May 2024 - Linux-kselftest-mirror

[PATCH v2 0/2] selftests/resctrl: SNC kernel support discovery

by Maciej Wieczor-Retman

Changes v2: - Removed patches 2 and 3 since now this part will be supported by the kernel. Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory into multiple NUMA nodes. When enabled, NUMA-aware applications can achieve better performance on bigger server platforms. SNC support in the kernel is currently in review [1]. With SNC enabled and kernel support in place all the tests will function normally. There might be a problem when SNC is enabled but the system is still using an older kernel version without SNC support. Currently the only message displayed in that situation is a guess that SNC might be enabled and is causing issues. That message also is displayed whenever the test fails on an Intel platform. Add a mechanism to discover kernel support for SNC which will add more meaning and certainty to the error message. Series was tested on Ice Lake server platforms with SNC disabled, SNC-2 and SNC-4. The tests were also ran with and without kernel support for SNC. Series applies cleanly on kselftest/next. [1] https://lore.kernel.org/all/20240503203325.21512-1-tony.luck@intel.com/ Previous versions of this series: [v1] https://lore.kernel.org/all/cover.1709721159.git.maciej.wieczor-retman@inte… Maciej Wieczor-Retman (2): selftests/resctrl: Adjust effective L3 cache size with SNC enabled selftests/resctrl: Adjust SNC support messages tools/testing/selftests/resctrl/cat_test.c | 2 +- tools/testing/selftests/resctrl/cmt_test.c | 6 +- tools/testing/selftests/resctrl/mba_test.c | 2 + tools/testing/selftests/resctrl/mbm_test.c | 4 +- tools/testing/selftests/resctrl/resctrl.h | 8 +- tools/testing/selftests/resctrl/resctrlfs.c | 131 +++++++++++++++++++- 6 files changed, 144 insertions(+), 9 deletions(-) -- 2.45.0

5 months, 4 weeks

3
18
0 0

[PATCH v4 00/14] security: digest_cache LSM

by Roberto Sassu

From: Roberto Sassu <roberto.sassu(a)huawei.com> Integrity detection and protection has long been a desirable feature, to reach a large user base and mitigate the risk of flaws in the software and attacks. However, while solutions exist, they struggle to reach the large user base, due to requiring higher than desired constraints on performance, flexibility and configurability, that only security conscious people are willing to accept. This is where the new digest_cache LSM comes into play, it offers additional support for new and existing integrity solutions, to make them faster and easier to deploy. The full documentation with the motivation and the solution details can be found in patch 14. The IMA integration patch set will be introduced separately. Also a PoC based on the current version of IPE can be provided. v3: - Rewrite documentation, and remove the installation instructions since they are now included in the README of digest-cache-tools - Add digest cache event notifier - Drop digest_cache_was_reset(), and send instead to asynchronous notifications - Fix digest_cache LSM Kconfig style issues (suggested by Randy Dunlap) - Propagate digest cache reset to directory entries - Destroy per directory entry mutex - Introduce RESET_USER bit, to clear the dig_user pointer on set/removexattr - Replace 'file content' with 'file data' (suggested by Mimi) - Introduce per digest cache mutex and replace verif_data_lock spinlock - Track changes of security.digest_list xattr - Stop tracking file_open and use file_release instead also for file writes - Add error messages in digest_cache_create() - Load/unload testing kernel module automatically during execution of test - Add tests for digest cache event notifier - Add test for ftruncate() - Remove DIGEST_CACHE_RESET_PREFETCH_BUF command in test and clear the buffer on read instead v2: - Include the TLV parser in this patch set (from user asymmetric keys and signatures) - Move from IMA and make an independent LSM - Remove IMA-specific stuff from this patch set - Add per algorithm hash table - Expect all digest lists to be in the same directory and allow changing the default directory - Support digest lookup on directories, when there is no security.digest_list xattr - Add seq num to digest list file name, to impose ordering on directory iteration - Add a new data type DIGEST_LIST_ENTRY_DATA for the nested data in the tlv digest list format - Add the concept of verification data attached to digest caches - Add the reset mechanism to track changes on digest lists and directory containing the digest lists - Add kernel selftests v1: - Add documentation in Documentation/security/integrity-digest-cache.rst - Pass the mask of IMA actions to digest_cache_alloc() - Add a reference count to the digest cache - Remove the path parameter from digest_cache_get(), and rely on the reference count to avoid the digest cache disappearing while being used - Rename the dentry_to_check parameter of digest_cache_get() to dentry - Rename digest_cache_get() to digest_cache_new() and add digest_cache_get() to set the digest cache in the iint of the inode for which the digest cache was requested - Add dig_owner and dig_user to the iint, to distinguish from which inode the digest cache was created from, and which is using it; consequently it makes the digest cache usable to measure/appraise other digest caches (support not yet enabled) - Add dig_owner_mutex and dig_user_mutex to serialize accesses to dig_owner and dig_user until they are initialized - Enforce strong synchronization and make the contenders wait until dig_owner and dig_user are assigned to the iint the first time - Move checking IMA actions on the digest list earlier, and fail if no action were performed (digest cache not usable) - Remove digest_cache_put(), not needed anymore with the introduction of the reference count - Fail immediately in digest_cache_lookup() if the digest algorithm is not set in the digest cache - Use 64 bit mask for IMA actions on the digest list instead of 8 bit - Return NULL in the inline version of digest_cache_get() - Use list_add_tail() instead of list_add() in the iterator - Copy the digest list path to a separate buffer in digest_cache_iter_dir() - Use digest list parsers verified with Frama-C - Explicitly disable (for now) the possibility in the IMA policy to use the digest cache to measure/appraise other digest lists - Replace exit(<value>) with return <value> in manage_digest_lists.c Roberto Sassu (14): lib: Add TLV parser security: Introduce the digest_cache LSM digest_cache: Add securityfs interface digest_cache: Add hash tables and operations digest_cache: Populate the digest cache from a digest list digest_cache: Parse tlv digest lists digest_cache: Parse rpm digest lists digest_cache: Add management of verification data digest_cache: Add support for directories digest cache: Prefetch digest lists if requested digest_cache: Reset digest cache on file/directory change digest_cache: Notify digest cache events selftests/digest_cache: Add selftests for digest_cache LSM docs: Add documentation of the digest_cache LSM Documentation/security/digest_cache.rst | 763 ++++++++++++++++ Documentation/security/index.rst | 1 + MAINTAINERS | 16 + include/linux/digest_cache.h | 117 +++ include/linux/kernel_read_file.h | 1 + include/linux/tlv_parser.h | 28 + include/uapi/linux/lsm.h | 1 + include/uapi/linux/tlv_digest_list.h | 72 ++ include/uapi/linux/tlv_parser.h | 59 ++ include/uapi/linux/xattr.h | 6 + lib/Kconfig | 3 + lib/Makefile | 3 + lib/tlv_parser.c | 214 +++++ lib/tlv_parser.h | 17 + security/Kconfig | 11 +- security/Makefile | 1 + security/digest_cache/Kconfig | 33 + security/digest_cache/Makefile | 11 + security/digest_cache/dir.c | 252 ++++++ security/digest_cache/htable.c | 268 ++++++ security/digest_cache/internal.h | 290 +++++++ security/digest_cache/main.c | 570 ++++++++++++ security/digest_cache/modsig.c | 66 ++ security/digest_cache/notifier.c | 135 +++ security/digest_cache/parsers/parsers.h | 15 + security/digest_cache/parsers/rpm.c | 223 +++++ security/digest_cache/parsers/tlv.c | 299 +++++++ security/digest_cache/populate.c | 163 ++++ security/digest_cache/reset.c | 235 +++++ security/digest_cache/secfs.c | 87 ++ security/digest_cache/verif.c | 119 +++ security/security.c | 3 +- tools/testing/selftests/Makefile | 1 + .../testing/selftests/digest_cache/.gitignore | 3 + tools/testing/selftests/digest_cache/Makefile | 24 + .../testing/selftests/digest_cache/all_test.c | 815 ++++++++++++++++++ tools/testing/selftests/digest_cache/common.c | 78 ++ tools/testing/selftests/digest_cache/common.h | 135 +++ .../selftests/digest_cache/common_user.c | 47 + .../selftests/digest_cache/common_user.h | 17 + tools/testing/selftests/digest_cache/config | 1 + .../selftests/digest_cache/generators.c | 248 ++++++ .../selftests/digest_cache/generators.h | 19 + .../selftests/digest_cache/testmod/Makefile | 16 + .../selftests/digest_cache/testmod/kern.c | 564 ++++++++++++ .../selftests/lsm/lsm_list_modules_test.c | 3 + 46 files changed, 6047 insertions(+), 6 deletions(-) create mode 100644 Documentation/security/digest_cache.rst create mode 100644 include/linux/digest_cache.h create mode 100644 include/linux/tlv_parser.h create mode 100644 include/uapi/linux/tlv_digest_list.h create mode 100644 include/uapi/linux/tlv_parser.h create mode 100644 lib/tlv_parser.c create mode 100644 lib/tlv_parser.h create mode 100644 security/digest_cache/Kconfig create mode 100644 security/digest_cache/Makefile create mode 100644 security/digest_cache/dir.c create mode 100644 security/digest_cache/htable.c create mode 100644 security/digest_cache/internal.h create mode 100644 security/digest_cache/main.c create mode 100644 security/digest_cache/modsig.c create mode 100644 security/digest_cache/notifier.c create mode 100644 security/digest_cache/parsers/parsers.h create mode 100644 security/digest_cache/parsers/rpm.c create mode 100644 security/digest_cache/parsers/tlv.c create mode 100644 security/digest_cache/populate.c create mode 100644 security/digest_cache/reset.c create mode 100644 security/digest_cache/secfs.c create mode 100644 security/digest_cache/verif.c create mode 100644 tools/testing/selftests/digest_cache/.gitignore create mode 100644 tools/testing/selftests/digest_cache/Makefile create mode 100644 tools/testing/selftests/digest_cache/all_test.c create mode 100644 tools/testing/selftests/digest_cache/common.c create mode 100644 tools/testing/selftests/digest_cache/common.h create mode 100644 tools/testing/selftests/digest_cache/common_user.c create mode 100644 tools/testing/selftests/digest_cache/common_user.h create mode 100644 tools/testing/selftests/digest_cache/config create mode 100644 tools/testing/selftests/digest_cache/generators.c create mode 100644 tools/testing/selftests/digest_cache/generators.h create mode 100644 tools/testing/selftests/digest_cache/testmod/Makefile create mode 100644 tools/testing/selftests/digest_cache/testmod/kern.c -- 2.34.1

6 months

6
57
0 0

[PATCH net-next v10 00/14] Device Memory TCP

by Mina Almasry

v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers the network are implemented as the following low level operations: Device-to-Host copy, Host-to-Host network transfer, and Host-to-Device copy. The implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from host memory and are processed by the TCP/IP stack normally. The NIC _must_ support header split to achieve this. Advantages: - Alleviate host memory bandwidth pressure, compared to existing network-transfer + device-copy semantics. - Alleviate PCIe BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Jakub Kicinski (1): net: page_pool: create hooks for custom page providers Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: convert to use netmem page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP Documentation/netlink/specs/netdev.yaml | 57 +++ Documentation/networking/devmem.rst | 258 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 11 +- include/linux/socket.h | 1 + include/net/devmem.h | 124 ++++++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 208 ++++++++- include/net/page_pool/helpers.h | 153 +++++-- include/net/page_pool/types.h | 33 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 29 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 19 + include/uapi/linux/uio.h | 17 + net/bpf/test_run.c | 5 +- net/core/Makefile | 3 +- net/core/datagram.c | 6 + net/core/dev.c | 6 +- net/core/devmem.c | 384 +++++++++++++++++ net/core/gro.c | 8 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 103 +++++ net/core/netdev_rx_queue.c | 74 ++++ net/core/page_pool.c | 368 +++++++++------- net/core/skbuff.c | 83 +++- net/core/sock.c | 61 +++ net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 254 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 10 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- tools/include/uapi/linux/netdev.h | 19 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 5 + tools/testing/selftests/net/ncdevmem.c | 542 ++++++++++++++++++++++++ 46 files changed, 2738 insertions(+), 267 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.45.1.288.g0e0cd299f1-goog

6 months, 1 week

13
70
0 0

[PATCH v2] selftests/vDSO: fix clang build errors and warnings

by John Hubbard

When building with clang, via: make LLVM=1 -C tools/testing/selftests ...there are several warnings, and an error. This fixes all of those and allows these tests to run and pass. 1. Fix linker error (undefined reference to memcpy) by providing a local version of memcpy. 2. clang complains about using this form: if (g = h & 0xf0000000) ...so factor out the assignment into a separate step. 3. The code is passing a signed const char* to elf_hash(), which expects a const unsigned char *. There are several callers, so fix this at the source by allowing the function to accept a signed argument, and then converting to unsigned operations, once inside the function. 4. clang doesn't have __attribute__((externally_visible)) and generates a warning to that effect. Fortunately, gcc 12 and gcc 13 do not seem to require that attribute in order to build, run and pass tests here, so remove it. [1] https://lore.kernel.org/all/20240329-selftests-libmk-llvm-rfc-v1-1-2f9ed7d1… Signed-off-by: John Hubbard <jhubbard(a)nvidia.com> --- Changes since the first version: 1) Rebased onto Linux 6.10-rc1 thanks, John Hubbard tools/testing/selftests/vDSO/parse_vdso.c | 16 +++++++++++----- .../selftests/vDSO/vdso_standalone_test_x86.c | 18 ++++++++++++++++-- 2 files changed, 27 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 413f75620a35..4ae417372e9e 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -55,14 +55,20 @@ static struct vdso_info ELF(Verdef) *verdef; } vdso_info; -/* Straight from the ELF specification. */ -static unsigned long elf_hash(const unsigned char *name) +/* + * Straight from the ELF specification...and then tweaked slightly, in order to + * avoid a few clang warnings. + */ +static unsigned long elf_hash(const char *name) { unsigned long h = 0, g; - while (*name) + const unsigned char *uch_name = (const unsigned char *)name; + + while (*uch_name) { - h = (h << 4) + *name++; - if (g = h & 0xf0000000) + h = (h << 4) + *uch_name++; + g = h & 0xf0000000; + if (g) h ^= g >> 24; h &= ~g; } diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 8a44ff973ee1..27f6fdf11969 100644 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -18,7 +18,7 @@ #include "parse_vdso.h" -/* We need a libc functions... */ +/* We need some libc functions... */ int strcmp(const char *a, const char *b) { /* This implementation is buggy: it never returns -1. */ @@ -34,6 +34,20 @@ int strcmp(const char *a, const char *b) return 0; } +/* + * The clang build needs this, although gcc does not. + * Stolen from lib/string.c. + */ +void *memcpy(void *dest, const void *src, size_t count) +{ + char *tmp = dest; + const char *s = src; + + while (count--) + *tmp++ = *s++; + return dest; +} + /* ...and two syscalls. This is x86-specific. */ static inline long x86_syscall3(long nr, long a0, long a1, long a2) { @@ -70,7 +84,7 @@ void to_base10(char *lastdig, time_t n) } } -__attribute__((externally_visible)) void c_main(void **stack) +void c_main(void **stack) { /* Parse the stack */ long argc = (long)*stack; base-commit: 2bfcfd584ff5ccc8bb7acde19b42570414bf880b -- 2.45.1

6 months, 1 week

4
7
0 0

[PATCH] tools/testing/selftests/livepatch: define max test-syscall processes

by Ryan Sullivan

Define a maximum allowable number of pids that can be livepatched in test-syscall.sh as with extremely large machines the output from a large number of processes overflows the dev/kmsg "expect" buffer in the "check_result" function and causes a false error. Reported-by: CKI Project <cki-project(a)redhat.com> Signed-off-by: Ryan Sullivan <rysulliv(a)redhat.com> --- tools/testing/selftests/livepatch/test-syscall.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/livepatch/test-syscall.sh b/tools/testing/selftests/livepatch/test-syscall.sh index b76a881d4013..289eb7d4c4b3 100755 --- a/tools/testing/selftests/livepatch/test-syscall.sh +++ b/tools/testing/selftests/livepatch/test-syscall.sh @@ -15,7 +15,10 @@ setup_config start_test "patch getpid syscall while being heavily hammered" -for i in $(seq 1 $(getconf _NPROCESSORS_ONLN)); do +NPROC=$(getconf _NPROCESSORS_ONLN) +MAXPROC=128 + +for i in $(seq 1 $(($NPROC < $MAXPROC ? $NPROC : $MAXPROC))); do ./test_klp-call_getpid & pids[$i]="$!" done -- 2.44.0

6 months, 1 week

5
8
0 0

testing/selftests/alsa/mixer-test: 10 failures on Dell XPS 13 9360

by Paul Menzel

Dear Linux folks, Running the ALSA kselftests with Linux 6.10-rc1, `mixer-test` shows ten failures: # Totals: pass:24 fail:0 xfail:0 xpass:0 skip:11 error:0 These are: not ok 5 write_invalid.0.40 not ok 11 write_valid.0.39 not ok 18 write_valid.0.38 not ok 25 write_valid.0.37 not ok 201 write_invalid.0.12 not ok 208 write_invalid.0.11 not ok 264 write_invalid.0.3 not ok 271 write_invalid.0.2 not ok 278 write_invalid.0.1 not ok 285 write_invalid.0.0 `./pcm-test` finishes with 5 out of 5 passes. The output `sudo alsa-info` is uploaded to the database [1], and the full output of `mixer-test` is attached. Kind regards, Paul [1]: https://alsa-project.org/db/?f=cf8e1e0f37775448b5e3361e5c3cd4d4e6037d4f

6 months, 1 week

4
8
0 0

[PATCH] kselftest/arm64: Include kernel mode NEON in fp-stress

by Mark Brown

Currently fp-stress only covers userspace use of floating point, it does not cover any kernel mode uses. Since currently kernel mode floating point usage can't be preempted and there are explicit preemption points in the existing implementations this isn't so important for fp-stress but when we readd preemption it will be good to try to exercise it. When the arm64 accelerated crypto operations are implemented we can relatively straightforwardly trigger kernel mode floating point usage by using the crypto userspace API to hash data, using the splice() support in an effort to minimise copying. We use /proc/crypto to check which accelerated implementations are available, picking the first symmetric hash we find. We run the kernel mode test unconditionally, replacing the second copy of the FPSIMD testcase for systems with FPSIMD only. If we don't think there are any suitable kernel mode implementations we fall back to running another copy of fpsimd-stress. There are a number issues with this approach, we don't actually verify that we are using an accelerated (or even CPU) implementation of the algorithm being tested and even with attempting to use splice() to minimise copying there are sizing limits on how much data gets spliced at once. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- This is mainly focused on trying to reproduce the issues reported by Asahi users with preemptable kernel mode floating point - as noted in the commit log it needs reenablement of preemptable floating point and removal of the preemption points in the current algorithm implementations to really have anything to exercise directly. There also seem to be race conditions when AF_ALG is built as a module, attempting to bind triggers module load but does not block. --- tools/testing/selftests/arm64/fp/.gitignore | 1 + tools/testing/selftests/arm64/fp/Makefile | 1 + tools/testing/selftests/arm64/fp/fp-stress.c | 26 +- tools/testing/selftests/arm64/fp/kernel-test.c | 324 +++++++++++++++++++++++++ 4 files changed, 343 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index 00e52c966281..8362e7ec35ad 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -2,6 +2,7 @@ fp-pidbench fp-ptrace fp-stress fpsimd-test +kernel-test rdvl-sme rdvl-sve sve-probe-vls diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 55d4f00d9e8e..d171021e4cdd 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -12,6 +12,7 @@ TEST_GEN_PROGS := \ vec-syscfg \ za-fork za-ptrace TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \ + kernel-test \ rdvl-sme rdvl-sve \ sve-test \ ssve-test \ diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c index dd31647b00a2..faac24bdefeb 100644 --- a/tools/testing/selftests/arm64/fp/fp-stress.c +++ b/tools/testing/selftests/arm64/fp/fp-stress.c @@ -319,6 +319,19 @@ static void start_fpsimd(struct child_data *child, int cpu, int copy) ksft_print_msg("Started %s\n", child->name); } +static void start_kernel(struct child_data *child, int cpu, int copy) +{ + int ret; + + ret = asprintf(&child->name, "KERNEL-%d-%d", cpu, copy); + if (ret == -1) + ksft_exit_fail_msg("asprintf() failed\n"); + + child_start(child, "./kernel-test"); + + ksft_print_msg("Started %s\n", child->name); +} + static void start_sve(struct child_data *child, int vl, int cpu) { int ret; @@ -438,7 +451,7 @@ int main(int argc, char **argv) int ret; int timeout = 10; int cpus, i, j, c; - int sve_vl_count, sme_vl_count, fpsimd_per_cpu; + int sve_vl_count, sme_vl_count; bool all_children_started = false; int seen_children; int sve_vls[MAX_VLS], sme_vls[MAX_VLS]; @@ -482,12 +495,7 @@ int main(int argc, char **argv) have_sme2 = false; } - /* Force context switching if we only have FPSIMD */ - if (!sve_vl_count && !sme_vl_count) - fpsimd_per_cpu = 2; - else - fpsimd_per_cpu = 1; - tests += cpus * fpsimd_per_cpu; + tests += cpus * 2; ksft_print_header(); ksft_set_plan(tests); @@ -542,8 +550,8 @@ int main(int argc, char **argv) tests); for (i = 0; i < cpus; i++) { - for (j = 0; j < fpsimd_per_cpu; j++) - start_fpsimd(&children[num_children++], i, j); + start_fpsimd(&children[num_children++], i, 0); + start_kernel(&children[num_children++], i, 0); for (j = 0; j < sve_vl_count; j++) start_sve(&children[num_children++], sve_vls[j], i); diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c new file mode 100644 index 000000000000..50db26a3ed79 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 ARM Limited. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <string.h> +#include <unistd.h> + +#include <sys/socket.h> + +#include <linux/kernel.h> +#include <linux/if_alg.h> + +#define DATA_SIZE (16 * 4096) + +static int base, sock; + +static int digest_len; +static char *ref; +static char *digest; +static char *alg_name; + +static struct iovec data_iov; +static int zerocopy[2]; +static int sigs; +static int iter; + +static void handle_exit_signal(int sig, siginfo_t *info, void *context) +{ + printf("Terminated by signal %d, iterations=%d, signals=%d\n", + sig, iter, sigs); + exit(0); +} + +static void handle_kick_signal(int sig, siginfo_t *info, void *context) +{ + sigs++; +} + +static char *drivers[] = { + "crct10dif-arm64-ce", + /* "crct10dif-arm64-neon", - Same priority as generic */ + "sha1-ce", + "sha224-arm64", + "sha224-arm64-neon", + "sha224-ce", + "sha256-arm64", + "sha256-arm64-neon", + "sha256-ce", + "sha384-ce", + "sha512-ce", + "sha3-224-ce", + "sha3-256-ce", + "sha3-384-ce", + "sha3-512-ce", + "sm3-ce", + "sm3-neon", +}; + +static bool create_socket(void) +{ + FILE *proc; + struct sockaddr_alg addr; + char buf[1024]; + char *c, *driver_name; + bool is_shash, match; + int ret, i; + + ret = socket(AF_ALG, SOCK_SEQPACKET, 0); + if (ret < 0) { + if (errno == EAFNOSUPPORT) { + printf("AF_ALG not supported\n"); + return false; + } + + printf("Failed to create AF_ALG socket: %s (%d)\n", + strerror(errno), errno); + return false; + } + base = ret; + + memset(&addr, 0, sizeof(addr)); + addr.salg_family = AF_ALG; + strncpy((char *)addr.salg_type, "hash", sizeof(addr.salg_type)); + + proc = fopen("/proc/crypto", "r"); + if (!proc) { + printf("Unable to open /proc/crypto\n"); + return false; + } + + driver_name = NULL; + is_shash = false; + match = false; + + /* Look through /proc/crypto for a driver with kernel mode FP usage */ + while (!match) { + c = fgets(buf, sizeof(buf), proc); + if (!c) { + if (feof(proc)) { + printf("Nothing found in /proc/crypto\n"); + return false; + } + continue; + } + + /* Algorithm descriptions are separated by a blank line */ + if (*c == '\n') { + if (is_shash && driver_name) { + for (i = 0; i < ARRAY_SIZE(drivers); i++) { + if (strcmp(drivers[i], + driver_name) == 0) { + match = true; + } + } + } + + if (!match) { + digest_len = 0; + + free(driver_name); + driver_name = NULL; + + free(alg_name); + alg_name = NULL; + + is_shash = false; + } + continue; + } + + /* Remove trailing newline */ + c = strchr(buf, '\n'); + if (c) + *c = '\0'; + + /* Find the field/value separator and start of the value */ + c = strchr(buf, ':'); + if (!c) + continue; + c += 2; + + if (strncmp(buf, "digestsize", strlen("digestsize")) == 0) + sscanf(c, "%d", &digest_len); + + if (strncmp(buf, "name", strlen("name")) == 0) + alg_name = strdup(c); + + if (strncmp(buf, "driver", strlen("driver")) == 0) + driver_name = strdup(c); + + if (strncmp(buf, "type", strlen("type")) == 0) + if (strncmp(c, "shash", strlen("shash")) == 0) + is_shash = true; + } + + strncpy((char *)addr.salg_name, alg_name, + sizeof(addr.salg_name) - 1); + + ret = bind(base, (struct sockaddr *)&addr, sizeof(addr)); + if (ret < 0) { + printf("Failed to bind %s: %s (%d)\n", + addr.salg_name, strerror(errno), errno); + return false; + } + + ret = accept(base, NULL, 0); + if (ret < 0) { + printf("Failed to accept %s: %s (%d)\n", + addr.salg_name, strerror(errno), errno); + return false; + } + + sock = ret; + + ret = pipe(zerocopy); + if (ret != 0) { + printf("Failed to create zerocopy pipe: %s (%d)\n", + strerror(errno), errno); + return false; + } + + ref = malloc(digest_len); + if (!ref) { + printf("Failed to allocated %d byte reference\n", digest_len); + return false; + } + + digest = malloc(digest_len); + if (!digest) { + printf("Failed to allocated %d byte digest\n", digest_len); + return false; + } + + return true; +} + +static bool compute_digest(void *buf) +{ + struct iovec iov; + int ret, wrote; + + iov = data_iov; + while (iov.iov_len) { + ret = vmsplice(zerocopy[1], &iov, 1, SPLICE_F_GIFT); + if (ret < 0) { + printf("Failed to send buffer: %s (%d)\n", + strerror(errno), errno); + return false; + } + + wrote = ret; + ret = splice(zerocopy[0], NULL, sock, NULL, wrote, 0); + if (ret < 0) { + printf("Failed to splice buffer: %s (%d)\n", + strerror(errno), errno); + } else if (ret != wrote) { + printf("Short splice: %d < %d\n", ret, wrote); + } + + iov.iov_len -= wrote; + iov.iov_base += wrote; + } + +reread: + ret = recv(sock, buf, digest_len, 0); + if (ret == 0) { + printf("No disgest returned\n"); + return false; + } + if (ret != digest_len) { + if (errno == -EAGAIN) + goto reread; + printf("Failed to get digest: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return true; +} + +int main(void) +{ + char *data; + struct sigaction sa; + int ret; + + /* Ensure we have unbuffered output */ + setvbuf(stdout, NULL, _IOLBF, 0); + + /* The parent will communicate with us via signals */ + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handle_exit_signal; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGTERM, &sa, NULL); + if (ret < 0) + printf("Failed to install SIGTERM handler: %s (%d)\n", + strerror(errno), errno); + + sa.sa_sigaction = handle_kick_signal; + ret = sigaction(SIGUSR2, &sa, NULL); + if (ret < 0) + printf("Failed to install SIGUSR2 handler: %s (%d)\n", + strerror(errno), errno); + + data = malloc(DATA_SIZE); + if (!data) { + printf("Failed to allocate data buffer\n"); + return EXIT_FAILURE; + } + memset(data, 0, DATA_SIZE); + + data_iov.iov_base = data; + data_iov.iov_len = DATA_SIZE; + + /* + * If we can't create a socket assume it's a lack of system + * support and fall back to a basic FPSIMD test for the + * benefit of fp-stress. + */ + if (!create_socket()) { + execl("./fpsimd-test", "./fpsimd-test", NULL); + printf("Failed to fall back to fspimd-test: %d (%s)\n", + errno, strerror(errno)); + return EXIT_FAILURE; + } + + /* + * Compute a reference digest we hope is repeatable, we do + * this at runtime partly to make it easier to play with + * parameters. + */ + if (!compute_digest(ref)) { + printf("Failed to compute reference digest\n"); + return EXIT_FAILURE; + } + + printf("AF_ALG using %s\n", alg_name); + + while (true) { + if (!compute_digest(digest)) { + printf("Failed to coempute digest, iter=%d\n", iter); + return EXIT_FAILURE; + } + + if (memcmp(ref, digest, digest_len) != 0) { + printf("Digest mismatch, iter=%d\n", iter); + return EXIT_FAILURE; + } + + iter++; + } + + return EXIT_FAILURE; +} --- base-commit: a38297e3fb012ddfa7ce0321a7e5a8daeb1872b6 change-id: 20240517-arm64-fp-stress-kernel-a09011b96f42 Best regards, -- Mark Brown <broonie(a)kernel.org>

6 months, 2 weeks

2
1
0 0

[RFC PATCH v2 0/2] Add a test to verify device probing on ACPI platforms

by Laura Nao

Hello, This v2 addresses some issues observed when running the ACPI probe kselftest proposed in v1[1] across various devices and improves the overall reliability of the test. The acpi-extract-ids script has been improved to: - Parse both .c and .h files - Add an option to print only IDs matched by a driver (i.e. defined in an ACPI match tables or in lists of IDs provided by the drivers) The test_unprobed_devices.sh script relies on sysfs information to determine if a device was successfully bound to a driver. Not all devices listed in /sys/devices are expected to have a driver folder, so the script has been adjusted to handle these cases and avoid generating false negatives. The test_unprobed_devices.sh test script logic has been modified to: - Check the status attribute (when available) to exclusively test hardware devices that are physically present, enabled and operational - Traverse only ACPI objects with a physical_node* link, to ensure testing of correctly enumerated devices - Skip devices whose HID or CID are not matched by any driver, as determined by the list generated through the acpi-extract-ids script - Skip devices with HID or CID listed in the ignored IDs list. This list has been added to contain IDs of devices that don't require a driver or cannot be represented as platform devices (e.g. ACPI container and module devices). - Skip devices that are natively enumerated and don't need a driver, such as certain PCI bridges - Skip devices unassigned to any subsystem, devices linked to other devices and class devices Some of the heuristics used by the script are suboptimal and might require adjustments over time. This kind of tests would greatly benefit from a dedicated interface that exposes information about devices expected to be matched by drivers and their probe status. Discussion regarding this matter was initiated in v1. As of now, I have not identified a suitable method for exposing this information; I plan on submitting a separate RFC to propose some options and engage in discussion. Meanwhile, this v2 focuses on utilizing already available information to provide an ACPI equivalent of the existing DT kselftest [2]. Adding in CC the people involved in the discussion at Plumbers [3], feel free to add anyone that might be interested in this. This series depends on: - https://lore.kernel.org/all/20240102141528.169947-1-laura.nao@collabora.com… - https://lore.kernel.org/all/20240131-ktap-sh-helpers-extend-v1-0-98ffb46871… Thanks, Laura [1] https://lore.kernel.org/all/20230925155806.1812249-2-laura.nao@collabora.co… [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/too… [3] https://www.youtube.com/watch?v=oE73eVSyFXQ&t=9377s Original cover letter: Regressions that prevent a driver from probing a device can significantly affect the functionality of a platform. A kselftest to verify if devices on a DT-based platform are probed correctly was recently introduced [4], but no such generic test is available for ACPI platforms yet. bootrr [5] provides device probe testing, but relies on a pre-defined list of the peripherals present on each DUT. On ACPI based hardware, a complete description of the platform is provided to the OS by the system firmware. ACPI namespace objects are mapped by the Linux ACPI subsystem into a device tree in /sys/devices/LNXSYSTEM:00; the information in this subtree can be parsed to build a list of the hw peripherals present on the DUT dynamically. This series adds a test to verify if the devices declared in the ACPI namespace and supported by the kernel are probed correctly. This work follows a similar approach to [4], adapted for the ACPI use case. The first patch introduces a script that builds a list of all ACPI device IDs supported by the kernel, by inspecting the acpi_device_id structs in the sources. This list can be used to avoid testing ACPI-enumerated devices that don't have a matching driver in the kernel. This script was highly inspired by the dt-extract-compatibles script [6]. In the second patch, a new kselftest is added. It parses the /sys/devices/LNXSYSTEM:00 tree to obtain a list of all platform peripherals and verifies which of those, if supported, are correctly bound to a driver. Feedback is much appreciated, Thank you, Laura [4] https://lore.kernel.org/all/20230828211424.2964562-1-nfraprado@collabora.co… [5] https://github.com/kernelci/bootr [6] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/scr… Laura Nao (2): acpi: Add script to extract ACPI device ids in the kernel kselftest: Add test to detect unprobed devices on ACPI platforms MAINTAINERS | 2 + scripts/acpi/acpi-extract-ids | 99 +++++++++++++ tools/testing/selftests/Makefile | 1 + tools/testing/selftests/acpi/.gitignore | 1 + tools/testing/selftests/acpi/Makefile | 21 +++ tools/testing/selftests/acpi/id_ignore_list | 3 + .../selftests/acpi/test_unprobed_devices.sh | 138 ++++++++++++++++++ 7 files changed, 265 insertions(+) create mode 100755 scripts/acpi/acpi-extract-ids create mode 100644 tools/testing/selftests/acpi/.gitignore create mode 100644 tools/testing/selftests/acpi/Makefile create mode 100644 tools/testing/selftests/acpi/id_ignore_list create mode 100755 tools/testing/selftests/acpi/test_unprobed_devices.sh -- 2.30.2

6 months, 2 weeks

1
3
0 0

[PATCH bpf-next v3 00/11] Add check for bpf lsm return value

by Xu Kuohai

From: Xu Kuohai <xukuohai(a)huawei.com> A bpf prog returning positive number attached to file_alloc_security hook will make kernel panic. Here is a panic log: [ 441.235774] BUG: kernel NULL pointer dereference, address: 00000000000009 [ 441.236748] #PF: supervisor write access in kernel mode [ 441.237429] #PF: error_code(0x0002) - not-present page [ 441.238119] PGD 800000000b02f067 P4D 800000000b02f067 PUD b031067 PMD 0 [ 441.238990] Oops: 0002 [#1] PREEMPT SMP PTI [ 441.239546] CPU: 0 PID: 347 Comm: loader Not tainted 6.8.0-rc6-gafe0cbf23373 #22 [ 441.240496] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b4 [ 441.241933] RIP: 0010:alloc_file+0x4b/0x190 [ 441.242485] Code: 8b 04 25 c0 3c 1f 00 48 8b b0 30 0c 00 00 e8 9c fe ff ff 48 3d 00 f0 ff fb [ 441.244820] RSP: 0018:ffffc90000c67c40 EFLAGS: 00010203 [ 441.245484] RAX: ffff888006a891a0 RBX: ffffffff8223bd00 RCX: 0000000035b08000 [ 441.246391] RDX: ffff88800b95f7b0 RSI: 00000000001fc110 RDI: f089cd0b8088ffff [ 441.247294] RBP: ffffc90000c67c58 R08: 0000000000000001 R09: 0000000000000001 [ 441.248209] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000001 [ 441.249108] R13: ffffc90000c67c78 R14: ffffffff8223bd00 R15: fffffffffffffff4 [ 441.250007] FS: 00000000005f3300(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 [ 441.251053] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 441.251788] CR2: 00000000000001a9 CR3: 000000000bdc4003 CR4: 0000000000170ef0 [ 441.252688] Call Trace: [ 441.253011] <TASK> [ 441.253296] ? __die+0x24/0x70 [ 441.253702] ? page_fault_oops+0x15b/0x480 [ 441.254236] ? fixup_exception+0x26/0x330 [ 441.254750] ? exc_page_fault+0x6d/0x1c0 [ 441.255257] ? asm_exc_page_fault+0x26/0x30 [ 441.255792] ? alloc_file+0x4b/0x190 [ 441.256257] alloc_file_pseudo+0x9f/0xf0 [ 441.256760] __anon_inode_getfile+0x87/0x190 [ 441.257311] ? lock_release+0x14e/0x3f0 [ 441.257808] bpf_link_prime+0xe8/0x1d0 [ 441.258315] bpf_tracing_prog_attach+0x311/0x570 [ 441.258916] ? __pfx_bpf_lsm_file_alloc_security+0x10/0x10 [ 441.259605] __sys_bpf+0x1bb7/0x2dc0 [ 441.260070] __x64_sys_bpf+0x20/0x30 [ 441.260533] do_syscall_64+0x72/0x140 [ 441.261004] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 441.261643] RIP: 0033:0x4b0349 [ 441.262045] Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 88 [ 441.264355] RSP: 002b:00007fff74daee38 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 [ 441.265293] RAX: ffffffffffffffda RBX: 00007fff74daef30 RCX: 00000000004b0349 [ 441.266187] RDX: 0000000000000040 RSI: 00007fff74daee50 RDI: 000000000000001c [ 441.267114] RBP: 000000000000001b R08: 00000000005ef820 R09: 0000000000000000 [ 441.268018] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004 [ 441.268907] R13: 0000000000000004 R14: 00000000005ef018 R15: 00000000004004e8 The reason is that the positive number returned by bpf prog is not a valid errno, and could not be filtered out with IS_ERR which is used by the file system to check errors. As a result, the filesystem mistakenly uses this random positive number as file pointer, causing panic. To fix this issue, there are two schemes: 1. Modify the calling sites of file_alloc_security to take positive return values as zero. 2. Make the bpf verifier to ensure no unpredicted value returned by lsm bpf prog. Considering that hook file_alloc_security never returned positive number before bpf lsm was introduced, and other lsm hooks may have the same problem, scheme 2 is more reasonable. So this series adds lsm return value check in verifier to fix it. v3: 1. Fix incorrect lsm hook return value ranges, and add disabled hook list for bpf lsm, and merge two LSM_RET_INT patches. (KP Singh) 2. Avoid bpf lsm progs attached to different hooks to call each other with tail call 3. Fix a CI failure caused by false rejection of AND operation 4. Add tests v2: https://lore.kernel.org/bpf/20240325095653.1720123-1-xukuohai@huaweicloud.c… fix bpf ci failure v1: https://lore.kernel.org/bpf/20240316122359.1073787-1-xukuohai@huaweicloud.c… Xu Kuohai (11): bpf, lsm: Annotate lsm hook return value range bpf, lsm: Add helper to read lsm hook return value range bpf, lsm: Check bpf lsm hook return values in verifier bpf, lsm: Add bpf lsm disabled hook list bpf: Avoid progs for different hooks calling each other with tail call bpf: Fix compare error in function retval_range_within bpf: Fix a false rejection caused by AND operation selftests/bpf: Avoid load failure for token_lsm.c selftests/bpf: Add return value checks for failed tests selftests/bpf: Add test for lsm tail call selftests/bpf: Add verifier tests for bpf lsm include/linux/bpf.h | 2 + include/linux/bpf_lsm.h | 8 + include/linux/lsm_hook_defs.h | 591 +++++++++--------- include/linux/lsm_hooks.h | 6 - kernel/bpf/bpf_lsm.c | 84 ++- kernel/bpf/btf.c | 5 +- kernel/bpf/core.c | 22 +- kernel/bpf/verifier.c | 82 ++- security/security.c | 1 + .../selftests/bpf/prog_tests/test_lsm.c | 46 +- .../selftests/bpf/prog_tests/verifier.c | 3 +- tools/testing/selftests/bpf/progs/err.h | 10 + .../selftests/bpf/progs/lsm_tailcall.c | 34 + .../selftests/bpf/progs/test_sig_in_xattr.c | 4 + .../bpf/progs/test_verify_pkcs7_sig.c | 8 +- tools/testing/selftests/bpf/progs/token_lsm.c | 4 +- .../bpf/progs/verifier_global_subprogs.c | 7 +- .../selftests/bpf/progs/verifier_lsm.c | 155 +++++ 18 files changed, 754 insertions(+), 318 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/lsm_tailcall.c create mode 100644 tools/testing/selftests/bpf/progs/verifier_lsm.c -- 2.30.2

6 months, 2 weeks

8
37
0 0

[PATCH v1 0/3] Userspace controls soft-offline HugeTLB pages

by Jiaqi Yan

Correctable memory errors are very common on servers with large amount of memory, and are corrected by ECC, but with two pain points to users: 1. Correction usually happens on the fly and adds latency overhead 2. Not-fully-proved theory states excessive correctable memory errors can develop into uncorrectable memory error. Soft offline is kernel's additional solution for memory pages having (excessive) corrected memory errors. Impacted page is migrated to healthy page if it is in use, then the original page is discarded for any future use. The actual policy on whether (and when) to soft offline should be maintained by userspace, especially in case of HugeTLB hugepages. Soft-offline dissolves a hugepage, either in-use or free, into chunks of 4K pages, reducing HugeTLB pool capacity by 1 hugepage. If userspace has not acknowledged such behavior, it may be surprised when later mmap hugepages MAP_FAILED due to lack of hugepages. In addition, discarding the entire 1G memory page only because of corrected memory errors sounds very costly and kernel better not doing under the hood. But today there are at least 2 such cases: 1. GHES driver sees both GHES_SEV_CORRECTED and CPER_SEC_ERROR_THRESHOLD_EXCEEDED after parsing CPER. 2. RAS Correctable Errors Collector counts correctable errors per PFN and when the counter for a PFN reaches threshold In both cases, userspace has no control of the soft offline performed by kernel's memory failure recovery. This patch series give userspace the control of soft-offlining HugeTLB pages: kernel only soft offlines hugepage if userspace has opt-ed in for that specific hugepage size, and exposed to userspace by a new sysfs entry called softoffline_corrected_errors under /sys/kernel/mm/hugepages/hugepages-${size}kB directory: * When softoffline_corrected_errors=0, skip soft offlining for all hugepages of size ${size}kB. * When softoffline_corrected_errors=1, soft offline as before this patch series. By default softoffline_corrected_errors is 1. This patch set is based at commit a52b4f11a2e1 ("selftest mm/mseal read-only elf memory segment"). Jiaqi Yan (3): mm/memory-failure: userspace controls soft-offlining hugetlb pages selftest/mm: test softoffline_corrected_errors behaviors docs: hugetlbpage.rst: add softoffline_corrected_errors Documentation/admin-guide/mm/hugetlbpage.rst | 15 +- include/linux/hugetlb.h | 17 ++ mm/hugetlb.c | 34 +++ mm/memory-failure.c | 7 + tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + .../selftests/mm/hugetlb-soft-offline.c | 262 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 8 files changed, 340 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/mm/hugetlb-soft-offline.c -- 2.45.1.288.g0e0cd299f1-goog

6 months, 2 weeks

3
10
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror May 2024