summaryrefslogtreecommitdiffstats
path: root/Documentation/networking/netmem.rst
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-08-19 10:09:22 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2026-08-19 10:09:22 -0700
commitf4cdf7ca9a1fdcca413157df19753f388a5a224e (patch)
tree60a31895b2446cd7fa27514e8c2843534a0de0da /Documentation/networking/netmem.rst
downloadlinux-stable-f4cdf7ca9a1fdcca413157df19753f388a5a224e.tar.gz
linux-stable-f4cdf7ca9a1fdcca413157df19753f388a5a224e.zip
Merge tag 'media/v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-mediagrafted
Pull media updates from Mauro Carvalho Chehab: - v4l2-core: added ISP statistics support and per-block validation - v4l2-core: Allow unknown HDR10 white point and luminance - New camera sensors: Sony IMX678 and IMX471m, Himax HM1092 IR sensor - New codec: Milos: VPU v2.0 codec support - isp driver: gained support for Dreamchip RPPX1 ISP framework - vsp1 driver: gained support for RZ/T2H and RZ/N2H - Novalake driver: gained CVS support for new NVL hardware - dvb-core: fix feed leak on failed DMX_ADD_PID - several driver fixes, cleanups and minor improvements * tag 'media/v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media: (308 commits) media: ipu-bridge: check all DMI entries when overriding sensor rotation media: v4l2-async: avoid deleting unlinked ASC entry on link error media: rzg2l-cru: Align bytesperline to hardware DMA stride requirement media: intel/ipu6: fix async notifier cleanup leak on parse error media: staging/ipu7: fix async notifier UAF on probe error path media: amd: isp4: fix self-deadlock in isp4sd_pwron_and_init() error path media: amd: isp4: release partial allocations in isp4if_alloc_fw_gpumem() media: rcar-isp: Fix VSPX reference leaks media: rcar-isp: Release ISPCORE resources media: i2c: imx415: Release runtime PM reference on VBLANK error media: i2c: imx415: Return test pattern write errors media: renesas: vsp1: Declare index variables in for loop statement media: renesas: vsp1: Make reset control optional to support platforms without a reset line media: dt-bindings: media: renesas,vsp1: Document RZ/T2H and RZ/N2H SoCs media: dt-bindings: media: renesas,fcp: Document RZ/T2H and RZ/N2H SoCs media: nxp: imx8-isi: Add additional 32-bit RGB format support media: nxp: imx8-isi: Add 16-bit raw Bayer format support media: nxp: imx8-isi: Implement per-stream reference counting for multiplexed streams media: nxp: imx8-isi: Use BIT_ULL() for 64-bit stream masks media: nxp: imx8-isi: Correct color map between V4L2 and ISI ...
Diffstat (limited to 'Documentation/networking/netmem.rst')
-rw-r--r--Documentation/networking/netmem.rst104
1 files changed, 104 insertions, 0 deletions
diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst
new file mode 100644
index 000000000..217869d11
--- /dev/null
+++ b/Documentation/networking/netmem.rst
@@ -0,0 +1,104 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+Netmem Support for Network Drivers
+==================================
+
+This document outlines the requirements for network drivers to support netmem,
+an abstract memory type that enables features like device memory TCP. By
+supporting netmem, drivers can work with various underlying memory types
+with little to no modification.
+
+Benefits of Netmem :
+
+* Flexibility: Netmem can be backed by different memory types (e.g., struct
+ page, DMA-buf), allowing drivers to support various use cases such as device
+ memory TCP.
+* Future-proof: Drivers with netmem support are ready for upcoming
+ features that rely on it.
+* Simplified Development: Drivers interact with a consistent API,
+ regardless of the underlying memory implementation.
+
+Driver RX Requirements
+======================
+
+1. The driver must support page_pool.
+
+2. The driver must support the tcp-data-split ethtool option.
+
+3. The driver must use the page_pool netmem APIs for payload memory. The netmem
+ APIs currently 1-to-1 correspond with page APIs. Conversion to netmem should
+ be achievable by switching the page APIs to netmem APIs and tracking memory
+ via netmem_refs in the driver rather than struct page * :
+
+ - page_pool_alloc -> page_pool_alloc_netmem
+ - page_pool_get_dma_addr -> page_pool_get_dma_addr_netmem
+ - page_pool_put_page -> page_pool_put_netmem
+
+ Not all page APIs have netmem equivalents at the moment. If your driver
+ relies on a missing netmem API, feel free to add and propose to netdev@, or
+ reach out to the maintainers and/or almasrymina@google.com for help adding
+ the netmem API.
+
+4. The driver must use the following PP_FLAGS:
+
+ - PP_FLAG_DMA_MAP: netmem is not dma-mappable by the driver. The driver
+ must delegate the dma mapping to the page_pool, which knows when
+ dma-mapping is (or is not) appropriate.
+ - PP_FLAG_DMA_SYNC_DEV: netmem dma addr is not necessarily dma-syncable
+ by the driver. The driver must delegate the dma syncing to the page_pool,
+ which knows when dma-syncing is (or is not) appropriate.
+ - PP_FLAG_ALLOW_UNREADABLE_NETMEM. The driver must specify this flag iff
+ tcp-data-split is enabled.
+
+5. The driver must not assume the netmem is readable and/or backed by pages.
+ The netmem returned by the page_pool may be unreadable, in which case
+ netmem_address() will return NULL. The driver must correctly handle
+ unreadable netmem, i.e. don't attempt to handle its contents when
+ netmem_address() is NULL.
+
+ Ideally, drivers should not have to check the underlying netmem type via
+ helpers like netmem_is_net_iov() or convert the netmem to any of its
+ underlying types via netmem_to_page() or netmem_to_net_iov(). In most cases,
+ netmem or page_pool helpers that abstract this complexity are provided
+ (and more can be added).
+
+6. The driver must use page_pool_dma_sync_netmem_for_cpu() in lieu of
+ dma_sync_single_range_for_cpu(). For some memory providers, dma_syncing for
+ CPU will be done by the page_pool, for others (particularly dmabuf memory
+ provider), dma syncing for CPU is the responsibility of the userspace using
+ dmabuf APIs. The driver must delegate the entire dma-syncing operation to
+ the page_pool which will do it correctly.
+
+7. Avoid implementing driver-specific recycling on top of the page_pool. Drivers
+ cannot hold onto a struct page to do their own recycling as the netmem may
+ not be backed by a struct page. However, you may hold onto a page_pool
+ reference with page_pool_fragment_netmem() or page_pool_ref_netmem() for
+ that purpose, but be mindful that some netmem types might have longer
+ circulation times, such as when userspace holds a reference in zerocopy
+ scenarios.
+
+Driver TX Requirements
+======================
+
+1. The Driver must not pass the netmem dma_addr to any of the dma-mapping APIs
+ directly. This is because netmem dma_addrs may come from a source like
+ dma-buf that is not compatible with the dma-mapping APIs.
+
+ Helpers like netmem_dma_unmap_page_attrs() & netmem_dma_unmap_addr_set()
+ should be used in lieu of dma_unmap_page[_attrs](), dma_unmap_addr_set().
+ The netmem variants will handle netmem dma_addrs correctly regardless of the
+ source, delegating to the dma-mapping APIs when appropriate.
+
+ Not all dma-mapping APIs have netmem equivalents at the moment. If your
+ driver relies on a missing netmem API, feel free to add and propose to
+ netdev@, or reach out to the maintainers and/or almasrymina@google.com for
+ help adding the netmem API.
+
+2. Driver should declare support by setting `netdev->netmem_tx` to the
+ appropriate mode:
+
+ - `NETMEM_TX_DMA`: for physical devices that perform DMA.
+
+ - `NETMEM_TX_NO_DMA`: for virtual or passthrough devices that do
+ not DMA, but still support handling of netmem-backed skbs.