mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Joerg Roedel <joro@8bytes.org>
To: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org, joro@8bytes.org, jroedel@suse.de
Subject: [PATCH 14/23] iommu/amd: Iterate over all aperture ranges in dma_ops_area_alloc
Date: Tue, 22 Dec 2015 23:21:19 +0100	[thread overview]
Message-ID: <1450822888-22590-15-git-send-email-joro@8bytes.org> (raw)
In-Reply-To: <1450822888-22590-1-git-send-email-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

This way we don't need to care about the next_index wrapping
around in dma_ops_alloc_addresses.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 62a4079..faf51a0 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1563,35 +1563,36 @@ static unsigned long dma_ops_area_alloc(struct device *dev,
 					unsigned long align_mask,
 					u64 dma_mask)
 {
-	int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	unsigned long next_bit, boundary_size, mask;
 	unsigned long address = -1;
-	int i = dom->next_index;
+	int start = dom->next_index;
+	int i;
 
 	mask = dma_get_seg_boundary(dev);
 
 	boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
 				   1UL << (BITS_PER_LONG - PAGE_SHIFT);
 
-	for (;i < max_index; ++i) {
-		struct aperture_range *range = dom->aperture[i];
+	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+		struct aperture_range *range;
+
+		range = dom->aperture[(start + i) % APERTURE_MAX_RANGES];
 
-		if (range->offset >= dma_mask)
-			break;
+		if (!range || range->offset >= dma_mask)
+			continue;
 
 		next_bit  = range->next_bit;
 
-		address = dma_ops_aperture_alloc(dom, dom->aperture[i], pages,
+		address = dma_ops_aperture_alloc(dom, range, pages,
 						 dma_mask, boundary_size,
 						 align_mask);
 		if (address != -1) {
-			address = dom->aperture[i]->offset +
-				  (address << PAGE_SHIFT);
+			address = range->offset + (address << PAGE_SHIFT);
 			dom->next_index = i;
 			break;
 		}
 
-		if (next_bit > dom->aperture[i]->next_bit)
+		if (next_bit > range->next_bit)
 			dom->need_flush = true;
 	}
 
@@ -1613,13 +1614,6 @@ static unsigned long dma_ops_alloc_addresses(struct device *dev,
 
 	address = dma_ops_area_alloc(dev, dom, pages, align_mask, dma_mask);
 
-	if (address == -1) {
-		dom->next_index = 0;
-		address = dma_ops_area_alloc(dev, dom, pages, align_mask,
-					     dma_mask);
-		dom->need_flush = true;
-	}
-
 	if (unlikely(address == -1))
 		address = DMA_ERROR_CODE;
 
-- 
1.9.1


  parent reply	other threads:[~2015-12-22 22:24 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-22 22:21 [PATCH 00/23] AMD IOMMU DMA-API Scalability Improvements Joerg Roedel
2015-12-22 22:21 ` [PATCH 01/23] iommu/amd: Warn only once on unexpected pte value Joerg Roedel
2015-12-22 22:21 ` [PATCH 02/23] iommu/amd: Move 'struct dma_ops_domain' definition to amd_iommu.c Joerg Roedel
2015-12-22 22:21 ` [PATCH 03/23] iommu/amd: Introduce bitmap_lock in struct aperture_range Joerg Roedel
2015-12-22 22:21 ` [PATCH 04/23] iommu/amd: Flush IOMMU TLB on __map_single error path Joerg Roedel
2015-12-22 22:21 ` [PATCH 05/23] iommu/amd: Flush the IOMMU TLB before the addresses are freed Joerg Roedel
2015-12-22 22:21 ` [PATCH 06/23] iommu/amd: Pass correct shift to iommu_area_alloc() Joerg Roedel
2015-12-22 22:21 ` [PATCH 07/23] iommu/amd: Add dma_ops_aperture_alloc() function Joerg Roedel
2015-12-22 22:21 ` [PATCH 08/23] iommu/amd: Move aperture_range.offset to another cache-line Joerg Roedel
2015-12-22 22:21 ` [PATCH 09/23] iommu/amd: Retry address allocation within one aperture Joerg Roedel
2015-12-22 22:21 ` [PATCH 10/23] iommu/amd: Flush iommu tlb in dma_ops_aperture_alloc() Joerg Roedel
2015-12-22 22:21 ` [PATCH 11/23] iommu/amd: Remove 'start' parameter from dma_ops_area_alloc Joerg Roedel
2015-12-22 22:21 ` [PATCH 12/23] iommu/amd: Rename dma_ops_domain->next_address to next_index Joerg Roedel
2015-12-22 22:21 ` [PATCH 13/23] iommu/amd: Flush iommu tlb in dma_ops_free_addresses Joerg Roedel
2015-12-22 22:21 ` Joerg Roedel [this message]
2015-12-22 22:21 ` [PATCH 15/23] iommu/amd: Remove need_flush from struct dma_ops_domain Joerg Roedel
2015-12-22 22:21 ` [PATCH 16/23] iommu/amd: Optimize dma_ops_free_addresses Joerg Roedel
2015-12-22 22:21 ` [PATCH 17/23] iommu/amd: Allocate new aperture ranges in dma_ops_alloc_addresses Joerg Roedel
2015-12-22 22:21 ` [PATCH 18/23] iommu/amd: Build io page-tables with cmpxchg64 Joerg Roedel
2015-12-22 22:21 ` [PATCH 19/23] iommu/amd: Initialize new aperture range before making it visible Joerg Roedel
2015-12-22 22:21 ` [PATCH 20/23] iommu/amd: Relax locking in dma_ops path Joerg Roedel
2015-12-22 22:21 ` [PATCH 21/23] iommu/amd: Make dma_ops_domain->next_index percpu Joerg Roedel
2015-12-22 22:21 ` [PATCH 22/23] iommu/amd: Use trylock to aquire bitmap_lock Joerg Roedel
2015-12-22 22:21 ` [PATCH 23/23] iommu/amd: Preallocate dma_ops apertures based on dma_mask Joerg Roedel

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=1450822888-22590-15-git-send-email-joro@8bytes.org \
    --to=joro@8bytes.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jroedel@suse.de \
    --cc=linux-kernel@vger.kernel.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

all inboxes | Powered by JetHome®