@ void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags, size_t len, struct ioat_dma_descriptor *hw); bool ioat_cleanup_preamble(struct ioat_chan_common *chan, unsigned long *phys_complete); +void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type); +void ioat_kobject_del(struct ioatdma_device *device); +extern struct sysfs_ops ioat_sysfs_ops; +extern struct ioat_sysfs_entry ioat_version_attr; +extern struct ioat_sysfs_entry ioat_cap_attr; #endif /* IOATDMA_H */ diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index fa3d6db6624c..5d6ac49e0d32 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -39,7 +39,7 @@ #include "registers.h" #include "hw.h" -static int ioat_ring_alloc_order = 8; +int ioat_ring_alloc_order = 8; module_param(ioat_ring_alloc_order, int, 0644); MODULE_PARM_DESC(ioat_ring_alloc_order, "ioat2+: allocate 2^n descriptors per channel (default: n=8)"); @@ -48,7 +48,7 @@ module_param(ioat_ring_max_alloc_order, int, 0644); MODULE_PARM_DESC(ioat_ring_max_alloc_order, "ioat2+: upper limit for dynamic ring resizing (default: n=16)"); -static void __ioat2_issue_pending(struct ioat2_dma_chan *ioat) +void __ioat2_issue_pending(struct ioat2_dma_chan *ioat) { void * __iomem reg_base = ioat->base.reg_base; @@ -63,7 +63,7 @@ static void __ioat2_issue_pending(struct ioat2_dma_chan *ioat) __func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount); } -static void ioat2_issue_pending(struct dma_chan *chan) +void ioat2_issue_pending(struct dma_chan *chan) { struct ioat2_dma_chan *ioat = to_ioat2_chan(chan); @@ -206,7 +206,7 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat) spin_unlock_bh(&chan->cleanup_lock); } -static void ioat2_cleanup_tasklet(unsigned long data) +void ioat2_cleanup_tasklet(unsigned long data) { struct ioat2_dma_chan *ioat = (void *) data; @@ -214,7 +214,7 @@ static void ioat2_cleanup_tasklet(unsigned long data) writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } -static void __restart_chan(struct ioat2_dma_chan *ioat) +void __ioat2_restart_chan(struct ioat2_dma_chan *ioat) { struct ioat_chan_common *chan = &ioat->base; @@ -255,12 +255,10 @@ static void ioat2_restart_channel(struct ioat2_dma_chan *ioat) if (ioat_cleanup_preamble(chan, &phys_complete)) __cleanup(ioat, phys_complete); - __restart_chan(ioat); + __ioat2_restart_chan(ioat); } -static bool reshape_ring(struct ioat2_dma_chan *ioat, int order); - -static void ioat2_timer_event(unsigned long data) +void ioat2_timer_event(unsigned long data) { struct ioat2_dma_chan *ioat = (void *) data; struct ioat_chan_common *chan = &ioat->base; @@ -321,7 +319,7 @@ static void ioat2_timer_event(unsigned long data) * ioat2_enumerate_channels - find and initialize the device's channels * @device: the device to be enumerated */ -static int ioat2_enumerate_channels(struct ioatdma_device *device) +int ioat2_enumerate_channels(struct ioatdma_device *device) { struct ioat2_dma_chan *ioat; struct device *dev = &device->pdev->dev; @@ -354,8 +352,8 @@ static int ioat2_enumerate_channels(struct ioatdma_device *device) break; ioat_init_channel(device, &ioat->base, i, - ioat2_timer_event, - ioat2_cleanup_tasklet, + device->timer_fn, + device->cleanup_tasklet, (unsigned long) ioat); ioat->xfercap_log = xfercap_log; spin_lock_init(&ioat->ring_lock); @@ -461,7 +459,7 @@ static struct ioat_ring_ent **ioat2_alloc_ring(struct dma_chan *c, int order, gf /* ioat2_alloc_chan_resources - allocate/initialize ioat2 descriptor ring * @chan: channel to be initialized */ -static int ioat2_alloc_chan_resources(struct dma_chan *c) +int ioat2_alloc_chan_resources(struct dma_chan *c) { struct ioat2_dma_chan *ioat = to_ioat2_chan(c); struct ioat_chan_common *chan = &ioat->base; @@ -515,7 +513,7 @@ static int ioat2_alloc_chan_resources(struct dma_chan *c) return 1 << ioat->alloc_order; } -static bool reshape_ring(struct ioat2_dma_chan *ioat, int order) +bool reshape_ring(struct ioat2_dma_chan *ioat, int order) { /* reshape differs from normal ring allocation in that we want * to allocate a new software ring while only @@ -628,7 +626,7 @@ static bool reshape_ring(struct ioat2_dma_chan *ioat, int order) * @ioat: ioat2,3 channel (ring) to operate on * @num_descs: allocation length */ -static int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_descs) +int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_descs) { struct ioat_chan_common *chan = &ioat->base; @@ -656,9 +654,11 @@ static int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_d spin_lock_bh(&chan->cleanup_lock); if (jiffies > chan->timer.expires && timer_pending(&chan->timer)) { + struct ioatdma_device *device = chan->device; + mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT); spin_unlock_bh(&chan->cleanup_lock); - ioat2_timer_event((unsigned long) ioat); + device->timer_fn((unsigned long) ioat); } else spin_unlock_bh(&chan->cleanup_lock); return -ENOMEM; @@ -671,7 +671,7 @@ static int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_d return 0; /* with ioat->ring_lock held */ } -static struct dma_async_tx_descriptor * +struct dma_async_tx_descriptor * ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest, dma_addr_t dma_src, size_t len, unsigned long flags) { @@ -711,6 +711,7 @@ ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest, desc->txd.flags = flags; desc->len = total_len; hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT); + hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE); hw->ctl_f.compl_write = 1; dump_desc_dbg(ioat, desc); /* we leave the channel locked to ensure in order submission */ @@ -722,11 +723,11 @@ ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest, * ioat2_free_chan_resources - release all the descriptors * @chan: the channel to be cleaned */ -static void ioat2_free_chan_resources(struct dma_chan *c) +void ioat2_free_chan_resources(struct dma_chan *c) { struct ioat2_dma_chan *ioat = to_ioat2_chan(c); struct ioat_chan_common *chan = &ioat->base; - struct ioatdma_device *ioatdma_device = chan->device; + struct ioatdma_device *device = chan->device; struct ioat_ring_ent *desc; const u16 total_descs = 1 << ioat->alloc_order; int descs; @@ -740,7 +741,7 @@ static void ioat2_free_chan_resources(struct dma_chan *c) tasklet_disable(&chan->cleanup_task); del_timer_sync(&chan->timer); - ioat2_cleanup(ioat); + device->cleanup_tasklet((unsigned long) ioat); /* Delay 100ms after reset to allow internal DMA logic to quiesce * before removing DMA descriptor resources. @@ -770,8 +771,7 @@ static void ioat2_free_chan_resources(struct dma_chan *c) kfree(ioat->ring); ioat->ring = NULL; ioat->alloc_order = 0; - pci_pool_free(ioatdma_device->completion_pool, - chan->completion, + pci_pool_free(device->completion_pool, chan->completion, chan->completion_dma); spin_unlock_bh(&ioat->ring_lock); @@ -781,66 +781,63 @@ static void ioat2_free_chan_resources(struct dma_chan *c) ioat->dmacount = 0; } -static enum dma_status +enum dma_status ioat2_is_complete(struct dma_chan *c, dma_cookie_t cookie, dma_cookie_t *done, dma_cookie_t *used) { struct ioat2_dma_chan *ioat = to_ioat2_chan(c); + struct ioatdma_device *device = ioat->base.device; if (ioat_is_complete(c, cookie, done, used) == DMA_SUCCESS) return DMA_SUCCESS; - ioat2_cleanup(ioat); + device->cleanup_tasklet((unsigned long) ioat); return ioat_is_complete(c, cookie, done, used); } -int __devinit ioat2_dma_probe(struct ioatdma_device *device, int dca) +static ssize_t ring_size_show(struct dma_chan *c, char *page) { - struct pci_dev *pdev = device->pdev; - struct dma_device *dma; - struct dma_chan *c; - struct ioat_chan_common *chan; - int err; + struct ioat2_dma_chan *ioat = to_ioat2_chan(c); - device->enumerate_channels = ioat2_enumerate_channels; - dma = &device->common; - dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock; - dma->device_issue_pending = ioat2_issue_pending; - dma->device_alloc_chan_resources = ioat2_alloc_chan_resources; - dma->device_free_chan_resources = ioat2_free_chan_resources; - dma->device_is_tx_complete = ioat2_is_complete; + return sprintf(page, "%d\n", (1 << ioat->alloc_order) & ~1); +} +static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size); - err = ioat_probe(device); - if (err) - return err; - ioat_set_tcp_copy_break(2048); +static ssize_t ring_active_show(struct dma_chan *c, char *page) +{ + struct ioat2_dma_chan *ioat = to_ioat2_chan(c); - list_for_each_entry(c, &dma->channels, device_node) { - chan = to_chan_common(c); - writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE | IOAT_DMA_DCA_ANY_CPU, - chan->reg_base + IOAT_DCACTRL_OFFSET); - } + /* ...taken outside the lock, no need to be precise */ + return sprintf(page, "%d\n", ioat2_ring_active(ioat)); +} +static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active); - err = ioat_register(device); - if (err) - return err; - if (dca) - device->dca = ioat2_dca_init(pdev, device->reg_base); +static struct attribute *ioat2_attrs[] = { + &ring_size_attr.attr, + &ring_active_attr.attr, + &ioat_cap_attr.attr, + &ioat_version_attr.attr, + NULL, +}; - return err; -} +struct kobj_type ioat2_ktype = { + .sysfs_ops = &ioat_sysfs_ops, + .default_attrs = ioat2_attrs, +}; -int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) +int __devinit ioat2_dma_probe(struct ioatdma_device *device, int dca) { struct pci_dev *pdev = device->pdev; struct dma_device *dma; struct dma_chan *c; struct ioat_chan_common *chan; int err; - u16 dev_id; device->enumerate_channels = ioat2_enumerate_channels; + device->cleanup_tasklet = ioat2_cleanup_tasklet; + device->timer_fn = ioat2_timer_event; + device->self_test = ioat_dma_self_test; dma = &device->common; dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock; dma->device_issue_pending = ioat2_issue_pending; @@ -848,35 +845,25 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) dma->device_free_chan_resources = ioat2_free_chan_resources; dma->device_is_tx_complete = ioat2_is_complete; - /* -= IOAT ver.3 workarounds =- */ - /* Write CHANERRMSK_INT with 3E07h to mask out the errors - * that can cause stability issues for IOAT ver.3 - */ - pci_write_config_dword(pdev, IOAT_PCI_CHANERRMASK_INT_OFFSET, 0x3e07); - - /* Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit - * (workaround for spurious config parity error after restart) - */ - pci_read_config_word(pdev, IOAT_PCI_DEVICE_ID_OFFSET, &dev_id); - if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0) - pci_write_config_dword(pdev, IOAT_PCI_DMAUNCERRSTS_OFFSET, 0x10); - err = ioat_probe(device); if (err) return err; - ioat_set_tcp_copy_break(262144); + ioat_set_tcp_copy_break(2048); list_for_each_entry(c, &dma->channels, device_node) { chan = to_chan_common(c); - writel(IOAT_DMA_DCA_ANY_CPU, + writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE | IOAT_DMA_DCA_ANY_CPU, chan->reg_base + IOAT_DCACTRL_OFFSET); } err = ioat_register(device); if (err) return err; + + ioat_kobject_add(device, &ioat2_ktype); + if (dca) - device->dca = ioat3_dca_init(pdev, device->reg_base); + device->dca = ioat2_dca_init(pdev, device->reg_base); return err; } diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h index ac00adc81974..1d849ef74d5f 100644 --- a/drivers/dma/ioat/dma_v2.h +++ b/drivers/dma/ioat/dma_v2.h @@ -27,6 +27,7 @@ extern int ioat_pending_level; +extern int ioat_ring_alloc_order; /* * workaround for IOAT ver.3.0 null descriptor issue @@ -114,10 +115,36 @@ static inline u16 ioat2_xferlen_to_descs(struct ioat2_dma_chan *ioat, size_t len return num_descs; } +/** + * struct ioat_ring_ent - wrapper around hardware descriptor + * @hw: hardware DMA descriptor (for memcpy) + * @fill: hardware fill descriptor + * @xor: hardware xor descriptor + * @xor_ex: hardware xor extension descriptor + * @pq: hardware pq descriptor + * @pq_ex: hardware pq extension descriptor + * @pqu: hardware pq update descriptor + * @raw: hardware raw (un-typed) descriptor + * @txd: the generic software descriptor for all engines + * @len: total transaction length for unmap + * @result: asynchronous result of validate operations + * @id: identifier for debug + */ + struct ioat_ring_ent { - struct ioat_dma_descriptor *hw; + union { + struct ioat_dma_descriptor *hw; + struct ioat_fill_descriptor *fill; + struct ioat_xor_descriptor *xor; + struct ioat_xor_ext_descriptor *xor_ex; + struct ioat_pq_descriptor *pq; + struct ioat_pq_ext_descriptor *pq_ex; + struct ioat_pq_update_descriptor *pqu; + struct ioat_raw_descriptor *raw; + }; size_t len; struct dma_async_tx_descriptor txd; + enum sum_check_flags *result; #ifdef DEBUG int id; #endif @@ -143,5 +170,21 @@ int __devinit ioat2_dma_probe(struct ioatdma_device *dev, int dca); int __devinit ioat3_dma_probe(struct ioatdma_device |