| Message ID | 20161231041024.GB2448@templeofstupid.com (mailing list archive) |
|---|---|
| State | Changes Requested |
| Headers | show |
On Fri, Dec 30, 2016 at 08:10:24PM -0800, Krister Johansen wrote: > diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c > index 90eddd9..9d82f8f 100644 > --- a/drivers/dma/ioat/init.c > +++ b/drivers/dma/ioat/init.c > @@ -693,7 +693,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) > /* doing 2 32bit writes to mmio since 1 64b write doesn't work */ > ioat_chan->completion = > dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool, > - GFP_KERNEL, &ioat_chan->completion_dma); > + GFP_ATOMIC, &ioat_chan->completion_dma); can you actually make it GFP_NOWAIT, we prefer that.
On Mon, Jan 02, 2017 at 03:54:13PM +0530, Vinod Koul wrote: > On Fri, Dec 30, 2016 at 08:10:24PM -0800, Krister Johansen wrote: > > > diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c > > index 90eddd9..9d82f8f 100644 > > --- a/drivers/dma/ioat/init.c > > +++ b/drivers/dma/ioat/init.c > > @@ -693,7 +693,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) > > /* doing 2 32bit writes to mmio since 1 64b write doesn't work */ > > ioat_chan->completion = > > dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool, > > - GFP_KERNEL, &ioat_chan->completion_dma); > > + GFP_ATOMIC, &ioat_chan->completion_dma); > > can you actually make it GFP_NOWAIT, we prefer that. Absolutely. I'll send one that's updated to use that instead. -K -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 90eddd9..9d82f8f 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -693,7 +693,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) /* doing 2 32bit writes to mmio since 1 64b write doesn't work */ ioat_chan->completion = dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool, - GFP_KERNEL, &ioat_chan->completion_dma); + GFP_ATOMIC, &ioat_chan->completion_dma); if (!ioat_chan->completion) return -ENOMEM; @@ -703,7 +703,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH); order = IOAT_MAX_ORDER; - ring = ioat_alloc_ring(c, order, GFP_KERNEL); + ring = ioat_alloc_ring(c, order, GFP_ATOMIC); if (!ring) return -ENOMEM;
On a kernel with DEBUG_LOCKS, ioat_free_chan_resources triggers an in_interrupt() warning. With PROVE_LOCKING, it reports detecting a SOFTIRQ-safe to SOFTIRQ-unsafe lock ordering in the same code path. This is because dma_generic_alloc_coherent() checks if the GFP flags permit blocking. It allocates from different subsystems if blocking is permitted. The free path knows how to return the memory to the correct allocator. If GFP_KERNEL is specified then the alloc and free end up going through cma_alloc(), which uses mutexes. Given that ioat_free_chan_resources() can be called in interrupt context, ioat_alloc_chan_resources() must specify GFP_ATOMIC so that the allocations do not block and instead use an allocator that uses spinlocks. Signed-off-by: Krister Johansen <kjlx@templeofstupid.com> --- drivers/dma/ioat/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)