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

[PATCH] selftests/kvm: Use vcpus count instead of hardcoded 0xff in test_icr

by Sukrut Heroorkar

Replace the hardcoded 0xff in test_icr() with the actual number of vcpus created for the vm. This address the existing TODO and keeps the test correct if it is ever run with multiple vcpus. Signed-off-by: Sukrut Heroorkar <hsukrut3(a)gmail.com> --- tools/testing/selftests/kvm/x86/xapic_state_test.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index fdebff1165c7..4af36682503e 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -56,6 +56,17 @@ static void x2apic_guest_code(void) } while (1); } +static unsigned int vm_nr_vcpus(struct kvm_vm *vm) +{ + struct kvm_vcpu *vcpu; + unsigned int count = 0; + + list_for_each_entry(vcpu, &vm->vcpus, list) + count++; + + return count; +} + static void ____test_icr(struct xapic_vcpu *x, uint64_t val) { struct kvm_vcpu *vcpu = x->vcpu; @@ -124,7 +135,7 @@ static void test_icr(struct xapic_vcpu *x) * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. */ icr = APIC_INT_ASSERT | 0xff; - for (i = 0; i < 0xff; i++) { + for (i = 0; i < vm_nr_vcpus(vcpu->vm); i++) { if (i == vcpu->id) continue; for (j = 0; j < 8; j++) -- 2.43.0

5 days, 18 hours

3
2
0 0

Re: [syzbot] [net?] WARNING: suspicious RCU usage in corrupted (3)

by syzbot

syzbot suspects this issue was fixed by commit: commit 7f12c33850482521c961c5c15a50ebe9b9a88d1e Author: Charalampos Mitrodimas <charmitro(a)posteo.net> Date: Wed Jun 11 17:20:43 2025 +0000 net, bpf: Fix RCU usage in task_cls_state() for BPF programs bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=13745562580000 start commit: 079e5c56a5c4 bpf: Fix error return value in bpf_copy_from_.. git tree: bpf-next kernel config: https://syzkaller.appspot.com/x/.config?x=c6c517d2f439239 dashboard link: https://syzkaller.appspot.com/bug?extid=9767c7ed68b95cfa69e6 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=114915f4580000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=15566170580000 If the result looks correct, please mark the issue as fixed by replying with: #syz fix: net, bpf: Fix RCU usage in task_cls_state() for BPF programs For information about bisection process see: https://goo.gl/tpsmEJ#bisection

5 days, 19 hours

1
0
0 0

[PATCH net-next 1/2] selftests: net: make the dump test less sensitive to mem accounting

by Jakub Kicinski

Recent changes to make netlink socket memory accounting must have broken the implicit assumption of the netlink-dump test that we can fit exactly 64 dumps into the socket. Handle the failure mode properly, and increase the dump count to 80 to make sure we still run into the error condition if the default buffer size increases in the future. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- tools/testing/selftests/net/netlink-dumps.c | 43 ++++++++++++++++----- 1 file changed, 33 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 07423f256f96..7618ebe528a4 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -31,9 +31,18 @@ struct ext_ack { const char *str; }; -/* 0: no done, 1: done found, 2: extack found, -1: error */ -static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) +enum get_ea_ret { + ERROR = -1, + NO_CTRL = 0, + FOUND_DONE, + FOUND_ERR, + FOUND_EXTACK, +}; + +static enum get_ea_ret +nl_get_extack(char *buf, size_t n, struct ext_ack *ea) { + enum get_ea_ret ret = NO_CTRL; const struct nlmsghdr *nlh; const struct nlattr *attr; ssize_t rem; @@ -41,15 +50,19 @@ static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) { nlh = (struct nlmsghdr *)&buf[n - rem]; if (!NLMSG_OK(nlh, rem)) - return -1; + return ERROR; - if (nlh->nlmsg_type != NLMSG_DONE) + if (nlh->nlmsg_type == NLMSG_ERROR) + ret = FOUND_ERR; + else if (nlh->nlmsg_type == NLMSG_DONE) + ret = FOUND_DONE; + else continue; ea->err = -*(int *)NLMSG_DATA(nlh); if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) - return 1; + return ret; ynl_attr_for_each(attr, nlh, sizeof(int)) { switch (ynl_attr_type(attr)) { @@ -68,10 +81,10 @@ static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) } } - return 2; + return FOUND_EXTACK; } - return 0; + return ret; } static const struct { @@ -99,9 +112,9 @@ static const struct { TEST(dump_extack) { int netlink_sock; + int i, cnt, ret; char buf[8192]; int one = 1; - int i, cnt; ssize_t n; netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); @@ -118,7 +131,7 @@ TEST(dump_extack) ASSERT_EQ(n, 0); /* Dump so many times we fill up the buffer */ - cnt = 64; + cnt = 80; for (i = 0; i < cnt; i++) { n = send(netlink_sock, &dump_neigh_bad, sizeof(dump_neigh_bad), 0); @@ -140,10 +153,20 @@ TEST(dump_extack) } ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); - EXPECT_EQ(nl_get_extack(buf, n, &ea), 2); + ret = nl_get_extack(buf, n, &ea); + /* Once we fill the buffer we'll see one ENOBUFS followed + * by a number of EBUSYs. Then the last recv() will finally + * trigger and complete the dump. + */ + if (ret == FOUND_ERR && (ea.err == ENOBUFS || ea.err == EBUSY)) + continue; + EXPECT_EQ(ret, FOUND_EXTACK); + EXPECT_EQ(ea.err, EINVAL); EXPECT_EQ(ea.attr_offs, sizeof(struct nlmsghdr) + sizeof(struct ndmsg)); } + /* Make sure last message was a full DONE+extack */ + EXPECT_EQ(ret, FOUND_EXTACK); } static const struct { -- 2.51.0

5 days, 19 hours

2
2
0 0

[PATCH v15 0/6] KVM: arm64: Provide guest support for GCS

by Mark Brown

The arm64 Guarded Control Stack (GCS) feature provides support for hardware protected stacks of return addresses, intended to provide hardening against return oriented programming (ROP) attacks and to make it easier to gather call stacks for applications such as profiling. When GCS is active a secondary stack called the Guarded Control Stack is maintained, protected with a memory attribute which means that it can only be written with specific GCS operations. The current GCS pointer can not be directly written to by userspace. When a BL is executed the value stored in LR is also pushed onto the GCS, and when a RET is executed the top of the GCS is popped and compared to LR with a fault being raised if the values do not match. GCS operations may only be performed on GCS pages, a data abort is generated if they are not. The combination of hardware enforcement and lack of extra instructions in the function entry and exit paths should result in something which has less overhead and is more difficult to attack than a purely software implementation like clang's shadow stacks. This series implements support for managing GCS for KVM guests, it also includes a fix for S1PIE which has also been sent separately as this feature is a dependency for GCS. It is based on: https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/gcs Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v15: - Rebase onto v6.17-rc1. - Link to v14: https://lore.kernel.org/r/20241005-arm64-gcs-v14-0-59060cd6092b@kernel.org Changes in v14: - Rebase onto arm64/for-next/gcs which includes all the non-KVM support. - Manage the fine grained traps for GCS instructions. - Manage PSTATE.EXLOCK when delivering exceptions to KVM guests. - Link to v13: https://lore.kernel.org/r/20241001-arm64-gcs-v13-0-222b78d87eee@kernel.org Changes in v13: - Rebase onto v6.12-rc1. - Allocate VM_HIGH_ARCH_6 since protection keys used all the existing bits. - Implement mm_release() and free transparently allocated GCSs there. - Use bit 32 of AT_HWCAP for GCS due to AT_HWCAP2 being filled. - Since we now only set GCSCRE0_EL1 on change ensure that it is initialised with GCSPR_EL0 accessible to EL0. - Fix OOM handling on thread copy. - Link to v12: https://lore.kernel.org/r/20240829-arm64-gcs-v12-0-42fec947436a@kernel.org Changes in v12: - Clarify and simplify the signal handling code so we work with the register state. - When checking for write aborts to shadow stack pages ensure the fault is a data abort. - Depend on !UPROBES. - Comment cleanups. - Link to v11: https://lore.kernel.org/r/20240822-arm64-gcs-v11-0-41b81947ecb5@kernel.org Changes in v11: - Remove the dependency on the addition of clone3() support for shadow stacks, rebasing onto v6.11-rc3. - Make ID_AA64PFR1_EL1.GCS writeable in KVM. - Hide GCS registers when GCS is not enabled for KVM guests. - Require HCRX_EL2.GCSEn if booting at EL1. - Require that GCSCR_EL1 and GCSCRE0_EL1 be initialised regardless of if we boot at EL2 or EL1. - Remove some stray use of bit 63 in signal cap tokens. - Warn if we see a GCS with VM_SHARED. - Remove rdundant check for VM_WRITE in fault handling. - Cleanups and clarifications in the ABI document. - Clean up and improve documentation of some sync placement. - Only set the EL0 GCS mode if it's actually changed. - Various minor fixes and tweaks. - Link to v10: https://lore.kernel.org/r/20240801-arm64-gcs-v10-0-699e2bd2190b@kernel.org Changes in v10: - Fix issues with THP. - Tighten up requirements for initialising GCSCR*. - Only generate GCS signal frames for threads using GCS. - Only context switch EL1 GCS registers if S1PIE is enabled. - Move context switch of GCSCRE0_EL1 to EL0 context switch. - Make GCS registers unconditionally visible to userspace. - Use FHU infrastructure. - Don't change writability of ID_AA64PFR1_EL1 for KVM. - Remove unused arguments from alloc_gcs(). - Typo fixes. - Link to v9: https://lore.kernel.org/r/20240625-arm64-gcs-v9-0-0f634469b8f0@kernel.org Changes in v9: - Rebase onto v6.10-rc3. - Restructure and clarify memory management fault handling. - Fix up basic-gcs for the latest clone3() changes. - Convert to newly merged KVM ID register based feature configuration. - Fixes for NV traps. - Link to v8: https://lore.kernel.org/r/20240203-arm64-gcs-v8-0-c9fec77673ef@kernel.org Changes in v8: - Invalidate signal cap token on stack when consuming. - Typo and other trivial fixes. - Don't try to use process_vm_write() on GCS, it intentionally does not work. - Fix leak of thread GCSs. - Rebase onto latest clone3() series. - Link to v7: https://lore.kernel.org/r/20231122-arm64-gcs-v7-0-201c483bd775@kernel.org Changes in v7: - Rebase onto v6.7-rc2 via the clone3() patch series. - Change the token used to cap the stack during signal handling to be compatible with GCSPOPM. - Fix flags for new page types. - Fold in support for clone3(). - Replace copy_to_user_gcs() with put_user_gcs(). - Link to v6: https://lore.kernel.org/r/20231009-arm64-gcs-v6-0-78e55deaa4dd@kernel.org Changes in v6: - Rebase onto v6.6-rc3. - Add some more gcsb_dsync() barriers following spec clarifications. - Due to ongoing discussion around clone()/clone3() I've not updated anything there, the behaviour is the same as on previous versions. - Link to v5: https://lore.kernel.org/r/20230822-arm64-gcs-v5-0-9ef181dd6324@kernel.org Changes in v5: - Don't map any permissions for user GCSs, we always use EL0 accessors or use a separate mapping of the page. - Reduce the standard size of the GCS to RLIMIT_STACK/2. - Enforce a PAGE_SIZE alignment requirement on map_shadow_stack(). - Clarifications and fixes to documentation. - More tests. - Link to v4: https://lore.kernel.org/r/20230807-arm64-gcs-v4-0-68cfa37f9069@kernel.org Changes in v4: - Implement flags for map_shadow_stack() allowing the cap and end of stack marker to be enabled independently or not at all. - Relax size and alignment requirements for map_shadow_stack(). - Add more blurb explaining the advantages of hardware enforcement. - Link to v3: https://lore.kernel.org/r/20230731-arm64-gcs-v3-0-cddf9f980d98@kernel.org Changes in v3: - Rebase onto v6.5-rc4. - Add a GCS barrier on context switch. - Add a GCS stress test. - Link to v2: https://lore.kernel.org/r/20230724-arm64-gcs-v2-0-dc2c1d44c2eb@kernel.org Changes in v2: - Rebase onto v6.5-rc3. - Rework prctl() interface to allow each bit to be locked independently. - map_shadow_stack() now places the cap token based on the size requested by the caller not the actual space allocated. - Mode changes other than enable via ptrace are now supported. - Expand test coverage. - Various smaller fixes and adjustments. - Link to v1: https://lore.kernel.org/r/20230716-arm64-gcs-v1-0-bf567f93bba6@kernel.org --- Mark Brown (6): arm64/gcs: Ensure FGTs for EL1 GCS instructions are disabled KVM: arm64: Manage GCS access and registers for guests KVM: arm64: Forward GCS exceptions to nested guests KVM: arm64: Set PSTATE.EXLOCK when entering an exception KVM: arm64: Allow GCS to be enabled for guests KVM: selftests: arm64: Add GCS registers to get-reg-list arch/arm64/include/asm/el2_setup.h | 4 +++ arch/arm64/include/asm/kvm_emulate.h | 3 ++ arch/arm64/include/asm/kvm_host.h | 14 +++++++++ arch/arm64/include/asm/vncr_mapping.h | 2 ++ arch/arm64/include/uapi/asm/ptrace.h | 1 + arch/arm64/kvm/handle_exit.c | 14 +++++++-- arch/arm64/kvm/hyp/exception.c | 37 ++++++++++++++++++++++++ arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 31 ++++++++++++++++++++ arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 10 +++++++ arch/arm64/kvm/sys_regs.c | 32 ++++++++++++++++++-- tools/testing/selftests/kvm/arm64/get-reg-list.c | 12 ++++++++ 11 files changed, 155 insertions(+), 5 deletions(-) --- base-commit: 8f5ae30d69d7543eee0d70083daf4de8fe15d585 change-id: 20230303-arm64-gcs-e311ab0d8729 Best regards, -- Mark Brown <broonie(a)kernel.org>

5 days, 20 hours

2
17
0 0

Re: [PATCH 5/9] KVM: selftests: Prevent PAGE_SIZE redefinition on x86

by Sean Christopherson

+lists Please keep discussions on-list unless there's something that can't/shouldn't be posted publicly, e.g. for confidentiality or security reasons. On Tue, Sep 02, 2025, Faruqui, Aqib wrote: > I suppose a fix for blindly using PAGE_SIZE in subsequent macros: > > #ifdef PAGE_SIZE > #undef PAGE_SIZE > #endif > #define PAGE_SIZE (1ULL << PAGE_SHIFT) > > Is no better and is instead blindly suppressing the compiler's redefinition warning. > > I'm having trouble finding what causes the conflict, any advice here? Maybe try a newer compiler? E.g. gcc-14.2 will spit out the exact location of the previous definition. In file included from include/x86/svm_util.h:13, from include/x86/sev.h:15, from lib/x86/sev.c:5: include/x86/processor.h:373:9: error: "PAGE_SIZE" redefined [-Werror] 373 | #define PAGE_SIZE (1ULL << PAGE_SHIFT) | ^~~~~~~~~ include/x86/processor.h:370:9: note: this is the location of the previous definition 370 | #define PAGE_SIZE BIT(12) | ^~~~~~~~~

5 days, 20 hours

2
2
0 0

[PATCH] selftests/filesystems: Use return value of the function 'chdir()'

by Alessandro Zanni

Fix to use the return value of the function 'chdir("/")' and check if the return is either 0 (ok) or 1 (not ok, so the test stops). The patch fies the solves the following errors: mount-notify_test.c:468:17: warning: ignoring return value of ‘chdir’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 468 | chdir("/"); mount-notify_test_ns.c:489:17: warning: ignoring return value of ‘chdir’ declared with attribute ‘warn_unused_result’ [-Wunused- result] 489 | chdir("/"); To reproduce the issue, use the command: make kselftest TARGET=filesystems/statmount Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> Reviewed-by: Jan Kara <jack(a)suse.cz> --- .../selftests/filesystems/mount-notify/mount-notify_test.c | 2 +- .../selftests/filesystems/mount-notify/mount-notify_test_ns.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index 5a3b0ace1a88..a7f899599d52 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -458,7 +458,7 @@ TEST_F(fanotify, rmdir) ASSERT_GE(ret, 0); if (ret == 0) { - chdir("/"); + ASSERT_EQ(0, chdir("/")); unshare(CLONE_NEWNS); mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); umount2("/a", MNT_DETACH); diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index d91946e69591..dc9eb3087a1a 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -486,7 +486,7 @@ TEST_F(fanotify, rmdir) ASSERT_GE(ret, 0); if (ret == 0) { - chdir("/"); + ASSERT_EQ(0, chdir("/")); unshare(CLONE_NEWNS); mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); umount2("/a", MNT_DETACH); -- 2.43.0

5 days, 21 hours

1
0
0 0

[PATCH] selftests/filesystems: Use return value of the function 'chdir()'

by Alessandro Zanni

Fix to use the return value of the function 'chdir("/")' and check if the return is either 0 (ok) or 1 (not ok, so the test stops). The patch fies the solves the following errors: mount-notify_test.c:468:17: warning: ignoring return value of ‘chdir’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 468 | chdir("/"); mount-notify_test_ns.c:489:17: warning: ignoring return value of ‘chdir’ declared with attribute ‘warn_unused_result’ [-Wunused- result] 489 | chdir("/"); To reproduce the issue, use the command: make kselftest TARGET=filesystems/statmount Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- .../selftests/filesystems/mount-notify/mount-notify_test.c | 2 +- .../selftests/filesystems/mount-notify/mount-notify_test_ns.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index 5a3b0ace1a88..a7f899599d52 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -458,7 +458,7 @@ TEST_F(fanotify, rmdir) ASSERT_GE(ret, 0); if (ret == 0) { - chdir("/"); + ASSERT_EQ(0, chdir("/")); unshare(CLONE_NEWNS); mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); umount2("/a", MNT_DETACH); diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index d91946e69591..dc9eb3087a1a 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -486,7 +486,7 @@ TEST_F(fanotify, rmdir) ASSERT_GE(ret, 0); if (ret == 0) { - chdir("/"); + ASSERT_EQ(0, chdir("/")); unshare(CLONE_NEWNS); mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); umount2("/a", MNT_DETACH); -- 2.43.0

5 days, 21 hours

1
0
0 0

[PATCH v3 bpf-next] selftests/bpf: Fix the issue where the error code is 0

by Feng Yang

From: Feng Yang <yangfeng(a)kylinos.cn> The error message printed here only uses the previous err value, which results in it being printed as 0. When bpf_map__attach_struct_ops encounters an error, it uses libbpf_err_ptr(err) to set errno = -err and returns NULL. Therefore, Using -errno can fix this issue. Fix before: run_subtest:FAIL:1019 bpf_map__attach_struct_ops failed for map pro_epilogue: err=0 Fix after: run_subtest:FAIL:1019 bpf_map__attach_struct_ops failed for map pro_epilogue: err=-9 Signed-off-by: Feng Yang <yangfeng(a)kylinos.cn> --- Changes in v3: - Use -errno here directly, thanks: Andrii Nakryiko. - Link to v2: https://lore.kernel.org/all/20250829014125.198653-1-yangfeng59949@163.com/ --- Changes in v2: - Use libbpf_get_error, thanks: Alexei Starovoitov. - Link to v1: https://lore.kernel.org/all/20250828081507.1380218-1-yangfeng59949@163.com/ --- tools/testing/selftests/bpf/test_loader.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 78423cf89e01..33d59c093a27 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -1083,7 +1083,7 @@ void run_subtest(struct test_loader *tester, link = bpf_map__attach_struct_ops(map); if (!link) { PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n", - bpf_map__name(map), err); + bpf_map__name(map), -errno); goto tobj_cleanup; } links[links_cnt++] = link; -- 2.25.1

5 days, 22 hours

2
1
0 0

[PATCH RFC 00/35] mm: remove nth_page()

by David Hildenbrand

This is based on mm-unstable and was cross-compiled heavily. I should probably have already dropped the RFC label but I want to hear first if I ignored some corner case (SG entries?) and I need to do at least a bit more testing. 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 -> #12 : disallow folios to have non-contiguous pages Patch #13 -> #20 : remove nth_page() usage within folios Patch #21 : disallow CMA allocations of non-contiguous pages Patch #22 -> #31 : sanity+check + remove nth_page() usage within SG entry Patch #32 : sanity-check + remove nth_page() usage in unpin_user_page_range_dirty_lock() Patch #33 : remove nth_page() in kfence Patch #34 : adjust stale comment regarding nth_page Patch #35 : 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… 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 (35): 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/hugetlb: cleanup hugetlb_folio_init_tail_vmemmap() 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/mm/percpu-km: drop nth_page() usage within single allocation fs: hugetlbfs: remove nth_page() usage within 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 "struct io_copy_cache" and one nth_page() usage 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: core: 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 | 25 ++++------ 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 | 4 +- io_uring/zcrx.c | 34 ++++--------- kernel/dma/remap.c | 2 +- mm/Kconfig | 3 +- mm/cma.c | 36 +++++++++----- mm/gup.c | 13 +++-- mm/hugetlb.c | 23 ++++----- mm/internal.h | 1 + mm/kfence/core.c | 17 ++++--- mm/memremap.c | 3 ++ mm/mm_init.c | 13 ++--- mm/page_alloc.c | 5 +- mm/pagewalk.c | 2 +- mm/percpu-km.c | 2 +- mm/util.c | 33 +++++++++++++ tools/testing/scatterlist/linux/mm.h | 1 - .../selftests/wireguard/qemu/kernel.config | 1 - 40 files changed, 203 insertions(+), 150 deletions(-) base-commit: c0e3b3f33ba7b767368de4afabaf7c1ddfdc3872 -- 2.50.1

5 days, 22 hours

14
90
0 0

[PATCH v2] selftests/arm64: Fix grammatical error in string literals

by Nikola Z. Ivanov

Fix grammatical error in <past tense verb> + <infinitive> construct related to memory allocation checks. In essence change "Failed to allocated" to "Failed to allocate". Signed-off-by: Nikola Z. Ivanov <zlatistiv(a)gmail.com> --- Changes in v2: - More descriptive commit message Original title is "Fix typos in malloc return value check" tools/testing/selftests/arm64/fp/fp-stress.c | 2 +- tools/testing/selftests/arm64/fp/kernel-test.c | 4 ++-- tools/testing/selftests/arm64/gcs/gcs-stress.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c index 74e23208b94c..ddc01efea3f9 100644 --- a/tools/testing/selftests/arm64/fp/fp-stress.c +++ b/tools/testing/selftests/arm64/fp/fp-stress.c @@ -549,7 +549,7 @@ int main(int argc, char **argv) evs = calloc(tests, sizeof(*evs)); if (!evs) - ksft_exit_fail_msg("Failed to allocated %d epoll events\n", + ksft_exit_fail_msg("Failed to allocate %d epoll events\n", tests); for (i = 0; i < cpus; i++) { diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c index e3cec3723ffa..0c40007d1282 100644 --- a/tools/testing/selftests/arm64/fp/kernel-test.c +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -188,13 +188,13 @@ static bool create_socket(void) ref = malloc(digest_len); if (!ref) { - printf("Failed to allocated %d byte reference\n", digest_len); + printf("Failed to allocate %d byte reference\n", digest_len); return false; } digest = malloc(digest_len); if (!digest) { - printf("Failed to allocated %d byte digest\n", digest_len); + printf("Failed to allocate %d byte digest\n", digest_len); return false; } diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress.c b/tools/testing/selftests/arm64/gcs/gcs-stress.c index bbc7f4950c13..cf316d78ea97 100644 --- a/tools/testing/selftests/arm64/gcs/gcs-stress.c +++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c @@ -433,7 +433,7 @@ int main(int argc, char **argv) evs = calloc(tests, sizeof(*evs)); if (!evs) - ksft_exit_fail_msg("Failed to allocated %d epoll events\n", + ksft_exit_fail_msg("Failed to allocate %d epoll events\n", tests); for (i = 0; i < gcs_threads; i++) -- 2.50.1

5 days, 23 hours

4
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror