Merge patch series "ns: support file handles"

Christian Brauner <brauner@kernel.org> says:

For a while now we have supported file handles for pidfds. This has
proven to be very useful.

Extend the concept to cover namespaces as well. After this patchset it
is possible to encode and decode namespace file handles using the
commong name_to_handle_at() and open_by_handle_at() apis.

Namespaces file descriptors can already be derived from pidfds which
means they aren't subject to overmount protection bugs. IOW, it's
irrelevant if the caller would not have access to an appropriate
/proc/<pid>/ns/ directory as they could always just derive the namespace
based on a pidfd already.

It has the same advantage as pidfds. It's possible to reliably and for
the lifetime of the system refer to a namespace without pinning any
resources and to compare them.

Permission checking is kept simple. If the caller is located in the
namespace the file handle refers to they are able to open it otherwise
they must hold privilege over the owning namespace of the relevant
namespace.

Both the network namespace and the mount namespace already have an
associated cookie that isn't recycled and is fully exposed to userspace.
Move this into ns_common and use the same id space for all namespaces so
they can trivially and reliably be compared.

There's more coming based on the iterator infrastructure but the series
is large enough and focuses on file handles.

Extensive selftests included.

* patches from https://lore.kernel.org/20250912-work-namespace-v2-0-1a247645cef5@kernel.org: (33 commits)
  selftests/namespaces: add file handle selftests
  selftests/namespaces: add identifier selftests
  tools: update nsfs.h uapi header
  nsfs: add missing id retrieval support
  nsfs: support exhaustive file handles
  nsfs: support file handles
  nsfs: add current_in_namespace()
  ns: add to_<type>_ns() to respective headers
  uts: support ns lookup
  user: support ns lookup
  time: support ns lookup
  pid: support ns lookup
  net: support ns lookup
  ipc: support ns lookup
  cgroup: support ns lookup
  mnt: support ns lookup
  nstree: make iterator generic
  ns: remove ns_alloc_inum()
  uts: use ns_common_init()
  user: use ns_common_init()
  ...

Signed-off-by: Christian Brauner <brauner@kernel.org>

2 files changed, 42 insertions, 2 deletions

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7415a3863891..f0f0d49d2544 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -178,6 +178,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
 #define KVM_EXIT_MEMORY_FAULT     39
+#define KVM_EXIT_TDX              40
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -447,6 +448,31 @@ struct kvm_run {
 			__u64 gpa;
 			__u64 size;
 		} memory_fault;
+		/* KVM_EXIT_TDX */
+		struct {
+			__u64 flags;
+			__u64 nr;
+			union {
+				struct {
+					__u64 ret;
+					__u64 data[5];
+				} unknown;
+				struct {
+					__u64 ret;
+					__u64 gpa;
+					__u64 size;
+				} get_quote;
+				struct {
+					__u64 ret;
+					__u64 leaf;
+					__u64 r11, r12, r13, r14;
+				} get_tdvmcall_info;
+				struct {
+					__u64 ret;
+					__u64 vector;
+				} setup_event_notify;
+			};
+		} tdx;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -935,6 +961,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2 240
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
+#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
diff --git a/tools/include/uapi/linux/nsfs.h b/tools/include/uapi/linux/nsfs.h
index 34127653fd00..33c9b578b3b2 100644
--- a/tools/include/uapi/linux/nsfs.h
+++ b/tools/include/uapi/linux/nsfs.h
@@ -16,8 +16,6 @@
 #define NS_GET_NSTYPE		_IO(NSIO, 0x3)
 /* Get owner UID (in the caller's user namespace) for a user namespace */
 #define NS_GET_OWNER_UID	_IO(NSIO, 0x4)
-/* Get the id for a mount namespace */
-#define NS_GET_MNTNS_ID		_IOR(NSIO, 0x5, __u64)
 /* Translate pid from target pid namespace into the caller's pid namespace. */
 #define NS_GET_PID_FROM_PIDNS	_IOR(NSIO, 0x6, int)
 /* Return thread-group leader id of pid in the callers pid namespace. */
@@ -42,4 +40,19 @@ struct mnt_ns_info {
 /* Get previous namespace. */
 #define NS_MNT_GET_PREV		_IOR(NSIO, 12, struct mnt_ns_info)
 
+/* Retrieve namespace identifiers. */
+#define NS_GET_MNTNS_ID		_IOR(NSIO, 5,  __u64)
+#define NS_GET_ID		_IOR(NSIO, 13, __u64)
+
+enum init_ns_ino {
+	IPC_NS_INIT_INO		= 0xEFFFFFFFU,
+	UTS_NS_INIT_INO		= 0xEFFFFFFEU,
+	USER_NS_INIT_INO	= 0xEFFFFFFDU,
+	PID_NS_INIT_INO		= 0xEFFFFFFCU,
+	CGROUP_NS_INIT_INO	= 0xEFFFFFFBU,
+	TIME_NS_INIT_INO	= 0xEFFFFFFAU,
+	NET_NS_INIT_INO		= 0xEFFFFFF9U,
+	MNT_NS_INIT_INO		= 0xEFFFFFF8U,
+};
+
 #endif /* __LINUX_NSFS_H */