- Linux-kselftest-mirror - lists.linaro.org

[RFC PATCH net-next v6 00/15] Device Memory TCP

by Mina Almasry

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 <shakeelb(a)google.com> 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 (14): queue_api: define queue api net: page_pool: factor out page_pool recycle check 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 | 52 +++ Documentation/networking/devmem.rst | 271 ++++++++++++ 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/netdevice.h | 24 ++ include/linux/skbuff.h | 67 ++- include/linux/socket.h | 1 + include/net/devmem.h | 127 ++++++ include/net/netdev_rx_queue.h | 1 + include/net/netmem.h | 234 +++++++++- include/net/page_pool/helpers.h | 154 +++++-- include/net/page_pool/types.h | 28 +- 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 | 14 + net/bpf/test_run.c | 5 +- net/core/Makefile | 2 +- net/core/datagram.c | 6 + net/core/dev.c | 6 +- net/core/devmem.c | 413 ++++++++++++++++++ net/core/gro.c | 7 +- net/core/netdev-genl-gen.c | 19 + net/core/netdev-genl-gen.h | 2 + net/core/netdev-genl.c | 123 ++++++ net/core/page_pool.c | 362 +++++++++------- net/core/skbuff.c | 110 ++++- net/core/sock.c | 61 +++ net/ipv4/tcp.c | 257 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 9 + net/ipv4/tcp_output.c | 5 +- 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 | 546 ++++++++++++++++++++++++ 42 files changed, 2764 insertions(+), 270 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 tools/testing/selftests/net/ncdevmem.c -- 2.44.0.rc1.240.g4c46232300-goog

1 year, 7 months

10
72
0 0

[PATCH net-next 00/11] selftests: mptcp: cleanups and 'ip mptcp' support

by Matthieu Baerts (NGI0)

Here are some patches from Geliang, doing different cleanups, and supporting 'ip mptcp' in more MPTCP selftests. Patch 1 checks that TC is available in selftests requiring it. Patch 2 adds 'ms' units in TC commands, to avoid confusions. Patches 3-9 are some prerequisites for patch 10: some export code from mptcp_join.sh to mptcp_lib.sh, to be re-used in pm_netlink.sh, mptcp_sockopt.sh and simult_flows.sh ; and others add helpers to pm_netlink.sh to easily support both 'ip mptcp' and 'pm_nl_ctl' tools to interact with the in-kernel MPTCP path-manager. Patch 10 adds a '-i' parameter in mptcp_sockopt.sh, pm_netlink.sh, and simult_flows.sh to use 'ip mptcp' tool instead of 'pm_nl_ctl'. Patch 11 fixes some ShellCheck warnings in pm_netlink.sh, in order to drop a ShellCheck's 'disable' instruction. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (11): selftests: mptcp: add tc check for check_tools selftests: mptcp: add ms units for tc-netem delay selftests: mptcp: export ip_mptcp to mptcp_lib selftests: mptcp: netlink: add 'limits' helpers selftests: mptcp: add {get,format}_endpoint(s) helpers selftests: mptcp: netlink: add change_address helper selftests: mptcp: join: update endpoint ops selftests: mptcp: export pm_nl endpoint ops selftests: mptcp: use pm_nl endpoint ops selftests: mptcp: ip_mptcp option for more scripts selftests: mptcp: netlink: drop disable=SC2086 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 2 +- tools/testing/selftests/net/mptcp/mptcp_join.sh | 155 ++---------- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 135 ++++++++++ tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 34 ++- tools/testing/selftests/net/mptcp/pm_netlink.sh | 281 +++++++++++++-------- tools/testing/selftests/net/mptcp/simult_flows.sh | 20 +- 6 files changed, 375 insertions(+), 252 deletions(-) --- base-commit: d76c740b2eaaddc5fc3a8b21eaec5b6b11e8c3f5 change-id: 20240405-upstream-net-next-20240405-mptcp-selftests-refactoring-f5ed9780df8e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 7 months

2
12
0 0

[PATCH net-next v3 0/5] selftests: net: groundwork for YNL-based tests

by Jakub Kicinski

Currently the options for writing networking tests are C, bash or some mix of the two. YAML/Netlink gives us the ability to easily interface with Netlink in higher level laguages. In particular, there is a Python library already available in tree, under tools/net. Add the scaffolding which allows writing tests using this library. The "scaffolding" is needed because the library lives under tools/net and uses YAML files from under Documentation/. So we need a small amount of glue code to find those things and add them to TEST_FILES. This series adds both a basic SW sanity test and driver test which can be run against netdevsim or a real device. When I develop core code I usually test with netdevsim, then a real device, and then a backport to Meta's kernel. Because of the lack of integration, until now I had to throw away the (YNL-based) test script and netdevsim code. Running tests in tree directly: $ ./tools/testing/selftests/net/nl_netdev.py KTAP version 1 1..2 ok 1 nl_netdev.empty_check ok 2 nl_netdev.lo_check # Totals: pass:2 fail:0 xfail:0 xpass:0 skip:0 error:0 in tree via make: $ make -C tools/testing/selftests/ TARGETS=net \ TEST_PROGS=nl_netdev.py TEST_GEN_PROGS="" run_tests [ ... ] and installed externally, all seem to work: $ make -C tools/testing/selftests/ TARGETS=net \ install INSTALL_PATH=/tmp/ksft-net $ /tmp/ksft-net/run_kselftest.sh -t net:nl_netdev.py [ ... ] For driver tests I followed the lead of net/forwarding and get the device name from env and/or a config file. v3: - fix up netdevsim C - various small nits in other patches (see changelog in patches) v2: https://lore.kernel.org/all/20240403023426.1762996-1-kuba@kernel.org/ - don't add to TARGETS, create a deperate variable with deps - support and use with - support and use passing arguments to tests v1: https://lore.kernel.org/all/20240402010520.1209517-1-kuba@kernel.org/ Jakub Kicinski (5): selftests: net: add scaffolding for Netlink tests in Python selftests: nl_netdev: add a trivial Netlink netdev test netdevsim: report stats by default, like a real device selftests: drivers: add scaffolding for Netlink tests in Python testing: net-drv: add a driver test for stats reporting drivers/net/netdevsim/ethtool.c | 11 ++ drivers/net/netdevsim/netdev.c | 49 ++++++++ tools/testing/selftests/Makefile | 10 +- tools/testing/selftests/drivers/net/Makefile | 7 ++ .../testing/selftests/drivers/net/README.rst | 30 +++++ .../selftests/drivers/net/lib/py/__init__.py | 17 +++ .../selftests/drivers/net/lib/py/env.py | 52 ++++++++ tools/testing/selftests/drivers/net/stats.py | 86 +++++++++++++ tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/lib/Makefile | 8 ++ .../testing/selftests/net/lib/py/__init__.py | 7 ++ tools/testing/selftests/net/lib/py/consts.py | 9 ++ tools/testing/selftests/net/lib/py/ksft.py | 96 +++++++++++++++ tools/testing/selftests/net/lib/py/nsim.py | 115 ++++++++++++++++++ tools/testing/selftests/net/lib/py/utils.py | 47 +++++++ tools/testing/selftests/net/lib/py/ynl.py | 49 ++++++++ tools/testing/selftests/net/nl_netdev.py | 24 ++++ 17 files changed, 617 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/drivers/net/Makefile create mode 100644 tools/testing/selftests/drivers/net/README.rst create mode 100644 tools/testing/selftests/drivers/net/lib/py/__init__.py create mode 100644 tools/testing/selftests/drivers/net/lib/py/env.py create mode 100755 tools/testing/selftests/drivers/net/stats.py create mode 100644 tools/testing/selftests/net/lib/Makefile create mode 100644 tools/testing/selftests/net/lib/py/__init__.py create mode 100644 tools/testing/selftests/net/lib/py/consts.py create mode 100644 tools/testing/selftests/net/lib/py/ksft.py create mode 100644 tools/testing/selftests/net/lib/py/nsim.py create mode 100644 tools/testing/selftests/net/lib/py/utils.py create mode 100644 tools/testing/selftests/net/lib/py/ynl.py create mode 100755 tools/testing/selftests/net/nl_netdev.py -- 2.44.0

1 year, 7 months

2
6
0 0

[PATCH AUTOSEL 6.1 12/13] bpf: Check bloom filter map value size

by Sasha Levin

From: Andrei Matei <andreimatei1(a)gmail.com> [ Upstream commit a8d89feba7e54e691ca7c4efc2a6264fa83f3687 ] This patch adds a missing check to bloom filter creating, rejecting values above KMALLOC_MAX_SIZE. This brings the bloom map in line with many other map types. The lack of this protection can cause kernel crashes for value sizes that overflow int's. Such a crash was caught by syzkaller. The next patch adds more guard-rails at a lower level. Signed-off-by: Andrei Matei <andreimatei1(a)gmail.com> Acked-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20240327024245.318299-2-andreimatei1@gmail.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/bpf/bloom_filter.c | 13 +++++++++++++ .../selftests/bpf/prog_tests/bloom_filter_map.c | 6 ++++++ 2 files changed, 19 insertions(+) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 48ee750849f25..78e810f49c445 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -88,6 +88,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -196,6 +208,7 @@ static int bloom_map_check_btf(const struct bpf_map *map, BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index d2d9e965eba59..f79815b7e951b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <sys/syscall.h> +#include <limits.h> #include <test_progs.h> #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) -- 2.43.0

1 year, 7 months

1
0
0 0

[PATCH AUTOSEL 6.6 21/22] selftests/ftrace: Fix event filter target_func selection

by Sasha Levin

From: Mark Rutland <mark.rutland(a)arm.com> [ Upstream commit 8ecab2e64572f1aecdfc5a8feae748abda6e3347 ] The event filter function test has been failing in our internal test farm: | # not ok 33 event filter function - test event filtering on functions Running the test in verbose mode indicates that this is because the test erroneously determines that kmem_cache_free() is the most common caller of kmem_cache_free(): # # + cut -d: -f3 trace # # + sed s/call_site=([^+]*)+0x.*/1/ # # + sort # # + uniq -c # # + sort # # + tail -n 1 # # + sed s/^[ 0-9]*// # # + target_func=kmem_cache_free ... and as kmem_cache_free() doesn't call itself, setting this as the filter function for kmem_cache_free() results in no hits, and consequently the test fails: # # + grep kmem_cache_free trace # # + grep kmem_cache_free # # + wc -l # # + hitcnt=0 # # + grep kmem_cache_free trace # # + grep -v kmem_cache_free # # + wc -l # # + misscnt=0 # # + [ 0 -eq 0 ] # # + exit_fail This seems to be because the system in question has tasks with ':' in their name (which a number of kernel worker threads have). These show up in the trace, e.g. test:.sh-1299 [004] ..... 2886.040608: kmem_cache_free: call_site=putname+0xa4/0xc8 ptr=000000000f4d22f4 name=names_cache ... and so when we try to extact the call_site with: cut -d: -f3 trace | sed 's/call_site=$[^+]*$+0x.*/\1/' ... the 'cut' command will extrace the column containing 'kmem_cache_free' rather than the column containing 'call_site=...', and the 'sed' command will leave this unchanged. Consequently, the test will decide to use 'kmem_cache_free' as the filter function, resulting in the failure seen above. Fix this by matching the 'call_site=<func>' part specifically to extract the function name. Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Reported-by: Aishwarya TCV <aishwarya.tcv(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-trace-kernel(a)vger.kernel.org Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../selftests/ftrace/test.d/filter/event-filter-function.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index 2de7c61d1ae30..3f74c09c56b62 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -24,7 +24,7 @@ echo 0 > events/enable echo "Get the most frequently calling function" sample_events -target_func=`cut -d: -f3 trace | sed 's/call_site=$[^+]*$+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +target_func=`cat trace | grep -o 'call_site=$[^+]*$' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` if [ -z "$target_func" ]; then exit_fail fi -- 2.43.0

1 year, 7 months

1
0
0 0

[PATCH AUTOSEL 6.6 20/22] bpf: Check bloom filter map value size

by Sasha Levin

From: Andrei Matei <andreimatei1(a)gmail.com> [ Upstream commit a8d89feba7e54e691ca7c4efc2a6264fa83f3687 ] This patch adds a missing check to bloom filter creating, rejecting values above KMALLOC_MAX_SIZE. This brings the bloom map in line with many other map types. The lack of this protection can cause kernel crashes for value sizes that overflow int's. Such a crash was caught by syzkaller. The next patch adds more guard-rails at a lower level. Signed-off-by: Andrei Matei <andreimatei1(a)gmail.com> Acked-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20240327024245.318299-2-andreimatei1@gmail.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/bpf/bloom_filter.c | 13 +++++++++++++ .../selftests/bpf/prog_tests/bloom_filter_map.c | 6 ++++++ 2 files changed, 19 insertions(+) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index addf3dd57b59b..35e1ddca74d21 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map) BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index d2d9e965eba59..f79815b7e951b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <sys/syscall.h> +#include <limits.h> #include <test_progs.h> #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) -- 2.43.0

1 year, 7 months

1
0
0 0

[PATCH AUTOSEL 6.8 24/25] selftests/ftrace: Fix event filter target_func selection

by Sasha Levin

From: Mark Rutland <mark.rutland(a)arm.com> [ Upstream commit 8ecab2e64572f1aecdfc5a8feae748abda6e3347 ] The event filter function test has been failing in our internal test farm: | # not ok 33 event filter function - test event filtering on functions Running the test in verbose mode indicates that this is because the test erroneously determines that kmem_cache_free() is the most common caller of kmem_cache_free(): # # + cut -d: -f3 trace # # + sed s/call_site=([^+]*)+0x.*/1/ # # + sort # # + uniq -c # # + sort # # + tail -n 1 # # + sed s/^[ 0-9]*// # # + target_func=kmem_cache_free ... and as kmem_cache_free() doesn't call itself, setting this as the filter function for kmem_cache_free() results in no hits, and consequently the test fails: # # + grep kmem_cache_free trace # # + grep kmem_cache_free # # + wc -l # # + hitcnt=0 # # + grep kmem_cache_free trace # # + grep -v kmem_cache_free # # + wc -l # # + misscnt=0 # # + [ 0 -eq 0 ] # # + exit_fail This seems to be because the system in question has tasks with ':' in their name (which a number of kernel worker threads have). These show up in the trace, e.g. test:.sh-1299 [004] ..... 2886.040608: kmem_cache_free: call_site=putname+0xa4/0xc8 ptr=000000000f4d22f4 name=names_cache ... and so when we try to extact the call_site with: cut -d: -f3 trace | sed 's/call_site=$[^+]*$+0x.*/\1/' ... the 'cut' command will extrace the column containing 'kmem_cache_free' rather than the column containing 'call_site=...', and the 'sed' command will leave this unchanged. Consequently, the test will decide to use 'kmem_cache_free' as the filter function, resulting in the failure seen above. Fix this by matching the 'call_site=<func>' part specifically to extract the function name. Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Reported-by: Aishwarya TCV <aishwarya.tcv(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-trace-kernel(a)vger.kernel.org Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../selftests/ftrace/test.d/filter/event-filter-function.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index 2de7c61d1ae30..3f74c09c56b62 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -24,7 +24,7 @@ echo 0 > events/enable echo "Get the most frequently calling function" sample_events -target_func=`cut -d: -f3 trace | sed 's/call_site=$[^+]*$+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +target_func=`cat trace | grep -o 'call_site=$[^+]*$' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` if [ -z "$target_func" ]; then exit_fail fi -- 2.43.0

1 year, 7 months

1
0
0 0

[PATCH AUTOSEL 6.8 23/25] bpf: Check bloom filter map value size

by Sasha Levin

From: Andrei Matei <andreimatei1(a)gmail.com> [ Upstream commit a8d89feba7e54e691ca7c4efc2a6264fa83f3687 ] This patch adds a missing check to bloom filter creating, rejecting values above KMALLOC_MAX_SIZE. This brings the bloom map in line with many other map types. The lack of this protection can cause kernel crashes for value sizes that overflow int's. Such a crash was caught by syzkaller. The next patch adds more guard-rails at a lower level. Signed-off-by: Andrei Matei <andreimatei1(a)gmail.com> Acked-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20240327024245.318299-2-andreimatei1@gmail.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/bpf/bloom_filter.c | 13 +++++++++++++ .../selftests/bpf/prog_tests/bloom_filter_map.c | 6 ++++++ 2 files changed, 19 insertions(+) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index addf3dd57b59b..35e1ddca74d21 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map) BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index 053f4d6da77a4..cc184e4420f6e 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <sys/syscall.h> +#include <limits.h> #include <test_progs.h> #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) -- 2.43.0

1 year, 7 months

1
0
0 0

[PATCH bpf-next] selftests/bpf: Add F_SETFL for fcntl

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> Incorrect arguments are passed to fcntl() in test_sockmap.c when invoking it to set file status flags. If O_NONBLOCK is used as 2nd argument and passed into fcntl, -EINVAL will be returned (See do_fcntl() in fs/fcntl.c). The correct approach is to use F_SETFL as 2nd argument, and O_NONBLOCK as 3rd one. Fixes: 16962b2404ac ("bpf: sockmap, add selftests") Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> --- tools/testing/selftests/bpf/test_sockmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 024a0faafb3b..34d6a1e6f664 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -603,7 +603,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, struct timeval timeout; fd_set w; - fcntl(fd, fd_flags); + fcntl(fd, F_SETFL, fd_flags); /* Account for pop bytes noting each iteration of apply will * call msg_pop_data helper so we need to account for this * by calculating the number of apply iterations. Note user -- 2.40.1

1 year, 7 months

3
5
0 0

[PATCH v4 0/4] libbpf: API to partially consume items from ringbuffer

by Andrea Righi

Introduce ring__consume_n() and ring_buffer__consume_n() API to partially consume items from one (or more) ringbuffer(s). This can be useful, for example, to consume just a single item or when we need to copy multiple items to a limited user-space buffer from the ringbuffer callback. Practical example (where this API can be used): https://github.com/sched-ext/scx/blob/b7c06b9ed9f72cad83c31e39e9c4e2cfd8683… See also: https://lore.kernel.org/lkml/20240310154726.734289-1-andrea.righi@canonical… v4: - add a selftest to test the new API - open a new 1.5.0 cycle v3: - rename ring__consume_max() -> ring__consume_n() and ring_buffer__consume_max() -> ring_buffer__consume_n() - add new API to a new 1.5.0 cycle - fixed minor nits / comments v2: - introduce a new API instead of changing the callback's retcode behavior Andrea Righi (4): libbpf: Start v1.5 development cycle libbpf: ringbuf: allow to consume up to a certain amount of items libbpf: Add ring__consume_n / ring_buffer__consume_n selftests/bpf: Add tests for ring__consume_n and ring_buffer__consume_n tools/lib/bpf/libbpf.h | 12 +++++ tools/lib/bpf/libbpf.map | 6 +++ tools/lib/bpf/libbpf_version.h | 2 +- tools/lib/bpf/ringbuf.c | 59 ++++++++++++++++++++---- tools/testing/selftests/bpf/prog_tests/ringbuf.c | 8 ++++ 5 files changed, 76 insertions(+), 11 deletions(-)

1 year, 7 months

3
9
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror