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

[PATCH net-next v4] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> --- v4 changes: - fix "else should follow close brace" (checkpatch ERROR) v3 changes: - add usleep instead of busy polling on sendmsg - simplify error handling by using error() and leaving cleanup to O/S - use loopback interface - don't bother creating TAP - send to localhost (::1) v2 changes: - remove superfluous namespace calls - unshare(2) suffices - remove usleep(). Don't wait for the interface to be ready, just send, and handle the (less likely) error case by retrying. - set destination address only once - document our use of the IPv6 link-local source address - send to port 9 (DISCARD) instead of 4242 (DONT PANIC) - ensure sockets are closed on failure paths - use KSFT exit codes for clarity v3: https://lore.kernel.org/netdev/20250901112248.5218-1-bacs@librecast.net v2: https://lore.kernel.org/netdev/20250831102908.14655-1-bacs@librecast.net v1: https://lore.kernel.org/netdev/20250825092548.4436-3-bacs@librecast.net tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 144 ++++++++++++++++++ 3 files changed, 146 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index eef0b8f8a7b0..276e0481d996 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation TEST_PROGS += route_hint.sh # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..6d1311e26501 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected stable + * kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable + * without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue by sending an IPv6 UDP packet to + * localhost (::1) on the loopback interface from the autoconfigured link-local + * address. + * + * sendmsg(2) returns bytes sent correctly on a working kernel, and returns -1 + * (EMSGSIZE) when the regression is present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <error.h> +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> +#include "../kselftest.h" + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* bring up interface */ +static int interface_up(int ctl, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) + error(KSFT_FAIL, errno, "ioctl SIOCGIFFLAGS"); + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) + error(KSFT_FAIL, errno, "open accept_dad"); + if (write(fd, "0", 1) != 1) + error(KSFT_FAIL, errno, "write accept_dad"); + + return close(fd); +} + +static int setup(void) +{ + struct ifreq ifr = { + .ifr_name = "lo" + }; + int fd = -1; + int ctl; + + /* we need to set MTU, so do this in a namespace to play nicely */ + if (unshare(CLONE_NEWNET) == -1) + error(KSFT_FAIL, errno, "unshare"); + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + error(KSFT_FAIL, errno, "socket"); + + /* ensure MTU is smaller than what we plan to send */ + ifr.ifr_mtu = MTU; + if (ioctl(ctl, SIOCSIFMTU, &ifr) == -1) + error(KSFT_FAIL, errno, "ioctl: set MTU"); + + disable_dad("lo"); + interface_up(ctl, &ifr); + + close(ctl); + return fd; +} + +int main(void) +{ + struct in6_addr addr = { + .s6_addr[15] = 0x01, /* ::1 */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 9 /* port 9/udp (DISCARD) */ + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int err = KSFT_FAIL; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + s = socket(AF_INET6, SOCK_DGRAM, 0); +send_again: + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + /* if interface wasn't ready, try again */ + if (errno == EADDRNOTAVAIL) { + usleep(1000); + goto send_again; + } + printf("[FAIL] sendmsg: %s\n", strerror(errno)); + } else if (rc != LARGER_THAN_MTU) { + printf("[FAIL] sendmsg() returned %zi, expected %i\n", rc, LARGER_THAN_MTU); + } else { + printf("[PASS] sendmsg() returned %zi\n", rc); + err = KSFT_PASS; + } + close(s); + close(ns_fd); + return err; +} base-commit: 864ecc4a6dade82d3f70eab43dad0e277aa6fc78 -- 2.49.1

3 months, 1 week

3
2
0 0

[PATCH 2/9] KVM: selftests: Add __packed attribute fallback

by Aqib Faruqui

Kernel UAPI headers use __packed but don't provide the definition in userspace builds. Add a fallback definition matching the kernel's implementation. This follows the same pattern used by BPF and SGX selftests. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/include/kvm_util.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 23a506d7e..7fae7f5e7 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -5,6 +5,10 @@ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H +#ifndef __packed +#define __packed __attribute__((__packed__)) +#endif + #include "test_util.h" #include <linux/compiler.h> -- 2.47.3

3 months, 1 week

3
2
0 0

[PATCH] selftests/mm: directly add pagesize instead of increase until page size

by Wei Yang

The check of is_backed_by_folio() is done on each page. Directly move pointer to next page instead of increase one and check if it is page size aligned. Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> --- tools/testing/selftests/mm/split_huge_page_test.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 10ae65ea032f..7f7016ba4054 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -423,9 +423,8 @@ static void split_pte_mapped_thp(void) /* smap does not show THPs after mremap, use kpageflags instead */ thp_size = 0; - for (i = 0; i < pagesize * 4; i++) - if (i % pagesize == 0 && - is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd)) + for (i = 0; i < pagesize * 4; i += pagesize) + if (is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd)) thp_size++; if (thp_size != 4) -- 2.34.1

3 months, 1 week

4
8
0 0

[PATCH v7 00/29] KVM: arm64: Implement support for SME

by Mark Brown

I've removed the RFC tag from this version of the series, but the items that I'm looking for feedback on remains the same: - The userspace ABI, in particular: - The vector length used for the SVE registers, access to the SVE registers and access to ZA and (if available) ZT0 depending on the current state of PSTATE.{SM,ZA}. - The use of a single finalisation for both SVE and SME. - The addition of control for enabling fine grained traps in a similar manner to FGU but without the UNDEF, I'm not clear if this is desired at all and at present this requires symmetric read and write traps like FGU. That seemed like it might be desired from an implementation point of view but we already have one case where we enable an asymmetric trap (for ARM64_WORKAROUND_AMPERE_AC03_CPU_38) and it seems generally useful to enable asymmetrically. This series implements support for SME use in non-protected KVM guests. Much of this is very similar to SVE, the main additional challenge that SME presents is that it introduces a new vector length similar to the SVE vector length and two new controls which change the registers seen by guests: - PSTATE.ZA enables the ZA matrix register and, if SME2 is supported, the ZT0 LUT register. - PSTATE.SM enables streaming mode, a new floating point mode which uses the SVE register set with the separately configured SME vector length. In streaming mode implementation of the FFR register is optional. It is also permitted to build systems which support SME without SVE, in this case when not in streaming mode no SVE registers or instructions are available. Further, there is no requirement that there be any overlap in the set of vector lengths supported by SVE and SME in a system, this is expected to be a common situation in practical systems. Since there is a new vector length to configure we introduce a new feature parallel to the existing SVE one with a new pseudo register for the streaming mode vector length. Due to the overlap with SVE caused by streaming mode rather than finalising SME as a separate feature we use the existing SVE finalisation to also finalise SME, a new define KVM_ARM_VCPU_VEC is provided to help make user code clearer. Finalising SVE and SME separately would introduce complication with register access since finalising SVE makes the SVE registers writeable by userspace and doing multiple finalisations results in an error being reported. Dealing with a state where the SVE registers are writeable due to one of SVE or SME being finalised but may have their VL changed by the other being finalised seems like needless complexity with minimal practical utility, it seems clearer to just express directly that only one finalisation can be done in the ABI. Access to the floating point registers follows the architecture: - When both SVE and SME are present: - If PSTATE.SM == 0 the vector length used for the Z and P registers is the SVE vector length. - If PSTATE.SM == 1 the vector length used for the Z and P registers is the SME vector length. - If only SME is present: - If PSTATE.SM == 0 the Z and P registers are inaccessible and the floating point state accessed via the encodings for the V registers. - If PSTATE.SM == 1 the vector length used for the Z and P registers - The SME specific ZA and ZT0 registers are only accessible if SVCR.ZA is 1. The VMM must understand this, in particular when loading state SVCR should be configured before other state. It should be noted that while the architecture refers to PSTATE.SM and PSTATE.ZA these PSTATE bits are not preserved in SPSR_ELx, they are only accessible via SVCR. There are a large number of subfeatures for SME, most of which only offer additional instructions but some of which (SME2 and FA64) add architectural state. These are configured via the ID registers as per usual. Protected KVM supported, with the implementation maintaining the existing restriction that the hypervisor will refuse to run if streaming mode or ZA is enabled. This both simplfies the code and avoids the need to allocate storage for host ZA and ZT0 state, there seems to be little practical use case for supporting this and the memory usage would be non-trivial. The new KVM_ARM_VCPU_VEC feature and ZA and ZT0 registers have not been added to the get-reg-list selftest, the idea of supporting additional features there without restructuring the program to generate all possible feature combinations has been rejected. I will post a separate series which does that restructuring. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v7: - Rebase onto v6.17-rc1. - Handle SMIDR_EL1 as a VM wide ID register and use this in feat_sme_smps(). - Expose affinity fields in SMIDR_EL1. - Remove SMPRI_EL1 from vcpu_sysreg, the value is always 0 currently. - Prevent userspace writes to SMPRIMAP_EL2. - Link to v6: https://lore.kernel.org/r/20250625-kvm-arm64-sme-v6-0-114cff4ffe04@kernel.o… Changes in v6: - Rebase onto v6.16-rc3. - Link to v5: https://lore.kernel.org/r/20250417-kvm-arm64-sme-v5-0-f469a2d5f574@kernel.o… Changes in v5: - Rebase onto v6.15-rc2. - Add pKVM guest support. - Always restore SVCR. - Link to v4: https://lore.kernel.org/r/20250214-kvm-arm64-sme-v4-0-d64a681adcc2@kernel.o… Changes in v4: - Rebase onto v6.14-rc2 and Mark Rutland's fixes. - Expose SME to nested guests. - Additional cleanups and test fixes following on from the rebase. - Flush register state on VMM PSTATE.{SM,ZA}. - Link to v3: https://lore.kernel.org/r/20241220-kvm-arm64-sme-v3-0-05b018c1ffeb@kernel.o… Changes in v3: - Rebase onto v6.12-rc2. - Link to v2: https://lore.kernel.org/r/20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.o… Changes in v2: - Rebase onto v6.7-rc3. - Configure subfeatures based on host system only. - Complete nVHE support. - There was some snafu with sending v1 out, it didn't make it to the lists but in case it hit people's inboxes I'm sending as v2. --- Mark Brown (29): arm64/sysreg: Update SMIDR_EL1 to DDI0601 2025-06 arm64/fpsimd: Update FA64 and ZT0 enables when loading SME state arm64/fpsimd: Decide to save ZT0 and streaming mode FFR at bind time arm64/fpsimd: Check enable bit for FA64 when saving EFI state arm64/fpsimd: Determine maximum virtualisable SME vector length KVM: arm64: Introduce non-UNDEF FGT control KVM: arm64: Pay attention to FFR parameter in SVE save and load KVM: arm64: Pull ctxt_has_ helpers to start of sysreg-sr.h KVM: arm64: Move SVE state access macros after feature test macros KVM: arm64: Rename SVE finalization constants to be more general KVM: arm64: Document the KVM ABI for SME KVM: arm64: Define internal features for SME KVM: arm64: Rename sve_state_reg_region KVM: arm64: Store vector lengths in an array KVM: arm64: Implement SME vector length configuration KVM: arm64: Support SME control registers KVM: arm64: Support TPIDR2_EL0 KVM: arm64: Support SME identification registers for guests KVM: arm64: Support SME priority registers KVM: arm64: Provide assembly for SME register access KVM: arm64: Support userspace access to streaming mode Z and P registers KVM: arm64: Flush register state on writes to SVCR.SM and SVCR.ZA KVM: arm64: Expose SME specific state to userspace KVM: arm64: Context switch SME state for guests KVM: arm64: Handle SME exceptions KVM: arm64: Expose SME to nested guests KVM: arm64: Provide interface for configuring and enabling SME for guests KVM: arm64: selftests: Add SME system registers to get-reg-list KVM: arm64: selftests: Add SME to set_id_regs test Documentation/virt/kvm/api.rst | 117 +++++++---- arch/arm64/include/asm/fpsimd.h | 26 +++ arch/arm64/include/asm/kvm_emulate.h | 6 + arch/arm64/include/asm/kvm_host.h | 169 ++++++++++++--- arch/arm64/include/asm/kvm_hyp.h | 5 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/include/asm/vncr_mapping.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 33 +++ arch/arm64/kernel/cpufeature.c | 2 - arch/arm64/kernel/fpsimd.c | 89 ++++---- arch/arm64/kvm/arm.c | 10 + arch/arm64/kvm/config.c | 8 +- arch/arm64/kvm/fpsimd.c | 28 ++- arch/arm64/kvm/guest.c | 252 ++++++++++++++++++++--- arch/arm64/kvm/handle_exit.c | 14 ++ arch/arm64/kvm/hyp/fpsimd.S | 28 ++- arch/arm64/kvm/hyp/include/hyp/switch.h | 175 ++++++++++++++-- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 110 ++++++---- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 86 ++++++-- arch/arm64/kvm/hyp/nvhe/pkvm.c | 85 ++++++-- arch/arm64/kvm/hyp/nvhe/switch.c | 4 +- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 6 + arch/arm64/kvm/hyp/vhe/switch.c | 17 +- arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 7 + arch/arm64/kvm/nested.c | 3 +- arch/arm64/kvm/reset.c | 156 ++++++++++---- arch/arm64/kvm/sys_regs.c | 141 ++++++++++++- arch/arm64/tools/sysreg | 8 +- include/uapi/linux/kvm.h | 1 + tools/testing/selftests/kvm/arm64/get-reg-list.c | 15 +- tools/testing/selftests/kvm/arm64/set_id_regs.c | 27 ++- 31 files changed, 1328 insertions(+), 304 deletions(-) --- base-commit: 062b3e4a1f880f104a8d4b90b767788786aa7b78 change-id: 20230301-kvm-arm64-sme-06a1246d3636 Best regards, -- Mark Brown <broonie(a)kernel.org>

3 months, 1 week

3
31
0 0

[PATCH v1 00/36] mm: remove nth_page()

by David Hildenbrand

This is based on mm-unstable. I will only CC non-MM folks on the cover letter and the respective patch to not flood too many inboxes (the lists receive all patches). -- As discussed recently with Linus, nth_page() is just nasty and we would like to remove it. To recap, the reason we currently need nth_page() within a folio is because on some kernel configs (SPARSEMEM without SPARSEMEM_VMEMMAP), the memmap is allocated per memory section. While buddy allocations cannot cross memory section boundaries, hugetlb and dax folios can. So crossing a memory section means that "page++" could do the wrong thing. Instead, nth_page() on these problematic configs always goes from page->pfn, to the go from (++pfn)->page, which is rather nasty. Likely, many people have no idea when nth_page() is required and when it might be dropped. We refer to such problematic PFN ranges and "non-contiguous pages". If we only deal with "contiguous pages", there is not need for nth_page(). Besides that "obvious" folio case, we might end up using nth_page() within CMA allocations (again, could span memory sections), and in one corner case (kfence) when processing memblock allocations (again, could span memory sections). So let's handle all that, add sanity checks, and remove nth_page(). Patch #1 -> #5 : stop making SPARSEMEM_VMEMMAP user-selectable + cleanups Patch #6 -> #13 : disallow folios to have non-contiguous pages Patch #14 -> #20 : remove nth_page() usage within folios Patch #21 : disallow CMA allocations of non-contiguous pages Patch #22 -> #32 : sanity+check + remove nth_page() usage within SG entry Patch #33 : sanity-check + remove nth_page() usage in unpin_user_page_range_dirty_lock() Patch #34 : remove nth_page() in kfence Patch #35 : adjust stale comment regarding nth_page Patch #36 : mm: remove nth_page() A lot of this is inspired from the discussion at [1] between Linus, Jason and me, so cudos to them. [1] https://lore.kernel.org/all/CAHk-=wiCYfNp4AJLBORU-c7ZyRBUp66W2-Et6cdQ4REx-G… RFC -> v1: * "wireguard: selftests: remove CONFIG_SPARSEMEM_VMEMMAP=y from qemu kernel config" -> Mention that it was never really relevant for the test * "mm/mm_init: make memmap_init_compound() look more like prep_compound_page()" -> Mention the setup of page links * "mm: limit folio/compound page sizes in problematic kernel configs" -> Improve comment for PUD handling, mentioning hugetlb and dax * "mm: simplify folio_page() and folio_page_idx()" -> Call variable "n" * "mm/hugetlb: cleanup hugetlb_folio_init_tail_vmemmap()" -> Keep __init_single_page() and refer to the usage of memblock_reserved_mark_noinit() * "fs: hugetlbfs: cleanup folio in adjust_range_hwpoison()" * "fs: hugetlbfs: remove nth_page() usage within folio in adjust_range_hwpoison()" -> Separate nth_page() removal from cleanups -> Further improve cleanups * "io_uring/zcrx: remove nth_page() usage within folio" -> Keep the io_copy_cache for now and limit to nth_page() removal * "mm/gup: drop nth_page() usage within folio when recording subpages" -> Cleanup record_subpages as bit * "mm/cma: refuse handing out non-contiguous page ranges" -> Replace another instance of "pfn_to_page(pfn)" where we already have the page * "scatterlist: disallow non-contigous page ranges in a single SG entry" -> We have to EXPORT the symbol. I thought about moving it to mm_inline.h, but I really don't want to include that in include/linux/scatterlist.h * "ata: libata-eh: drop nth_page() usage within SG entry" * "mspro_block: drop nth_page() usage within SG entry" * "memstick: drop nth_page() usage within SG entry" * "mmc: drop nth_page() usage within SG entry" -> Keep PAGE_SHIFT * "scsi: scsi_lib: drop nth_page() usage within SG entry" * "scsi: sg: drop nth_page() usage within SG entry" -> Split patches, Keep PAGE_SHIFT * "crypto: remove nth_page() usage within SG entry" -> Keep PAGE_SHIFT * "kfence: drop nth_page() usage" -> Keep modifying i and use "start_pfn" only instead Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jason Gunthorpe <jgg(a)nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Marek Szyprowski <m.szyprowski(a)samsung.com> Cc: Robin Murphy <robin.murphy(a)arm.com> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Marco Elver <elver(a)google.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Brendan Jackman <jackmanb(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Zi Yan <ziy(a)nvidia.com> Cc: Dennis Zhou <dennis(a)kernel.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Christoph Lameter <cl(a)gentwo.org> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: x86(a)kernel.org Cc: linux-arm-kernel(a)lists.infradead.org Cc: linux-mips(a)vger.kernel.org Cc: linux-s390(a)vger.kernel.org Cc: linux-crypto(a)vger.kernel.org Cc: linux-ide(a)vger.kernel.org Cc: intel-gfx(a)lists.freedesktop.org Cc: dri-devel(a)lists.freedesktop.org Cc: linux-mmc(a)vger.kernel.org Cc: linux-arm-kernel(a)axis.com Cc: linux-scsi(a)vger.kernel.org Cc: kvm(a)vger.kernel.org Cc: virtualization(a)lists.linux.dev Cc: linux-mm(a)kvack.org Cc: io-uring(a)vger.kernel.org Cc: iommu(a)lists.linux.dev Cc: kasan-dev(a)googlegroups.com Cc: wireguard(a)lists.zx2c4.com Cc: netdev(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-riscv(a)lists.infradead.org David Hildenbrand (36): mm: stop making SPARSEMEM_VMEMMAP user-selectable arm64: Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" s390/Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" x86/Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" wireguard: selftests: remove CONFIG_SPARSEMEM_VMEMMAP=y from qemu kernel config mm/page_alloc: reject unreasonable folio/compound page sizes in alloc_contig_range_noprof() mm/memremap: reject unreasonable folio/compound page sizes in memremap_pages() mm/hugetlb: check for unreasonable folio sizes when registering hstate mm/mm_init: make memmap_init_compound() look more like prep_compound_page() mm: sanity-check maximum folio size in folio_set_order() mm: limit folio/compound page sizes in problematic kernel configs mm: simplify folio_page() and folio_page_idx() mm/hugetlb: cleanup hugetlb_folio_init_tail_vmemmap() mm/mm/percpu-km: drop nth_page() usage within single allocation fs: hugetlbfs: remove nth_page() usage within folio in adjust_range_hwpoison() fs: hugetlbfs: cleanup folio in adjust_range_hwpoison() mm/pagewalk: drop nth_page() usage within folio in folio_walk_start() mm/gup: drop nth_page() usage within folio when recording subpages io_uring/zcrx: remove nth_page() usage within folio mips: mm: convert __flush_dcache_pages() to __flush_dcache_folio_pages() mm/cma: refuse handing out non-contiguous page ranges dma-remap: drop nth_page() in dma_common_contiguous_remap() scatterlist: disallow non-contigous page ranges in a single SG entry ata: libata-eh: drop nth_page() usage within SG entry drm/i915/gem: drop nth_page() usage within SG entry mspro_block: drop nth_page() usage within SG entry memstick: drop nth_page() usage within SG entry mmc: drop nth_page() usage within SG entry scsi: scsi_lib: drop nth_page() usage within SG entry scsi: sg: drop nth_page() usage within SG entry vfio/pci: drop nth_page() usage within SG entry crypto: remove nth_page() usage within SG entry mm/gup: drop nth_page() usage in unpin_user_page_range_dirty_lock() kfence: drop nth_page() usage block: update comment of "struct bio_vec" regarding nth_page() mm: remove nth_page() arch/arm64/Kconfig | 1 - arch/mips/include/asm/cacheflush.h | 11 +++-- arch/mips/mm/cache.c | 8 ++-- arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - crypto/ahash.c | 4 +- crypto/scompress.c | 8 ++-- drivers/ata/libata-sff.c | 6 +-- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 +- drivers/memstick/core/mspro_block.c | 3 +- drivers/memstick/host/jmb38x_ms.c | 3 +- drivers/memstick/host/tifm_ms.c | 3 +- drivers/mmc/host/tifm_sd.c | 4 +- drivers/mmc/host/usdhi6rol0.c | 4 +- drivers/scsi/scsi_lib.c | 3 +- drivers/scsi/sg.c | 3 +- drivers/vfio/pci/pds/lm.c | 3 +- drivers/vfio/pci/virtio/migrate.c | 3 +- fs/hugetlbfs/inode.c | 33 +++++-------- include/crypto/scatterwalk.h | 4 +- include/linux/bvec.h | 7 +-- include/linux/mm.h | 48 +++++++++++++++---- include/linux/page-flags.h | 5 +- include/linux/scatterlist.h | 3 +- io_uring/zcrx.c | 4 +- kernel/dma/remap.c | 2 +- mm/Kconfig | 3 +- mm/cma.c | 39 +++++++++------ mm/gup.c | 14 ++++-- mm/hugetlb.c | 22 +++++---- mm/internal.h | 1 + mm/kfence/core.c | 12 +++-- mm/memremap.c | 3 ++ mm/mm_init.c | 15 +++--- mm/page_alloc.c | 5 +- mm/pagewalk.c | 2 +- mm/percpu-km.c | 2 +- mm/util.c | 34 +++++++++++++ tools/testing/scatterlist/linux/mm.h | 1 - .../selftests/wireguard/qemu/kernel.config | 1 - 40 files changed, 202 insertions(+), 129 deletions(-) base-commit: efa7612003b44c220551fd02466bfbad5180fc83 -- 2.50.1

3 months, 1 week

14
141
0 0

[PATCH net-next v3] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> --- Thanks again Willem for the prompt review. I've incorporated your suggested changes into v3. v3 changes: - add usleep instead of busy polling on sendmsg - simplify error handling by using error() and leaving cleanup to O/S - use loopback interface - don't bother creating TAP - send to localhost (::1) v2 changes: - remove superfluous namespace calls - unshare(2) suffices - remove usleep(). Don't wait for the interface to be ready, just send, and handle the (less likely) error case by retrying. - set destination address only once - document our use of the IPv6 link-local source address - send to port 9 (DISCARD) instead of 4242 (DONT PANIC) - ensure sockets are closed on failure paths - use KSFT exit codes for clarity v2: https://lore.kernel.org/netdev/20250831102908.14655-1-bacs@librecast.net v1: https://lore.kernel.org/netdev/20250825092548.4436-3-bacs@librecast.net tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 145 ++++++++++++++++++ 3 files changed, 147 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index eef0b8f8a7b0..276e0481d996 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation TEST_PROGS += route_hint.sh # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..be79a0340826 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected stable + * kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable + * without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue by sending an IPv6 UDP packet to + * localhost (::1) on the loopback interface from the autoconfigured link-local + * address. + * + * sendmsg(2) returns bytes sent correctly on a working kernel, and returns -1 + * (EMSGSIZE) when the regression is present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <error.h> +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> +#include "../kselftest.h" + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* bring up interface */ +static int interface_up(int ctl, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) + error(KSFT_FAIL, errno, "ioctl SIOCGIFFLAGS"); + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) + error(KSFT_FAIL, errno, "open accept_dad"); + if (write(fd, "0", 1) != 1) + error(KSFT_FAIL, errno, "write accept_dad"); + + return close(fd); +} + +static int setup(void) +{ + struct ifreq ifr = { + .ifr_name = "lo" + }; + int fd = -1; + int ctl; + + /* we need to set MTU, so do this in a namespace to play nicely */ + if (unshare(CLONE_NEWNET) == -1) + error(KSFT_FAIL, errno, "unshare"); + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + error(KSFT_FAIL, errno, "socket"); + + /* ensure MTU is smaller than what we plan to send */ + ifr.ifr_mtu = MTU; + if (ioctl(ctl, SIOCSIFMTU, &ifr) == -1) + error(KSFT_FAIL, errno, "ioctl: set MTU"); + + disable_dad("lo"); + interface_up(ctl, &ifr); + + close(ctl); + return fd; +} + +int main(void) +{ + struct in6_addr addr = { + .s6_addr[15] = 0x01, /* ::1 */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 9 /* port 9/udp (DISCARD) */ + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int err = KSFT_FAIL; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + s = socket(AF_INET6, SOCK_DGRAM, 0); +send_again: + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + /* if interface wasn't ready, try again */ + if (errno == EADDRNOTAVAIL) { + usleep(1000); + goto send_again; + } + printf("[FAIL] sendmsg: %s\n", strerror(errno)); + } else if (rc != LARGER_THAN_MTU) { + printf("[FAIL] sendmsg() returned %zi, expected %i\n", rc, LARGER_THAN_MTU); + } + else { + printf("[PASS] sendmsg() returned %zi\n", rc); + err = KSFT_PASS; + } + close(s); + close(ns_fd); + return err; +} base-commit: 864ecc4a6dade82d3f70eab43dad0e277aa6fc78 -- 2.49.1

3 months, 1 week

1
0
0 0

[PATCH v5 0/7] Add support for FEAT_{LS64, LS64_V} and related tests

by Yicong Yang

From: Yicong Yang <yangyicong(a)hisilicon.com> Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. Add support for Armv8.7 FEAT_{LS64, LS64_V}: - Add identifying and enabling in the cpufeature list - Expose the support of these features to userspace through HWCAP3 and cpuinfo - Add related hwcap test - Handle the trap of unsupported memory (normal/uncacheable) access in a VM A real scenario for this feature is that the userspace driver can make use of this to implement direct WQE (workqueue entry) - a mechanism to fill WQE directly into the hardware. Picked Marc's 2 patches form [1] for handling the LS64 trap in a VM on emulated MMIO and the introduce of KVM_EXIT_ARM_LDST64B. [1] https://lore.kernel.org/linux-arm-kernel/20240815125959.2097734-1-maz@kerne… Tested with updated hwcap test: [root@localhost tmp]# dmesg | grep "All CPU(s) started" [ 14.789859] CPU: All CPU(s) started at EL2 [root@localhost tmp]# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64_V # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 root@localhost:/mnt# dmesg | grep "All CPU(s) started" [ 0.281152] CPU: All CPU(s) started at EL1 root@localhost:/mnt# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 Change since v4: - Rebase on v6.17-rc2 and fix the conflicts Link: https://lore.kernel.org/linux-arm-kernel/20250715081356.12442-1-yangyicong@… Change since v3: - Inject DABT fault for LS64 fault on unsupported memory but with valid memslot Link: https://lore.kernel.org/linux-arm-kernel/20250626080906.64230-1-yangyicong@… Change since v2: - Handle the LS64 fault to userspace and allow userspace to inject LS64 fault - Reorder the patches to make KVM handling prior to feature support Link: https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-1-yangyicong@… Change since v1: - Drop the support for LS64_ACCDATA - handle the DABT of unsupported memory type after checking the memory attributes Link: https://lore.kernel.org/linux-arm-kernel/20241202135504.14252-1-yangyicong@… Marc Zyngier (2): KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B Yicong Yang (5): KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1 arm64: Add support for FEAT_{LS64, LS64_V} KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest kselftest/arm64: Add HWCAP test for FEAT_{LS64, LS64_V} Documentation/arch/arm64/booting.rst | 12 +++ Documentation/arch/arm64/elf_hwcaps.rst | 6 ++ Documentation/virt/kvm/api.rst | 43 +++++++++-- arch/arm64/include/asm/el2_setup.h | 12 ++- arch/arm64/include/asm/esr.h | 8 ++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/asm/kvm_emulate.h | 7 ++ arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/kernel/cpufeature.c | 51 +++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/kvm/inject_fault.c | 22 ++++++ arch/arm64/kvm/mmio.c | 27 ++++++- arch/arm64/kvm/mmu.c | 14 +++- arch/arm64/tools/cpucaps | 2 + include/uapi/linux/kvm.h | 3 +- tools/testing/selftests/arm64/abi/hwcap.c | 90 +++++++++++++++++++++++ 16 files changed, 292 insertions(+), 11 deletions(-) -- 2.24.0

3 months, 1 week

1
8
0 0

[PATCH v2] KVM: loongarch: selftests: Remove common tests built by TEST_GEN_PROGS_COMMON

by dayss1224＠gmail.com

From: Dong Yang <dayss1224(a)gmail.com> Remove the common KVM test cases already added to TEST_GEN_PROGS_COMMON as following: demand_paging_test dirty_log_test guest_print_test kvm_binary_stats_test kvm_create_max_vcpus kvm_page_table_test set_memory_region_test Fixes: a867688c8cbb ("KVM: selftests: Add supported test cases for LoongArch") Signed-off-by: Quan Zhou <zhouquan(a)iscas.ac.cn> Signed-off-by: Dong Yang <dayss1224(a)gmail.com> Changes in v2: - Add "TEST_GEN_PROGS_loongarch = $(TEST_GEN_PROGS_COMMON)" to include common tests --- tools/testing/selftests/kvm/Makefile.kvm | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 38b95998e1e6..3fd1c2ae68d0 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -198,18 +198,12 @@ TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += get-reg-list TEST_GEN_PROGS_riscv += steal_time +TEST_GEN_PROGS_loongarch = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_loongarch += coalesced_io_test -TEST_GEN_PROGS_loongarch += demand_paging_test TEST_GEN_PROGS_loongarch += dirty_log_perf_test -TEST_GEN_PROGS_loongarch += dirty_log_test -TEST_GEN_PROGS_loongarch += guest_print_test TEST_GEN_PROGS_loongarch += hardware_disable_test -TEST_GEN_PROGS_loongarch += kvm_binary_stats_test -TEST_GEN_PROGS_loongarch += kvm_create_max_vcpus -TEST_GEN_PROGS_loongarch += kvm_page_table_test TEST_GEN_PROGS_loongarch += memslot_modification_stress_test TEST_GEN_PROGS_loongarch += memslot_perf_test -TEST_GEN_PROGS_loongarch += set_memory_region_test SPLIT_TESTS += arch_timer SPLIT_TESTS += get-reg-list base-commit: b23ff7e52a79f4fe2382e3564719b97b718166d1 -- 2.34.1

3 months, 1 week

1
0
0 0

[PATCHSET V1 0/2] cpuidle, bpf: Introduce BPF-based extensible cpuidle policy via struct_ops

by Lin Yikai

Summary ---------- Hi, everyone, This patch set introduces an extensible cpuidle governor framework using BPF struct_ops, enabling dynamic implementation of idle-state selection policies via BPF programs. Motivation ---------- As is well-known, CPUs support multiple idle states (e.g., C0, C1, C2, ...), where deeper states reduce power consumption, but results in longer wakeup latency, potentially affecting performance. Existing generic cpuidle governors operate effectively in common scenarios but exhibit suboptimal behavior in specific Android phone's use cases. Our testing reveals that during low-utilization scenarios (e.g., screen-off background tasks like music playback with CPU utilization <10%), the C0 state occupies ~50% of idle time, causing significant energy inefficiency. Reducing C0 to ≤20% could yield ≥5% power savings on mobile phones. To address this, we expect: 1.Dynamic governor switching to power-saved policies for low cpu utilization scenarios (e.g., screen-off mode) 2.Dynamic switching to alternate governors for high-performance scenarios (e.g., gaming) OverView ---------- The BPF cpuidle ext governor registers at postcore_initcall() but remains disabled by default due to its low priority "rating" with value "1". Activation requires adjust higer "rating" than other governors within BPF. Core Components: 1.**struct cpuidle_gov_ext_ops** – BPF-overridable operations: - ops.enable()/ops.disable(): enable or disable callback - ops.select(): cpu Idle-state selection logic - ops.set_stop_tick(): Scheduler tick management after state selection - ops.reflect(): feedback info about previous idle state. - ops.init()/ops.deinit(): Initialization or cleanup. 2.**Critical kfuncs for kernel state access**: - bpf_cpuidle_ext_gov_update_rating(): Activate ext governor by raising rating must be called from "ops.init()" - bpf_cpuidle_ext_gov_latency_req(): get idle-state latency constraints - bpf_tick_nohz_get_sleep_length(): get CPU sleep duration in tickless mode Future work ---------- 1. Scenario detection: Identifying low-utilization states (e.g., screen-off + background music) 2. Policy optimization: Optimizing state-selection algorithms for specific scenarios Lin Yikai (2): Subject: [PATCH v1 1/2] cpuidle: Implement BPF extensible cpuidle class Subject: [PATCH v1 2/2] selftests/bpf: Add selftests drivers/cpuidle/Kconfig | 12 + drivers/cpuidle/governors/Makefile | 1 + drivers/cpuidle/governors/ext.c | 537 ++++++++++++++++++ .../bpf/prog_tests/test_cpuidle_gov_ext.c | 28 + .../selftests/bpf/progs/cpuidle_gov_ext.c | 208 +++++++ 5 files changed, 786 insertions(+) create mode 100644 drivers/cpuidle/governors/ext.c create mode 100644 tools/testing/selftests/bpf/prog_tests/test_cpuidle_gov_ext.c create mode 100644 tools/testing/selftests/bpf/progs/cpuidle_gov_ext.c -- 2.43.0

3 months, 1 week

4
6
0 0

[PATCH net-next] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 204 ++++++++++++++++++ 3 files changed, 206 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b31a71f2b372..f83f91b758ae 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..21e1a3cdc63d --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected + * stable kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: + * a18dfa9925b9 ("ipv6: save dontfrag in cork") + * was backported to stable without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue. sendmsg returns correctly (8192) + * on a working kernel, and returns -1 (EMSGSIZE) when the regression is + * present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* ensure MTU is smaller than what we plan to send */ +static int set_mtu(int ctl, char *ifname, struct ifreq *ifr) +{ + ifr->ifr_mtu = MTU; + return ioctl(ctl, SIOCSIFMTU, ifr); +} + +/* bring up interface */ +static int interface_up(int ctl, char *ifname, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) { + perror("ioctl SIOCGIFFLAGS"); + return -1; + } + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) { + perror("open accept_dad"); + return -1; + } + if (write(fd, "0", 1) != 1) { + perror("write"); + return -1; + } + return close(fd); +} + +/* create TAP interface that will be deleted when this process exits */ +static int create_interface(int ctl, char *ifname, struct ifreq *ifr) +{ + int fd; + + fd = open("/dev/net/tun", O_RDWR); + if (fd == -1) { + perror("open tun"); + return -1; + } + + ifr->ifr_flags = IFF_TAP | IFF_NO_PI; + if (ioctl(fd, TUNSETIFF, (void *)ifr) == -1) { + close(fd); + perror("ioctl: TUNSETIFF"); + return -1; + } + strcpy(ifname, ifr->ifr_name); + + return fd; +} + +/* we need to set MTU, so do this in a namespace to play nicely */ +static int create_namespace(void) +{ + const char *netns_path = "/proc/self/ns/net"; + int fd; + + if (unshare(CLONE_NEWNET) != 0) { + perror("unshare"); + return -1; + } + + fd = open(netns_path, O_RDONLY); + if (fd == -1) { + perror("open"); + return -1; + } + + if (setns(fd, CLONE_NEWNET)) { + perror("setns"); + return -1; + } + + return 0; +} + +static int setup(void) +{ + struct ifreq ifr = {0}; + char ifname[IFNAMSIZ]; + int fd = -1; + int ctl; + + if (create_namespace() == -1) + return -1; + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + return -1; + + memset(ifname, 0, sizeof(ifname)); + fd = create_interface(ctl, ifname, &ifr); + if (fd == -1) + goto err_close_ctl; + if (disable_dad(ifname) == -1) + goto err_close_fd; + if (interface_up(ctl, ifname, &ifr) == -1) + goto err_close_fd; + if (set_mtu(ctl, ifname, &ifr) == -1) + goto err_close_fd; + usleep(10000); /* give interface a moment to wake up */ + goto err_close_ctl; +err_close_fd: + close(fd); + fd = -1; +err_close_ctl: + close(ctl); + return fd; +} + +int main(void) +{ + /* address doesn't matter, use an IPv6 multicast address for simplicity */ + struct in6_addr addr = { + .s6_addr[0] = 0xff, /* multicast */ + .s6_addr[1] = 0x12, /* set flags (T, link-local) */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 4242 + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + if (ns_fd == -1) + return 1; + s = socket(AF_INET6, SOCK_DGRAM, 0); + msg.msg_name = (struct sockaddr *)&sa; + msg.msg_namelen = sizeof(sa); + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + perror("send"); + return 1; + } else if (rc != LARGER_THAN_MTU) { + fprintf(stderr, "send() returned %zi\n", rc); + return 1; + } + close(s); + close(ns_fd); + + return 0; +} -- 2.49.1

3 months, 1 week

3
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror