June 2025 - Linux-kselftest-mirror

[PATCH net-next] selftests: devmem: configure HDS threshold

by Taehee Yoo

The devmem TCP requires the hds-thresh value to be 0, but it doesn't change it automatically. Therefore, configure_hds_thresh() is added to handle this. The run_devmem_tests() now tests hds_thresh, but it skips test if the hds_thresh_max value is 0. Signed-off-by: Taehee Yoo <ap420073(a)gmail.com> --- .../selftests/drivers/net/hw/ncdevmem.c | 86 +++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index cc9b40d9c5d5..d78b5e5697d7 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -349,6 +349,72 @@ static int configure_headersplit(bool on) return ret; } +static int configure_hds_thresh(int len) +{ + struct ethtool_rings_get_req *get_req; + struct ethtool_rings_get_rsp *get_rsp; + struct ethtool_rings_set_req *req; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = ethtool_rings_set_req_alloc(); + ethtool_rings_set_req_set_header_dev_index(req, ifindex); + ethtool_rings_set_req_set_hds_thresh(req, len); + ret = ethtool_rings_set(ys, req); + if (ret < 0) + fprintf(stderr, "YNL failed: %s\n", ys->err.msg); + ethtool_rings_set_req_free(req); + + if (ret == 0) { + get_req = ethtool_rings_get_req_alloc(); + ethtool_rings_get_req_set_header_dev_index(get_req, ifindex); + get_rsp = ethtool_rings_get(ys, get_req); + ethtool_rings_get_req_free(get_req); + if (get_rsp) + fprintf(stderr, "HDS threshold: %d\n", + get_rsp->hds_thresh); + ethtool_rings_get_rsp_free(get_rsp); + } + + ynl_sock_destroy(ys); + + return ret; +} + +static int get_hds_thresh_max(void) +{ + struct ethtool_rings_get_req *get_req; + struct ethtool_rings_get_rsp *get_rsp; + struct ynl_error yerr; + unsigned int ret = 0; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + get_req = ethtool_rings_get_req_alloc(); + ethtool_rings_get_req_set_header_dev_index(get_req, ifindex); + get_rsp = ethtool_rings_get(ys, get_req); + ethtool_rings_get_req_free(get_req); + if (get_rsp) + ret = get_rsp->hds_thresh_max; + ethtool_rings_get_rsp_free(get_rsp); + + ynl_sock_destroy(ys); + + return ret; +} + static int configure_rss(void) { return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue); @@ -565,6 +631,9 @@ static int do_server(struct memory_buffer *mem) if (configure_headersplit(1)) error(1, 0, "Failed to enable TCP header split\n"); + if (configure_hds_thresh(0)) + error(1, 0, "Failed to set HDS threshold\n"); + /* Configure RSS to divert all traffic from our devmem queues */ if (configure_rss()) error(1, 0, "Failed to configure rss\n"); @@ -725,10 +794,14 @@ static int do_server(struct memory_buffer *mem) void run_devmem_tests(void) { struct memory_buffer *mem; + int hds_thresh_max = 0; struct ynl_sock *ys; mem = provider->alloc(getpagesize() * NUM_PAGES); + hds_thresh_max = get_hds_thresh_max(); + if (hds_thresh_max < 0) + error(1, 0, "Failed to get hds_thresh_max"); /* Configure RSS to divert all traffic from our devmem queues */ if (configure_rss()) error(1, 0, "rss error\n"); @@ -750,6 +823,19 @@ void run_devmem_tests(void) if (configure_headersplit(1)) error(1, 0, "Failed to configure header split\n"); + /* Do not test hds_thresh if hds_thresh_max value is 0 */ + if (hds_thresh_max) { + if (configure_hds_thresh(1)) + error(1, 0, "Failed to configure HDS threshold\n"); + + if (!bind_rx_queue(ifindex, mem->fd, create_queues(), + num_queues, &ys)) + error(1, 0, "Configure dmabuf with non-zero HDS threshold should have failed\n"); + + if (configure_hds_thresh(0)) + error(1, 0, "Failed to configure HDS threshold\n"); + } + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) error(1, 0, "Failed to bind\n"); -- 2.34.1

5 months, 1 week

3
4
0 0

[PATCH] selftests: cachestat: add tests for mmap

by Suresh K C

From: Suresh K C <suresh.k.chandrappa(a)gmail.com> Add a test case to verify cachestat behavior with memory-mapped files using mmap(). This ensures that pages accessed via mmap are correctly accounted for in the page cache. Tested on x86_64 with default kernel config Signed-off-by: Suresh K C <suresh.k.chandrappa(a)gmail.com> --- .../selftests/cachestat/test_cachestat.c | 39 ++++++++++++++++--- 1 file changed, 33 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index 632ab44737ec..b6452978dae0 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -33,6 +33,11 @@ void print_cachestat(struct cachestat *cs) cs->nr_evicted, cs->nr_recently_evicted); } +enum file_type { + FILE_MMAP, + FILE_SHMEM +}; + bool write_exactly(int fd, size_t filesize) { int random_fd = open("/dev/urandom", O_RDONLY); @@ -202,7 +207,7 @@ static int test_cachestat(const char *filename, bool write_random, bool create, return ret; } -bool test_cachestat_shmem(void) +bool run_cachestat_test(enum file_type type) { size_t PS = sysconf(_SC_PAGESIZE); size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ @@ -212,27 +217,43 @@ bool test_cachestat_shmem(void) char *filename = "tmpshmcstat"; struct cachestat cs; bool ret = true; + int fd; unsigned long num_pages = compute_len / PS; - int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + if (type == FILE_SHMEM) + fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + else + fd = open(filename, O_RDWR | O_CREAT | O_TRUNC, 0666); if (fd < 0) { - ksft_print_msg("Unable to create shmem file.\n"); + ksft_print_msg("Unable to create file.\n"); ret = false; goto out; } if (ftruncate(fd, filesize)) { - ksft_print_msg("Unable to truncate shmem file.\n"); + ksft_print_msg("Unable to truncate file.\n"); ret = false; goto close_fd; } if (!write_exactly(fd, filesize)) { - ksft_print_msg("Unable to write to shmem file.\n"); + ksft_print_msg("Unable to write to file.\n"); ret = false; goto close_fd; } + if (type == FILE_MMAP){ + char *map = mmap(NULL, filesize, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (map == MAP_FAILED) { + ksft_print_msg("mmap failed.\n"); + ret = false; + goto close_fd; + } + for (int i = 0; i < filesize; i++) { + map[i] = 'A'; + } + map[filesize - 1] = 'X'; + } syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); if (syscall_ret) { @@ -308,12 +329,18 @@ int main(void) break; } - if (test_cachestat_shmem()) + if (run_cachestat_test(FILE_SHMEM)) ksft_test_result_pass("cachestat works with a shmem file\n"); else { ksft_test_result_fail("cachestat fails with a shmem file\n"); ret = 1; } + if (run_cachestat_test(FILE_MMAP)) + ksft_test_result_pass("cachestat works with a mmap file\n"); + else { + ksft_test_result_fail("cachestat fails with a mmap file\n"); + ret = 1; + } return ret; } -- 2.43.0

5 months, 1 week

3
2
0 0

[PATCH v9 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v9 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (3): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (12): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option send control tcp: accecn: AccECN option ceb/cep heuristic tcp: accecn: AccECN ACE field multi-wrap heuristic tcp: try to avoid safer when ACKs are thinned .../networking/net_cachelines/tcp_sock.rst | 14 + include/linux/tcp.h | 34 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 225 ++++++- include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 3 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 30 +- net/ipv4/tcp_input.c | 622 +++++++++++++++++- net/ipv4/tcp_ipv4.c | 7 +- net/ipv4/tcp_minisocks.c | 91 ++- net/ipv4/tcp_output.c | 325 ++++++++- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 14 files changed, 1285 insertions(+), 96 deletions(-) -- 2.34.1

5 months, 2 weeks

3
28
0 0

[PATCH net-next v3 0/3] selftest: net: Add selftest for netpoll

by Breno Leitao

I am submitting a new selftest for the netpoll subsystem specifically targeting the case where the RX is polling in the TX path, which is a case that we don't have any test in the tree today. This is done when netpoll_poll_dev() called, and this test creates a scenario when that is probably. The test does the following: 1) Configuring a single RX/TX queue to increase contention on the interface. 2) Generating background traffic to saturate the network, mimicking real-world congestion. 3) Sending netconsole messages to trigger netpoll polling and monitor its behavior. 4) Using dynamic netconsole targets via configfs, with the ability to delete and recreate targets during the test. 5) Running bpftrace in parallel to verify that netpoll_poll_dev() is called when expected. If it is called, then the test passes, otherwise the test is marked as skipped. In order to achieve it, I stole Jakub's bpftrace helper from [1], and did some small changes that I found useful to use the helper. So, this patchset basically contains: 1) The code stolen from Jakub 2) Improvements on bpftrace() helper 3) The selftest itself Link: https://lore.kernel.org/all/20250421222827.283737-22-kuba@kernel.org/ [1] --- Changes in v3: - Make pylint happy (Simon) - Remove the unnecessary patch in bpftrace to raise an exception when it fails. (Jakub) - Improved the bpftrace code (Willem) - Stop sending messages if bpftrace is not alive anymore. - Link to v2: https://lore.kernel.org/r/20250625-netpoll_test-v2-0-47d27775222c@debian.org Changes in v2: - Stole Jakub's helper to run bpftrace - Removed the DEBUG option and moved logs to logging - Change the code to have a higher chance of calling netpoll_poll_dev(). In my current configuration, it is hitting multiple times during the test. - Save and restore TX/RX queue size (Jakub) - Link to v1: https://lore.kernel.org/r/20250620-netpoll_test-v1-1-5068832f72fc@debian.org --- Breno Leitao (2): selftests: drv-net: Strip '@' prefix from bpftrace map keys selftests: net: add netpoll basic functionality test Jakub Kicinski (1): selftests: drv-net: add helper/wrapper for bpftrace tools/testing/selftests/drivers/net/Makefile | 1 + .../selftests/drivers/net/lib/py/__init__.py | 3 +- .../testing/selftests/drivers/net/netpoll_basic.py | 345 +++++++++++++++++++++ tools/testing/selftests/net/lib/py/utils.py | 35 +++ 4 files changed, 383 insertions(+), 1 deletion(-) --- base-commit: 8efa26fcbf8a7f783fd1ce7dd2a409e9b7758df0 change-id: 20250612-netpoll_test-a1324d2057c8 Best regards, -- Breno Leitao <leitao(a)debian.org>

5 months, 2 weeks

3
8
0 0

[PATCH net-next 2/2] selftests: seg6: fix instaces typo in comments

by Andrea Mayer

Fix a typo: instaces -> instances The typo has been identified using codespell, and the tool does not report any additional issues in the selftests considered. Signed-off-by: Andrea Mayer <andrea.mayer(a)uniroma2.it> --- tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh | 2 +- tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh | 2 +- tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh | 2 +- tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh index ba730655a7bf..4bc135e5c22c 100755 --- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh @@ -594,7 +594,7 @@ setup_rt_local_sids() dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index bedf0ce885c2..34b781a2ae74 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -681,7 +681,7 @@ setup_rt_local_sids() set_underlay_sids_reachability "${rt}" "${rt_neighs}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 3efce1718c5f..6a68c7eff1dc 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -395,7 +395,7 @@ setup_rt_local_sids() dev "${VRF_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh index cabc70538ffe..0979b5316fdf 100755 --- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh @@ -343,7 +343,7 @@ setup_rt_local_sids() encap seg6local action End dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behaviors instaces are grouped together in the 'localsid' + # Endpoint behaviors instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule add \ to "${VPN_LOCATOR_SERVICE}::/16" \ -- 2.20.1

5 months, 2 weeks

2
1
0 0

Re: [PATCH] selftests/mm: add test for (BATCH_PROCESS)MADV_DONTNEED

by wang lian

I deeply appreciate for your criticism. This is my first patch and I will improve it based on what we have discussed so far.

5 months, 2 weeks

3
5
0 0

[PATCH 0/3] arm64: Support FEAT_LSFE (Large System Float Extension)

by Mark Brown

FEAT_LSFE is optional from v9.5, it adds new instructions for atomic memory operations with floating point values. We have no immediate use for it in kernel, provide a hwcap so userspace can discover it and allow the ID register field to be exposed to KVM guests. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (3): arm64/hwcap: Add hwcap for FEAT_LSFE KVM: arm64: Expose FEAT_LSFE to guests kselftest/arm64: Add lsfe to the hwcaps test Documentation/arch/arm64/elf_hwcaps.rst | 4 ++++ arch/arm64/include/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/kernel/cpufeature.c | 2 ++ arch/arm64/kernel/cpuinfo.c | 1 + arch/arm64/kvm/sys_regs.c | 4 +++- tools/testing/selftests/arm64/abi/hwcap.c | 21 +++++++++++++++++++++ 7 files changed, 33 insertions(+), 1 deletion(-) --- base-commit: 86731a2a651e58953fc949573895f2fa6d456841 change-id: 20250625-arm64-lsfe-0810cf98adc2 Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 2 weeks

2
6
0 0

[PATCH net-next 6/6] selftests: net: extend SCM_PIDFD test to cover stale pidfds

by Alexander Mikhalitsyn

Extend SCM_PIDFD test scenarios to also cover dead task's pidfd retrieval and reading its exit info. Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: Shuah Khan <shuah(a)kernel.org> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Simon Horman <horms(a)kernel.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: David Rheinsberg <david(a)readahead.eu> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- .../testing/selftests/net/af_unix/scm_pidfd.c | 217 ++++++++++++++---- 1 file changed, 173 insertions(+), 44 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..37e034874034 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../../pidfd/pidfd.h" #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -26,6 +27,8 @@ #define SCM_PIDFD 0x04 #endif +#define CHILD_EXIT_CODE_OK 123 + static void child_die() { exit(1); @@ -126,16 +129,65 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } +struct cmsg_data { + struct ucred *ucred; + int *pidfd; +}; + +static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) +{ + struct cmsghdr *cmsg; + int data = 0; + + if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*res->pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + res->pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*res->ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + res->ucred = (void *)CMSG_DATA(cmsg); + } + } + + if (!res->pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!res->ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + return 0; +} + static int cmsg_check(int fd) { struct msghdr msg = { 0 }; - struct cmsghdr *cmsg; + struct cmsg_data res; struct iovec iov; - struct ucred *ucred = NULL; int data = 0; char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; - int *pidfd = NULL; pid_t parent_pid; int err; @@ -158,53 +210,99 @@ static int cmsg_check(int fd) return 1; } - for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; - cmsg = CMSG_NXTHDR(&msg, cmsg)) { - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_PIDFD) { - if (cmsg->cmsg_len < sizeof(*pidfd)) { - log_err("CMSG parse: SCM_PIDFD wrong len"); - return 1; - } + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } - pidfd = (void *)CMSG_DATA(cmsg); - } + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); + return 1; + } - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_CREDENTIALS) { - if (cmsg->cmsg_len < sizeof(*ucred)) { - log_err("CMSG parse: SCM_CREDENTIALS wrong len"); - return 1; - } + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + close(*res.pidfd); + return 1; + } - ucred = (void *)CMSG_DATA(cmsg); - } + close(*res.pidfd); + return 0; +} + +static int cmsg_check_dead(int fd, int expected_pid) +{ + int err; + struct msghdr msg = { 0 }; + struct cmsg_data res; + struct iovec iov; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + pid_t client_pid; + struct pidfd_info info = { + .mask = PIDFD_INFO_EXIT, + }; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; } - /* send(pfd, "x", sizeof(char), 0) */ - if (data != 'x') { + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + /* send(cfd, "y", sizeof(char), 0) */ + if (data != 'y') { log_err("recvmsg: data corruption"); return 1; } - if (!pidfd) { - log_err("CMSG parse: SCM_PIDFD not found"); + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); return 1; } - if (!ucred) { - log_err("CMSG parse: SCM_CREDENTIALS not found"); + /* + * pidfd from SCM_PIDFD should point to the client_pid. + * Let's read exit information and check if it's what + * we expect to see. + */ + if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) { + log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__); + close(*res.pidfd); return 1; } - /* pidfd from SCM_PIDFD should point to the parent process PID */ - parent_pid = - get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); - if (parent_pid != getppid()) { - log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + if (!(info.mask & PIDFD_INFO_EXIT)) { + log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__); + close(*res.pidfd); return 1; } + err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1; + if (err != CHILD_EXIT_CODE_OK) { + log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK); + close(*res.pidfd); + return 1; + } + + close(*res.pidfd); return 0; } @@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract) memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); } +static int sk_enable_cred_pass(int sk) +{ + int on = 0; + + on = 1; + if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + return 1; + } + + if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + return 1; + } + + return 0; +} + static void client(FIXTURE_DATA(scm_pidfd) *self, const FIXTURE_VARIANT(scm_pidfd) *variant) { @@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, struct ucred peer_cred; int peer_pidfd; pid_t peer_pid; - int on = 0; cfd = socket(AF_UNIX, variant->type, 0); if (cfd < 0) { @@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } - on = 1; - if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { - log_err("Failed to set SO_PASSCRED"); - child_die(); - } - - if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { - log_err("Failed to set SO_PASSPIDFD"); + if (sk_enable_cred_pass(cfd)) { + log_err("sk_enable_cred_pass() failed"); child_die(); } @@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } + /* send something to the parent so it can receive SCM_PIDFD too and validate it */ + if (send(cfd, "y", sizeof(char), 0) == -1) { + log_err("Failed to send(cfd, \"y\", sizeof(char), 0)"); + child_die(); + } + /* skip further for SOCK_DGRAM as it's not applicable */ if (variant->type == SOCK_DGRAM) return; @@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test) close(self->server); close(self->startup_pipe[0]); client(self, variant); - exit(0); + + /* + * It's a bit unusual, but in case of success we return non-zero + * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it + * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead(). + */ + exit(CHILD_EXIT_CODE_OK); } close(self->startup_pipe[1]); @@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test) ASSERT_NE(-1, err); } - close(pfd); waitpid(self->client_pid, &child_status, 0); - ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + /* see comment before exit(CHILD_EXIT_CODE_OK) */ + ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + + err = sk_enable_cred_pass(pfd); + ASSERT_EQ(0, err); + + err = cmsg_check_dead(pfd, self->client_pid); + ASSERT_EQ(0, err); + + close(pfd); } TEST_HARNESS_MAIN -- 2.43.0

5 months, 2 weeks

1
0
0 0

[RFC PATCH v8 0/7] Add NUMA mempolicy support for KVM guest-memfd

by Shivank Garg

This series introduces NUMA-aware memory placement support for KVM guests with guest_memfd memory backends. It builds upon Fuad Tabba's work that enabled host-mapping for guest_memfd memory [1] and can be applied directly on KVM tree (branch:queue, base commit:7915077245) [2]. == Background == KVM's guest-memfd memory backend currently lacks support for NUMA policy enforcement, causing guest memory allocations to be distributed across host nodes according to kernel's default behavior, irrespective of any policy specified by the VMM. This limitation arises because conventional userspace NUMA control mechanisms like mbind(2) don't work since the memory isn't directly mapped to userspace when allocations occur. Fuad's work [1] provides the necessary mmap capability, and this series leverages it to enable mbind(2). == Implementation == This series implements proper NUMA policy support for guest-memfd by: 1. Adding mempolicy-aware allocation APIs to the filemap layer. 2. Introducing custom inodes (via a dedicated slab-allocated inode cache, kvm_gmem_inode_info) to store NUMA policy and metadata for guest memory. 3. Implementing get/set_policy vm_ops in guest_memfd to support NUMA policy. With these changes, VMMs can now control guest memory placement by mapping guest_memfd file descriptor and using mbind(2) to specify: - Policy modes: default, bind, interleave, or preferred - Host NUMA nodes: List of target nodes for memory allocation These Policies affect only future allocations and do not migrate existing memory. This matches mbind(2)'s default behavior which affects only new allocations unless overridden with MPOL_MF_MOVE/MPOL_MF_MOVE_ALL flags (Not supported for guest_memfd as it is unmovable by design). == Upstream Plan == Phased approach as per David's guest_memfd extension overview [3] and community calls [4]: Phase 1 (this series): 1. Focuses on shared guest_memfd support (non-CoCo VMs). 2. Builds on Fuad's host-mapping work. Phase2 (future work): 1. NUMA support for private guest_memfd (CoCo VMs). 2. Depends on SNP in-place conversion support [5]. This series provides a clean integration path for NUMA-aware memory management for guest_memfd and lays the groundwork for future confidential computing NUMA capabilities. Please review and provide feedback! Thanks, Shivank == Changelog == - v1,v2: Extended the KVM_CREATE_GUEST_MEMFD IOCTL to pass mempolicy. - v3: Introduced fbind() syscall for VMM memory-placement configuration. - v4-v6: Current approach using shared_policy support and vm_ops (based on suggestions from David [6] and guest_memfd bi-weekly upstream call discussion [7]). - v7: Use inodes to store NUMA policy instead of file [8]. - v8: Rebase on top of Fuad's V12: Host mmaping for guest_memfd memory. [1] https://lore.kernel.org/all/20250611133330.1514028-1-tabba@google.com [2] https://git.kernel.org/pub/scm/virt/kvm/kvm.git/log/?h=queue [3] https://lore.kernel.org/all/c1c9591d-218a-495c-957b-ba356c8f8e09@redhat.com [4] https://docs.google.com/document/d/1M6766BzdY1Lhk7LiR5IqVR8B8mG3cr-cxTxOrAo… [5] https://lore.kernel.org/all/20250613005400.3694904-1-michael.roth@amd.com [6] https://lore.kernel.org/all/6fbef654-36e2-4be5-906e-2a648a845278@redhat.com [7] https://lore.kernel.org/all/2b77e055-98ac-43a1-a7ad-9f9065d7f38f@amd.com [8] https://lore.kernel.org/all/diqzbjumm167.fsf@ackerleytng-ctop.c.googlers.com Ackerley Tng (1): KVM: guest_memfd: Use guest mem inodes instead of anonymous inodes Shivank Garg (5): security: Export anon_inode_make_secure_inode for KVM guest_memfd mm/mempolicy: Export memory policy symbols KVM: guest_memfd: Add slab-allocated inode cache KVM: guest_memfd: Enforce NUMA mempolicy using shared policy KVM: guest_memfd: selftests: Add tests for mmap and NUMA policy support Shivansh Dhiman (1): mm/filemap: Add mempolicy support to the filemap layer fs/anon_inodes.c | 20 +- include/linux/fs.h | 2 + include/linux/pagemap.h | 41 +++ include/uapi/linux/magic.h | 1 + mm/filemap.c | 27 +- mm/mempolicy.c | 6 + tools/testing/selftests/kvm/Makefile.kvm | 1 + .../testing/selftests/kvm/guest_memfd_test.c | 123 ++++++++- virt/kvm/guest_memfd.c | 254 ++++++++++++++++-- virt/kvm/kvm_main.c | 7 +- virt/kvm/kvm_mm.h | 10 +- 11 files changed, 456 insertions(+), 36 deletions(-) -- 2.43.0 --- == Earlier Postings == v7: https://lore.kernel.org/all/20250408112402.181574-1-shivankg@amd.com v6: https://lore.kernel.org/all/20250226082549.6034-1-shivankg@amd.com v5: https://lore.kernel.org/all/20250219101559.414878-1-shivankg@amd.com v4: https://lore.kernel.org/all/20250210063227.41125-1-shivankg@amd.com v3: https://lore.kernel.org/all/20241105164549.154700-1-shivankg@amd.com v2: https://lore.kernel.org/all/20240919094438.10987-1-shivankg@amd.com v1: https://lore.kernel.org/all/20240916165743.201087-1-shivankg@amd.com

5 months, 2 weeks

8
33
0 0

[PATCH v3 0/3] replace `allow(...)` lints with `expect(...)`

by Onur Özkan

Changes in v3: - `#![expect(internal_features)]` is reverted from `rust/compiler_builtins.rs` which was done in the first 2 versions. Onur Özkan (3): replace `#[allow(...)]` with `#[expect(...)]` rust: remove `#[allow(clippy::unnecessary_cast)]` rust: remove `#[allow(clippy::non_send_fields_in_send_ty)]` drivers/gpu/nova-core/regs.rs | 2 +- rust/kernel/alloc/allocator_test.rs | 2 +- rust/kernel/cpufreq.rs | 1 - rust/kernel/devres.rs | 2 +- rust/kernel/driver.rs | 2 +- rust/kernel/drm/ioctl.rs | 8 ++++---- rust/kernel/error.rs | 3 +-- rust/kernel/init.rs | 6 +++--- rust/kernel/kunit.rs | 2 +- rust/kernel/opp.rs | 4 ++-- rust/kernel/types.rs | 2 +- rust/macros/helpers.rs | 2 +- 12 files changed, 17 insertions(+), 19 deletions(-) -- 2.50.0

5 months, 2 weeks

4
15
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror June 2025