June 2024 - Linux-kselftest-mirror

[PATCH net-next 5/5] selftests: forwarding: Add test for minimum and maximum MTU

by Petr Machata

From: Amit Cohen <amcohen(a)nvidia.com> Add cases to check minimum and maximum MTU which are exposed via "ip -d link show". Test configuration and traffic. Use VLAN devices as usually VLAN header (4 bytes) is not included in the MTU, and drivers should configure hardware correctly to send maximum MTU payload size in VLAN tagged packets. $ ./min_max_mtu.sh TEST: ping [ OK ] TEST: ping6 [ OK ] TEST: Test maximum MTU configuration [ OK ] TEST: Test traffic, packet size is maximum MTU [ OK ] TEST: Test minimum MTU configuration [ OK ] TEST: Test traffic, packet size is minimum MTU [ OK ] Signed-off-by: Amit Cohen <amcohen(a)nvidia.com> Reviewed-by: Petr Machata <petrm(a)nvidia.com> Signed-off-by: Petr Machata <petrm(a)nvidia.com> --- Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kselftest(a)vger.kernel.org .../testing/selftests/net/forwarding/Makefile | 1 + .../selftests/net/forwarding/min_max_mtu.sh | 283 ++++++++++++++++++ 2 files changed, 284 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/min_max_mtu.sh diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 99576d7ecbf6..224346426ef2 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -39,6 +39,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ ipip_hier_gre.sh \ lib_sh_test.sh \ local_termination.sh \ + min_max_mtu.sh \ mirror_gre_bound.sh \ mirror_gre_bridge_1d.sh \ mirror_gre_bridge_1d_vlan.sh \ diff --git a/tools/testing/selftests/net/forwarding/min_max_mtu.sh b/tools/testing/selftests/net/forwarding/min_max_mtu.sh new file mode 100755 index 000000000000..97bb8b221bed --- /dev/null +++ b/tools/testing/selftests/net/forwarding/min_max_mtu.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 | +# | | +# | $h1.10 + | +# | 192.0.2.2/24 | | +# | 2001:db8:1::2/64 | | +# | | | +# | $h1 + | +# | | | +# +------------------|-+ +# | +# +------------------|-+ +# | SW | | +# | $swp1 + | +# | | | +# | $swp1.10 + | +# | 192.0.2.1/24 | +# | 2001:db8:1::1/64 | +# | | +# +--------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + max_mtu_config_test + max_mtu_traffic_test + min_mtu_config_test + min_mtu_traffic_test +" + +NUM_NETIFS=2 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.2/24 2001:db8:1::2/64 +} + +h1_destroy() +{ + vlan_destroy $h1 10 192.0.2.2/24 2001:db8:1::2/64 + simple_if_fini $h1 +} + +switch_create() +{ + ip li set dev $swp1 up + vlan_create $swp1 10 "" 192.0.2.1/24 2001:db8:1::1/64 +} + +switch_destroy() +{ + ip li set dev $swp1 down + vlan_destroy $swp1 10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + + switch_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + switch_destroy + + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 192.0.2.1 +} + +ping_ipv6() +{ + ping6_test $h1.10 2001:db8:1::1 +} + +min_max_mtu_get_if() +{ + local dev=$1; shift + local min_max=$1; shift + + ip -d -j link show $dev | jq ".[].$min_max" +} + +ensure_compatible_min_max_mtu() +{ + local min_max=$1; shift + + local mtu=$(min_max_mtu_get_if ${NETIFS[p1]} $min_max) + local i + + for ((i = 2; i <= NUM_NETIFS; ++i)); do + local current_mtu=$(min_max_mtu_get_if ${NETIFS[p$i]} $min_max) + + if [ $current_mtu -ne $mtu ]; then + return 1 + fi + done +} + +mtu_set_if() +{ + local dev=$1; shift + local mtu=$1; shift + local should_fail=${1:-0}; shift + + mtu_set $dev $mtu 2>/dev/null + check_err_fail $should_fail $? "Set MTU $mtu for $dev" +} + +mtu_set_all_if() +{ + local mtu=$1; shift + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_set_if ${NETIFS[p$i]} $mtu + mtu_set_if ${NETIFS[p$i]}.10 $mtu + done +} + +mtu_restore_all_if() +{ + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_restore ${NETIFS[p$i]}.10 + mtu_restore ${NETIFS[p$i]} + done +} + +mtu_test_ping4() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 20 bytes for IP header + local ping_headers_len=$((20 + 8)) + local pkt_size=$((mtu - ping_headers_len)) + + ping_do $h1.10 192.0.2.1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping, packet size: $pkt_size" +} + +mtu_test_ping6() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 40 bytes for IPv6 header + local ping6_headers_len=$((40 + 8)) + local pkt_size=$((mtu - ping6_headers_len)) + + ping6_do $h1.10 2001:db8:1::1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping6, packet size: $pkt_size" +} + +max_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local max_mtu=$(min_max_mtu_get_if $dev "max_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $max_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((max_mtu + 1)) $should_fail + mtu_restore $dev + done + + log_test "Test maximum MTU configuration" +} + +max_mtu_traffic_test() +{ + local should_fail + local max_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "max_mtu"; then + log_test_xfail "Topology has incompatible maximum MTU values" + return + fi + + max_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "max_mtu") + + should_fail=0 + mtu_set_all_if $max_mtu + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + should_fail=1 + mtu_set_all_if $((max_mtu - 1)) + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + log_test "Test traffic, packet size is maximum MTU" +} + +min_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local min_mtu=$(min_max_mtu_get_if $dev "min_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $min_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((min_mtu - 1)) $should_fail + mtu_restore $dev + done + + log_test "Test minimum MTU configuration" +} + +min_mtu_traffic_test() +{ + local should_fail=0 + local min_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "min_mtu"; then + log_test_xfail "Topology has incompatible minimum MTU values" + return + fi + + min_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "min_mtu") + mtu_set_all_if $min_mtu + mtu_test_ping4 $min_mtu $should_fail + # Do not test minimum MTU with IPv6, as IPv6 requires higher MTU. + + mtu_restore_all_if + + log_test "Test traffic, packet size is minimum MTU" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS -- 2.45.0

1 year, 4 months

1
0
0 0

[PATCH][next] kselftest/arm64: Fix a couple of spelling mistakes

by Colin Ian King

There are two spelling mistakes in some error messages. Fix them. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/arm64/fp/kernel-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c index 50db26a3ed79..e8da3b4cbd23 100644 --- a/tools/testing/selftests/arm64/fp/kernel-test.c +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -233,7 +233,7 @@ static bool compute_digest(void *buf) reread: ret = recv(sock, buf, digest_len, 0); if (ret == 0) { - printf("No disgest returned\n"); + printf("No digest returned\n"); return false; } if (ret != digest_len) { @@ -308,7 +308,7 @@ int main(void) while (true) { if (!compute_digest(digest)) { - printf("Failed to coempute digest, iter=%d\n", iter); + printf("Failed to compute digest, iter=%d\n", iter); return EXIT_FAILURE; } -- 2.39.2

1 year, 4 months

3
2
0 0

[PATCH v2 0/2] Add test to distinguish between thread's signal mask and ucontext_t

by Dev Jain

This patch series is motivated by the following observation: Raise a signal, jump to signal handler. The ucontext_t structure dumped by kernel to userspace has a uc_sigmask field having the mask of blocked signals. If you run a fresh minimalistic program doing this, this field is empty, even if you block some signals while registering the handler with sigaction(). Here is what the man-pages have to say: sigaction(2): "sa_mask specifies a mask of signals which should be blocked (i.e., added to the signal mask of the thread in which the signal handler is invoked) during execution of the signal handler. In addition, the signal which triggered the handler will be blocked, unless the SA_NODEFER flag is used." signal(7): Under "Execution of signal handlers", (1.3) implies: "The thread's current signal mask is accessible via the ucontext_t object that is pointed to by the third argument of the signal handler." But, (1.4) states: "Any signals specified in act->sa_mask when registering the handler with sigprocmask(2) are added to the thread's signal mask. The signal being delivered is also added to the signal mask, unless SA_NODEFER was specified when registering the handler. These signals are thus blocked while the handler executes." There clearly is no distinction being made in the man pages between "Thread's signal mask" and ucontext_t; this logically should imply that a signal blocked by populating struct sigaction should be visible in ucontext_t. Here is what the kernel code does (for Aarch64): do_signal() -> handle_signal() -> sigmask_to_save(), which returns &current->blocked, is passed to setup_rt_frame() -> setup_sigframe() -> __copy_to_user(). Hence, &current->blocked is copied to ucontext_t exposed to userspace. Returning back to handle_signal(), signal_setup_done() -> signal_delivered() -> sigorsets() and set_current_blocked() are responsible for using information from struct ksignal ksig, which was populated through the sigaction() system call in kernel/signal.c: copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa)), to update &current->blocked; hence, the set of blocked signals for the current thread is updated AFTER the kernel dumps ucontext_t to userspace. Assuming that the above is indeed the intended behaviour, because it semantically makes sense, since the signals blocked using sigaction() remain blocked only till the execution of the handler, and not in the context present before jumping to the handler (but nothing can be confirmed from the man-pages), the series introduces a test for mangling with uc_sigmask. I will send a separate series to fix the man-pages. The proposed selftest has been tested out on Aarch32, Aarch64 and x86_64. Changes in v2: - Replace all occurrences of SIGPIPE with SIGSEGV - Fixed a mismatch between code comment and ksft log - Add a testcase: Raise the same signal again; it must not be queued - Remove unneeded <assert.h>, <unistd.h> - Give a detailed test description in the comments; also describe the exact meaning of delivered and blocked - Handle errors for all libc functions/syscalls - Mention tests in Makefile and .gitignore in alphabetical order Dev Jain (2): selftests: Rename sigaltstack to generic signal selftests: Add a test mangling with uc_sigmask tools/testing/selftests/Makefile | 2 +- .../{sigaltstack => signal}/.gitignore | 3 +- .../{sigaltstack => signal}/Makefile | 3 +- .../current_stack_pointer.h | 0 .../selftests/signal/mangle_uc_sigmask.c | 194 ++++++++++++++++++ .../sas.c => signal/sigaltstack.c} | 0 6 files changed, 199 insertions(+), 3 deletions(-) rename tools/testing/selftests/{sigaltstack => signal}/.gitignore (57%) rename tools/testing/selftests/{sigaltstack => signal}/Makefile (53%) rename tools/testing/selftests/{sigaltstack => signal}/current_stack_pointer.h (100%) create mode 100644 tools/testing/selftests/signal/mangle_uc_sigmask.c rename tools/testing/selftests/{sigaltstack/sas.c => signal/sigaltstack.c} (100%) -- 2.34.1

1 year, 4 months

2
9
0 0

[PATCH net-next v11 00/13] Device Memory TCP

by Mina Almasry

v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> 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> 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/mp_dmabuf_devmem.h | 46 ++ 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 | 22 +- 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 | 375 ++++++++++++++++ net/core/gro.c | 3 +- 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 | 360 +++++++++------- net/core/skbuff.c | 83 +++- net/core/sock.c | 61 +++ net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 261 +++++++++++- 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 ++++++++++++++++++++++++ 47 files changed, 2759 insertions(+), 266 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 include/net/mp_dmabuf_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 -- 2.45.2.505.gda0bf45e8d-goog

1 year, 4 months

2
14
0 0

[PATCH net-next v7 0/2] Add F_SETFL for fcntl in test_sockmap

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> v7: - a better fix for tls_sw_recvmsg. v6: - add a fix for tls_sw_recvmsg(). v5: - add a new patch "Check recv lengths in test_sockmap" instead of using "continue" in msg_loop. v4: - address Martin's comments for v3. (thanks.) - add Yonghong's "Acked-by" tags. (thanks.) - update subject-prefix from "bpf-next" to "bpf". Patch 1, v3 of "selftests/bpf: Add F_SETFL for fcntl": - detect nonblock flag automatically, then test_sockmap can run in both block and nonblock modes. - use continue instead of again in v2. Patch 2, fix for umount cgroup2 error. Geliang Tang (2): tls: receive msg again for sk_redirect selftests/bpf: Add F_SETFL for fcntl in test_sockmap net/tls/tls_sw.c | 3 +++ tools/testing/selftests/bpf/test_sockmap.c | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) -- 2.43.0

1 year, 4 months

2
3
0 0

[PATCH v2 0/2] usercopy: Convert test_user_copy to KUnit test

by Kees Cook

Hi, This builds on the proposal[1] from Mark and lets me convert the existing usercopy selftest to KUnit. Besides adding this basic test to the KUnit collection, it also opens the door for execve testing (which depends on having a functional current->mm), and should provide the basic infrastructure for adding Mark's much more complete usercopy tests. v2: - dropped "initial VMA", turns out it wasn't needed (Mark) - various cleanups in the test itself (Vitor) - moved new kunit resource to a separate file (David) v1: https://lore.kernel.org/all/20240519190422.work.715-kees@kernel.org/ -Kees [1] https://lore.kernel.org/lkml/20230321122514.1743889-2-mark.rutland@arm.com/ Kees Cook (2): kunit: test: Add vm_mmap() allocation resource manager usercopy: Convert test_user_copy to KUnit test MAINTAINERS | 1 + include/kunit/test.h | 17 ++ lib/Kconfig.debug | 21 +- lib/Makefile | 2 +- lib/kunit/Makefile | 1 + lib/kunit/user_alloc.c | 111 +++++++++ lib/{test_user_copy.c => usercopy_kunit.c} | 273 ++++++++++----------- 7 files changed, 271 insertions(+), 155 deletions(-) create mode 100644 lib/kunit/user_alloc.c rename lib/{test_user_copy.c => usercopy_kunit.c} (47%) -- 2.34.1

1 year, 4 months

3
8
0 0

[PATCH] selftests: seccomp: fix format-zero-length warnings

by Amer Al Shanawany

seccomp_benchmark.c:197:24: warning: zero-length gnu_printf format string [-Wformat-zero-length] 197 | ksft_print_msg(""); | ^~ seccomp_benchmark.c:202:24: warning: zero-length gnu_printf format string [-Wformat-zero-length] 202 | ksft_print_msg(""); | ^~ seccomp_benchmark.c:204:24: warning: zero-length gnu_printf format string [-Wformat-zero-length] 204 | ksft_print_msg(""); | ^~ Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202312260235.Uj5ug8K9-lkp@intel.com/ Signed-off-by: Amer Al Shanawany <amer.shanawany(a)gmail.com> --- tools/testing/selftests/seccomp/seccomp_benchmark.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index b83099160fbc..ed04b89de9c6 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -194,14 +194,14 @@ int main(int argc, char *argv[]) ksft_set_plan(7); ksft_print_msg("Running on:\n"); - ksft_print_msg(""); + ksft_print_msg(" "); system("uname -a"); ksft_print_msg("Current BPF sysctl settings:\n"); /* Avoid using "sysctl" which may not be installed. */ - ksft_print_msg(""); + ksft_print_msg(" "); system("grep -H . /proc/sys/net/core/bpf_jit_enable"); - ksft_print_msg(""); + ksft_print_msg(" "); system("grep -H . /proc/sys/net/core/bpf_jit_harden"); affinity(); -- 2.43.0

1 year, 4 months

3
7
0 0

[PATCH bpf-next v5 00/12] bpf: Support dumping kfunc prototypes from BTF

by Daniel Xu

This patchset enables both detecting as well as dumping compilable prototypes for kfuncs. The first commit instructs pahole to DECL_TAG kfuncs when available. This requires v1.27 which was released on 6/11/24. With it, users will be able to look at BTF inside vmlinux (or modules) and check if the kfunc they want is available. The final commit teaches bpftool how to dump kfunc prototypes. This is done for developer convenience. The rest of the commits are fixups to enable selftests to use the newly dumped kfunc prototypes. With these, selftests will regularly exercise the newly added codepaths. Tested with and without the required pahole changes: * https://github.com/kernel-patches/bpf/pull/7186 * https://github.com/kernel-patches/bpf/pull/7187 === Changelog === From v4: * Change bpf_session_cookie() return type * Only fixup used fentry test kfunc prototypes * Extract out projection detection into shared btf_is_projection_of() * Fix kernel test robot build warnings about doc comments From v3: * Teach selftests to use dumped prototypes From v2: * Update Makefile.btf with pahole flag * More error checking * Output formatting changes * Drop already-merged commit From v1: * Add __weak annotation * Use btf_dump for kfunc prototypes * Update kernel bpf_rdonly_cast() signature Daniel Xu (12): kbuild: bpf: Tell pahole to DECL_TAG kfuncs bpf: selftests: Fix bpf_iter_task_vma_new() prototype bpf: selftests: Fix fentry test kfunc prototypes bpf: selftests: Fix bpf_cpumask_first_zero() kfunc prototype bpf: selftests: Fix bpf_map_sum_elem_count() kfunc prototype bpf: Make bpf_session_cookie() kfunc return long * bpf: selftests: Namespace struct_opt callbacks in bpf_dctcp bpf: verifier: Relax caller requirements for kfunc projection type args bpf: treewide: Align kfunc signatures to prog point-of-view bpf: selftests: nf: Opt out of using generated kfunc prototypes bpf: selftests: xfrm: Opt out of using generated kfunc prototypes bpftool: Support dumping kfunc prototypes from BTF fs/verity/measure.c | 5 +- include/linux/bpf.h | 8 +-- include/linux/btf.h | 1 + kernel/bpf/btf.c | 13 ++++- kernel/bpf/crypto.c | 24 +++++--- kernel/bpf/helpers.c | 39 +++++++++---- kernel/bpf/verifier.c | 12 +++- kernel/trace/bpf_trace.c | 17 +++--- net/core/filter.c | 32 +++++++---- scripts/Makefile.btf | 2 +- tools/bpf/bpftool/btf.c | 55 +++++++++++++++++++ .../testing/selftests/bpf/bpf_experimental.h | 2 +- tools/testing/selftests/bpf/progs/bpf_dctcp.c | 36 ++++++------ .../selftests/bpf/progs/get_func_ip_test.c | 7 +-- .../selftests/bpf/progs/ip_check_defrag.c | 10 ++-- .../selftests/bpf/progs/map_percpu_stats.c | 2 +- .../selftests/bpf/progs/nested_trust_common.h | 2 +- .../testing/selftests/bpf/progs/test_bpf_nf.c | 1 + .../selftests/bpf/progs/test_bpf_nf_fail.c | 1 + .../bpf/progs/verifier_netfilter_ctx.c | 6 +- .../selftests/bpf/progs/xdp_synproxy_kern.c | 1 + tools/testing/selftests/bpf/progs/xfrm_info.c | 1 + 22 files changed, 193 insertions(+), 84 deletions(-) -- 2.44.0

1 year, 4 months

2
9
0 0

[PATCH] selftests: arm64: Fix redundancy of a testcase

by Dev Jain

Currently, we are writing the same value as we read, into the TLS register; hence, we cannot confirm updation of the register, making the testcase "verify_tpidr_one" redundant. Fix this; while at it, do a style change. Signed-off-by: Dev Jain <dev.jain(a)arm.com> --- tools/testing/selftests/arm64/abi/ptrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index abe4d58d731d..c105703442f9 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -47,7 +47,7 @@ static void test_tpidr(pid_t child) /* ...write a new value.. */ write_iov.iov_len = sizeof(uint64_t); - write_val[0] = read_val[0]++; + write_val[0] = read_val[0] + 1; ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov); ksft_test_result(ret == 0, "write_tpidr_one\n"); @@ -108,7 +108,7 @@ static void test_tpidr(pid_t child) /* Writing only TPIDR... */ write_iov.iov_len = sizeof(uint64_t); memcpy(write_val, read_val, sizeof(read_val)); - write_val[0] += 1; + ++write_val[0]; ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov); if (ret == 0) { -- 2.39.2

1 year, 4 months

3
3
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>

1 year, 4 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror June 2024