All of lore.kernel.org
 help / color / mirror / Atom feed
From: konrad@kernel.org (Konrad Rzeszutek Wilk)
Subject: [PATCH resend] swiotlb: ensure that page-sized mappings are page-aligned
Date: Sun, 15 Jan 2017 12:41:08 -0500	[thread overview]
Message-ID: <20170115174106.GA6150@localhost.localdomain> (raw)
In-Reply-To: <1484160991-29624-1-git-send-email-nikita.yoush@cogentembedded.com>

On Wed, Jan 11, 2017@09:56:31PM +0300, Nikita Yushchenko wrote:
> Some drivers do depend on page mappings to be page aligned.
> 
> Swiotlb already enforces such alignment for mappings greater than page,
> extend that to page-sized mappings as well.
> 
> Without this fix, nvme hits BUG() in nvme_setup_prps(), because that routine
> assumes page-aligned mappings.
> 
> Signed-off-by: Nikita Yushchenko <nikita.yoush at cogentembedded.com>

I queued it up in stable/for-linus-4.10 in swiotlb queue tree.

> ---
>  lib/swiotlb.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/swiotlb.c b/lib/swiotlb.c
> index 975b8fc..a8d74a7 100644
> --- a/lib/swiotlb.c
> +++ b/lib/swiotlb.c
> @@ -483,11 +483,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
>  		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
>  
>  	/*
> -	 * For mappings greater than a page, we limit the stride (and
> -	 * hence alignment) to a page size.
> +	 * For mappings greater than or equal to a page, we limit the stride
> +	 * (and hence alignment) to a page size.
>  	 */
>  	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
> -	if (size > PAGE_SIZE)
> +	if (size >= PAGE_SIZE)
>  		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
>  	else
>  		stride = 1;
> -- 
> 2.1.4
> 

WARNING: multiple messages have this Message-ID (diff)
From: Konrad Rzeszutek Wilk <konrad@kernel.org>
To: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	linux-kernel@vger.kernel.org,
	Artemi Ivanov <artemi.ivanov@cogentembedded.com>,
	Christoph Hellwig <hch@lst.de>,
	linux-nvme@lists.infradead.org
Subject: Re: [PATCH resend] swiotlb: ensure that page-sized mappings are page-aligned
Date: Sun, 15 Jan 2017 12:41:08 -0500	[thread overview]
Message-ID: <20170115174106.GA6150@localhost.localdomain> (raw)
In-Reply-To: <1484160991-29624-1-git-send-email-nikita.yoush@cogentembedded.com>

On Wed, Jan 11, 2017 at 09:56:31PM +0300, Nikita Yushchenko wrote:
> Some drivers do depend on page mappings to be page aligned.
> 
> Swiotlb already enforces such alignment for mappings greater than page,
> extend that to page-sized mappings as well.
> 
> Without this fix, nvme hits BUG() in nvme_setup_prps(), because that routine
> assumes page-aligned mappings.
> 
> Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com>

I queued it up in stable/for-linus-4.10 in swiotlb queue tree.

> ---
>  lib/swiotlb.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/swiotlb.c b/lib/swiotlb.c
> index 975b8fc..a8d74a7 100644
> --- a/lib/swiotlb.c
> +++ b/lib/swiotlb.c
> @@ -483,11 +483,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
>  		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
>  
>  	/*
> -	 * For mappings greater than a page, we limit the stride (and
> -	 * hence alignment) to a page size.
> +	 * For mappings greater than or equal to a page, we limit the stride
> +	 * (and hence alignment) to a page size.
>  	 */
>  	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
> -	if (size > PAGE_SIZE)
> +	if (size >= PAGE_SIZE)
>  		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
>  	else
>  		stride = 1;
> -- 
> 2.1.4
> 

  parent reply	other threads:[~2017-01-15 17:41 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-11 18:56 [PATCH resend] swiotlb: ensure that page-sized mappings are page-aligned Nikita Yushchenko
2017-01-11 18:56 ` Nikita Yushchenko
2017-01-12  7:55 ` Christoph Hellwig
2017-01-12  7:55   ` Christoph Hellwig
2017-01-12  9:09 ` Sagi Grimberg
2017-01-12  9:09   ` Sagi Grimberg
2017-01-15 17:41 ` Konrad Rzeszutek Wilk [this message]
2017-01-15 17:41   ` Konrad Rzeszutek Wilk

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=20170115174106.GA6150@localhost.localdomain \
    --to=konrad@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.