netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Petr Tesarik <ptesarik@suse.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: linux-kernel@vger.kernel.org,
	"Cong Wang" <xiyou.wangcong@gmail.com>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Olivia Mackall" <olivia@selenic.com>,
	"Herbert Xu" <herbert@gondor.apana.org.au>,
	"Jason Wang" <jasowang@redhat.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Eugenio Pérez" <eperezma@redhat.com>,
	"James E.J. Bottomley" <James.Bottomley@hansenpartnership.com>,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	"Gerd Hoffmann" <kraxel@redhat.com>,
	"Xuan Zhuo" <xuanzhuo@linux.alibaba.com>,
	"Marek Szyprowski" <m.szyprowski@samsung.com>,
	"Robin Murphy" <robin.murphy@arm.com>,
	"Stefano Garzarella" <sgarzare@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Paolo Abeni" <pabeni@redhat.com>,
	"Simon Horman" <horms@kernel.org>,
	"Leon Romanovsky" <leon@kernel.org>,
	"Jason Gunthorpe" <jgg@ziepe.ca>,
	linux-doc@vger.kernel.org, linux-crypto@vger.kernel.org,
	virtualization@lists.linux.dev, linux-scsi@vger.kernel.org,
	iommu@lists.linux.dev, kvm@vger.kernel.org,
	netdev@vger.kernel.org
Subject: Re: [PATCH RFC 05/13] dma-debug: track cache clean flag in entries
Date: Fri, 2 Jan 2026 08:59:33 +0100	[thread overview]
Message-ID: <20260102085933.2f78123b@mordecai> (raw)
In-Reply-To: <c0df5d43759202733ccff045f834bd214977945f.1767089672.git.mst@redhat.com>

On Tue, 30 Dec 2025 05:16:00 -0500
"Michael S. Tsirkin" <mst@redhat.com> wrote:

> If a driver is bugy and has 2 overlapping mappings but only
> sets cache clean flag on the 1st one of them, we warn.
> But if it only does it for the 2nd one, we don't.
> 
> Fix by tracking cache clean flag in the entry.
> Shrink map_err_type to u8 to avoid bloating up the struct.
> 
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
>  kernel/dma/debug.c | 25 ++++++++++++++++++++-----
>  1 file changed, 20 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
> index 7e66d863d573..9bd14fd4c51b 100644
> --- a/kernel/dma/debug.c
> +++ b/kernel/dma/debug.c
> @@ -63,6 +63,7 @@ enum map_err_types {
>   * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
>   * @paddr: physical start address of the mapping
>   * @map_err_type: track whether dma_mapping_error() was checked
> + * @is_cache_clean: driver promises not to write to buffer while mapped
>   * @stack_len: number of backtrace entries in @stack_entries
>   * @stack_entries: stack of backtrace history
>   */
> @@ -76,7 +77,8 @@ struct dma_debug_entry {
>  	int		 sg_call_ents;
>  	int		 sg_mapped_ents;
>  	phys_addr_t	 paddr;
> -	enum map_err_types  map_err_type;
> +	u8		 map_err_type;

Where exactly is the bloat? With my configuration, the size of struct
dma_debug_entry is 128 bytes, with enough padding bytes at the end to
keep it at 128 even if I keep this member an enum...

Anyway, if there is a reason to keep this member small, I prefer to
pack enum map_err_types instead:

@@ -46,9 +46,9 @@ enum {
 enum map_err_types {
 	MAP_ERR_CHECK_NOT_APPLICABLE,
 	MAP_ERR_NOT_CHECKED,
 	MAP_ERR_CHECKED,
-};
+} __packed;
 
 #define DMA_DEBUG_STACKTRACE_ENTRIES 5
 
 /**

This will shrink it to a single byte but it will also keep the type
information.

> +	bool		 is_cache_clean;
>  #ifdef CONFIG_STACKTRACE
>  	unsigned int	stack_len;
>  	unsigned long	stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
> @@ -472,12 +474,15 @@ static int active_cacheline_dec_overlap(phys_addr_t cln)
>  	return active_cacheline_set_overlap(cln, --overlap);
>  }
>  
> -static int active_cacheline_insert(struct dma_debug_entry *entry)
> +static int active_cacheline_insert(struct dma_debug_entry *entry,
> +				   bool *overlap_cache_clean)
>  {
>  	phys_addr_t cln = to_cacheline_number(entry);
>  	unsigned long flags;
>  	int rc;
>  
> +	*overlap_cache_clean = false;
> +
>  	/* If the device is not writing memory then we don't have any
>  	 * concerns about the cpu consuming stale data.  This mitigates
>  	 * legitimate usages of overlapping mappings.
> @@ -487,8 +492,14 @@ static int active_cacheline_insert(struct dma_debug_entry *entry)
>  
>  	spin_lock_irqsave(&radix_lock, flags);
>  	rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
> -	if (rc == -EEXIST)
> +	if (rc == -EEXIST) {
> +		struct dma_debug_entry *existing;
> +
>  		active_cacheline_inc_overlap(cln);
> +		existing = radix_tree_lookup(&dma_active_cacheline, cln);
> +		if (existing)
> +			*overlap_cache_clean = existing->is_cache_clean;

*nitpick*

IIUC radix_tree_insert() returns -EEXIST only if the key is already
present in the tree. Since radix_lock is not released between the
insert attempt and this lookup, I don't see how this lookup could
possibly fail. If it's not expected to fail, I would add a WARN_ON().

Please, do correct me if I'm missing something.

Other than that, LGTM.

Petr T

> +	}
>  	spin_unlock_irqrestore(&radix_lock, flags);
>  
>  	return rc;
> @@ -583,20 +594,24 @@ DEFINE_SHOW_ATTRIBUTE(dump);
>   */
>  static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
>  {
> +	bool overlap_cache_clean;
>  	struct hash_bucket *bucket;
>  	unsigned long flags;
>  	int rc;
>  
> +	entry->is_cache_clean = !!(attrs & DMA_ATTR_CPU_CACHE_CLEAN);
> +
>  	bucket = get_hash_bucket(entry, &flags);
>  	hash_bucket_add(bucket, entry);
>  	put_hash_bucket(bucket, flags);
>  
> -	rc = active_cacheline_insert(entry);
> +	rc = active_cacheline_insert(entry, &overlap_cache_clean);
>  	if (rc == -ENOMEM) {
>  		pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n");
>  		global_disable = true;
>  	} else if (rc == -EEXIST &&
> -		   !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_CPU_CACHE_CLEAN)) &&
> +		   !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
> +		   !(entry->is_cache_clean && overlap_cache_clean) &&
>  		   !(IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) &&
>  		     is_swiotlb_active(entry->dev))) {
>  		err_printk(entry->dev, entry,


  reply	other threads:[~2026-01-02  7:59 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-30 10:15 [PATCH RFC 00/13] fix DMA aligment issues around virtio Michael S. Tsirkin
2025-12-30 10:15 ` [PATCH RFC 01/13] dma-mapping: add __dma_from_device_align_begin/end Michael S. Tsirkin
2025-12-31 14:01   ` Petr Tesarik
2025-12-31 14:40     ` Michael S. Tsirkin
2025-12-31 20:48     ` Michael S. Tsirkin
2026-01-02  8:14       ` Petr Tesarik
2025-12-30 10:15 ` [PATCH RFC 02/13] docs: dma-api: document __dma_align_begin/end Michael S. Tsirkin
2025-12-30 10:15 ` [PATCH RFC 03/13] dma-mapping: add DMA_ATTR_CPU_CACHE_CLEAN Michael S. Tsirkin
2025-12-30 10:15 ` [PATCH RFC 04/13] docs: dma-api: document DMA_ATTR_CPU_CACHE_CLEAN Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 05/13] dma-debug: track cache clean flag in entries Michael S. Tsirkin
2026-01-02  7:59   ` Petr Tesarik [this message]
2026-01-02 11:17     ` Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 06/13] virtio: add virtqueue_add_inbuf_cache_clean API Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 07/13] vsock/virtio: fix DMA alignment for event_list Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 08/13] vsock/virtio: use virtqueue_add_inbuf_cache_clean for events Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 09/13] virtio_input: fix DMA alignment for evts Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 10/13] virtio_scsi: fix DMA cacheline issues for events Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 11/13] virtio-rng: fix DMA alignment for data buffer Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 12/13] virtio_input: use virtqueue_add_inbuf_cache_clean for events Michael S. Tsirkin
2025-12-30 10:16 ` [PATCH RFC 13/13] vsock/virtio: reorder fields to reduce struct padding Michael S. Tsirkin
2025-12-30 16:40 ` [PATCH RFC 14/13] gpio: virtio: fix DMA alignment Michael S. Tsirkin
2026-01-02 12:46   ` Bartosz Golaszewski
2025-12-30 16:40 ` [PATCH RFC 15/13] gpio: virtio: reorder fields to reduce struct padding Michael S. Tsirkin
2026-01-02 12:47   ` Bartosz Golaszewski
2026-01-02 13:02     ` Michael S. Tsirkin
2026-01-02 13:27       ` Bartosz Golaszewski
2025-12-31 13:12 ` [PATCH RFC 00/13] fix DMA aligment issues around virtio Petr Tesarik
2025-12-31 14:42   ` Michael S. Tsirkin

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=20260102085933.2f78123b@mordecai \
    --to=ptesarik@suse.com \
    --cc=James.Bottomley@hansenpartnership.com \
    --cc=corbet@lwn.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=eperezma@redhat.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=horms@kernel.org \
    --cc=iommu@lists.linux.dev \
    --cc=jasowang@redhat.com \
    --cc=jgg@ziepe.ca \
    --cc=kraxel@redhat.com \
    --cc=kuba@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=m.szyprowski@samsung.com \
    --cc=martin.petersen@oracle.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=olivia@selenic.com \
    --cc=pabeni@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=robin.murphy@arm.com \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux.dev \
    --cc=xiyou.wangcong@gmail.com \
    --cc=xuanzhuo@linux.alibaba.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;
as well as URLs for NNTP newsgroup(s).