From 275029353953c2117941ade84f02a2303912fad1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 23 Mar 2012 13:36:42 -0700 Subject: ioat: fix size of 'completion' for Xen Starting with v3.2 Jonathan reports that Xen crashes loading the ioatdma driver. A debug run shows: ioatdma 0000:00:16.4: desc[0]: (0x300cc7000->0x300cc7040) cookie: 0 flags: 0x2 ctl: 0x29 (op: 0 int_en: 1 compl: 1) ... ioatdma 0000:00:16.4: ioat_get_current_completion: phys_complete: 0xcc7000 ...which shows that in this environment GFP_KERNEL memory may be backed by a 64-bit dma address. This breaks the driver's assumption that an unsigned long should be able to contain the physical address for descriptor memory. Switch to dma_addr_t which beyond being the right size, is the true type for the data i.e. an io-virtual address inidicating the engine's last processed descriptor. [stable: 3.2+] Cc: Reported-by: Jonathan Nieder Reported-by: William Dauchy Tested-by: William Dauchy Tested-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dma/ioat/dma_v3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/dma/ioat/dma_v3.c') diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index f519c93a61e..2dbf32b0273 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -256,7 +256,7 @@ static bool desc_has_ext(struct ioat_ring_ent *desc) * The difference from the dma_v2.c __cleanup() is that this routine * handles extended descriptors and dma-unmapping raid operations. */ -static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete) +static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete) { struct ioat_chan_common *chan = &ioat->base; struct ioat_ring_ent *desc; @@ -314,7 +314,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete) static void ioat3_cleanup(struct ioat2_dma_chan *ioat) { struct ioat_chan_common *chan = &ioat->base; - unsigned long phys_complete; + dma_addr_t phys_complete; spin_lock_bh(&chan->cleanup_lock); if (ioat_cleanup_preamble(chan, &phys_complete)) @@ -333,7 +333,7 @@ static void ioat3_cleanup_event(unsigned long data) static void ioat3_restart_channel(struct ioat2_dma_chan *ioat) { struct ioat_chan_common *chan = &ioat->base; - unsigned long phys_complete; + dma_addr_t phys_complete; ioat2_quiesce(chan, 0); if (ioat_cleanup_preamble(chan, &phys_complete)) @@ -348,7 +348,7 @@ static void ioat3_timer_event(unsigned long data) struct ioat_chan_common *chan = &ioat->base; if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) { - unsigned long phys_complete; + dma_addr_t phys_complete; u64 status; status = ioat_chansts(chan); -- cgit v1.2.3-70-g09d2 From f26df1a1a9452573af7b6cea9a4723593e838568 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 4 Apr 2012 16:10:41 -0700 Subject: ioatdma: DMA copy alignment needed to address IOAT DMA silicon errata Silicon errata where when RAID and legacy descriptors are mixed, the legacy (memcpy and friends) operation must have alignment of 64 bytes to avoid hanging. This effects Intel Xeon C55xx, C35xx, E5-2600. Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dma/ioat/dma_v3.c | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'drivers/dma/ioat/dma_v3.c') diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 2dbf32b0273..dfe925fa57a 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -1147,6 +1147,44 @@ static int ioat3_reset_hw(struct ioat_chan_common *chan) return ioat2_reset_sync(chan, msecs_to_jiffies(200)); } +static bool is_jf_ioat(struct pci_dev *pdev) +{ + switch (pdev->device) { + case PCI_DEVICE_ID_INTEL_IOAT_JSF0: + case PCI_DEVICE_ID_INTEL_IOAT_JSF1: + case PCI_DEVICE_ID_INTEL_IOAT_JSF2: + case PCI_DEVICE_ID_INTEL_IOAT_JSF3: + case PCI_DEVICE_ID_INTEL_IOAT_JSF4: + case PCI_DEVICE_ID_INTEL_IOAT_JSF5: + case PCI_DEVICE_ID_INTEL_IOAT_JSF6: + case PCI_DEVICE_ID_INTEL_IOAT_JSF7: + case PCI_DEVICE_ID_INTEL_IOAT_JSF8: + case PCI_DEVICE_ID_INTEL_IOAT_JSF9: + return true; + default: + return false; + } +} + +static bool is_snb_ioat(struct pci_dev *pdev) +{ + switch (pdev->device) { + case PCI_DEVICE_ID_INTEL_IOAT_SNB0: + case PCI_DEVICE_ID_INTEL_IOAT_SNB1: + case PCI_DEVICE_ID_INTEL_IOAT_SNB2: + case PCI_DEVICE_ID_INTEL_IOAT_SNB3: + case PCI_DEVICE_ID_INTEL_IOAT_SNB4: + case PCI_DEVICE_ID_INTEL_IOAT_SNB5: + case PCI_DEVICE_ID_INTEL_IOAT_SNB6: + case PCI_DEVICE_ID_INTEL_IOAT_SNB7: + case PCI_DEVICE_ID_INTEL_IOAT_SNB8: + case PCI_DEVICE_ID_INTEL_IOAT_SNB9: + return true; + default: + return false; + } +} + int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) { struct pci_dev *pdev = device->pdev; @@ -1167,6 +1205,9 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) dma->device_alloc_chan_resources = ioat2_alloc_chan_resources; dma->device_free_chan_resources = ioat2_free_chan_resources; + if (is_jf_ioat(pdev) || is_snb_ioat(pdev)) + dma->copy_align = 6; + dma_cap_set(DMA_INTERRUPT, dma->cap_mask); dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock; -- cgit v1.2.3-70-g09d2