From: Christoph Hellwig <hch@lst.de>
To: Amit Pundir <amit.pundir@linaro.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
jeremy.linton@arm.com, Sumit Semwal <sumit.semwal@linaro.org>,
iommu@lists.linux-foundation.org,
John Stultz <john.stultz@linaro.org>,
linux-rpi-kernel@lists.infradead.org,
David Rientjes <rientjes@google.com>,
Robin Murphy <robin.murphy@arm.com>,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH] dma-pool: Do not allocate pool memory from CMA
Date: Fri, 24 Jul 2020 15:41:14 +0200 [thread overview]
Message-ID: <20200724134114.GA3152@lst.de> (raw)
In-Reply-To: <CAMi1Hd3O2HHBsnt=sac7FdcW0-3=4S3g_F9f__2h5gTsudfirA@mail.gmail.com>
Yes, the iommu is an interesting case, and the current code is
wrong for that. Can you try the patch below? It contains a modified
version of Nicolas' patch to try CMA again for the expansion and a new
(for now hackish) way to not apply the addressability check for dma-iommu
allocations.
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 6bc74a2d51273e..ec5e525d2b9309 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -3,7 +3,9 @@
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2020 Google LLC
*/
+#include <linux/cma.h>
#include <linux/debugfs.h>
+#include <linux/dma-contiguous.h>
#include <linux/dma-direct.h>
#include <linux/dma-noncoherent.h>
#include <linux/init.h>
@@ -55,6 +57,31 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
pool_size_kernel += size;
}
+static bool cma_in_zone(gfp_t gfp)
+{
+ phys_addr_t end;
+ unsigned long size;
+ struct cma *cma;
+
+ cma = dev_get_cma_area(NULL);
+ if (!cma)
+ return false;
+
+ size = cma_get_size(cma);
+ if (!size)
+ return false;
+ end = cma_get_base(cma) - memblock_start_of_DRAM() + size - 1;
+
+ /* CMA can't cross zone boundaries, see cma_activate_area() */
+ if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA) &&
+ end <= DMA_BIT_MASK(zone_dma_bits))
+ return true;
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32) &&
+ end <= DMA_BIT_MASK(32))
+ return true;
+ return true;
+}
+
static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
gfp_t gfp)
{
@@ -68,7 +95,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
do {
pool_size = 1 << (PAGE_SHIFT + order);
- page = alloc_pages(gfp, order);
+ if (cma_in_zone(gfp))
+ page = dma_alloc_from_contiguous(NULL, 1 << order,
+ order, false);
+ if (!page)
+ page = alloc_pages(gfp, order);
} while (!page && order-- > 0);
if (!page)
goto out;
@@ -251,7 +282,11 @@ void *dma_alloc_from_pool(struct device *dev, size_t size,
continue;
phys = gen_pool_virt_to_phys(pool, val);
- if (dma_coherent_ok(dev, phys, size))
+ /*
+ * Only apply the addressability check for dma-direct.
+ * This is a nasty hack and won't work e.g. for arm.
+ */
+ if (get_dma_ops(dev) || dma_coherent_ok(dev, phys, size))
break;
gen_pool_free(pool, val, size);
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2020-07-24 13:41 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-08 16:49 [PATCH] dma-pool: Do not allocate pool memory from CMA Nicolas Saenz Julienne
2020-07-08 16:58 ` Christoph Hellwig
2020-07-08 23:14 ` Jeremy Linton
2020-07-09 21:47 ` David Rientjes via iommu
2020-07-21 7:21 ` Amit Pundir
2020-07-21 8:39 ` Nicolas Saenz Julienne
2020-07-21 8:54 ` Amit Pundir
2020-07-21 11:15 ` Nicolas Saenz Julienne
2020-07-21 11:28 ` Christoph Hellwig
2020-07-21 11:37 ` Nicolas Saenz Julienne
2020-07-21 12:16 ` Amit Pundir
2020-07-21 12:15 ` Amit Pundir
2020-07-21 12:45 ` Nicolas Saenz Julienne
2020-07-21 15:22 ` Amit Pundir
2020-07-21 16:27 ` Nicolas Saenz Julienne
2020-07-23 5:14 ` Amit Pundir
2020-07-24 9:36 ` Nicolas Saenz Julienne
2020-07-24 11:06 ` Amit Pundir
2020-07-24 13:41 ` Christoph Hellwig [this message]
2020-07-24 16:19 ` Amit Pundir
2020-07-24 16:27 ` Christoph Hellwig
2020-07-27 17:56 ` Nicolas Saenz Julienne
2020-07-28 9:13 ` Christoph Hellwig
2020-07-28 9:30 ` Nicolas Saenz Julienne
2020-07-28 10:09 ` Christoph Hellwig
2020-07-31 1:10 ` Nathan Chancellor
2020-07-31 7:19 ` Amit Pundir
2020-07-31 10:09 ` Nicolas Saenz Julienne
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200724134114.GA3152@lst.de \
--to=hch@lst.de \
--cc=amit.pundir@linaro.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jeremy.linton@arm.com \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rpi-kernel@lists.infradead.org \
--cc=rientjes@google.com \
--cc=robin.murphy@arm.com \
--cc=sumit.semwal@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).