On Sun, Aug 30, 2020 at 11:04:21AM +0200, Cédric Le Goater wrote:
> Hello,
>
> On 7/8/20 5:24 PM, Christoph Hellwig wrote:
> > Use the DMA API bypass mechanism for direct window mappings. This uses
> > common code and speed up the direct mapping case by avoiding indirect
> > calls just when not using dma ops at all. It also fixes a problem where
> > the sync_* methods were using the bypass check for DMA allocations, but
> > those are part of the streaming ops.
> >
> > Note that this patch loses the DMA_ATTR_WEAK_ORDERING override, which
> > has never been well defined, as is only used by a few drivers, which
> > IIRC never showed up in the typical Cell blade setups that are affected
> > by the ordering workaround.
> >
> > Fixes: efd176a04bef ("powerpc/pseries/dma: Allow SWIOTLB")
> > Signed-off-by: Christoph Hellwig <h...@lst.de>
> > ---
> > arch/powerpc/Kconfig | 1 +
> > arch/powerpc/include/asm/device.h | 5 --
> > arch/powerpc/kernel/dma-iommu.c | 90 ++++---------------------------
> > 3 files changed, 10 insertions(+), 86 deletions(-)
>
> I am seeing corruptions on a couple of POWER9 systems (boston) when
> stressed with IO. stress-ng gives some results but I have first seen
> it when compiling the kernel in a guest and this is still the best way
> to raise the issue.
>
> These systems have of a SAS Adaptec controller :
>
> 0003:01:00.0 Serial Attached SCSI controller: Adaptec Series 8 12G SAS/PCIe
> 3 (rev 01)
>
> When the failure occurs, the POWERPC EEH interrupt fires and dumps
> lowlevel PHB4 registers among which :
>
> [ 2179.251069490,3] PHB#0003[0:3]: phbErrorStatus =
> 0000028000000000
> [ 2179.251117476,3] PHB#0003[0:3]: phbFirstErrorStatus =
> 0000020000000000
>
> The bits raised identify a PPC 'TCE' error, which means it is related
> to DMAs. See below for more details.
>
>
> Reverting this patch "fixes" the issue but it is probably else where,
> in some other layers or in the aacraid driver. How should I proceed
> to get more information ?
The aacraid DMA masks look like a mess. Can you try the hack
below and see it it helps?
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 769af4ca9ca97e..79c6b744dbb66c 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -2228,18 +2228,6 @@ int aac_get_adapter_info(struct aac_dev* dev)
expose_physicals = 0;
}
- if (dev->dac_support) {
- if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(64))) {
- if (!dev->in_reset)
- dev_info(&dev->pdev->dev, "64 Bit DAC
enabled\n");
- } else if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(32))) {
- dev_info(&dev->pdev->dev, "DMA mask set failed, 64 Bit
DAC disabled\n");
- dev->dac_support = 0;
- } else {
- dev_info(&dev->pdev->dev, "No suitable DMA
available\n");
- rcode = -ENOMEM;
- }
- }
/*
* Deal with configuring for the individualized limits of each packet
* interface.
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index adbdc3b7c7a706..dbb23b351a4e7d 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1479,7 +1479,6 @@ static int _aac_reset_adapter(struct aac_dev *aac, int
forced, u8 reset_type)
struct Scsi_Host *host = aac->scsi_host_ptr;
int jafo = 0;
int bled;
- u64 dmamask;
int num_of_fibs = 0;
/*
@@ -1558,22 +1557,7 @@ static int _aac_reset_adapter(struct aac_dev *aac, int
forced, u8 reset_type)
kfree(aac->fsa_dev);
aac->fsa_dev = NULL;
- dmamask = DMA_BIT_MASK(32);
quirks = aac_get_driver_ident(index)->quirks;
- if (quirks & AAC_QUIRK_31BIT)
- retval = pci_set_dma_mask(aac->pdev, dmamask);
- else if (!(quirks & AAC_QUIRK_SRC))
- retval = pci_set_dma_mask(aac->pdev, dmamask);
- else
- retval = pci_set_consistent_dma_mask(aac->pdev, dmamask);
-
- if (quirks & AAC_QUIRK_31BIT && !retval) {
- dmamask = DMA_BIT_MASK(31);
- retval = pci_set_consistent_dma_mask(aac->pdev, dmamask);
- }
-
- if (retval)
- goto out;
if ((retval = (*(aac_get_driver_ident(index)->init))(aac)))
goto out;
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 8588da0a065551..d897a9d59e24a1 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1634,8 +1634,6 @@ static int aac_probe_one(struct pci_dev *pdev, const
struct pci_device_id *id)
struct list_head *insert = &aac_devices;
int error;
int unique_id = 0;
- u64 dmamask;
- int mask_bits = 0;
extern int aac_sync_mode;
/*
@@ -1658,33 +1656,6 @@ static int aac_probe_one(struct pci_dev *pdev, const
struct pci_device_id *id)
if (error)
goto out;
- if (!(aac_drivers[index].quirks & AAC_QUIRK_SRC)) {
- error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
- if (error) {
- dev_err(&pdev->dev, "PCI 32 BIT dma mask set failed");
- goto out_disable_pdev;
- }
- }
-
- /*
- * If the quirk31 bit is set, the adapter needs adapter
- * to driver communication memory to be allocated below 2gig
- */
- if (aac_drivers[index].quirks & AAC_QUIRK_31BIT) {
- dmamask = DMA_BIT_MASK(31);
- mask_bits = 31;
- } else {
- dmamask = DMA_BIT_MASK(32);
- mask_bits = 32;
- }
-
- error = pci_set_consistent_dma_mask(pdev, dmamask);
- if (error) {
- dev_err(&pdev->dev, "PCI %d B consistent dma mask set failed\n"
- , mask_bits);
- goto out_disable_pdev;
- }
-
pci_set_master(pdev);
shost = scsi_host_alloc(&aac_driver_template, sizeof(struct aac_dev));
