public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: kernel-team@android.com, Will Deacon <will@kernel.org>,
	iommu@lists.linux.dev, Christoph Hellwig <hch@lst.de>,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	Robin Murphy <robin.murphy@arm.com>,
	Petr Tesarik <petr.tesarik1@huawei-partners.com>,
	Dexuan Cui <decui@microsoft.com>,
	Nicolin Chen <nicolinc@nvidia.com>,
	Michael Kelley <mhklinux@outlook.com>
Subject: [PATCH v5 6/6] swiotlb: Remove pointless stride adjustment for allocations >= PAGE_SIZE
Date: Wed, 28 Feb 2024 13:39:30 +0000	[thread overview]
Message-ID: <20240228133930.15400-7-will@kernel.org> (raw)
In-Reply-To: <20240228133930.15400-1-will@kernel.org>

For swiotlb allocations >= PAGE_SIZE, the slab search historically
adjusted the stride to avoid checking unaligned slots. However, this is
no longer needed now that the code around it has evolved and the
stride is calculated from the required alignment.

Either 'alloc_align_mask' is used to specify the allocation alignment or
the DMA 'min_align_mask' is used to align the allocation with 'orig_addr'.
At least one of these masks is always non-zero.

In light of that, remove the redundant (and slightly confusing) check.

Link: https://lore.kernel.org/r/SN6PR02MB4157089980E6FC58D5557BCED4572@SN6PR02MB4157.namprd02.prod.outlook.com
Reported-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 kernel/dma/swiotlb.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c381a7ed718f..0d8805569f5e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1006,13 +1006,6 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	 */
 	stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask));
 
-	/*
-	 * For allocations of PAGE_SIZE or larger only look for page aligned
-	 * allocations.
-	 */
-	if (alloc_size >= PAGE_SIZE)
-		stride = umax(stride, PAGE_SHIFT - IO_TLB_SHIFT + 1);
-
 	spin_lock_irqsave(&area->lock, flags);
 	if (unlikely(nslots > pool->area_nslabs - area->used))
 		goto not_found;
-- 
2.44.0.rc1.240.g4c46232300-goog


  parent reply	other threads:[~2024-02-28 13:39 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-28 13:39 [PATCH v5 0/6] Fix double allocation in swiotlb_alloc() Will Deacon
2024-02-28 13:39 ` [PATCH v5 1/6] swiotlb: Fix double-allocation of slots due to broken alignment handling Will Deacon
2024-02-29  5:44   ` Michael Kelley
2024-02-28 13:39 ` [PATCH v5 2/6] swiotlb: Enforce page alignment in swiotlb_alloc() Will Deacon
2024-02-28 13:39 ` [PATCH v5 3/6] swiotlb: Honour dma_alloc_coherent() " Will Deacon
2024-02-28 13:39 ` [PATCH v5 4/6] swiotlb: Fix alignment checks when both allocation and DMA masks are present Will Deacon
2024-02-28 13:39 ` [PATCH v5 5/6] iommu/dma: Force swiotlb_max_mapping_size on an untrusted device Will Deacon
2024-02-29  5:57   ` Michael Kelley
2024-02-28 13:39 ` Will Deacon [this message]
2024-02-29  6:07   ` [PATCH v5 6/6] swiotlb: Remove pointless stride adjustment for allocations >= PAGE_SIZE Michael Kelley
2024-02-29  7:36     ` Michael Kelley
2024-02-29 13:33       ` Christoph Hellwig
2024-02-29 15:44         ` Michael Kelley
2024-02-29 15:47           ` Christoph Hellwig
2024-03-01 15:39             ` Petr Tesařík
2024-03-01 16:38               ` Robin Murphy
2024-03-01 17:33                 ` Petr Tesařík
2024-03-01 17:08               ` Petr Tesařík
2024-03-01 17:54                 ` Robin Murphy
2024-03-01 18:42                   ` Petr Tesařík
2024-03-04  3:31                     ` Michael Kelley
2024-03-04 11:00                       ` Petr Tesařík
2024-03-04 13:37                         ` Robin Murphy
2024-03-04 15:55                           ` Petr Tesařík
2024-03-04 16:02                             ` Will Deacon
2024-03-04 16:10                               ` Michael Kelley
2024-03-04 16:53                                 ` Robin Murphy
2024-03-04 18:22                                   ` Michael Kelley
2024-03-05 11:20                                     ` Robin Murphy
2024-03-05 15:15                                       ` Petr Tesařík
2024-03-04 19:04                                 ` Petr Tesařík
2024-03-05 14:08                                   ` Christoph Hellwig
2024-03-04 16:04                             ` Michael Kelley
2024-03-04 17:11                               ` Robin Murphy
2024-03-04 18:08                                 ` Michael Kelley
2024-03-05 14:05                           ` Christoph Hellwig
2024-03-04 15:32     ` Will Deacon

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=20240228133930.15400-7-will@kernel.org \
    --to=will@kernel.org \
    --cc=decui@microsoft.com \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux.dev \
    --cc=kernel-team@android.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=m.szyprowski@samsung.com \
    --cc=mhklinux@outlook.com \
    --cc=nicolinc@nvidia.com \
    --cc=petr.tesarik1@huawei-partners.com \
    --cc=robin.murphy@arm.com \
    /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