linux-stable.git/kernel/dma/mapping.c, branch v5.15.208

dma: fix call order in dmam_free_coherent

2024-08-19T03:45:23+00:00

[ Upstream commit 28e8b7406d3a1f5329a03aa25a43aa28e087cb20 ]

dmam_free_coherent() frees a DMA allocation, which makes the
freed vaddr available for reuse, then calls devres_destroy()
to remove and free the data structure used to track the DMA
allocation. Between the two calls, it is possible for a
concurrent task to make an allocation with the same vaddr
and add it to the devres list.

If this happens, there will be two entries in the devres list
with the same vaddr and devres_destroy() can free the wrong
entry, triggering the WARN_ON() in dmam_match.

Fix by destroying the devres entry before freeing the DMA
allocation.

Tested:
  kokonut //net/encryption
    http://sponge2/b9145fe6-0f72-4325-ac2f-a84d81075b03

Fixes: 9ac7849e35f7 ("devres: device resource management")
Signed-off-by: Lance Richardson 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

dma-mapping: add dma_opt_mapping_size()

2024-04-10T14:18:47+00:00

[ Upstream commit a229cc14f3395311b899e5e582b71efa8dd01df0 ]

Streaming DMA mapping involving an IOMMU may be much slower for larger
total mapping size. This is because every IOMMU DMA mapping requires an
IOVA to be allocated and freed. IOVA sizes above a certain limit are not
cached, which can have a big impact on DMA mapping performance.

Provide an API for device drivers to know this "optimal" limit, such that
they may try to produce mapping which don't exceed it.

Signed-off-by: John Garry 
Reviewed-by: Damien Le Moal 
Acked-by: Martin K. Petersen 
Signed-off-by: Christoph Hellwig 
Stable-dep-of: afc5aa46ed56 ("iommu/dma: Force swiotlb_max_mapping_size on an untrusted device")
Signed-off-by: Sasha Levin

dma-mapping: remove bogus test for pfn_valid from dma_map_resource

2022-04-27T12:38:50+00:00

commit a9c38c5d267cb94871dfa2de5539c92025c855d7 upstream.

dma_map_resource() uses pfn_valid() to ensure the range is not RAM.
However, pfn_valid() only checks for availability of the memory map for a
PFN but it does not ensure that the PFN is actually backed by RAM.

As dma_map_resource() is the only method in DMA mapping APIs that has this
check, simply drop the pfn_valid() test from dma_map_resource().

Link: https://lore.kernel.org/all/20210824173741.GC623@arm.com/
Signed-off-by: Mike Rapoport 
Reviewed-by: Christoph Hellwig 
Acked-by: David Hildenbrand 
Link: https://lore.kernel.org/r/20210930013039.11260-2-rppt@kernel.org
Signed-off-by: Will Deacon 
Fixes: 859a85ddf90e ("mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE")
Link: https://lore.kernel.org/r/Yl0IZWT2nsiYtqBT@linux.ibm.com
Signed-off-by: Georgi Djakov 
Signed-off-by: Greg Kroah-Hartman

dma-debug: teach add_dma_entry() about DMA_ATTR_SKIP_CPU_SYNC

2021-10-18T10:46:45+00:00

Mapping something twice should be possible as long as,
DMA_ATTR_SKIP_CPU_SYNC is passed to the strictly speaking second relevant
mapping operation (that attempts to map the same thing). So, don't issue a
warning if the specified condition is met in add_dma_entry().

Signed-off-by: Hamza Mahfooz 
Signed-off-by: Christoph Hellwig

dma-mapping: fix the kerneldoc for dma_map_sgtable()

2021-10-11T11:43:04+00:00

htmldocs began producing the following warnings:

  kernel/dma/mapping.c:256: WARNING: Definition list ends without a
             blank line; unexpected unindent.
  kernel/dma/mapping.c:257: WARNING: Bullet list ends without a blank
             line; unexpected unindent.

Reformatting the list without hyphens fixes the warnings and produces
both a readable text and HTML output.

Fixes: fffe3cc8c219 ("dma-mapping: allow map_sg() ops to return negative error code")
Reported-by: Stephen Rothwell 
Signed-off-by: Logan Gunthorpe 
Signed-off-by: Christoph Hellwig

dma-mapping: fix the kerneldoc for dma_map_sg_attrs

2021-09-06T12:40:47+00:00

Add the missing description for the nents parameter, and fix a trivial
misalignment.

Fixes: fffe3cc8c219 ("dma-mapping: allow map_sg() ops to return negative error codes")
Reported-by: Stephen Rothwell 
Signed-off-by: Christoph Hellwig

dma-mapping: return an unsigned int from dma_map_sg{,_attrs}

2021-08-14T07:18:36+00:00

These can only return 0 for failure or the number of entries, so turn
the return value into an unsigned int.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Logan Gunthorpe

dma-mapping: disallow .map_sg operations from returning zero on error

2021-08-09T15:15:02+00:00

Now that all the .map_sg operations have been converted to returning
proper error codes, drop the code to handle a zero return value,
add a warning if a zero is returned.

Signed-off-by: Logan Gunthorpe 
Signed-off-by: Christoph Hellwig

dma-mapping: allow map_sg() ops to return negative error codes

2021-08-09T15:13:02+00:00

Allow dma_map_sgtable() to pass errors from the map_sg() ops. This
will be required for returning appropriate error codes when mapping
P2PDMA memory.

Introduce __dma_map_sg_attrs() which will return the raw error code
from the map_sg operation (whether it be negative or zero). Then add a
dma_map_sg_attrs() wrapper to convert any negative errors to zero to
satisfy the existing calling convention.

dma_map_sgtable() defines three error codes that .map_sg implementations
are allowed to return: -EINVAL, -ENOMEM and -EIO. The latter of which
is a generic return for cases that are passing DMA_MAPPING_ERROR
through.

dma_map_sgtable() will convert a zero error return for old map_sg() ops
into a -EIO return and return any negative errors as reported.

This allows map_sg implementations to start returning multiple
negative error codes. Legacy map_sg implementations can continue
to return zero until they are all converted.

Signed-off-by: Logan Gunthorpe 
Signed-off-by: Christoph Hellwig

dma-mapping: add a dma_alloc_noncontiguous API

2021-03-15T09:02:31+00:00

Add a new API that returns a potentiall virtually non-contigous sg_table
and a DMA address.  This API is only properly implemented for dma-iommu
and will simply return a contigious chunk as a fallback.

The intent is that drivers can use this API if either:

 - no kernel mapping or only temporary kernel mappings are required.
   That is as a better replacement for DMA_ATTR_NO_KERNEL_MAPPING
 - a kernel mapping is required for cached and DMA mapped pages, but
   the driver also needs the pages to e.g. map them to userspace.
   In that sense it is a replacement for some aspects of the recently
   removed and never fully implemented DMA_ATTR_NON_CONSISTENT

Signed-off-by: Christoph Hellwig 
Reviewed-by: Tomasz Figa 
Tested-by: Ricardo Ribalda