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

[GIT PULL] __auto_type conversion for v6.19-rc1

by H. Peter Anvin

Hi Linus, The following changes since commit c2f2b01b74be8b40a2173372bcd770723f87e7b2: Merge tag 'i3c/for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/i3c/linux (2025-12-08 11:25:14 +0900) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/hpa/linux-auto.git for you to fetch changes up to branch auto-type-for-6.19 (4ecc26fa585216f98d71411ce182f9e823d94c8c): tools/virtio: replace "__auto_type" with "auto" (2025-12-08 15:32:15 -0800) ---------------------------------------------------------------- H. Peter Anvin (7): compiler_types.h: add "auto" as a macro for "__auto_type" include/linux: change "__auto_type" to "auto" fs/proc: replace "__auto_type" with "const auto" arch/nios2: replace "__auto_type" and adjacent equivalent with "auto" arch/x86: replace "__auto_type" with "auto" selftests/bpf: replace "__auto_type" with "auto" tools/virtio: replace "__auto_type" with "auto" arch/nios2/include/asm/uaccess.h | 8 ++++---- arch/x86/include/asm/bug.h | 2 +- arch/x86/include/asm/string_64.h | 6 +++--- arch/x86/include/asm/uaccess_64.h | 2 +- fs/proc/inode.c | 19 +++++++++---------- include/linux/cleanup.h | 6 +++--- include/linux/compiler.h | 2 +- include/linux/compiler_types.h | 13 +++++++++++++ include/linux/minmax.h | 6 +++--- .../testing/selftests/bpf/prog_tests/socket_helpers.h | 9 +++++++-- tools/virtio/linux/compiler.h | 2 +- 11 files changed, 46 insertions(+), 29 deletions(-) diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h index b8299082adbe..6ccc9a232c23 100644 --- a/arch/nios2/include/asm/uaccess.h +++ b/arch/nios2/include/asm/uaccess.h @@ -172,15 +172,15 @@ do { \ #define __put_user(x, ptr) \ ({ \ - __auto_type __pu_ptr = (ptr); \ - typeof(*__pu_ptr) __pu_val = (typeof(*__pu_ptr))(x); \ + auto __pu_ptr = (ptr); \ + auto __pu_val = (typeof(*__pu_ptr))(x); \ __put_user_common(__pu_val, __pu_ptr); \ }) #define put_user(x, ptr) \ ({ \ - __auto_type __pu_ptr = (ptr); \ - typeof(*__pu_ptr) __pu_val = (typeof(*__pu_ptr))(x); \ + auto __pu_ptr = (ptr); \ + auto __pu_val = (typeof(*__pu_ptr))(x); \ access_ok(__pu_ptr, sizeof(*__pu_ptr)) ? \ __put_user_common(__pu_val, __pu_ptr) : \ -EFAULT; \ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index ee23b98353d7..d561a8443c13 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -129,7 +129,7 @@ do { \ #define __WARN_FLAGS(cond_str, flags) \ do { \ - __auto_type __flags = BUGFLAG_WARNING|(flags); \ + auto __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ _BUG_FLAGS(cond_str, ASM_UD2, __flags, ARCH_WARN_REACHABLE); \ instrumentation_end(); \ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 79e9695dc13e..4635616863f5 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -31,7 +31,7 @@ KCFI_REFERENCE(__memset); #define __HAVE_ARCH_MEMSET16 static inline void *memset16(uint16_t *s, uint16_t v, size_t n) { - const __auto_type s0 = s; + const auto s0 = s; asm volatile ( "rep stosw" : "+D" (s), "+c" (n) @@ -44,7 +44,7 @@ static inline void *memset16(uint16_t *s, uint16_t v, size_t n) #define __HAVE_ARCH_MEMSET32 static inline void *memset32(uint32_t *s, uint32_t v, size_t n) { - const __auto_type s0 = s; + const auto s0 = s; asm volatile ( "rep stosl" : "+D" (s), "+c" (n) @@ -57,7 +57,7 @@ static inline void *memset32(uint32_t *s, uint32_t v, size_t n) #define __HAVE_ARCH_MEMSET64 static inline void *memset64(uint64_t *s, uint64_t v, size_t n) { - const __auto_type s0 = s; + const auto s0 = s; asm volatile ( "rep stosq" : "+D" (s), "+c" (n) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 641f45c22f9d..915124011c27 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -72,7 +72,7 @@ static inline void __user *mask_user_address(const void __user *ptr) return ret; } #define masked_user_access_begin(x) ({ \ - __auto_type __masked_ptr = (x); \ + auto __masked_ptr = (x); \ __masked_ptr = mask_user_address(__masked_ptr); \ __uaccess_begin(); __masked_ptr; }) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 2d3425cfa94b..b7634f975d98 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -303,7 +303,7 @@ static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter) static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos) { - __auto_type read = pde->proc_ops->proc_read; + const auto read = pde->proc_ops->proc_read; if (read) return read(file, buf, count, ppos); return -EIO; @@ -325,7 +325,7 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - __auto_type write = pde->proc_ops->proc_write; + const auto write = pde->proc_ops->proc_write; if (write) return write(file, buf, count, ppos); return -EIO; @@ -347,7 +347,7 @@ static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts) { - __auto_type poll = pde->proc_ops->proc_poll; + const auto poll = pde->proc_ops->proc_poll; if (poll) return poll(file, pts); return DEFAULT_POLLMASK; @@ -369,7 +369,7 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { - __auto_type ioctl = pde->proc_ops->proc_ioctl; + const auto ioctl = pde->proc_ops->proc_ioctl; if (ioctl) return ioctl(file, cmd, arg); return -ENOTTY; @@ -392,7 +392,7 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne #ifdef CONFIG_COMPAT static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { - __auto_type compat_ioctl = pde->proc_ops->proc_compat_ioctl; + const auto compat_ioctl = pde->proc_ops->proc_compat_ioctl; if (compat_ioctl) return compat_ioctl(file, cmd, arg); return -ENOTTY; @@ -414,7 +414,7 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma) { - __auto_type mmap = pde->proc_ops->proc_mmap; + const auto mmap = pde->proc_ops->proc_mmap; if (mmap) return mmap(file, vma); return -EIO; @@ -497,7 +497,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) if (!use_pde(pde)) return -ENOENT; - __auto_type release = pde->proc_ops->proc_release; + const auto release = pde->proc_ops->proc_release; if (release) { pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); if (!pdeo) { @@ -534,10 +534,9 @@ static int proc_reg_release(struct inode *inode, struct file *file) struct pde_opener *pdeo; if (pde_is_permanent(pde)) { - __auto_type release = pde->proc_ops->proc_release; - if (release) { + const auto release = pde->proc_ops->proc_release; + if (release) return release(inode, file); - } return 0; } diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 0b55a8f6c59e..8d41b917c77d 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -212,10 +212,10 @@ #define __free(_name) __cleanup(__free_##_name) -#define __get_and_null(p, nullvalue) \ +#define __get_and_null(p, nullvalue) \ ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ + auto __ptr = &(p); \ + auto __val = *__ptr; \ *__ptr = nullvalue; \ __val; \ }) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ff71bebe56f5..04487c9bd751 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -190,7 +190,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define data_race(expr) \ ({ \ __kcsan_disable_current(); \ - __auto_type __v = (expr); \ + auto __v = (expr); \ __kcsan_enable_current(); \ __v; \ }) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3eac51d68426..41172a28ce76 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -13,6 +13,19 @@ #ifndef __ASSEMBLY__ +/* + * C23 introduces "auto" as a standard way to define type-inferred + * variables, but "auto" has been a (useless) keyword even since K&R C, + * so it has always been "namespace reserved." + * + * Until at some future time we require C23 support, we need the gcc + * extension __auto_type, but there is no reason to put that elsewhere + * in the source code. + */ +#if __STDC_VERSION__ < 202311L +# define auto __auto_type +#endif + /* * Skipped when running bindgen due to a libclang issue; * see https://github.com/rust-lang/rust-bindgen/issues/2244. diff --git a/include/linux/minmax.h b/include/linux/minmax.h index eaaf5c008e4d..a0158db54a04 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -89,7 +89,7 @@ __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __careful_cmp_once(op, x, y, ux, uy) ({ \ - __auto_type ux = (x); __auto_type uy = (y); \ + auto ux = (x); auto uy = (y); \ BUILD_BUG_ON_MSG(!__types_ok(ux, uy), \ #op"("#x", "#y") signedness error"); \ __cmp(op, ux, uy); }) @@ -129,7 +129,7 @@ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) #define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ - __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + auto ux = (x); auto uy = (y); auto uz = (z); \ BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz), \ #op"3("#x", "#y", "#z") signedness error"); \ __cmp(op, ux, __cmp(op, uy, uz)); }) @@ -203,7 +203,7 @@ * This macro checks @val/@lo/@hi to make sure they have compatible * signedness. */ -#define clamp(val, lo, hi) __careful_clamp(__auto_type, val, lo, hi) +#define clamp(val, lo, hi) __careful_clamp(auto, val, lo, hi) /** * clamp_t - return a value clamped to a given range using a given type diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h index e02cabcc814e..0d59503a0c73 100644 --- a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -17,11 +17,16 @@ #define VMADDR_CID_LOCAL 1 #endif +/* include/linux/compiler_types.h */ +#if __STDC_VERSION__ < 202311L && !defined(auto) +# define auto __auto_type +#endif + /* include/linux/cleanup.h */ #define __get_and_null(p, nullvalue) \ ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ + auto __ptr = &(p); \ + auto __val = *__ptr; \ *__ptr = nullvalue; \ __val; \ }) diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h index 204ef0e9f542..725b93bfeee1 100644 --- a/tools/virtio/linux/compiler.h +++ b/tools/virtio/linux/compiler.h @@ -31,7 +31,7 @@ */ #define data_race(expr) \ ({ \ - __auto_type __v = (expr); \ + auto __v = (expr); \ __v; \ })

5 days, 16 hours

5
12
0 0

[PATCH net-next v7 0/5] net: devmem: improve cpu cost of RX token management

by Bobby Eshleman

This series improves the CPU cost of RX token management by adding an attribute to NETDEV_CMD_BIND_RX that configures sockets using the binding to avoid the xarray allocator and instead use a per-binding niov array and a uref field in niov. Improvement is ~13% cpu util per RX user thread. Using kperf, the following results were observed: Before: Average RX worker idle %: 13.13, flows 4, test runs 11 After: Average RX worker idle %: 26.32, flows 4, test runs 11 Two other approaches were tested, but with no improvement. Namely, 1) using a hashmap for tokens and 2) keeping an xarray of atomic counters but using RCU so that the hotpath could be mostly lockless. Neither of these approaches proved better than the simple array in terms of CPU. The attribute NETDEV_A_DMABUF_AUTORELEASE is added to toggle the optimization. It is an optional attribute and defaults to 0 (i.e., optimization on). To: David S. Miller <davem(a)davemloft.net> To: Eric Dumazet <edumazet(a)google.com> To: Jakub Kicinski <kuba(a)kernel.org> To: Paolo Abeni <pabeni(a)redhat.com> To: Simon Horman <horms(a)kernel.org> To: Kuniyuki Iwashima <kuniyu(a)google.com> To: Willem de Bruijn <willemb(a)google.com> To: Neal Cardwell <ncardwell(a)google.com> To: David Ahern <dsahern(a)kernel.org> To: Mina Almasry <almasrymina(a)google.com> To: Arnd Bergmann <arnd(a)arndb.de> To: Jonathan Corbet <corbet(a)lwn.net> To: Andrew Lunn <andrew+netdev(a)lunn.ch> To: Shuah Khan <shuah(a)kernel.org> Cc: Stanislav Fomichev <sdf(a)fomichev.me> Cc: netdev(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-doc(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> Changes in v7: - use netlink instead of sockopt (Stan) - restrict system to only one mode, dmabuf bindings can not co-exist with different modes (Stan) - use static branching to enforce single system-wide mode (Stan) - Link to v6: https://lore.kernel.org/r/20251104-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v6: - renamed 'net: devmem: use niov array for token management' to refer to optionality of new config - added documentation and tests - make autorelease flag per-socket sockopt instead of binding field / sysctl - many per-patch changes (see Changes sections per-patch) - Link to v5: https://lore.kernel.org/r/20251023-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v5: - add sysctl to opt-out of performance benefit, back to old token release - Link to v4: https://lore.kernel.org/all/20250926-scratch-bobbyeshleman-devmem-tcp-token… Changes in v4: - rebase to net-next - Link to v3: https://lore.kernel.org/r/20250926-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v3: - make urefs per-binding instead of per-socket, reducing memory footprint - fallback to cleaning up references in dmabuf unbind if socket leaked tokens - drop ethtool patch - Link to v2: https://lore.kernel.org/r/20250911-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v2: - net: ethtool: prevent user from breaking devmem single-binding rule (Mina) - pre-assign niovs in binding->vec for RX case (Mina) - remove WARNs on invalid user input (Mina) - remove extraneous binding ref get (Mina) - remove WARN for changed binding (Mina) - always use GFP_ZERO for binding->vec (Mina) - fix length of alloc for urefs - use atomic_set(, 0) to initialize sk_user_frags.urefs - Link to v1: https://lore.kernel.org/r/20250902-scratch-bobbyeshleman-devmem-tcp-token-u… --- Bobby Eshleman (5): net: devmem: rename tx_vec to vec in dmabuf binding net: devmem: refactor sock_devmem_dontneed for autorelease split net: devmem: implement autorelease token management net: devmem: document NETDEV_A_DMABUF_AUTORELEASE netlink attribute selftests: drv-net: devmem: add autorelease tests Documentation/netlink/specs/netdev.yaml | 12 +++ Documentation/networking/devmem.rst | 70 +++++++++++++ include/net/netmem.h | 1 + include/net/sock.h | 7 +- include/uapi/linux/netdev.h | 1 + net/core/devmem.c | 121 ++++++++++++++++++---- net/core/devmem.h | 13 ++- net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 13 ++- net/core/sock.c | 103 ++++++++++++++---- net/ipv4/tcp.c | 78 +++++++++++--- net/ipv4/tcp_ipv4.c | 13 ++- net/ipv4/tcp_minisocks.c | 3 +- tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/drivers/net/hw/devmem.py | 22 +++- tools/testing/selftests/drivers/net/hw/ncdevmem.c | 19 ++-- 16 files changed, 401 insertions(+), 81 deletions(-) --- base-commit: 4c52142904b33b41c3ff7ee58670b4e3b3bf1120 change-id: 20250829-scratch-bobbyeshleman-devmem-tcp-token-upstream-292be174d503 Best regards, -- Bobby Eshleman <bobbyeshleman(a)meta.com>

5 days, 17 hours

5
13
0 0

[PATCH kvm-next V11 0/7] Add NUMA mempolicy support for KVM guest-memfd

by Shivank Garg

This series introduces NUMA-aware memory placement support for KVM guests with guest_memfd memory backends. It builds upon Fuad Tabba's work (V17) that enabled host-mapping for guest_memfd memory [1] and can be applied directly applied on KVM tree [2] (branch kvm-next, base commit: a6ad5413, Merge branch 'guest-memfd-mmap' into HEAD) == Background == KVM's guest-memfd memory backend currently lacks support for NUMA policy enforcement, causing guest memory allocations to be distributed across host nodes according to kernel's default behavior, irrespective of any policy specified by the VMM. This limitation arises because conventional userspace NUMA control mechanisms like mbind(2) don't work since the memory isn't directly mapped to userspace when allocations occur. Fuad's work [1] provides the necessary mmap capability, and this series leverages it to enable mbind(2). == Implementation == This series implements proper NUMA policy support for guest-memfd by: 1. Adding mempolicy-aware allocation APIs to the filemap layer. 2. Introducing custom inodes (via a dedicated slab-allocated inode cache, kvm_gmem_inode_info) to store NUMA policy and metadata for guest memory. 3. Implementing get/set_policy vm_ops in guest_memfd to support NUMA policy. With these changes, VMMs can now control guest memory placement by mapping guest_memfd file descriptor and using mbind(2) to specify: - Policy modes: default, bind, interleave, or preferred - Host NUMA nodes: List of target nodes for memory allocation These Policies affect only future allocations and do not migrate existing memory. This matches mbind(2)'s default behavior which affects only new allocations unless overridden with MPOL_MF_MOVE/MPOL_MF_MOVE_ALL flags (Not supported for guest_memfd as it is unmovable by design). == Upstream Plan == Phased approach as per David's guest_memfd extension overview [3] and community calls [4]: Phase 1 (this series): 1. Focuses on shared guest_memfd support (non-CoCo VMs). 2. Builds on Fuad's host-mapping work [1]. Phase2 (future work): 1. NUMA support for private guest_memfd (CoCo VMs). 2. Depends on SNP in-place conversion support [5]. This series provides a clean integration path for NUMA-aware memory management for guest_memfd and lays the groundwork for future confidential computing NUMA capabilities. Thanks, Shivank == Changelog == - v1,v2: Extended the KVM_CREATE_GUEST_MEMFD IOCTL to pass mempolicy. - v3: Introduced fbind() syscall for VMM memory-placement configuration. - v4-v6: Current approach using shared_policy support and vm_ops (based on suggestions from David [6] and guest_memfd bi-weekly upstream call discussion [7]). - v7: Use inodes to store NUMA policy instead of file [8]. - v8: Rebase on top of Fuad's V12: Host mmaping for guest_memfd memory. - v9: Rebase on top of Fuad's V13 and incorporate review comments - V10: Rebase on top of Fuad's V17. Use latest guest_memfd inode patch from Ackerley (with David's review comments). Use newer kmem_cache_create() API variant with arg parameter (Vlastimil) - V11: Rebase on kvm-next, remove RFC tag, use Ackerley's latest patch and fix a rcu race bug during kvm module unload. [1] https://lore.kernel.org/all/20250729225455.670324-1-seanjc@google.com [2] https://git.kernel.org/pub/scm/virt/kvm/kvm.git/log/?h=next [3] https://lore.kernel.org/all/c1c9591d-218a-495c-957b-ba356c8f8e09@redhat.com [4] https://docs.google.com/document/d/1M6766BzdY1Lhk7LiR5IqVR8B8mG3cr-cxTxOrAo… [5] https://lore.kernel.org/all/20250613005400.3694904-1-michael.roth@amd.com [6] https://lore.kernel.org/all/6fbef654-36e2-4be5-906e-2a648a845278@redhat.com [7] https://lore.kernel.org/all/2b77e055-98ac-43a1-a7ad-9f9065d7f38f@amd.com [8] https://lore.kernel.org/all/diqzbjumm167.fsf@ackerleytng-ctop.c.googlers.com Ackerley Tng (1): KVM: guest_memfd: Use guest mem inodes instead of anonymous inodes Matthew Wilcox (Oracle) (2): mm/filemap: Add NUMA mempolicy support to filemap_alloc_folio() mm/filemap: Extend __filemap_get_folio() to support NUMA memory policies Shivank Garg (4): mm/mempolicy: Export memory policy symbols KVM: guest_memfd: Add slab-allocated inode cache KVM: guest_memfd: Enforce NUMA mempolicy using shared policy KVM: guest_memfd: selftests: Add tests for mmap and NUMA policy support fs/bcachefs/fs-io-buffered.c | 2 +- fs/btrfs/compression.c | 4 +- fs/btrfs/verity.c | 2 +- fs/erofs/zdata.c | 2 +- fs/f2fs/compress.c | 2 +- include/linux/pagemap.h | 18 +- include/uapi/linux/magic.h | 1 + mm/filemap.c | 23 +- mm/mempolicy.c | 6 + mm/readahead.c | 2 +- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../testing/selftests/kvm/guest_memfd_test.c | 121 ++++++++ virt/kvm/guest_memfd.c | 262 ++++++++++++++++-- virt/kvm/kvm_main.c | 7 +- virt/kvm/kvm_mm.h | 9 +- 15 files changed, 412 insertions(+), 50 deletions(-) -- 2.43.0 --- == Earlier Postings == v10: https://lore.kernel.org/all/20250811090605.16057-2-shivankg@amd.com v9: https://lore.kernel.org/all/20250713174339.13981-2-shivankg@amd.com v8: https://lore.kernel.org/all/20250618112935.7629-1-shivankg@amd.com v7: https://lore.kernel.org/all/20250408112402.181574-1-shivankg@amd.com v6: https://lore.kernel.org/all/20250226082549.6034-1-shivankg@amd.com v5: https://lore.kernel.org/all/20250219101559.414878-1-shivankg@amd.com v4: https://lore.kernel.org/all/20250210063227.41125-1-shivankg@amd.com v3: https://lore.kernel.org/all/20241105164549.154700-1-shivankg@amd.com v2: https://lore.kernel.org/all/20240919094438.10987-1-shivankg@amd.com v1: https://lore.kernel.org/all/20240916165743.201087-1-shivankg@amd.com

5 days, 19 hours

10
38
0 0

[PATCH v1 1/3] selftests/mm: fix va_high_addr_switch.sh return value

by Chunyu Hu

Patch series "Fix va_high_addr_switch.sh test failure - again", v1. There are two issues exist for the va_high_addr_switch test. One issue is the test return value is ignored in va_high_addr_switch.sh. The second is the va_high_addr_switch requires 6 hugepages but it requires 5. Besides that, the nr_hugepages setup in run_vmtests.sh for arm64 can be done in va_high_addr_switch.sh too. This patch: (of 3) The return value should be return value of va_high_addr_switch, otherwise a test failure would be silently ignored. Fixes: d9d957bd7b61 ("selftests/mm: alloc hugepages in va_high_addr_switch test") CC: Luiz Capitulino <luizcap(a)redhat.com> Signed-off-by: Chunyu Hu <chuhu(a)redhat.com> --- tools/testing/selftests/mm/va_high_addr_switch.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index a7d4b02b21dd..f89fe078a8e6 100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -114,4 +114,6 @@ save_nr_hugepages # 4 keep_mapped pages, and one for tmp usage setup_nr_hugepages 5 ./va_high_addr_switch --run-hugetlb +retcode=$? restore_nr_hugepages +exit $retcode -- 2.49.0

5 days, 22 hours

2
6
0 0

[PATCH v12] exec: Fix dead-lock in de_thread with ptrace_attach

by Bernd Edlinger

This introduces signal->exec_bprm, which is used to fix the case when at least one of the sibling threads is traced, and therefore the trace process may dead-lock in ptrace_attach, but de_thread will need to wait for the tracer to continue execution. The solution is to detect this situation and allow ptrace_attach to continue by temporarily releasing the cred_guard_mutex, while de_thread() is still waiting for traced zombies to be eventually released by the tracer. In the case of the thread group leader we only have to wait for the thread to become a zombie, which may also need co-operation from the tracer due to PTRACE_O_TRACEEXIT. When a tracer wants to ptrace_attach a task that already is in execve, we simply retry the ptrace_may_access check while temporarily installing the new credentials and dumpability which are about to be used after execve completes. If the ptrace_attach happens on a thread that is a sibling-thread of the thread doing execve, it is sufficient to check against the old credentials, as this thread will be waited for, before the new credentials are installed. Other threads die quickly since the cred_guard_mutex is released, but a deadly signal is already pending. In case the mutex_lock_killable misses the signal, the non-zero current->signal->exec_bprm makes sure they release the mutex immediately and return with -ERESTARTNOINTR. This means there is no API change, unlike the previous version of this patch which was discussed here: https://lore.kernel.org/lkml/b6537ae6-31b1-5c50-f32b-8b8332ace882@hotmail.d… See tools/testing/selftests/ptrace/vmaccess.c for a test case that gets fixed by this change. Note that since the test case was originally designed to test the ptrace_attach returning an error in this situation, the test expectation needed to be adjusted, to allow the API to succeed at the first attempt. Signed-off-by: Bernd Edlinger <bernd.edlinger(a)hotmail.de> --- fs/exec.c | 69 ++++++++++++++++------- fs/proc/base.c | 6 ++ include/linux/cred.h | 1 + include/linux/sched/signal.h | 18 ++++++ kernel/cred.c | 28 +++++++-- kernel/ptrace.c | 32 +++++++++++ kernel/seccomp.c | 12 +++- tools/testing/selftests/ptrace/vmaccess.c | 23 +++++--- 8 files changed, 155 insertions(+), 34 deletions(-) v10: Changes to previous version, make the PTRACE_ATTACH retun -EAGAIN, instead of execve return -ERESTARTSYS. Added some lessions learned to the description. v11: Check old and new credentials in PTRACE_ATTACH again without changing the API. Note: I got actually one response from an automatic checker to the v11 patch, https://lore.kernel.org/lkml/202107121344.wu68hEPF-lkp@intel.com/ which is complaining about: >> kernel/ptrace.c:425:26: sparse: sparse: incorrect type in assignment (different address spaces) @@ expected struct cred const *old_cred @@ got struct cred const [noderef] __rcu *real_cred @@ 417 struct linux_binprm *bprm = task->signal->exec_bprm; 418 const struct cred *old_cred; 419 struct mm_struct *old_mm; 420 421 retval = down_write_killable(&task->signal->exec_update_lock); 422 if (retval) 423 goto unlock_creds; 424 task_lock(task); > 425 old_cred = task->real_cred; v12: Essentially identical to v11. - Fixed a minor merge conflict in linux v5.17, and fixed the above mentioned nit by adding __rcu to the declaration. - re-tested the patch with all linux versions from v5.11 to v6.6 v10 was an alternative approach which did imply an API change. But I would prefer to avoid such an API change. The difficult part is getting the right dumpability flags assigned before de_thread starts, hope you like this version. If not, the v10 is of course also acceptable. Thanks Bernd. diff --git a/fs/exec.c b/fs/exec.c index 2f2b0acec4f0..902d3b230485 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1041,11 +1041,13 @@ static int exec_mmap(struct mm_struct *mm) return 0; } -static int de_thread(struct task_struct *tsk) +static int de_thread(struct task_struct *tsk, struct linux_binprm *bprm) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; + struct task_struct *t = tsk; + bool unsafe_execve_in_progress = false; if (thread_group_empty(tsk)) goto no_thread_group; @@ -1068,6 +1070,19 @@ static int de_thread(struct task_struct *tsk) if (!thread_group_leader(tsk)) sig->notify_count--; + while_each_thread(tsk, t) { + if (unlikely(t->ptrace) + && (t != tsk->group_leader || !t->exit_state)) + unsafe_execve_in_progress = true; + } + + if (unlikely(unsafe_execve_in_progress)) { + spin_unlock_irq(lock); + sig->exec_bprm = bprm; + mutex_unlock(&sig->cred_guard_mutex); + spin_lock_irq(lock); + } + while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); @@ -1158,6 +1173,11 @@ static int de_thread(struct task_struct *tsk) release_task(leader); } + if (unlikely(unsafe_execve_in_progress)) { + mutex_lock(&sig->cred_guard_mutex); + sig->exec_bprm = NULL; + } + sig->group_exec_task = NULL; sig->notify_count = 0; @@ -1169,6 +1189,11 @@ static int de_thread(struct task_struct *tsk) return 0; killed: + if (unlikely(unsafe_execve_in_progress)) { + mutex_lock(&sig->cred_guard_mutex); + sig->exec_bprm = NULL; + } + /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exec_task = NULL; @@ -1253,6 +1278,24 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) return retval; + /* If the binary is not readable then enforce mm->dumpable=0 */ + would_dump(bprm, bprm->file); + if (bprm->have_execfd) + would_dump(bprm, bprm->executable); + + /* + * Figure out dumpability. Note that this checking only of current + * is wrong, but userspace depends on it. This should be testing + * bprm->secureexec instead. + */ + if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || + is_dumpability_changed(current_cred(), bprm->cred) || + !(uid_eq(current_euid(), current_uid()) && + gid_eq(current_egid(), current_gid()))) + set_dumpable(bprm->mm, suid_dumpable); + else + set_dumpable(bprm->mm, SUID_DUMP_USER); + /* * Ensure all future errors are fatal. */ @@ -1261,7 +1304,7 @@ int begin_new_exec(struct linux_binprm * bprm) /* * Make this the only thread in the thread group. */ - retval = de_thread(me); + retval = de_thread(me, bprm); if (retval) goto out; @@ -1284,11 +1327,6 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out; - /* If the binary is not readable then enforce mm->dumpable=0 */ - would_dump(bprm, bprm->file); - if (bprm->have_execfd) - would_dump(bprm, bprm->executable); - /* * Release all of the old mmap stuff */ @@ -1350,18 +1388,6 @@ int begin_new_exec(struct linux_binprm * bprm) me->sas_ss_sp = me->sas_ss_size = 0; - /* - * Figure out dumpability. Note that this checking only of current - * is wrong, but userspace depends on it. This should be testing - * bprm->secureexec instead. - */ - if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || - !(uid_eq(current_euid(), current_uid()) && - gid_eq(current_egid(), current_gid()))) - set_dumpable(current->mm, suid_dumpable); - else - set_dumpable(current->mm, SUID_DUMP_USER); - perf_event_exec(); __set_task_comm(me, kbasename(bprm->filename), true); @@ -1480,6 +1506,11 @@ static int prepare_bprm_creds(struct linux_binprm *bprm) if (mutex_lock_interruptible(&current->signal->cred_guard_mutex)) return -ERESTARTNOINTR; + if (unlikely(current->signal->exec_bprm)) { + mutex_unlock(&current->signal->cred_guard_mutex); + return -ERESTARTNOINTR; + } + bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index ffd54617c354..0da9adfadb48 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2788,6 +2788,12 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, if (rv < 0) goto out_free; + if (unlikely(current->signal->exec_bprm)) { + mutex_unlock(&current->signal->cred_guard_mutex); + rv = -ERESTARTNOINTR; + goto out_free; + } + rv = security_setprocattr(PROC_I(inode)->op.lsm, file->f_path.dentry->d_name.name, page, count); diff --git a/include/linux/cred.h b/include/linux/cred.h index f923528d5cc4..b01e309f5686 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -159,6 +159,7 @@ extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); +extern bool is_dumpability_changed(const struct cred *, const struct cred *); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0014d3adaf84..14df7073a0a8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -234,9 +234,27 @@ struct signal_struct { struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ + struct linux_binprm *exec_bprm; /* Used to check ptrace_may_access + * against new credentials while + * de_thread is waiting for other + * traced threads to terminate. + * Set while de_thread is executing. + * The cred_guard_mutex is released + * after de_thread() has called + * zap_other_threads(), therefore + * a fatal signal is guaranteed to be + * already pending in the unlikely + * event, that + * current->signal->exec_bprm happens + * to be non-zero after the + * cred_guard_mutex was acquired. + */ + struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) + * Held while execve runs, except when + * a sibling thread is being traced. * Deprecated do not use in new code. * Use exec_update_lock instead. */ diff --git a/kernel/cred.c b/kernel/cred.c index 98cb4eca23fb..586cb6c7cf6b 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -433,6 +433,28 @@ static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) return false; } +/** + * is_dumpability_changed - Will changing creds from old to new + * affect the dumpability in commit_creds? + * + * Return: false - dumpability will not be changed in commit_creds. + * Return: true - dumpability will be changed to non-dumpable. + * + * @old: The old credentials + * @new: The new credentials + */ +bool is_dumpability_changed(const struct cred *old, const struct cred *new) +{ + if (!uid_eq(old->euid, new->euid) || + !gid_eq(old->egid, new->egid) || + !uid_eq(old->fsuid, new->fsuid) || + !gid_eq(old->fsgid, new->fsgid) || + !cred_cap_issubset(old, new)) + return true; + + return false; +} + /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned @@ -467,11 +489,7 @@ int commit_creds(struct cred *new) get_cred(new); /* we will require a ref for the subj creds too */ /* dumpability changes */ - if (!uid_eq(old->euid, new->euid) || - !gid_eq(old->egid, new->egid) || - !uid_eq(old->fsuid, new->fsuid) || - !gid_eq(old->fsgid, new->fsgid) || - !cred_cap_issubset(old, new)) { + if (is_dumpability_changed(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 443057bee87c..eb1c450bb7d7 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -20,6 +20,7 @@ #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> +#include <linux/binfmts.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> @@ -435,6 +436,28 @@ static int ptrace_attach(struct task_struct *task, long request, if (retval) goto unlock_creds; + if (unlikely(task->in_execve)) { + struct linux_binprm *bprm = task->signal->exec_bprm; + const struct cred __rcu *old_cred; + struct mm_struct *old_mm; + + retval = down_write_killable(&task->signal->exec_update_lock); + if (retval) + goto unlock_creds; + task_lock(task); + old_cred = task->real_cred; + old_mm = task->mm; + rcu_assign_pointer(task->real_cred, bprm->cred); + task->mm = bprm->mm; + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); + rcu_assign_pointer(task->real_cred, old_cred); + task->mm = old_mm; + task_unlock(task); + up_write(&task->signal->exec_update_lock); + if (retval) + goto unlock_creds; + } + write_lock_irq(&tasklist_lock); retval = -EPERM; if (unlikely(task->exit_state)) @@ -508,6 +531,14 @@ static int ptrace_traceme(void) { int ret = -EPERM; + if (mutex_lock_interruptible(&current->signal->cred_guard_mutex)) + return -ERESTARTNOINTR; + + if (unlikely(current->signal->exec_bprm)) { + mutex_unlock(&current->signal->cred_guard_mutex); + return -ERESTARTNOINTR; + } + write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { @@ -523,6 +554,7 @@ static int ptrace_traceme(void) } } write_unlock_irq(&tasklist_lock); + mutex_unlock(&current->signal->cred_guard_mutex); return ret; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 255999ba9190..b29bbfa0b044 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1955,9 +1955,15 @@ static long seccomp_set_mode_filter(unsigned int flags, * Make sure we cannot change seccomp or nnp state via TSYNC * while another thread is in the middle of calling exec. */ - if (flags & SECCOMP_FILTER_FLAG_TSYNC && - mutex_lock_killable(&current->signal->cred_guard_mutex)) - goto out_put_fd; + if (flags & SECCOMP_FILTER_FLAG_TSYNC) { + if (mutex_lock_killable(&current->signal->cred_guard_mutex)) + goto out_put_fd; + + if (unlikely(current->signal->exec_bprm)) { + mutex_unlock(&current->signal->cred_guard_mutex); + goto out_put_fd; + } + } spin_lock_irq(&current->sighand->siglock); diff --git a/tools/testing/selftests/ptrace/vmaccess.c b/tools/testing/selftests/ptrace/vmaccess.c index 4db327b44586..3b7d81fb99bb 100644 --- a/tools/testing/selftests/ptrace/vmaccess.c +++ b/tools/testing/selftests/ptrace/vmaccess.c @@ -39,8 +39,15 @@ TEST(vmaccess) f = open(mm, O_RDONLY); ASSERT_GE(f, 0); close(f); - f = kill(pid, SIGCONT); - ASSERT_EQ(f, 0); + f = waitpid(-1, NULL, 0); + ASSERT_NE(f, -1); + ASSERT_NE(f, 0); + ASSERT_NE(f, pid); + f = waitpid(-1, NULL, 0); + ASSERT_EQ(f, pid); + f = waitpid(-1, NULL, 0); + ASSERT_EQ(f, -1); + ASSERT_EQ(errno, ECHILD); } TEST(attach) @@ -57,22 +64,24 @@ TEST(attach) sleep(1); k = ptrace(PTRACE_ATTACH, pid, 0L, 0L); - ASSERT_EQ(errno, EAGAIN); - ASSERT_EQ(k, -1); + ASSERT_EQ(k, 0); k = waitpid(-1, &s, WNOHANG); ASSERT_NE(k, -1); ASSERT_NE(k, 0); ASSERT_NE(k, pid); ASSERT_EQ(WIFEXITED(s), 1); ASSERT_EQ(WEXITSTATUS(s), 0); - sleep(1); - k = ptrace(PTRACE_ATTACH, pid, 0L, 0L); + k = waitpid(-1, &s, 0); + ASSERT_EQ(k, pid); + ASSERT_EQ(WIFSTOPPED(s), 1); + ASSERT_EQ(WSTOPSIG(s), SIGTRAP); + k = ptrace(PTRACE_CONT, pid, 0L, 0L); ASSERT_EQ(k, 0); k = waitpid(-1, &s, 0); ASSERT_EQ(k, pid); ASSERT_EQ(WIFSTOPPED(s), 1); ASSERT_EQ(WSTOPSIG(s), SIGSTOP); - k = ptrace(PTRACE_DETACH, pid, 0L, 0L); + k = ptrace(PTRACE_CONT, pid, 0L, 0L); ASSERT_EQ(k, 0); k = waitpid(-1, &s, 0); ASSERT_EQ(k, pid); -- 2.39.2

6 days

17
70
0 0

[PATCH net 0/4] mptcp: misc fixes for v6.19-rc1

by Matthieu Baerts (NGI0)

Here are various unrelated fixes: - Patches 1-2: ignore unknown in-kernel PM endpoint flags instead of pretending they are supported. A fix for v5.7. - Patch 3: avoid potential unnecessary rtx timer expiration. A fix for v5.15. - Patch 4: avoid a deadlock on fallback in case of SKB creation failure while re-injecting. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (2): mptcp: pm: ignore unknown endpoint flags selftests: mptcp: pm: ensure unknown flags are ignored Paolo Abeni (2): mptcp: schedule rtx timer only after pushing data mptcp: avoid deadlock on fallback while reinjecting include/uapi/linux/mptcp.h | 1 + net/mptcp/pm_netlink.c | 3 ++- net/mptcp/protocol.c | 22 ++++++++++++++-------- tools/testing/selftests/net/mptcp/pm_netlink.sh | 4 ++++ tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 11 +++++++++++ 5 files changed, 32 insertions(+), 9 deletions(-) --- base-commit: 0373d5c387f24de749cc22e694a14b3a7c7eb515 change-id: 20251205-net-mptcp-misc-fixes-6-19-rc1-5174bd3df981 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

6 days, 1 hour

2
5
0 0

[PATCH nf-next v2 0/4] Add IP6IP6 flowtable SW acceleration

by Lorenzo Bianconi

Introduce SW acceleration for IP6IP6 tunnels in the netfilter flowtable infrastructure. --- Changes in v2: - Fix compilation when CONFIG_IPV6 is disabled - Rely on ipv6_skip_exthdr() in nf_flow_ip6_tunnel_proto() to avoid use-after-free issues - Drop patch 2/5 from v1 - Link to v1: https://lore.kernel.org/r/20251207-b4-flowtable-offload-ip6ip6-v1-0-18e3ab7… --- Lorenzo Bianconi (4): netfilter: Introduce tunnel metadata info in nf_flowtable_ctx struct netfilter: flowtable: Add IP6IP6 rx sw acceleration netfilter: flowtable: Add IP6IP6 tx sw acceleration selftests: netfilter: nft_flowtable.sh: Add IP6IP6 flowtable selftest net/ipv6/ip6_tunnel.c | 27 +++ net/netfilter/nf_flow_table_ip.c | 229 ++++++++++++++++++--- .../selftests/net/netfilter/nft_flowtable.sh | 62 +++++- 3 files changed, 275 insertions(+), 43 deletions(-) --- base-commit: f8156ef0fd8232055396ebf1e044fa06fb8bc388 change-id: 20251207-b4-flowtable-offload-ip6ip6-8e9a2c6f3a77 Best regards, -- Lorenzo Bianconi <lorenzo(a)kernel.org>

6 days, 5 hours

1
4
0 0

[PATCH v5 0/3] selftests: cgroup: Enhance robustness with polling helpers

by Guopeng Zhang

Hi all, This patch series introduces improvements to the cgroup selftests by adding a helper function to better handle asynchronous updates in cgroup statistics. These changes are especially useful for managing cgroup stats like memory.stat and cgroup.stat, which can be affected by delays (e.g., RCU callbacks and asynchronous rstat flushing). Patch 1/3 adds cg_read_key_long_poll(), a generic helper to poll a numeric key in a cgroup file until it reaches an expected value or a retry limit is hit. Patches 2/3 and 3/3 convert existing tests to use this helper, making them more robust on busy systems. v5: - Drop the "/* 3s total */" comment from MEMCG_SOCKSTAT_WAIT_RETRIES as suggested by Shakeel, so it does not become stale if the wait interval changes. - Elaborate in the commit message of patch 3/3 on the rationale behind the 8s timeout in test_kmem_dead_cgroups(), and add a comment next to KMEM_DEAD_WAIT_RETRIES explaining that it is a generous upper bound derived from stress testing and not tied to a specific kernel constant. - Add Reviewed-by: Shakeel Butt <shakeel.butt(a)linux.dev> to this series. - Link to v4: https://lore.kernel.org/all/20251124123816.486164-1-zhangguopeng@kylinos.cn/ v4: - Patch 1/3: Add the cg_read_key_long_poll() helper to poll cgroup keys with retries and configurable intervals. - Patch 2/3: Update test_memcg_sock() to use cg_read_key_long_poll() for handling delayed "sock " counter updates in memory.stat. - Patch 3/3: Replace the sleep-and-retry logic in test_kmem_dead_cgroups() with cg_read_key_long_poll() for waiting on nr_dying_descendants. - Link to v3: https://lore.kernel.org/all/p655qedqjaakrnqpytc6dltejfluxo6jrffcltfz2ivonmk… v3: - Move MEMCG_SOCKSTAT_WAIT_* defines after the #include block as suggested. - Link to v2: https://lore.kernel.org/all/5ad2b75f-748a-4e93-8d11-63295bda0cbf@linux.dev/ v2: - Clarify the rationale for the 3s timeout and mention the periodic rstat flush interval (FLUSH_TIME = 2 * HZ) in the comment. - Replace hardcoded retry count and wait interval with macros to avoid magic numbers and make the timeout calculation explicit. - Link to v1: https://lore.kernel.org/all/20251119122758.85610-1-ioworker0@gmail.com/ Thanks to Michal Koutný for the suggestion, and to Lance Yang and Shakeel Butt for their reviews and feedback. Guopeng Zhang (3): selftests: cgroup: Add cg_read_key_long_poll() to poll a cgroup key with retries selftests: cgroup: make test_memcg_sock robust against delayed sock stats selftests: cgroup: Replace sleep with cg_read_key_long_poll() for waiting on nr_dying_descendants .../selftests/cgroup/lib/cgroup_util.c | 21 ++++++++++++ .../cgroup/lib/include/cgroup_util.h | 5 +++ tools/testing/selftests/cgroup/test_kmem.c | 33 +++++++++---------- .../selftests/cgroup/test_memcontrol.c | 20 ++++++++++- 4 files changed, 60 insertions(+), 19 deletions(-) -- 2.25.1

6 days, 18 hours

3
7
0 0

[PATCH v8 00/13] Direct Map Removal Support for guest_memfd

by Kalyazin, Nikita

[ based on kvm/next ] Unmapping virtual machine guest memory from the host kernel's direct map is a successful mitigation against Spectre-style transient execution issues: if the kernel page tables do not contain entries pointing to guest memory, then any attempted speculative read through the direct map will necessarily be blocked by the MMU before any observable microarchitectural side-effects happen. This means that Spectre-gadgets and similar cannot be used to target virtual machine memory. Roughly 60% of speculative execution issues fall into this category [1, Table 1]. This patch series extends guest_memfd with the ability to remove its memory from the host kernel's direct map, to be able to attain the above protection for KVM guests running inside guest_memfd. Additionally, a Firecracker branch with support for these VMs can be found on GitHub [2]. For more details, please refer to the v5 cover letter. No substantial changes in design have taken place since. See also related write() syscall support in guest_memfd [3] where the interoperation between the two features is described. Changes since v7: - David: separate patches for adding x86 and ARM support - Dave/Will: drop support for disabling TLB flushes v7: https://lore.kernel.org/kvm/20250924151101.2225820-1-patrick.roy@campus.lmu… v6: https://lore.kernel.org/kvm/20250912091708.17502-1-roypat@amazon.co.uk v5: https://lore.kernel.org/kvm/20250828093902.2719-1-roypat@amazon.co.uk v4: https://lore.kernel.org/kvm/20250221160728.1584559-1-roypat@amazon.co.uk RFCv3: https://lore.kernel.org/kvm/20241030134912.515725-1-roypat@amazon.co.uk RFCv2: https://lore.kernel.org/kvm/20240910163038.1298452-1-roypat@amazon.co.uk RFCv1: https://lore.kernel.org/kvm/20240709132041.3625501-1-roypat@amazon.co.uk [1] https://download.vusec.net/papers/quarantine_raid23.pdf [2] https://github.com/firecracker-microvm/firecracker/tree/feature/secret-hidi… [3] https://lore.kernel.org/kvm/20251114151828.98165-1-kalyazin@amazon.com Patrick Roy (13): x86: export set_direct_map_valid_noflush to KVM module x86/tlb: export flush_tlb_kernel_range to KVM module mm: introduce AS_NO_DIRECT_MAP KVM: guest_memfd: Add stub for kvm_arch_gmem_invalidate KVM: guest_memfd: Add flag to remove from direct map KVM: x86: define kvm_arch_gmem_supports_no_direct_map() KVM: arm64: define kvm_arch_gmem_supports_no_direct_map() KVM: selftests: load elf via bounce buffer KVM: selftests: set KVM_MEM_GUEST_MEMFD in vm_mem_add() if guest_memfd != -1 KVM: selftests: Add guest_memfd based vm_mem_backing_src_types KVM: selftests: cover GUEST_MEMFD_FLAG_NO_DIRECT_MAP in existing selftests KVM: selftests: stuff vm_mem_backing_src_type into vm_shape KVM: selftests: Test guest execution from direct map removed gmem Documentation/virt/kvm/api.rst | 22 ++++--- arch/arm64/include/asm/kvm_host.h | 13 ++++ arch/x86/include/asm/kvm_host.h | 9 +++ arch/x86/include/asm/tlbflush.h | 3 +- arch/x86/mm/pat/set_memory.c | 1 + arch/x86/mm/tlb.c | 1 + include/linux/kvm_host.h | 14 ++++ include/linux/pagemap.h | 16 +++++ include/linux/secretmem.h | 18 ------ include/uapi/linux/kvm.h | 1 + lib/buildid.c | 4 +- mm/gup.c | 19 ++---- mm/mlock.c | 2 +- mm/secretmem.c | 8 +-- .../testing/selftests/kvm/guest_memfd_test.c | 17 ++++- .../testing/selftests/kvm/include/kvm_util.h | 37 ++++++++--- .../testing/selftests/kvm/include/test_util.h | 8 +++ tools/testing/selftests/kvm/lib/elf.c | 8 +-- tools/testing/selftests/kvm/lib/io.c | 23 +++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 59 +++++++++-------- tools/testing/selftests/kvm/lib/test_util.c | 8 +++ tools/testing/selftests/kvm/lib/x86/sev.c | 1 + .../selftests/kvm/pre_fault_memory_test.c | 1 + .../selftests/kvm/set_memory_region_test.c | 52 +++++++++++++-- .../kvm/x86/private_mem_conversions_test.c | 7 +- virt/kvm/guest_memfd.c | 64 +++++++++++++++++-- 26 files changed, 314 insertions(+), 102 deletions(-) base-commit: e0c26d47def7382d7dbd9cad58bc653aed75737a -- 2.50.1

1 week

5
21
0 0

[PATCH bpf-next v2 0/5] Add cryptographic hash and signature verification kfuncs to BPF

by Daniel Hodges

This series extends BPF's cryptographic capabilities by adding kfuncs for SHA hashing and ECDSA signature verification. These functions enable BPF programs to perform cryptographic operations for use cases such as content verification, integrity checking, and data authentication. BPF programs increasingly need to verify data integrity and authenticity in networking, security, and observability contexts. While BPF already supports symmetric encryption/decryption, it lacks support for: 1. Cryptographic hashing - needed for content verification, fingerprinting, and preparing message digests for signature operations 2. Asymmetric signature verification - needed to verify signed data without requiring the signing key in the datapath These capabilities enable use cases such as: - Verifying signed network packets or application data in XDP/TC programs - Implementing integrity checks in tracing and security monitoring - Building zero-trust security models where BPF programs verify credentials - Content-addressed storage and deduplication in BPF-based filesystems Implementation: The implementation follows BPF's existing crypto patterns: 1. Uses bpf_dynptr for safe memory access without page fault risks 2. Leverages the kernel's existing crypto library (lib/crypto/sha256.c and crypto/ecdsa.c) rather than reimplementing algorithms 3. Provides context-based API for ECDSA to enable key reuse and support multiple program types (syscall, XDP, TC) 4. Includes comprehensive selftests with NIST test vectors Patch 1: crypto: Add BPF hash algorithm type registration module - Adds bpf_crypto_shash module in crypto/ subsystem - Registers hash type with BPF crypto infrastructure - Enables hash algorithm access through unified bpf_crypto_type interface - Implements callbacks: alloc_tfm, free_tfm, hash, digestsize, get_flags - Manages shash_desc lifecycle internally Patch 2: bpf: Add SHA hash kfunc for cryptographic hashing - Adds bpf_crypto_hash() kfunc for SHA-256/384/512 - Extends bpf_crypto_type structure with hash operations - Updates bpf_crypto_ctx_create() to support keyless operations - Protected by CONFIG_CRYPTO_HASH2 guards - Uses kernel's crypto library implementations Patch 3: selftests/bpf: Add tests for bpf_crypto_hash kfunc - Tests basic functionality with NIST "abc" test vectors - Validates error handling for invalid parameters (zero-length input) - Ensures correct hash output for SHA-256, SHA-384, and SHA-512 - Adds CONFIG_CRYPTO_HASH2 and CONFIG_CRYPTO_SHA512 to selftest config Patch 4: bpf: Add ECDSA signature verification kfuncs - Context-based API: bpf_ecdsa_ctx_create/acquire/release pattern - Supports NIST curves (P-256, P-384, P-521) - Adds bpf_ecdsa_verify() for signature verification - Includes size query functions: keysize, digestsize, maxsize - Enables use in non-sleepable contexts via pre-allocated contexts - Uses crypto_sig API with p1363 format (r || s signatures) Patch 5: selftests/bpf: Add tests for ECDSA signature verification - Tests valid signature acceptance with RFC 6979 test vectors for P-256 - Tests invalid signature rejection - Tests size query functions (keysize, digestsize, maxsize) - Uses well-known NIST test vectors with "sample" message v2: - Fixed redundant __bpf_dynptr_is_rdonly() checks (Vadim) - Added BPF hash algorithm type registration module in crypto/ subsystem - Added CONFIG_CRYPTO_HASH2 guards around bpf_crypto_hash() kfunc and its BTF registration, matching the pattern used for CONFIG_CRYPTO_ECDSA - Added mandatory digestsize validation for hash operations Test Results ============ All tests pass on x86_64 for both crypto_hash and ecdsa_verify test suites. Daniel Hodges (5): crypto: Add BPF hash algorithm type registration module bpf: Add SHA hash kfunc for cryptographic hashing selftests/bpf: Add tests for bpf_crypto_hash kfunc bpf: Add ECDSA signature verification kfuncs selftests/bpf: Add tests for ECDSA signature verification kfuncs crypto/Makefile | 3 + crypto/bpf_crypto_shash.c | 94 ++++++ include/linux/bpf_crypto.h | 2 + kernel/bpf/crypto.c | 306 ++++++++++++++++++++- tools/testing/selftests/bpf/config | 2 + .../testing/selftests/bpf/prog_tests/crypto_hash.c | 158 +++++++++++ .../selftests/bpf/prog_tests/ecdsa_verify.c | 74 +++++ tools/testing/selftests/bpf/progs/crypto_hash.c | 141 ++++++++++ tools/testing/selftests/bpf/progs/ecdsa_verify.c | 159 +++++++++++ 9 files changed, 931 insertions(+), 8 deletions(-) create mode 100644 crypto/bpf_crypto_shash.c create mode 100644 tools/testing/selftests/bpf/prog_tests/crypto_hash.c create mode 100644 tools/testing/selftests/bpf/prog_tests/ecdsa_verify.c create mode 100644 tools/testing/selftests/bpf/progs/crypto_hash.c create mode 100644 tools/testing/selftests/bpf/progs/ecdsa_verify.c -- 2.51.0

1 week

5
12
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror