March 2025 - Linux-kselftest-mirror

[PATCH net] selftests: drv-net: use defer in the ping test

by Jakub Kicinski

Make sure the test cleans up after itself. The XDP off statements at the end of the test may not be reached. Fixes: 75cc19c8ff89 ("selftests: drv-net: add xdp cases for ping.py") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: ap420073(a)gmail.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/ping.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index 93f4b411b378..fc69bfcc37c4 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -7,7 +7,7 @@ from lib.py import ksft_run, ksft_exit from lib.py import ksft_eq, KsftSkipEx, KsftFailEx from lib.py import EthtoolFamily, NetDrvEpEnv from lib.py import bkg, cmd, wait_port_listen, rand_port -from lib.py import ethtool, ip +from lib.py import defer, ethtool, ip remote_ifname="" no_sleep=False @@ -60,6 +60,7 @@ no_sleep=False prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True) + defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off") if no_sleep != True: time.sleep(10) @@ -68,7 +69,9 @@ no_sleep=False test_dir = os.path.dirname(os.path.realpath(__file__)) prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog)) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off") if no_sleep != True: time.sleep(10) @@ -78,6 +81,7 @@ no_sleep=False prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0] if xdp_info['xdp']['mode'] != 1: """ @@ -94,10 +98,11 @@ no_sleep=False test_dir = os.path.dirname(os.path.realpath(__file__)) prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) try: cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") except Exception as e: - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) raise KsftSkipEx('device does not support native-multi-buffer XDP') if no_sleep != True: @@ -111,6 +116,7 @@ no_sleep=False cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True) except Exception as e: raise KsftSkipEx('device does not support offloaded XDP') + defer(ip, f"link set dev {cfg.ifname} xdpoffload off") cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) if no_sleep != True: @@ -157,7 +163,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpgeneric off" % cfg.ifname) def test_xdp_generic_mb(cfg, netnl) -> None: _set_xdp_generic_mb_on(cfg) @@ -169,7 +174,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpgeneric off" % cfg.ifname) def test_xdp_native_sb(cfg, netnl) -> None: _set_xdp_native_sb_on(cfg) @@ -181,7 +185,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdp off" % cfg.ifname) def test_xdp_native_mb(cfg, netnl) -> None: _set_xdp_native_mb_on(cfg) @@ -193,14 +196,12 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdp off" % cfg.ifname) def test_xdp_offload(cfg, netnl) -> None: _set_xdp_offload_on(cfg) _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpoffload off" % cfg.ifname) def main() -> None: with NetDrvEpEnv(__file__) as cfg: @@ -213,7 +214,6 @@ no_sleep=False test_xdp_native_mb, test_xdp_offload], args=(cfg, EthtoolFamily())) - set_interface_init(cfg) ksft_exit() -- 2.48.1

6 months, 3 weeks

3
2
0 0

[PATCH v4 00/12] Direct Map Removal for guest_memfd

by Patrick Roy

Unmapping virtual machine guest memory from the host kernel's direct map is a successful mitigation against Spectre-style transient execution issues: If the kernel page tables do not contain entries pointing to guest memory, then any attempted speculative read through the direct map will necessarily be blocked by the MMU before any observable microarchitectural side-effects happen. This means that Spectre-gadgets and similar cannot be used to target virtual machine memory. Roughly 60% of speculative execution issues fall into this category [1, Table 1]. This patch series extends guest_memfd with the ability to remove its memory from the host kernel's direct map, to be able to attain the above protection for KVM guests running inside guest_memfd. === Changes to RFC v3 === - Settle relationship between direct map removal and shared/private memory in guest_memfd (David H.) - Omit TLB flushes upon direct map removal again - Settle uABI for how KVM accesses guest memory in non-CoCo guest_memfd VMs (upstream guest_memfd calls) - Add selftests that exercise the codepaths of non-CoCo guest_memfd VMs Lastly, this series is rebased on top of Fuad's v4 for shared mapping of guest_memfd [2]. The KVM parts should also apply on top of 0ad2507d5d93 ("Linux 6.14-rc3"), but the selftest patches need Fuad's series as base. === Overview === guest_memfd should be usable for "non-CoCo" VMs - virtual machines where host userspace is trusted (e.g. can have access to all of guest memory), but which should still be hardened against speculative execution attacks (Spectre, etc.) staged through potentially existing gadgets in the host kernel. To attain this hardening, unmap guest memory from the host kernels address space (e.g. zap direct map entries), while allowing KVM to continue accessing guest memory through userspace mappings. This works because KVM already almost always uses userspace mappings whenever KVM needs to access guest memory - the only parts that require direct map entries (because they use GUP) are KVM's MMU, and kvm-clock on x86. Building on top of guest_memfd sidesteps the MMU problem, as for memslots with KVM_MEM_GUEST_MEMFD set, the MMU consumes fd + offset directly without going through any VMAs. kvm-clock on the other hand is not strictly needed (guests boot fine without it), so ignore it for now. === Implementation === Make KVM_CREATE_GUEST_MEMFD accept a flag (KVM_GMEM_NO_DIRECT_MAP) that instructs it to remove newly allocated folios from the host kernels direct map immediately after preparation. Nothing further is needed to make non-CoCo VMs work - particularly, KVM does not need to be taught any special ways of accessing guest memory if it is in guest_memfd. Userspace can simply mmap guest_memfd (via KVM_GMEM_SHARED_MEM added in Fuad's series), and set the memslot's userspace_addr to this userspace mapping of guest_memfd. === Open Questions === In this patch series, stale TLB entries do not get flushed after direct map entries are marked as not present. This is fine from a functional point of view (as the mapping is still valid, it's just temporarily not supposed to be used), but pokes a theoretical hole into the speculation protection: Something could try to keep alive stale TLB entries for specific pages until the guest starts using them for sensitive information, and then stage a Spectre attack on that memory, despite it being unmapped. In practice, this would require knowing in advance, at gmem fault-time, which pages will eventually contain information of interest, and then preventing these specific TLB entries from getting naturally evicted (where the number of pages that can be targeted like this is limited by the size of the TLB). These seem to be fairly difficult requisites to fulfill, but we were wondering what the community thinks. === Summary === Patch 1 adds a struct address_space flag that indices that folios in a mapping are direct map removed, and threads it through mm code to ensure direct map removed folios don't end up in places where they can cause mayhem (particularly, we reject them in get_user_pages). Since these checks end up being duplicates of already existing checks for secretmem folios, patch 2 unifies the two by using the new address_space flag for secretmem mappings. Patches 3 through 5 are about support for direct map removal in guest_memfd, while patches 6 through 12 are about testing the non-CoCo setup in KVM selftests, with patches 6 through 9 being preparatory, and patches 10 through 12 adding the actual test cases. [1]: https://download.vusec.net/papers/quarantine_raid23.pdf [2]: https://lore.kernel.org/kvm/20250218172500.807733-1-tabba@google.com/ [RFC v1]: https://lore.kernel.org/kvm/20240709132041.3625501-1-roypat@amazon.co.uk/ [RFC v2]: https://lore.kernel.org/kvm/20240910163038.1298452-1-roypat@amazon.co.uk/ [RFC v3]: https://lore.kernel.org/kvm/20241030134912.515725-1-roypat@amazon.co.uk/ Patrick Roy (12): mm: introduce AS_NO_DIRECT_MAP mm/secretmem: set AS_NO_DIRECT_MAP instead of special-casing KVM: guest_memfd: Add flag to remove from direct map KVM: Add capability to discover KVM_GMEM_NO_DIRECT_MAP support KVM: Documentation: document KVM_GMEM_NO_DIRECT_MAP flag KVM: selftests: load elf via bounce buffer KVM: selftests: set KVM_MEM_GUEST_MEMFD in vm_mem_add() if guest_memfd != -1 KVM: selftests: Add guest_memfd based vm_mem_backing_src_types KVM: selftests: stuff vm_mem_backing_src_type into vm_shape KVM: selftests: adjust test_create_guest_memfd_invalid KVM: selftests: set KVM_GMEM_NO_DIRECT_MAP in mem conversion tests KVM: selftests: Test guest execution from direct map removed gmem Documentation/virt/kvm/api.rst | 13 ++++ include/linux/pagemap.h | 16 +++++ include/linux/secretmem.h | 18 ------ include/uapi/linux/kvm.h | 3 + lib/buildid.c | 4 +- mm/gup.c | 14 +--- mm/mlock.c | 2 +- mm/secretmem.c | 6 +- .../testing/selftests/kvm/guest_memfd_test.c | 2 +- .../testing/selftests/kvm/include/kvm_util.h | 29 ++++++--- .../testing/selftests/kvm/include/test_util.h | 8 +++ tools/testing/selftests/kvm/lib/elf.c | 8 +-- tools/testing/selftests/kvm/lib/io.c | 23 +++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 64 +++++++++++-------- tools/testing/selftests/kvm/lib/test_util.c | 8 +++ tools/testing/selftests/kvm/lib/x86/sev.c | 1 + .../selftests/kvm/pre_fault_memory_test.c | 1 + .../selftests/kvm/set_memory_region_test.c | 40 ++++++++++++ .../kvm/x86/private_mem_conversions_test.c | 7 +- virt/kvm/guest_memfd.c | 24 ++++++- virt/kvm/kvm_main.c | 5 ++ 21 files changed, 214 insertions(+), 82 deletions(-) base-commit: da40655874b54a2b563f8ceb3ed839c6cd38e0b4 -- 2.48.1

6 months, 3 weeks

3
25
0 0

[PATCH v1 1/3] selftests/mm: Fix half_ufd_size_MB calculation

by Ryan Roberts

$half_ufd_size_MB is supposed to be half of the available hugetlb memory expressed in MB. But previously it was calculated in pages since $freepgs is the number of free pages. When huge pages are 2M it doesn't make a whole lot of difference; the number of pages that get used is just halved. But on arm64 with 16K or 64K base pages, the PMD size (and default hugetlb size) is 32M and 512M respectively. So in this case we end up passing a number of MB that is smaller than a single hugetlb page and the test raises an error. Fixes: 2e47a445d7b3 ("selftests/mm: run_vmtests.sh: fix hugetlb mem size calculation") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> --- tools/testing/selftests/mm/run_vmtests.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index da7e26668103..14fa9d40d574 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -304,7 +304,7 @@ uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 # Hugetlb tests require source and destination huge pages. Pass in half # the size of the free pages we have, which is used for *each*. -half_ufd_size_MB=$((freepgs / 2)) +half_ufd_size_MB=$(((freepgs * hpgsize_KB / 2) / 1024)) CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 -- 2.43.0

6 months, 3 weeks

3
9
0 0

[PATCH] rseq/selftests: ensure the rseq abi TLS is actually 1024 bytes

by Michael Jeanson

Adding the aligned(1024) attribute to the definition of __rseq_abi did not increase its size to 1024, for this attribute to impact the size of __rseq_abi it would need to be added to the declaration of 'struct rseq_abi'. We only want to increase the size of the TLS allocation to ensure registration will succeed with future extended ABI. Use a union with a dummy member to ensure we allocate 1024 bytes. Signed-off-by: Michael Jeanson <mjeanson(a)efficios.com> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> --- tools/testing/selftests/rseq/rseq.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index f6156790c3b4..aa9ae866bc1a 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -71,9 +71,20 @@ static int rseq_ownership; /* Original struct rseq allocation size is 32 bytes. */ #define ORIG_RSEQ_ALLOC_SIZE 32 +/* + * Use a union to ensure we allocate a TLS area of 1024 bytes to accomodate an + * rseq registration that is larger than the current rseq ABI. + */ +union rseq { + struct rseq_abi abi; + char dummy[RSEQ_THREAD_AREA_ALLOC_SIZE]; +}; + static -__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"), aligned(RSEQ_THREAD_AREA_ALLOC_SIZE))) = { - .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, +__thread union rseq __rseq __attribute__((tls_model("initial-exec"))) = { + .abi = { + .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, + }, }; static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len, @@ -149,7 +160,7 @@ int rseq_register_current_thread(void) /* Treat libc's ownership as a successful registration. */ return 0; } - rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); + rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); if (rc) { /* * After at least one thread has registered successfully @@ -183,7 +194,7 @@ int rseq_unregister_current_thread(void) /* Treat libc's ownership as a successful unregistration. */ return 0; } - rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); if (rc) return -1; return 0; @@ -249,7 +260,7 @@ void rseq_init(void) rseq_ownership = 1; /* Calculate the offset of the rseq area from the thread pointer. */ - rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + rseq_offset = (void *)&__rseq.abi - rseq_thread_pointer(); /* rseq flags are deprecated, always set to 0. */ rseq_flags = 0; -- 2.43.0

6 months, 3 weeks

2
3
0 0

[PATCH 00/13] selftests/bpf: Integrate test_xsk.c to test_progs framework

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the script tests into prog_tests. The test_xsk.sh script tests lots of AF_XDP use cases. The tests it uses are defined in xksxceiver.c. As this script is used to test real hardware, the goal here is to keep it as is and only integrate the tests on veth peers into the test_progs framework. Three tests are flaky on s390 so they won't be integrated to test_progs yet (I'm currently trying to make them more robust). PATCH 1 & 2 fix some small issues xskxceiver.c PATCH 3 to 9 rework the xskxceiver to ease the integration in the test_progs framework. Two main points are addressed in them : - wrap kselftest calls behind macros to ease their replacement later - handle all errors to release resources instead of calling exit() when any error occurs. PATCH 10 extracts test_xsk[.c/.h] from xskxceiver[.c/.h] to make the tests available to test_progs PATCH 11 enables kselftest de-activation PATCH 12 isolates the flaky tests PATCH 13 integrate the non-flaky tests to the test_progs framework Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (13): selftests/bpf: test_xsk: Initialize bitmap before use selftests/bpf: test_xsk: Fix memory leaks selftests/bpf: test_xsk: Wrap ksft_*() behind macros selftests/bpf: test_xsk: Add return value to init_iface() selftests/bpf: test_xsk: Don't exit immediately when xsk_attach fails selftests/bpf: test_xsk: Don't exit immediately when gettimeofday fails selftests/bpf: test_xsk: Don't exit immediately when workers fail selftests/bpf: test_xsk: Don't exit immediately if validate_traffic fails selftests/bpf: test_xsk: Don't exit immediately on allocation failures selftests/bpf: test_xsk: Split xskxceiver selftests/bpf: test_xsk: Make kselftest dependency optional selftests/bpf: test_xsk: Isolate flaky tests selftests/bpf: test_xsk: Integrate test_xsk.c to test_progs framework tools/testing/selftests/bpf/Makefile | 13 +- tools/testing/selftests/bpf/prog_tests/test_xsk.c | 2416 ++++++++++++++++++++ tools/testing/selftests/bpf/prog_tests/test_xsk.h | 299 +++ tools/testing/selftests/bpf/prog_tests/xsk.c | 178 ++ tools/testing/selftests/bpf/xskxceiver.c | 2543 +-------------------- tools/testing/selftests/bpf/xskxceiver.h | 153 -- 6 files changed, 3021 insertions(+), 2581 deletions(-) --- base-commit: 720c696b16a1b1680f64cac9b3bb9e312a23ac47 change-id: 20250218-xsk-0cf90e975d14 Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

6 months, 3 weeks

3
18
0 0

[PATCH 1/2] selftests/pid_namespace: fix building with clang-20

by Dmitry Antipov

When using 'make LLVM=1 W=1 -C tools/testing/selftests/pid_namespace' with clang-20, I've noticed the following: pid_max.c:42:8: error: call to undeclared function 'mount'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 42 | ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); | ^ pid_max.c:42:29: error: use of undeclared identifier 'MS_PRIVATE' 42 | ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); | ^ ... So include '<sys/mount.h>' to add all of the required declarations. Signed-off-by: Dmitry Antipov <dmantipov(a)yandex.ru> --- tools/testing/selftests/pid_namespace/pid_max.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c index 51c414faabb0..972bedc475f1 100644 --- a/tools/testing/selftests/pid_namespace/pid_max.c +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -11,6 +11,7 @@ #include <string.h> #include <syscall.h> #include <sys/wait.h> +#include <sys/mount.h> #include "../kselftest_harness.h" #include "../pidfd/pidfd.h" -- 2.48.1

6 months, 3 weeks

2
2
0 0

[PATCH v4 iproute2-next 0/1] DualPI2 iproute2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find DUALPI2 iproute2 patch v4. v4 - Add min_qlen_step to dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step amrking. v3 - Add memlimit to dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update manual to align latest implementation and clarify the queue naming and default unit - Use common "get_scaled_alpha_beta" and clean print_opt for Dualpi2 v2 - Rename get_float in dualpi2 to get_float_min_max in utils.c - Move get_float from iplink_can.c in utils.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Add print function for JSON of dualpi2 (Stephen Hemminger <stephen(a)networkplumber.org>) For more details of DualPI2, plesae refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best Regards, Chia-Yu Chia-Yu Chang (1): tc: add dualpi2 scheduler module bash-completion/tc | 11 +- include/uapi/linux/pkt_sched.h | 39 +++ include/utils.h | 2 + ip/iplink_can.c | 14 - lib/utils.c | 30 ++ man/man8/tc-dualpi2.8 | 249 ++++++++++++++++ tc/Makefile | 1 + tc/q_dualpi2.c | 508 +++++++++++++++++++++++++++++++++ 8 files changed, 839 insertions(+), 15 deletions(-) create mode 100644 man/man8/tc-dualpi2.8 create mode 100644 tc/q_dualpi2.c -- 2.34.1

6 months, 3 weeks

3
7
0 0

[PATCH 0/2] selftests: livepatch: test if ftrace can trace a livepatched function

by Filipe Xavier

This patchset add ftrace helpers functions and add a new test makes sure that ftrace can trace a function that was introduced by a livepatch. Signed-off-by: Filipe Xavier <felipeaggger(a)gmail.com> --- Filipe Xavier (2): selftests: livepatch: add new ftrace helpers functions selftests: livepatch: test if ftrace can trace a livepatched function tools/testing/selftests/livepatch/functions.sh | 45 ++++++++++++++++++++++++ tools/testing/selftests/livepatch/test-ftrace.sh | 35 ++++++++++++++++++ 2 files changed, 80 insertions(+) --- base-commit: 848e076317446f9c663771ddec142d7c2eb4cb43 change-id: 20250306-ftrace-sftest-livepatch-60d9dc472235 Best regards, -- Filipe Xavier <felipeaggger(a)gmail.com>

6 months, 3 weeks

3
7
0 0

[PATCH] tools/nolibc: Add support for SPARC

by Thomas Weißschuh

Add support for 32bit and 64bit SPARC to nolibc. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- This is only tested on QEMU. Any tests on real hardware would be very welcome. --- tools/include/nolibc/arch-sparc.h | 191 ++++++++++++++++++++++++++++ tools/include/nolibc/arch.h | 2 + tools/testing/selftests/nolibc/Makefile | 11 ++ tools/testing/selftests/nolibc/run-tests.sh | 2 + 4 files changed, 206 insertions(+) diff --git a/tools/include/nolibc/arch-sparc.h b/tools/include/nolibc/arch-sparc.h new file mode 100644 index 0000000000000000000000000000000000000000..cb5543eca87bb4d52cfba4c0668e35cbbf6dd124 --- /dev/null +++ b/tools/include/nolibc/arch-sparc.h @@ -0,0 +1,191 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * SPARC (32bit and 64bit) specific definitions for NOLIBC + * Copyright (C) 2025 Thomas Weißschuh <linux(a)weissschuh.net> + */ + +#ifndef _NOLIBC_ARCH_SPARC_H +#define _NOLIBC_ARCH_SPARC_H + +#include <linux/unistd.h> + +#include "compiler.h" +#include "crt.h" + +/* + * Syscalls for SPARC: + * - registers are native word size + * - syscall number is passed in g1 + * - arguments are in o0-o5 + * - the system call is performed by calling a trap instruction + * - syscall return value is in 0a + * - syscall error flag is in the carry bit of the processor status register + */ + +#ifdef __arch64__ + +#define _NOLIBC_SYSCALL "t 0x6d\n" \ + "bcs,a %%xcc, 1f\n" \ + "sub %%g0, %%o0, %%o0\n" \ + "1:\n" + +#else + +#define _NOLIBC_SYSCALL "t 0x10\n" \ + "bcs,a 1f\n" \ + "sub %%g0, %%o0, %%o0\n" \ + "1:\n" + +#endif /* __arch64__ */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0"); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + register long _arg5 __asm__ ("o4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + register long _arg5 __asm__ ("o4") = (long)(arg5); \ + register long _arg6 __asm__ ("o5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) +{ + __asm__ volatile ( + /* + * Save stack pointer to o0, as arg1 of _start_c. + * Account for window save area and stack bias. + */ +#ifdef __arch64__ + "add %sp, 128 + 2047, %o0\n" +#else + "add %sp, 64, %o0\n" +#endif + "b,a _start_c\n" /* transfer to c runtime */ + ); + __nolibc_entrypoint_epilogue(); +} + +static pid_t getpid(void); + +static __attribute__((unused)) +pid_t sys_fork(void) +{ + pid_t parent, ret; + + parent = getpid(); + ret = my_syscall0(__NR_fork); + + /* The syscall returns the parent pid in the child instead of 0 */ + if (ret == parent) + return 0; + else + return ret; +} +#define sys_fork sys_fork + +#endif /* _NOLIBC_ARCH_SPARC_H */ diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 8a2c143c0fba288147e5a7bf9db38ffb08367616..b8c1da9a88d1593d5a97f60909ede5d0c17699eb 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -33,6 +33,8 @@ #include "arch-s390.h" #elif defined(__loongarch__) #include "arch-loongarch.h" +#elif defined(__sparc__) +#include "arch-sparc.h" #else #error Unsupported Architecture #endif diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 58bcbbd029bc3ad9ccac968191b703ccf5df0717..5060e189dc842d761dd13d70b8afdb2ff3390bc5 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -56,6 +56,8 @@ ARCH_mips32be = mips ARCH_riscv32 = riscv ARCH_riscv64 = riscv ARCH_s390x = s390 +ARCH_sparc32 = sparc +ARCH_sparc64 = sparc ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) # kernel image names by architecture @@ -76,6 +78,8 @@ IMAGE_riscv64 = arch/riscv/boot/Image IMAGE_s390x = arch/s390/boot/bzImage IMAGE_s390 = arch/s390/boot/bzImage IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi +IMAGE_sparc32 = arch/sparc/boot/image +IMAGE_sparc64 = arch/sparc/boot/image IMAGE = $(objtree)/$(IMAGE_$(XARCH)) IMAGE_NAME = $(notdir $(IMAGE)) @@ -97,6 +101,8 @@ DEFCONFIG_riscv64 = defconfig DEFCONFIG_s390x = defconfig DEFCONFIG_s390 = defconfig compat.config DEFCONFIG_loongarch = defconfig +DEFCONFIG_sparc32 = sparc32_defconfig +DEFCONFIG_sparc64 = sparc64_defconfig DEFCONFIG = $(DEFCONFIG_$(XARCH)) EXTRACONFIG = $(EXTRACONFIG_$(XARCH)) @@ -122,6 +128,8 @@ QEMU_ARCH_riscv64 = riscv64 QEMU_ARCH_s390x = s390x QEMU_ARCH_s390 = s390x QEMU_ARCH_loongarch = loongarch64 +QEMU_ARCH_sparc32 = sparc +QEMU_ARCH_sparc64 = sparc64 QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) QEMU_ARCH_USER_ppc64le = ppc64le @@ -152,6 +160,8 @@ QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_T QEMU_ARGS_s390x = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise @@ -174,6 +184,7 @@ CFLAGS_s390x = -m64 CFLAGS_s390 = -m31 CFLAGS_mips32le = -EL -mabi=32 -fPIC CFLAGS_mips32be = -EB -mabi=32 +CFLAGS_sparc32 = $(call cc-option,-m32) CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ $(call cc-option,-fno-stack-protector) $(call cc-option,-Wmissing-prototypes) \ diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index 0299a0912d4049dd12217f9835b81d231e1d2bfd..040956a9f5b8dda3e78abc0d4b6073f4fcd9e3ee 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -25,6 +25,7 @@ all_archs=( riscv32 riscv64 s390x s390 loongarch + sparc32 sparc64 ) archs="${all_archs[@]}" @@ -111,6 +112,7 @@ crosstool_arch() { loongarch) echo loongarch64;; mips*) echo mips;; s390*) echo s390;; + sparc*) echo sparc64;; *) echo "$1";; esac } --- base-commit: bceb73904c855c78402dca94c82915f078f259dd change-id: 20250226-nolibc-sparc-abf4775dc813 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

6 months, 3 weeks

3
5
0 0

[PATCH v9 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vEVENTQ)

by Nicolin Chen

As the vIOMMU infrastructure series part-3, this introduces a new vEVENTQ object. The existing FAULT object provides a nice notification pathway to the user space with a queue already, so let vEVENTQ reuse that. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VEVENTQ (new). An IOMMUFD_CMD_VEVENTQ_ALLOC is introduced to allocate vEVENTQ object for vIOMMUs. One vIOMMU can have multiple vEVENTQs in different types but can not support multiple vEVENTQs in the same type. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level event data structure. So, this also adds some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new ioctl and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v9 Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_veventq-v9 Changelog v9 * Add Acked-by from Will * Fix typo in commit logs and reviewer name * Allow invaid nested STE for C_BAD_STE report * Drop extra indentation in arm_smmu_handle_event() * Drop comments in arm_smmu_attach_prepare_vmaster() v8 https://lore.kernel.org/all/cover.1740504232.git.nicolinc@nvidia.com/ * Add Reviewed-by from Jason and Pranjal * Fix errno returned in arm_smmu_handle_event() * Validate domain->type outside of arm_smmu_attach_prepare_vmaster() * Drop unnecessary vmaster comparison in arm_smmu_attach_commit_vmaster() v7 https://lore.kernel.org/all/cover.1740238876.git.nicolinc@nvidia.com/ * Rebase on Jason's for-next tree for latest fault.c * Add Reviewed-by * Update commit logs * Add __reserved field sanity * Skip kfree() on the static header * Replace "bool on_list" with list_is_last() * Use u32 for flags in iommufd_vevent_header * Drop casting in iommufd_viommu_get_vdev_id() * Update the bounding logic to veventq->sequence * Add missing cpu_to_le64() around STRTAB_STE_1_MEV * Reuse veventq->common.lock to fence sequence and num_events * Rename overflow to lost_events and log it in upon kmalloc failure * Correct the error handling part in iommufd_veventq_deliver_fetch() * Add an arm_smmu_clear_vmaster() to simplify identity/blocked domain attach ops * Add additional four event records to forward to user space VM, and update the uAPI doc * Reuse the existing smmu->streams_mutex lock to fence master->vmaster pointer, instead of adding a new rwsem v6 https://lore.kernel.org/all/cover.1737754129.git.nicolinc@nvidia.com/ * Drop supports_veventq viommu op * Split bug/cosmetics fixes out of the series * Drop the blocking mutex around copy_to_user() * Add veventq_depth in uAPI to limit vEVENTQ size * Revise the documentation for a clear description * Fix sparse warnings in arm_vmaster_report_event() * Rework iommufd_viommu_get_vdev_id() to return -ENOENT v.s. 0 * Allow Abort/Bypass STEs to allocate vEVENTQ and set STE.MEV for DoS mitigations v5 https://lore.kernel.org/all/cover.1736237481.git.nicolinc@nvidia.com/ * Add Reviewed-by from Baolu * Reorder the OBJ list as well * Fix alphabetical order after renaming in v4 * Add supports_veventq viommu op for vEVENTQ type validation v4 https://lore.kernel.org/all/cover.1735933254.git.nicolinc@nvidia.com/ * Rename "vIRQ" to "vEVENTQ" * Use flexible array in struct iommufd_vevent * Add the new ioctl command to union ucmd_buffer * Fix the alphabetical order in union ucmd_buffer too * Rename _TYPE_NONE to _TYPE_DEFAULT aligning with vIOMMU naming v3 https://lore.kernel.org/all/cover.1734477608.git.nicolinc@nvidia.com/ * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd/fault: Move two fault functions out of the header iommufd/fault: Add an iommufd_fault_init() helper iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VEVENTQ and IOMMUFD_CMD_VEVENTQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_event helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VEVENT for vEVENTQ coverage iommufd/selftest: Add IOMMU_VEVENTQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VEVENTQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report events that belong to devices attached to vIOMMU iommu/arm-smmu-v3: Set MEV bit in nested STE for DoS mitigations drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 36 ++ drivers/iommu/iommufd/iommufd_private.h | 135 +++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 23 + include/uapi/linux/iommufd.h | 105 +++ tools/testing/selftests/iommu/iommufd_utils.h | 115 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 60 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 80 ++- drivers/iommu/iommufd/driver.c | 72 +++ drivers/iommu/iommufd/eventq.c | 597 ++++++++++++++++++ drivers/iommu/iommufd/fault.c | 342 ---------- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 7 + drivers/iommu/iommufd/selftest.c | 54 ++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 36 ++ .../selftests/iommu/iommufd_fail_nth.c | 7 + Documentation/userspace-api/iommufd.rst | 17 + 19 files changed, 1298 insertions(+), 408 deletions(-) create mode 100644 drivers/iommu/iommufd/eventq.c delete mode 100644 drivers/iommu/iommufd/fault.c base-commit: a05df03a88bc1088be8e9d958f208d6484691e43 -- 2.43.0

6 months, 3 weeks

2
15
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror March 2025