From 26bb32768fe6552de044f782a58b3272073fbfc0 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Mon, 3 Mar 2025 13:20:44 +0200 Subject: ptrace: introduce PTRACE_SET_SYSCALL_INFO request PTRACE_SET_SYSCALL_INFO is a generic ptrace API that complements PTRACE_GET_SYSCALL_INFO by letting the ptracer modify details of system calls the tracee is blocked in. This API allows ptracers to obtain and modify system call details in a straightforward and architecture-agnostic way, providing a consistent way of manipulating the system call number and arguments across architectures. As in case of PTRACE_GET_SYSCALL_INFO, PTRACE_SET_SYSCALL_INFO also does not aim to address numerous architecture-specific system call ABI peculiarities, like differences in the number of system call arguments for such system calls as pread64 and preadv. The current implementation supports changing only those bits of system call information that are used by strace system call tampering, namely, syscall number, syscall arguments, and syscall return value. Support of changing additional details returned by PTRACE_GET_SYSCALL_INFO, such as instruction pointer and stack pointer, could be added later if needed, by using struct ptrace_syscall_info.flags to specify the additional details that should be set. Currently, "flags" and "reserved" fields of struct ptrace_syscall_info must be initialized with zeroes; "arch", "instruction_pointer", and "stack_pointer" fields are currently ignored. PTRACE_SET_SYSCALL_INFO currently supports only PTRACE_SYSCALL_INFO_ENTRY, PTRACE_SYSCALL_INFO_EXIT, and PTRACE_SYSCALL_INFO_SECCOMP operations. Other operations could be added later if needed. Ideally, PTRACE_SET_SYSCALL_INFO should have been introduced along with PTRACE_GET_SYSCALL_INFO, but it didn't happen. The last straw that convinced me to implement PTRACE_SET_SYSCALL_INFO was apparent failure to provide an API of changing the first system call argument on riscv architecture. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_SET_SYSCALL_INFO Modify information about the system call that caused the stop. The "data" argument is a pointer to struct ptrace_syscall_info that specifies the system call information to be set. The "addr" argument should be set to sizeof(struct ptrace_syscall_info)). Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Link: https://lkml.kernel.org/r/20250303112044.GF24170@strace.io Signed-off-by: Dmitry V. Levin Reviewed-by: Alexey Gladkov Reviewed-by: Charlie Jenkins Tested-by: Charlie Jenkins Reviewed-by: Eugene Syromiatnikov Reviewed-by: Oleg Nesterov Cc: Alexander Gordeev Cc: Andreas Larsson Cc: anton ivanov Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Brian Cain Cc: Christian Borntraeger Cc: Christian Zankel Cc: Christophe Leroy Cc: Dave Hansen Cc: Davide Berardi Cc: David S. Miller Cc: Dinh Nguyen Cc: Eugene Syromyatnikov Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Jonas Bonn Cc: Maciej W. Rozycki Cc: Madhavan Srinivasan Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Frysinger Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Renzo Davoi Cc: Richard Weinberger Cc: Rich Felker Cc: Russel King Cc: Shuah Khan Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- include/uapi/linux/ptrace.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index 72c038fc71d0..5f8ef6156752 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -74,6 +74,7 @@ struct seccomp_metadata { }; #define PTRACE_GET_SYSCALL_INFO 0x420e +#define PTRACE_SET_SYSCALL_INFO 0x4212 #define PTRACE_SYSCALL_INFO_NONE 0 #define PTRACE_SYSCALL_INFO_ENTRY 1 #define PTRACE_SYSCALL_INFO_EXIT 2 @@ -81,7 +82,8 @@ struct seccomp_metadata { struct ptrace_syscall_info { __u8 op; /* PTRACE_SYSCALL_INFO_* */ - __u8 pad[3]; + __u8 reserved; + __u16 flags; __u32 arch; __u64 instruction_pointer; __u64 stack_pointer; @@ -98,6 +100,7 @@ struct ptrace_syscall_info { __u64 nr; __u64 args[6]; __u32 ret_data; + __u32 reserved2; } seccomp; }; }; @@ -142,6 +145,8 @@ struct ptrace_sud_config { __u64 len; }; +/* 0x4212 is PTRACE_SET_SYSCALL_INFO */ + /* * These values are stored in task->ptrace_message * by ptrace_stop to describe the current syscall-stop. -- cgit v1.2.3 From a516403787e08119b70ce8bfff985272ef318a58 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Mon, 24 Mar 2025 06:53:26 +0000 Subject: fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions Patch series "fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions", v2. Introduce the PAGE_IS_GUARD flag in the PAGEMAP_SCAN ioctl to expose information about guard regions. This allows userspace tools, such as CRIU, to detect and handle guard regions. Currently, CRIU utilizes PAGEMAP_SCAN as a more efficient alternative to parsing /proc/pid/pagemap. Without this change, guard regions are incorrectly reported as swap-anon regions, leading CRIU to attempt dumping them and subsequently failing. The series includes updates to the documentation and selftests to reflect the new functionality. This patch (of 3): Introduce the PAGE_IS_GUARD flag in the PAGEMAP_SCAN ioctl to expose information about guard regions. This allows userspace tools, such as CRIU, to detect and handle guard regions. Link: https://lkml.kernel.org/r/20250324065328.107678-1-avagin@google.com Link: https://lkml.kernel.org/r/20250324065328.107678-2-avagin@google.com Signed-off-by: Andrei Vagin Acked-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Cc: Jonathan Corbet Cc: Shuah Khan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/pagemap.rst | 1 + fs/proc/task_mmu.c | 17 ++++++++++------- include/uapi/linux/fs.h | 1 + 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index afce291649dd..e60e9211fd9b 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -250,6 +250,7 @@ Following flags about pages are currently supported: - ``PAGE_IS_PFNZERO`` - Page has zero PFN - ``PAGE_IS_HUGE`` - Page is PMD-mapped THP or Hugetlb backed - ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty +- ``PAGE_IS_GUARD`` - Page is a part of a guard region The ``struct pm_scan_arg`` is used as the argument of the IOCTL. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 994cde10e3f4..b9e4fbbdf6e6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2087,7 +2087,8 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY | \ + PAGE_IS_GUARD) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -2128,12 +2129,14 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; - if (p->masks_of_interest & PAGE_IS_FILE) { - swp = pte_to_swp_entry(pte); - if (is_pfn_swap_entry(swp) && - !folio_test_anon(pfn_swap_entry_folio(swp))) - categories |= PAGE_IS_FILE; - } + swp = pte_to_swp_entry(pte); + if (is_guard_swp_entry(swp)) + categories |= PAGE_IS_GUARD; + else if ((p->masks_of_interest & PAGE_IS_FILE) && + is_pfn_swap_entry(swp) && + !folio_test_anon(pfn_swap_entry_folio(swp))) + categories |= PAGE_IS_FILE; + if (pte_swp_soft_dirty(pte)) categories |= PAGE_IS_SOFT_DIRTY; } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index e762e1af650c..0098b0ce8ccb 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -361,6 +361,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) #define PAGE_IS_SOFT_DIRTY (1 << 7) +#define PAGE_IS_GUARD (1 << 8) /* * struct page_region - Page region with flags -- cgit v1.2.3