February 2023 - Linux-kselftest-mirror

[PATCH] tools: Copy linux/align.h into tools/

by Ackerley Tng

This provides alignment macros for use in selftests. Also clean up tools/include/linux/bitmap.h's inline definition of IS_ALIGNED(). Signed-off-by: Ackerley Tng <ackerleytng(a)google.com> --- tools/include/linux/align.h | 15 +++++++++++++++ tools/include/linux/bitmap.h | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) create mode 100644 tools/include/linux/align.h diff --git a/tools/include/linux/align.h b/tools/include/linux/align.h new file mode 100644 index 000000000000..2b4acec7b95a --- /dev/null +++ b/tools/include/linux/align.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ALIGN_H +#define _LINUX_ALIGN_H + +#include <linux/const.h> + +/* @a is a power of 2 value */ +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) +#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) +#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +#endif /* _LINUX_ALIGN_H */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index f3566ea0f932..8c6852dba04f 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -3,6 +3,7 @@ #define _TOOLS_LINUX_BITMAP_H #include <string.h> +#include <linux/align.h> #include <linux/bitops.h> #include <linux/find.h> #include <stdlib.h> @@ -126,7 +127,6 @@ static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) static inline bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) -- 2.39.2.722.g9855ee24e9-goog

1 year, 1 month

2
1
0 0

[PATCH v3 00/13] Overhauling amx_test

by Mingwei Zhang

In this version, I have integrated Aaron's changes to the amx_test. In addition, we also integrated one fix patch for a kernel warning due to xsave address issue. Patch 1: Fix a host FPU kernel warning due to missing XTILEDATA in xinit. Patch 2-8: Overhaul amx_test. These patches were basically from v2. Patch 9-13: Overhaul amx_test from Aaron. I modified the changelog a little bit. v2 -> v3: - integrate Aaron's 5 commits with minor changes on commit message. - Add one fix patch for a kernel warning. v2: https://lore.kernel.org/all/20230214184606.510551-1-mizhang@google.com/ Aaron Lewis (5): KVM: selftests: x86: Assert that XTILE is XSAVE-enabled KVM: selftests: x86: Assert that both XTILE{CFG,DATA} are XSAVE-enabled KVM: selftests: x86: Remove redundant check that XSAVE is supported KVM: selftests: x86: Check that the palette table exists before using it KVM: selftests: x86: Check that XTILEDATA supports XFD Mingwei Zhang (8): x86/fpu/xstate: Avoid getting xstate address of init_fpstate if fpstate contains the component KVM: selftests: x86: Add a working xstate data structure KVM: selftests: x86: Fix an error in comment of amx_test KVM: selftests: x86: Add check of CR0.TS in the #NM handler in amx_test KVM: selftests: x86: Add the XFD check to IA32_XFD in #NM handler KVM: selftests: x86: Fix the checks to XFD_ERR using and operation KVM: selftests: x86: Enable checking on xcomp_bv in amx_test KVM: selftests: x86: Repeat the checking of xheader when IA32_XFD[XTILEDATA] is set in amx_test arch/x86/kernel/fpu/xstate.c | 10 ++- .../selftests/kvm/include/x86_64/processor.h | 14 ++++ tools/testing/selftests/kvm/x86_64/amx_test.c | 80 +++++++++---------- 3 files changed, 59 insertions(+), 45 deletions(-) -- 2.39.2.637.g21b0678d19-goog

1 year, 1 month

4
30
0 0

[PATCH v2 1/1] KVM: selftests: Adjust VM's initial stack address to align with SysV ABI spec

by Ackerley Tng

Align the guest stack to match calling sequence requirements in section "The Stack Frame" of the System V ABI AMD64 Architecture Processor Supplement, which requires the value (%rsp + 8), NOT %rsp, to be a multiple of 16 when control is transferred to the function entry point. I.e. in a normal function call, %rsp needs to be 16-byte aligned _before_ CALL, not after. This fixes unexpected #GPs in guest code when the compiler uses SSE instructions, e.g. to initialize memory, as many SSE instructions require memory operands (including those on the stack) to be 16-byte-aligned. Signed-off-by: Ackerley Tng <ackerleytng(a)google.com> --- This patch is a follow-up from discussions at https://lore.kernel.org/lkml/20230121001542.2472357-9-ackerleytng@google.co… v1 -> v2: Cleaned the patch up after getting comments from Sean in v1: https://lore.kernel.org/lkml/Y%2FfHLdvKHlK6D%2F1v@google.com/ Please also see https://lore.kernel.org/lkml/20230227174654.94641-1-ackerleytng@google.com/ regarding providing alignment macros for selftests. --- .../selftests/kvm/lib/x86_64/processor.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index ae1e573d94ce..a0669d31bb85 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#include "linux/bitmap.h" #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -573,6 +574,21 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + stack_vaddr += DEFAULT_STACK_PGS * getpagesize(); + + /* + * Align stack to match calling sequence requirements in section "The + * Stack Frame" of the System V ABI AMD64 Architecture Processor + * Supplement, which requires the value (%rsp + 8) to be a multiple of + * 16 when control is transferred to the function entry point. + * + * If this code is ever used to launch a vCPU with 32-bit entry point it + * may need to subtract 4 bytes instead of 8 bytes. + */ + TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE), + "__vm_vaddr_alloc() did not provide a page-aligned address"); + stack_vaddr -= 8; + vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpu); @@ -580,7 +596,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, &regs); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + regs.rsp = stack_vaddr; regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, &regs); -- 2.39.2.722.g9855ee24e9-goog

1 year, 1 month

2
2
0 0

[PATCH v1 0/2] KVM: s390: CMMA migration selftest and small bugfix

by Nico Boehr

Add a new selftest for CMMA migration. Also fix a small issue found during development of the test. Nico Boehr (2): KVM: s390: selftests: add selftest for CMMA migration KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes arch/s390/kvm/kvm-s390.c | 4 + tools/testing/selftests/kvm/Makefile | 1 + tools/testing/selftests/kvm/s390x/cmma_test.c | 679 ++++++++++++++++++ 3 files changed, 684 insertions(+) create mode 100644 tools/testing/selftests/kvm/s390x/cmma_test.c -- 2.39.1

1 year, 1 month

2
10
0 0

[PATCH net-next v2 0/5] tls: implement key updates for TLS1.3

by Sabrina Dubroca

This adds support for receiving KeyUpdate messages (RFC 8446, 4.6.3 [1]). A sender transmits a KeyUpdate message and then changes its TX key. The receiver should react by updating its RX key before processing the next message. This patchset implements key updates by: 1. pausing decryption when a KeyUpdate message is received, to avoid attempting to use the old key to decrypt a record encrypted with the new key 2. returning -EKEYEXPIRED to syscalls that cannot receive the KeyUpdate message, until the rekey has been performed by userspace 3. passing the KeyUpdate message to userspace as a control message 4. allowing updates of the crypto_info via the TLS_TX/TLS_RX setsockopts This API has been tested with gnutls to make sure that it allows userspace libraries to implement key updates [2]. Thanks to Frantisek Krenzelok <fkrenzel(a)redhat.com> for providing the implementation in gnutls and testing the kernel patches. Note: in a future series, I'll clean up tls_set_sw_offload and eliminate the per-cipher copy-paste using tls_cipher_size_desc. [1] https://www.rfc-editor.org/rfc/rfc8446#section-4.6.3 [2] https://gitlab.com/gnutls/gnutls/-/merge_requests/1625 Changes in v2 use reverse xmas tree ordering in tls_set_sw_offload and do_tls_setsockopt_conf turn the alt_crypto_info into an else if selftests: add rekey_fail test Vadim suggested simplifying tls_set_sw_offload by copying the new crypto_info in the context in do_tls_setsockopt_conf, and then detecting the rekey in tls_set_sw_offload based on whether the iv was already set, but I don't think we can have a common error path (otherwise we'd free the aead etc on rekey failure). I decided instead to reorganize tls_set_sw_offload so that the context is unmodified until we know the rekey cannot fail. Some fields will be touched during the rekey, but they will be set to the same value they had before the rekey (prot->rec_seq_size, etc). Apoorv suggested to name the struct tls_crypto_info_keys "tls13" rather than "tls12". Since we're using the same crypto_info data for TLS1.3 as for 1.2, even if the tests only run for TLS1.3, I'd rather keep the "tls12" name, in case we end up adding a "tls13_crypto_info_aes_gcm_128" type in the future. Kuniyuki and Apoorv also suggested preventing rekeys on RX when we haven't received a matching KeyUpdate message, but I'd rather let userspace handle this and have a symmetric API between TX and RX on the kernel side. It's a bit of a foot-gun, but we can't really stop a broken userspace from rolling back the rec_seq on an existing crypto_info either, and that seems like a worse possible breakage. Sabrina Dubroca (5): tls: remove tls_context argument from tls_set_sw_offload tls: block decryption when a rekey is pending tls: implement rekey for TLS1.3 selftests: tls: add key_generation argument to tls_crypto_info_init selftests: tls: add rekey tests include/net/tls.h | 4 + net/tls/tls.h | 3 +- net/tls/tls_device.c | 2 +- net/tls/tls_main.c | 37 +++- net/tls/tls_sw.c | 189 +++++++++++++---- tools/testing/selftests/net/tls.c | 336 +++++++++++++++++++++++++++++- 6 files changed, 511 insertions(+), 60 deletions(-) -- 2.38.1

1 year, 1 month

2
20
0 0

[PATCH v2 00/41] RPCSEC GSS krb5 enhancements

by Chuck Lever

The purpose of this series is to improve/harden the security provided by the Linux kernel's RPCSEC GSS Kerberos 5 mechanism. There are lots of clean-ups in this series, but the pertinent feature is the addition of a clean deprecation path for the DES- and SHA1-based encryption types in accordance with Internet BCPs. This series disables DES-based enctypes by default, provides a mechanism for disabling SHA1-based enctypes, and introduces two modern enctypes that do not use deprecated crypto algorithms. Not only does that improve security for Kerberos 5 users, but it also prepares SunRPC for eventually switching to a shared common kernel Kerberos 5 implementation, which surely will not implement any deprecated encryption types (in particular, DES-based ones). Today, MIT supports both of the newly-introduced enctypes, but Heimdal does not appear to. Thus distributions can enable and disable kernel enctype support to match the set of enctypes supported in their user space Kerberos libraries. Scott has been kicking the tires -- we've found no regressions with the current SHA1-based enctypes, while the new ones are disabled by default until we have an opportunity for interop testing. The KUnit tests for the new enctypes pass and this implementation successfully interoperates with itself using these enctypes. Therefore I believe it to be safe to merge. When this series gets merged, the Linux NFS community should select and announce a date-certain for removal of SunRPC's DES-based enctype code. --- Changes since v1: - Addressed Simo's NAK on "SUNRPC: Improve Kerberos confounder generation" - Added Cc: linux-kselftest@ for review of the KUnit-related patches Chuck Lever (41): SUNRPC: Add header ifdefs to linux/sunrpc/gss_krb5.h SUNRPC: Remove .blocksize field from struct gss_krb5_enctype SUNRPC: Remove .conflen field from struct gss_krb5_enctype SUNRPC: Improve Kerberos confounder generation SUNRPC: Obscure Kerberos session key SUNRPC: Refactor set-up for aux_cipher SUNRPC: Obscure Kerberos encryption keys SUNRPC: Obscure Kerberos signing keys SUNRPC: Obscure Kerberos integrity keys SUNRPC: Refactor the GSS-API Per Message calls in the Kerberos mechanism SUNRPC: Remove another switch on ctx->enctype SUNRPC: Add /proc/net/rpc/gss_krb5_enctypes file NFSD: Replace /proc/fs/nfsd/supported_krb5_enctypes with a symlink SUNRPC: Replace KRB5_SUPPORTED_ENCTYPES macro SUNRPC: Enable rpcsec_gss_krb5.ko to be built without CRYPTO_DES SUNRPC: Remove ->encrypt and ->decrypt methods from struct gss_krb5_enctype SUNRPC: Rename .encrypt_v2 and .decrypt_v2 methods SUNRPC: Hoist KDF into struct gss_krb5_enctype SUNRPC: Clean up cipher set up for v1 encryption types SUNRPC: Parametrize the key length passed to context_v2_alloc_cipher() SUNRPC: Add new subkey length fields SUNRPC: Refactor CBC with CTS into helpers SUNRPC: Add gk5e definitions for RFC 8009 encryption types SUNRPC: Add KDF-HMAC-SHA2 SUNRPC: Add RFC 8009 encryption and decryption functions SUNRPC: Advertise support for RFC 8009 encryption types SUNRPC: Support the Camellia enctypes SUNRPC: Add KDF_FEEDBACK_CMAC SUNRPC: Advertise support for the Camellia encryption types SUNRPC: Move remaining internal definitions to gss_krb5_internal.h SUNRPC: Add KUnit tests for rpcsec_krb5.ko SUNRPC: Export get_gss_krb5_enctype() SUNRPC: Add KUnit tests RFC 3961 Key Derivation SUNRPC: Add Kunit tests for RFC 3962-defined encryption/decryption SUNRPC: Add KDF KUnit tests for the RFC 6803 encryption types SUNRPC: Add checksum KUnit tests for the RFC 6803 encryption types SUNRPC: Add encryption KUnit tests for the RFC 6803 encryption types SUNRPC: Add KDF-HMAC-SHA2 Kunit tests SUNRPC: Add RFC 8009 checksum KUnit tests SUNRPC: Add RFC 8009 encryption KUnit tests SUNRPC: Add encryption self-tests fs/nfsd/nfsctl.c | 74 +- include/linux/sunrpc/gss_krb5.h | 196 +-- include/linux/sunrpc/gss_krb5_enctypes.h | 41 - net/sunrpc/.kunitconfig | 30 + net/sunrpc/Kconfig | 96 +- net/sunrpc/auth_gss/Makefile | 2 + net/sunrpc/auth_gss/auth_gss.c | 17 + net/sunrpc/auth_gss/gss_krb5_crypto.c | 656 +++++-- net/sunrpc/auth_gss/gss_krb5_internal.h | 232 +++ net/sunrpc/auth_gss/gss_krb5_keys.c | 416 ++++- net/sunrpc/auth_gss/gss_krb5_mech.c | 730 +++++--- net/sunrpc/auth_gss/gss_krb5_seal.c | 122 +- net/sunrpc/auth_gss/gss_krb5_seqnum.c | 2 + net/sunrpc/auth_gss/gss_krb5_test.c | 2040 ++++++++++++++++++++++ net/sunrpc/auth_gss/gss_krb5_unseal.c | 63 +- net/sunrpc/auth_gss/gss_krb5_wrap.c | 124 +- net/sunrpc/auth_gss/svcauth_gss.c | 65 + 17 files changed, 4001 insertions(+), 905 deletions(-) delete mode 100644 include/linux/sunrpc/gss_krb5_enctypes.h create mode 100644 net/sunrpc/.kunitconfig create mode 100644 net/sunrpc/auth_gss/gss_krb5_internal.h create mode 100644 net/sunrpc/auth_gss/gss_krb5_test.c -- Chuck Lever

1 year, 1 month

8
64
0 0

[PATCH v2 0/6] use canonical ftrace path whenever possible

by Ross Zwisler

Changes in v2: * Dropped patches which were pulled into maintainer trees. * Split BPF patches out into another series targeting bpf-next. * trace-agent now falls back to debugfs if tracefs isn't present. * Added Acked-by from mst(a)redhat.com to series. * Added a typo fixup for the virtio-trace README. Steven, assuming there are no objections, would you feel comfortable taking this series through your tree? --- The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing There are many places where this older debugfs path is still used in code comments, selftests, examples and tools, so let's update them to avoid confusion. I've broken up the series as best I could by maintainer or directory, and I've only sent people the patches that I think they care about to avoid spamming everyone. Ross Zwisler (6): tracing: always use canonical ftrace path selftests: use canonical ftrace path leaking_addresses: also skip canonical ftrace path tools/kvm_stat: use canonical ftrace path tools/virtio: use canonical ftrace path tools/virtio: fix typo in README instructions include/linux/kernel.h | 2 +- include/linux/tracepoint.h | 4 ++-- kernel/trace/Kconfig | 20 +++++++++---------- kernel/trace/kprobe_event_gen_test.c | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/synth_event_gen_test.c | 2 +- kernel/trace/trace.c | 2 +- samples/user_events/example.c | 4 ++-- scripts/leaking_addresses.pl | 1 + scripts/tracing/draw_functrace.py | 6 +++--- tools/kvm/kvm_stat/kvm_stat | 2 +- tools/lib/api/fs/tracing_path.c | 4 ++-- .../testing/selftests/user_events/dyn_test.c | 2 +- .../selftests/user_events/ftrace_test.c | 10 +++++----- .../testing/selftests/user_events/perf_test.c | 8 ++++---- tools/testing/selftests/vm/protection_keys.c | 4 ++-- tools/tracing/latency/latency-collector.c | 2 +- tools/virtio/virtio-trace/README | 4 ++-- tools/virtio/virtio-trace/trace-agent.c | 12 +++++++---- 19 files changed, 49 insertions(+), 44 deletions(-) -- 2.39.1.637.g21b0678d19-goog

1 year, 1 month

5
8
0 0

[PATCH mm-unstable v1] selftests/vm: cow: Add COW tests for collapsing of PTE-mapped anon THP

by David Hildenbrand

Currently, anonymous PTE-mapped THPs cannot be collapsed in-place: collapsing (e.g., via MADV_COLLAPSE) implies allocating a fresh THP and mapping that new THP via a PMD: as it's a fresh anon THP, it will get the exclusive flag set on the head page and everybody is happy. However, if the kernel would ever support in-place collapse of anonymous THPs (replacing a page table mapping each sub-page of a THP via PTEs with a single PMD mapping the complete THP), exclusivity information stored for each sub-page would have to be collapsed accordingly: (1) All PTEs map !exclusive anon sub-pages: the in-place collapsed THP must not not have the exclusive flag set on the head page mapped by the PMD. This is the easiest case to handle ("simply don't set any exclusive flags"). (2) All PTEs map exclusive anon sub-pages: when collapsing, we have to clear the exclusive flag from all tail pages and only leave the exclusive flag set for the head page. Otherwise, fork() after collapse would not clear the exclusive flags from the tail pages and we'd be in trouble once PTE-mapping the shared THP when writing to shared tail pages that still have the exclusive flag set. This would effectively revert what the PTE-mapping code does when propagating the exclusive flag to all sub-pages. (3) PTEs map a mixture of exclusive and !exclusive anon sub-pages (can happen e.g., due to MADV_DONTFORK before fork()). We must not collapse the THP in-place, otherwise bad things may happen: the exclusive flags of sub-pages would get ignored and the exclusive flag of the head page would get used instead. Now that we have MADV_COLLAPSE in place to trigger collapsing a THP, let's add some test cases that would bail out early, if we'd voluntarily/accidantially unlock in-place collapse for anon THPs and forget about taking proper care of exclusive flags. Running the test on a kernel with MADV_COLLAPSE support: # [INFO] Anonymous THP tests # [RUN] Basic COW after fork() when collapsing before fork() ok 169 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (fully shared) ok 170 # SKIP MADV_COLLAPSE failed: Invalid argument # [RUN] Basic COW after fork() when collapsing after fork() (lower shared) ok 171 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (upper shared) ok 172 No leak from parent into child For now, MADV_COLLAPSE always seems to fail if all PTEs map shared sub-pages. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Nadav Amit <nadav.amit(a)gmail.com> Cc: Zach O'Keefe <zokeefe(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- A patch from Hugh made me explore the wonderful world of in-place collapse of THP, and I was briefly concerned that it would apply to anon THP as well. After thinking about it a bit, I decided to add test cases, to better be safe than sorry in any case, and to document how PG_anon_exclusive is to be handled in that case. --- tools/testing/selftests/vm/cow.c | 228 +++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+) diff --git a/tools/testing/selftests/vm/cow.c b/tools/testing/selftests/vm/cow.c index 26f6ea3079e2..16216d893d96 100644 --- a/tools/testing/selftests/vm/cow.c +++ b/tools/testing/selftests/vm/cow.c @@ -30,6 +30,10 @@ #include "../kselftest.h" #include "vm_util.h" +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif + static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -1178,6 +1182,228 @@ static int tests_per_anon_test_case(void) return tests; } +enum anon_thp_collapse_test { + ANON_THP_COLLAPSE_UNSHARED, + ANON_THP_COLLAPSE_FULLY_SHARED, + ANON_THP_COLLAPSE_LOWER_SHARED, + ANON_THP_COLLAPSE_UPPER_SHARED, +}; + +static void do_test_anon_thp_collapse(char *mem, size_t size, + enum anon_thp_collapse_test test) +{ + struct comm_pipes comm_pipes; + char buf; + int ret; + + ret = setup_comm_pipes(&comm_pipes); + if (ret) { + ksft_test_result_fail("pipe() failed\n"); + return; + } + + /* + * Trigger PTE-mapping the THP by temporarily mapping a single subpage + * R/O, such that we can try collapsing it later. + */ + ret = mprotect(mem + pagesize, pagesize, PROT_READ); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + /* Collapse before actually COW-sharing the page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* COW-share the full PTE-mapped THP. */ + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* Don't COW-share the upper part of the THP. */ + ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + /* Don't COW-share the lower part of the THP. */ + ret = madvise(mem, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + ret = fork(); + if (ret < 0) { + ksft_test_result_fail("fork() failed\n"); + goto close_comm_pipes; + } else if (!ret) { + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + case ANON_THP_COLLAPSE_FULLY_SHARED: + exit(child_memcmp_fn(mem, size, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + exit(child_memcmp_fn(mem, size / 2, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + exit(child_memcmp_fn(mem + size / 2, size / 2, + &comm_pipes)); + break; + default: + assert(false); + } + } + + while (read(comm_pipes.child_ready[0], &buf, 1) != 1) + ; + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* + * Revert MADV_DONTFORK such that we merge the VMAs and are + * able to actually collapse. + */ + ret = madvise(mem, size, MADV_DOFORK); + if (ret) { + ksft_test_result_fail("MADV_DOFORK failed\n"); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + /* FALLTHROUGH */ + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* Collapse before anyone modified the COW-shared page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + /* Modify the page. */ + memset(mem, 0xff, size); + write(comm_pipes.parent_ready[1], "0", 1); + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + + ksft_test_result(!ret, "No leak from parent into child\n"); +close_comm_pipes: + close_comm_pipes(&comm_pipes); +} + +static void test_anon_thp_collapse_unshared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UNSHARED); +} + +static void test_anon_thp_collapse_fully_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_FULLY_SHARED); +} + +static void test_anon_thp_collapse_lower_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_LOWER_SHARED); +} + +static void test_anon_thp_collapse_upper_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UPPER_SHARED); +} + +/* + * Test cases that are specific to anonymous THP: pages in private mappings + * that may get shared via COW during fork(). + */ +static const struct test_case anon_thp_test_cases[] = { + /* + * Basic COW test for fork() without any GUP when collapsing a THP + * before fork(). + * + * Re-mapping a PTE-mapped anon THP using a single PMD ("in-place + * collapse") might easily get COW handling wrong when not collapsing + * exclusivity information properly. + */ + { + "Basic COW after fork() when collapsing before fork()", + test_anon_thp_collapse_unshared, + }, + /* Basic COW test, but collapse after COW-sharing a full THP. */ + { + "Basic COW after fork() when collapsing after fork() (fully shared)", + test_anon_thp_collapse_fully_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the lower half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (lower shared)", + test_anon_thp_collapse_lower_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the upper half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (upper shared)", + test_anon_thp_collapse_upper_shared, + }, +}; + +static void run_anon_thp_test_cases(void) +{ + int i; + + if (!thpsize) + return; + + ksft_print_msg("[INFO] Anonymous THP tests\n"); + + for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) { + struct test_case const *test_case = &anon_thp_test_cases[i]; + + ksft_print_msg("[RUN] %s\n", test_case->desc); + do_run_with_thp(test_case->fn, THP_RUN_PMD); + } +} + +static int tests_per_anon_thp_test_case(void) +{ + return thpsize ? 1 : 0; +} + typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); static void test_cow(char *mem, const char *smem, size_t size) @@ -1518,6 +1744,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); @@ -1526,6 +1753,7 @@ int main(int argc, char **argv) ksft_exit_fail_msg("opening pagemap failed\n"); run_anon_test_cases(); + run_anon_thp_test_cases(); run_non_anon_test_cases(); err = ksft_get_fail_cnt(); -- 2.39.0

1 year, 1 month

2
2
0 0

[PATCH 00/14] Add iommufd physical device operations for replace and alloc hwpt

by Jason Gunthorpe

This is the basic functionality for iommufd to support iommufd_device_replace() and IOMMU_HWPT_ALLOC for physical devices. iommufd_device_replace() allows changing the HWPT associated with the device to a new IOAS or HWPT. Replace does this in way that failure leaves things unchanged, and utilizes the iommu iommu_group_replace_domain() API to allow the iommu driver to perform an optional non-disruptive change. IOMMU_HWPT_ALLOC allows HWPTs to be explicitly allocated by the user and used by attach or replace. At this point it isn't very useful since the HWPT is the same as the automatically managed HWPT from the IOAS. However a following series will allow userspace to customize the created HWPT. The implementation is complicated because we have to introduce some per-iommu_group memory in iommufd and redo how we think about multi-device groups to be more explicit. This solves all the locking problems in the prior attempts. This series is infrastructure work for the following series which: - Add replace for attach - Expose replace through VFIO APIs - Implement driver parameters for HWPT creation (nesting) Once review of this is complete I will keep it on a side branch and accumulate the following series when they are ready so we can have a stable base and make more incremental progress. When we have all the parts together to get a full implementation it can go to Linus. I have this on github: https://github.com/jgunthorpe/linux/commits/iommufd_hwpt Jason Gunthorpe (12): iommufd: Move isolated msi enforcement to iommufd_device_bind() iommufd: Add iommufd_group iommufd: Replace the hwpt->devices list with iommufd_group iommufd: Use the iommufd_group to avoid duplicate reserved groups and msi setup iommufd: Make sw_msi_start a group global iommufd: Move putting a hwpt to a helper function iommufd: Add enforced_cache_coherency to iommufd_hw_pagetable_alloc() iommufd: Add iommufd_device_replace() iommufd: Make destroy_rwsem use a lock class per object type iommufd: Add IOMMU_HWPT_ALLOC iommufd/selftest: Return the real idev id from selftest mock_domain iommufd/selftest: Add a selftest for IOMMU_HWPT_ALLOC Nicolin Chen (2): iommu: Introduce a new iommu_group_replace_domain() API iommufd/selftest: Test iommufd_device_replace() drivers/iommu/iommu-priv.h | 10 + drivers/iommu/iommu.c | 30 ++ drivers/iommu/iommufd/device.c | 482 +++++++++++++----- drivers/iommu/iommufd/hw_pagetable.c | 96 +++- drivers/iommu/iommufd/io_pagetable.c | 5 +- drivers/iommu/iommufd/iommufd_private.h | 44 +- drivers/iommu/iommufd/iommufd_test.h | 7 + drivers/iommu/iommufd/main.c | 17 +- drivers/iommu/iommufd/selftest.c | 40 ++ include/linux/iommufd.h | 1 + include/uapi/linux/iommufd.h | 26 + tools/testing/selftests/iommu/iommufd.c | 64 ++- .../selftests/iommu/iommufd_fail_nth.c | 57 ++- tools/testing/selftests/iommu/iommufd_utils.h | 59 ++- 14 files changed, 758 insertions(+), 180 deletions(-) create mode 100644 drivers/iommu/iommu-priv.h base-commit: ac395958f9156733246b5bc3a481c6d38c321a7a -- 2.39.1

1 year, 1 month

4
63
0 0

[PATCH] KVM: selftest: Add dependency rules in makefile for C source code

by Yu Zhang

Currently, KVM selftests have to run "make clean && make" to rebuild the entire test suite each time a header file is modified. Define "-MD" as an EXTRA_CFLAGS, so we can generate the dependency rules for each target object, whose prerequisites contains the source file and the included header files as well. And including those dependency files in KVM selftests' makefile will release us from such annoyance. Signed-off-by: Yu Zhang <yu.c.zhang(a)linux.intel.com> --- tools/testing/selftests/kvm/Makefile | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 1750f91dd936..b329e0d1a460 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -180,6 +180,8 @@ TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) LIBKVM += $(LIBKVM_$(ARCH_DIR)) +OVERRIDE_TARGETS = 1 + # lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most # importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, # which causes the environment variable to override the makefile). @@ -198,9 +200,11 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ + -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. \ $(KHDR_INCLUDES) +EXTRA_CFLAGS += -MD + no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) @@ -218,11 +222,22 @@ LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) -EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.* +TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) +TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) +-include $(TEST_DEP_FILES) + +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ +$(TEST_GEN_OBJ): %.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(EXTRA_CFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) cscope.* x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + $(CC) $(CFLAGS) $(CPPFLAGS) $(EXTRA_CFLAGS) $(TARGET_ARCH) -c $< -o $@ $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -- 2.25.1

1 year, 1 month

2
2
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror February 2023