[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20231025084426.2739-1-petrtesarik@huaweicloud.com>
Date: Wed, 25 Oct 2023 10:44:25 +0200
From: Petr Tesarik <petrtesarik@...weicloud.com>
To: Christoph Hellwig <hch@....de>,
Marek Szyprowski <m.szyprowski@...sung.com>,
Robin Murphy <robin.murphy@....com>,
Petr Tesarik <petr.tesarik1@...wei-partners.com>,
iommu@...ts.linux.dev (open list:DMA MAPPING HELPERS),
linux-kernel@...r.kernel.org (open list)
Cc: Wangkefeng <wangkefeng.wang@...wei.com>,
Roberto Sassu <roberto.sassu@...weicloud.com>,
petr@...arici.cz, Ben Greear <greearb@...delatech.com>
Subject: [PATCH] swiotlb: Do not try to allocate a TLB bigger than MAX_ORDER pages
From: Petr Tesarik <petr.tesarik1@...wei-partners.com>
When allocating a new pool at runtime, reduce the number of slabs so that
the allocation order is at most MAX_ORDER. This avoids a kernel WARNING in
__alloc_pages().
The warning is relatively benign, because the pool size is subsequently
reduced when allocation fails, but it is silly to start with a request that
is known to fail, especially since this is the default behavior if the
kernel is built with CONFIG_SWIOTLB_DYNAMIC=y and booted without any
swiotlb= parameter.
Reported-by: Ben Greear <greearb@...delatech.com>
Closes: https://lore.kernel.org/netdev/4f173dd2-324a-0240-ff8d-abf5c191be18@candelatech.com/
Fixes: 1aaa736815eb ("swiotlb: allocate a new memory pool when existing pools are full")
Signed-off-by: Petr Tesarik <petr.tesarik1@...wei-partners.com>
---
kernel/dma/swiotlb.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 01637677736f..dff067bd56b1 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -678,6 +678,11 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
size_t pool_size;
size_t tlb_size;
+ if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
+ nslabs = SLABS_PER_PAGE << MAX_ORDER;
+ nareas = limit_nareas(nareas, nslabs);
+ }
+
pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas);
pool = kzalloc(pool_size, gfp);
if (!pool)
--
2.42.0
Powered by blists - more mailing lists