iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: Benjamin Herrenschmidt
	<benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>,
	Paul Mackerras <paulus-eUNUBHrolfbYtjvyW6yDsg@public.gmane.org>,
	Michael Ellerman <mpe-Gsx/Oe8HsFggBc27wqDAHg@public.gmane.org>,
	Tony Luck <tony.luck-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	Fenghua Yu <fenghua.yu-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
	iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
	linux-ia64-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>,
	Konrad Rzeszutek Wilk
	<konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Subject: [PATCH 02/20] kernel/dma/direct: refine dma_direct_alloc zone selection
Date: Mon, 30 Jul 2018 18:38:06 +0200	[thread overview]
Message-ID: <20180730163824.10064-3-hch@lst.de> (raw)
In-Reply-To: <20180730163824.10064-1-hch-jcswGhMUV9g@public.gmane.org>

We need to take the DMA offset and encryption bit into account when selecting
a zone.  Add a helper that takes those into account and use it.

Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 kernel/dma/direct.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index d32d4f0d2c0c..c2c1df8827f2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -58,6 +58,14 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 	return addr + size - 1 <= dev->coherent_dma_mask;
 }
 
+static bool dma_coherent_below(struct device *dev, u64 mask)
+{
+	dma_addr_t addr = force_dma_unencrypted() ?
+		__phys_to_dma(dev, mask) : phys_to_dma(dev, mask);
+
+	return dev->coherent_dma_mask <= addr;
+}
+
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
@@ -70,9 +78,9 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	gfp &= ~__GFP_ZERO;
 
 	/* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
-	if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+	if (dma_coherent_below(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)))
 		gfp |= GFP_DMA;
-	if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
+	if (dma_coherent_below(dev, DMA_BIT_MASK(32) && !(gfp & GFP_DMA)))
 		gfp |= GFP_DMA32;
 
 again:
@@ -92,14 +100,14 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
-		    dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
+		    dma_coherent_below(dev, DMA_BIT_MASK(64)) &&
 		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
 			gfp |= GFP_DMA32;
 			goto again;
 		}
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA) &&
-		    dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+		    dma_coherent_below(dev, DMA_BIT_MASK(32)) &&
 		    !(gfp & GFP_DMA)) {
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
 			goto again;
-- 
2.18.0

  parent reply	other threads:[~2018-07-30 16:38 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-30 16:38 use generic DMA mapping code in powerpc Christoph Hellwig
     [not found] ` <20180730163824.10064-1-hch-jcswGhMUV9g@public.gmane.org>
2018-07-30 16:38   ` [PATCH 01/20] kernel/dma/direct: take DMA offset into account in dma_direct_supported Christoph Hellwig
     [not found]     ` <20180730163824.10064-2-hch-jcswGhMUV9g@public.gmane.org>
2018-08-08 23:44       ` Benjamin Herrenschmidt
     [not found]         ` <74068e4d2135ecad8645048ed97b1114891ccace.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-22  6:53           ` Christoph Hellwig
     [not found]             ` <20180822065359.GB19284-jcswGhMUV9g@public.gmane.org>
2018-08-22 23:59               ` Benjamin Herrenschmidt
     [not found]                 ` <079a961eaf548644250719df83930d3d72e34cac.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-23  5:24                   ` Christoph Hellwig
     [not found]                     ` <20180823052403.GA14388-jcswGhMUV9g@public.gmane.org>
2018-08-23  5:24                       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` Christoph Hellwig [this message]
     [not found]     ` <20180730163824.10064-3-hch-jcswGhMUV9g@public.gmane.org>
2018-08-08 23:54       ` [PATCH 02/20] kernel/dma/direct: refine dma_direct_alloc zone selection Benjamin Herrenschmidt
     [not found]         ` <7177553cdb5cd1b968f653a52d7e88bd71aae4d8.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-22  6:58           ` Christoph Hellwig
     [not found]             ` <20180822065856.GC19284-jcswGhMUV9g@public.gmane.org>
2018-08-23  0:01               ` Benjamin Herrenschmidt
     [not found]                 ` <d9866d44704073ecc418f62da0ba7587ce7c9af8.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-23  5:26                   ` Christoph Hellwig
2018-07-30 16:38   ` [PATCH 03/20] dma-mapping: make the get_required_mask method available unconditionally Christoph Hellwig
2018-07-30 16:38   ` [PATCH 04/20] ia64: remove get_required_mask implementation Christoph Hellwig
2018-07-30 16:38   ` [PATCH 05/20] swiotlb: allow the architecture to provide a get_required_mask hook Christoph Hellwig
     [not found]     ` <20180730163824.10064-6-hch-jcswGhMUV9g@public.gmane.org>
2018-08-27 16:06       ` Konrad Rzeszutek Wilk
2018-07-30 16:38   ` [PATCH 06/20] dma-noncoherent: add an optional arch hook for ->get_required_mask Christoph Hellwig
2018-07-30 16:38   ` [PATCH 07/20] powerpc/dma: remove the unused ARCH_HAS_DMA_MMAP_COHERENT define Christoph Hellwig
     [not found]     ` <20180730163824.10064-8-hch-jcswGhMUV9g@public.gmane.org>
2018-08-08 23:56       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 08/20] powerpc/dma: remove the unused dma_nommu_ops export Christoph Hellwig
     [not found]     ` <20180730163824.10064-9-hch-jcswGhMUV9g@public.gmane.org>
2018-07-31 12:16       ` Christoph Hellwig
     [not found]         ` <20180731121625.GA29793-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:01           ` Benjamin Herrenschmidt
     [not found]             ` <f7daffa5481ab82f345aa5bf9f63f40caa068456.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-22  6:45               ` Christoph Hellwig
     [not found]                 ` <20180822064531.GA19284-jcswGhMUV9g@public.gmane.org>
2018-08-22 23:50                   ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 09/20] powerpc/dma: remove the unused ISA_DMA_THRESHOLD export Christoph Hellwig
     [not found]     ` <20180730163824.10064-10-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:14       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 10/20] powerpc/dma-noncoherent: don't disable irqs over kmap_atomic Christoph Hellwig
     [not found]     ` <20180730163824.10064-11-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:27       ` Benjamin Herrenschmidt
     [not found]         ` <bfa22816fee0759cfee28705b427be3586c7d2e3.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-22  7:02           ` Christoph Hellwig
     [not found]             ` <20180822070241.GD19284-jcswGhMUV9g@public.gmane.org>
2018-08-22 23:45               ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 11/20] powerpc/dma: split the two __dma_alloc_coherent implementations Christoph Hellwig
     [not found]     ` <20180730163824.10064-12-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:40       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 12/20] powerpc/dma: use phys_to_dma instead of get_dma_offset Christoph Hellwig
     [not found]     ` <20180730163824.10064-13-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:43       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 13/20] powerpc/dma: remove get_dma_offset Christoph Hellwig
     [not found]     ` <20180730163824.10064-14-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:45       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 14/20] powerpc/dma: replace dma_nommu_dma_supported with dma_direct_supported Christoph Hellwig
     [not found]     ` <20180730163824.10064-15-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:49       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 15/20] powerpc/dma: remove the unused unmap_page and unmap_sg methods Christoph Hellwig
     [not found]     ` <20180730163824.10064-16-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:49       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 16/20] powerpc/dma: use dma_direct_{alloc,free} Christoph Hellwig
     [not found]     ` <20180730163824.10064-17-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:52       ` Benjamin Herrenschmidt
2018-08-27  8:51         ` Scott Wood
2018-07-30 16:38   ` [PATCH 17/20] powerpc/dma-swiotlb: use generic swiotlb_dma_ops Christoph Hellwig
     [not found]     ` <20180730163824.10064-18-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  0:54       ` Benjamin Herrenschmidt
     [not found]         ` <556a4302d13b1caafb223112c4de43d959146215.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-09  1:57           ` Benjamin Herrenschmidt
     [not found]             ` <777010cd04645b55aa4197eddcc880f010f0ef6d.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-08-22  7:04               ` Christoph Hellwig
2018-07-30 16:38   ` [PATCH 18/20] powerpc/dma-noncoherent: use generic dma_noncoherent_ops Christoph Hellwig
     [not found]     ` <20180730163824.10064-19-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  1:00       ` Benjamin Herrenschmidt
2018-07-30 16:38   ` [PATCH 19/20] powerpc/dma: use the generic dma-direct map_page and map_sg routines Christoph Hellwig
2018-07-30 16:38   ` [PATCH 20/20] powerpc/dma: remove dma_nommu_mmap_coherent Christoph Hellwig
     [not found]     ` <20180730163824.10064-21-hch-jcswGhMUV9g@public.gmane.org>
2018-08-09  1:05       ` Benjamin Herrenschmidt

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=20180730163824.10064-3-hch@lst.de \
    --to=hch-jcswghmuv9g@public.gmane.org \
    --cc=benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org \
    --cc=fenghua.yu-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
    --cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
    --cc=konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org \
    --cc=linux-ia64-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org \
    --cc=mpe-Gsx/Oe8HsFggBc27wqDAHg@public.gmane.org \
    --cc=paulus-eUNUBHrolfbYtjvyW6yDsg@public.gmane.org \
    --cc=robin.murphy-5wv7dgnIgG8@public.gmane.org \
    --cc=tony.luck-ral2JQCrhuEAvxtiuMwx3w@public.gmane.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).