[RFC PATCH 3/6] um: install guest mappings via pidfd_mmap() in seccomp mode

[Cong Wang]

From: Cong Wang <cwang at multikernel.io>

In SECCOMP mode, map()/unmap() now install into the stub's address
space directly from the monitor via pidfd_mmap()/pidfd_munmap(),
resolving the physmem fd in the monitor's own fd table. The stub neither
receives the fd nor executes mmap/munmap itself.

The ptrace (SKAS0) mode is unchanged: it keeps batching STUB_SYSCALL_MMAP
/MUNMAP for the stub to execute, which works on any host kernel and
needs no new syscall. Only the seccomp path, where the stub is
sandboxed, is converted.

Assisted-by: Claude:claude-opus-4.8
Signed-off-by: Cong Wang <cwang at multikernel.io>
---
 arch/um/os-Linux/skas/mem.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index 8b9921ac3ef8..f751a1ea1c4c 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -9,6 +9,8 @@
 #include <errno.h>
 #include <string.h>
 #include <sys/mman.h>
+#include <sys/syscall.h>
+#include <linux/pidfd.h>
 #include <init.h>
 #include <as-layout.h>
 #include <mm_id.h>
@@ -236,6 +238,21 @@ int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot,
 {
 	struct stub_syscall *sc;
 
+	if (using_seccomp) {
+		struct pidfd_mmap_args args = {
+			.size	= sizeof(args),
+			.addr	= virt,
+			.len	= len,
+			.prot	= prot,
+			.flags	= MAP_SHARED | MAP_FIXED,
+			.pgoff	= offset >> UM_KERN_PAGE_SHIFT,
+			.fd	= phys_fd,
+		};
+		long res = syscall(__NR_pidfd_mmap, mm_idp->stub_pidfd, &args, 0);
+
+		return res < 0 ? -errno : 0;
+	}
+
 	/* Compress with previous syscall if that is possible */
 	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MMAP, virt);
 	if (sc && sc->mem.prot == prot &&
@@ -268,6 +285,13 @@ int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len)
 {
 	struct stub_syscall *sc;
 
+	if (using_seccomp) {
+		long res = syscall(__NR_pidfd_munmap, mm_idp->stub_pidfd,
+				   addr, len);
+
+		return res < 0 ? -errno : 0;
+	}
+
 	/* Compress with previous syscall if that is possible */
 	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MUNMAP, addr);
 	if (sc) {
-- 
2.43.0