summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-11-02 15:27:42 -0700
committerDavid S. Miller <davem@davemloft.net>2019-11-02 15:29:58 -0700
commitae8a76fb8b5d03fa2adc7249dc6131ba6a0c6119 (patch)
treeb197a7452b46abf51ffab8485236ccab69664d5c
parentd31e95585ca697fb31440c6fe30113adc85ecfbd (diff)
parent358fdb456288d48874d44a064a82bfb0d9963fa0 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says: ==================== pull-request: bpf-next 2019-11-02 The following pull-request contains BPF updates for your *net-next* tree. We've added 30 non-merge commits during the last 7 day(s) which contain a total of 41 files changed, 1864 insertions(+), 474 deletions(-). The main changes are: 1) Fix long standing user vs kernel access issue by introducing bpf_probe_read_user() and bpf_probe_read_kernel() helpers, from Daniel. 2) Accelerated xskmap lookup, from Björn and Maciej. 3) Support for automatic map pinning in libbpf, from Toke. 4) Cleanup of BTF-enabled raw tracepoints, from Alexei. 5) Various fixes to libbpf and selftests. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--Documentation/bpf/index.rst9
-rw-r--r--Documentation/bpf/s390.rst205
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/maccess.c43
-rw-r--r--include/linux/bpf.h30
-rw-r--r--include/linux/bpf_types.h1
-rw-r--r--include/linux/uaccess.h16
-rw-r--r--include/net/xdp_sock.h51
-rw-r--r--include/uapi/linux/bpf.h124
-rw-r--r--kernel/bpf/core.c12
-rw-r--r--kernel/bpf/syscall.c6
-rw-r--r--kernel/bpf/verifier.c39
-rw-r--r--kernel/bpf/xskmap.c112
-rw-r--r--kernel/trace/bpf_trace.c231
-rw-r--r--lib/test_bpf.c112
-rw-r--r--mm/maccess.c70
-rw-r--r--net/xdp/xsk.c33
-rw-r--r--samples/bpf/map_perf_test_kern.c4
-rw-r--r--samples/bpf/test_map_in_map_kern.c4
-rw-r--r--samples/bpf/test_probe_write_user_kern.c2
-rw-r--r--tools/include/uapi/linux/bpf.h124
-rw-r--r--tools/lib/bpf/bpf.c8
-rw-r--r--tools/lib/bpf/bpf.h5
-rw-r--r--tools/lib/bpf/bpf_helpers.h6
-rw-r--r--tools/lib/bpf/libbpf.c466
-rw-r--r--tools/lib/bpf/libbpf.h23
-rw-r--r--tools/lib/bpf/libbpf.map5
-rw-r--r--tools/lib/bpf/libbpf_probes.c1
-rw-r--r--tools/lib/bpf/xsk.c83
-rw-r--r--tools/testing/selftests/bpf/Makefile16
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pinning.c210
-rw-r--r--tools/testing/selftests/bpf/prog_tests/probe_user.c78
-rw-r--r--tools/testing/selftests/bpf/progs/kfree_skb.c4
-rw-r--r--tools/testing/selftests/bpf/progs/pyperf.h67
-rw-r--r--tools/testing/selftests/bpf/progs/strobemeta.h36
-rw-r--r--tools/testing/selftests/bpf/progs/test_pinning.c31
-rw-r--r--tools/testing/selftests/bpf/progs/test_pinning_invalid.c16
-rw-r--r--tools/testing/selftests/bpf/progs/test_probe_user.c26
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcp_estats.c2
-rwxr-xr-xtools/testing/selftests/bpf/test_offload.py3
-rw-r--r--tools/testing/selftests/bpf/test_sysctl.c23
41 files changed, 1863 insertions, 476 deletions
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 801a6ed3f2e5..4f5410b61441 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -47,6 +47,15 @@ Program types
prog_flow_dissector
+Testing BPF
+===========
+
+.. toctree::
+ :maxdepth: 1
+
+ s390
+
+
.. Links:
.. _Documentation/networking/filter.txt: ../networking/filter.txt
.. _man-pages: https://www.kernel.org/doc/man-pages/
diff --git a/Documentation/bpf/s390.rst b/Documentation/bpf/s390.rst
new file mode 100644
index 000000000000..21ecb309daea
--- /dev/null
+++ b/Documentation/bpf/s390.rst
@@ -0,0 +1,205 @@
+===================
+Testing BPF on s390
+===================
+
+1. Introduction
+***************
+
+IBM Z are mainframe computers, which are descendants of IBM System/360 from
+year 1964. They are supported by the Linux kernel under the name "s390". This
+document describes how to test BPF in an s390 QEMU guest.
+
+2. One-time setup
+*****************
+
+The following is required to build and run the test suite:
+
+ * s390 GCC
+ * s390 development headers and libraries
+ * Clang with BPF support
+ * QEMU with s390 support
+ * Disk image with s390 rootfs
+
+Debian supports installing compiler and libraries for s390 out of the box.
+Users of other distros may use debootstrap in order to set up a Debian chroot::
+
+ sudo debootstrap \
+ --variant=minbase \
+ --include=sudo \
+ testing \
+ ./s390-toolchain
+ sudo mount --rbind /dev ./s390-toolchain/dev
+ sudo mount --rbind /proc ./s390-toolchain/proc
+ sudo mount --rbind /sys ./s390-toolchain/sys
+ sudo chroot ./s390-toolchain
+
+Once on Debian, the build prerequisites can be installed as follows::
+
+ sudo dpkg --add-architecture s390x
+ sudo apt-get update
+ sudo apt-get install \
+ bc \
+ bison \
+ cmake \
+ debootstrap \
+ dwarves \
+ flex \
+ g++ \
+ gcc \
+ g++-s390x-linux-gnu \
+ gcc-s390x-linux-gnu \
+ gdb-multiarch \
+ git \
+ make \
+ python3 \
+ qemu-system-misc \
+ qemu-utils \
+ rsync \
+ libcap-dev:s390x \
+ libelf-dev:s390x \
+ libncurses-dev
+
+Latest Clang targeting BPF can be installed as follows::
+
+ git clone https://github.com/llvm/llvm-project.git
+ ln -s ../../clang llvm-project/llvm/tools/
+ mkdir llvm-project-build
+ cd llvm-project-build
+ cmake \
+ -DLLVM_TARGETS_TO_BUILD=BPF \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DCMAKE_INSTALL_PREFIX=/opt/clang-bpf \
+ ../llvm-project/llvm
+ make
+ sudo make install
+ export PATH=/opt/clang-bpf/bin:$PATH
+
+The disk image can be prepared using a loopback mount and debootstrap::
+
+ qemu-img create -f raw ./s390.img 1G
+ sudo losetup -f ./s390.img
+ sudo mkfs.ext4 /dev/loopX
+ mkdir ./s390.rootfs
+ sudo mount /dev/loopX ./s390.rootfs
+ sudo debootstrap \
+ --foreign \
+ --arch=s390x \
+ --variant=minbase \
+ --include=" \
+ iproute2, \
+ iputils-ping, \
+ isc-dhcp-client, \
+ kmod, \
+ libcap2, \
+ libelf1, \
+ netcat, \
+ procps" \
+ testing \
+ ./s390.rootfs
+ sudo umount ./s390.rootfs
+ sudo losetup -d /dev/loopX
+
+3. Compilation
+**************
+
+In addition to the usual Kconfig options required to run the BPF test suite, it
+is also helpful to select::
+
+ CONFIG_NET_9P=y
+ CONFIG_9P_FS=y
+ CONFIG_NET_9P_VIRTIO=y
+ CONFIG_VIRTIO_PCI=y
+
+as that would enable a very easy way to share files with the s390 virtual
+machine.
+
+Compiling kernel, modules and testsuite, as well as preparing gdb scripts to
+simplify debugging, can be done using the following commands::
+
+ make ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- menuconfig
+ make ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- bzImage modules scripts_gdb
+ make ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- \
+ -C tools/testing/selftests \
+ TARGETS=bpf \
+ INSTALL_PATH=$PWD/tools/testing/selftests/kselftest_install \
+ install
+
+4. Running the test suite
+*************************
+
+The virtual machine can be started as follows::
+
+ qemu-system-s390x \
+ -cpu max,zpci=on \
+ -smp 2 \
+ -m 4G \
+ -kernel linux/arch/s390/boot/compressed/vmlinux \
+ -drive file=./s390.img,if=virtio,format=raw \
+ -nographic \
+ -append 'root=/dev/vda rw console=ttyS1' \
+ -virtfs local,path=./linux,security_model=none,mount_tag=linux \
+ -object rng-random,filename=/dev/urandom,id=rng0 \
+ -device virtio-rng-ccw,rng=rng0 \
+ -netdev user,id=net0 \
+ -device virtio-net-ccw,netdev=net0
+
+When using this on a real IBM Z, ``-enable-kvm`` may be added for better
+performance. When starting the virtual machine for the first time, disk image
+setup must be finalized using the following command::
+
+ /debootstrap/debootstrap --second-stage
+
+Directory with the code built on the host as well as ``/proc`` and ``/sys``
+need to be mounted as follows::
+
+ mkdir -p /linux
+ mount -t 9p linux /linux
+ mount -t proc proc /proc
+ mount -t sysfs sys /sys
+
+After that, the test suite can be run using the following commands::
+
+ cd /linux/tools/testing/selftests/kselftest_install
+ ./run_kselftest.sh
+
+As usual, tests can be also run individually::
+
+ cd /linux/tools/testing/selftests/bpf
+ ./test_verifier
+
+5. Debugging
+************
+
+It is possible to debug the s390 kernel using QEMU GDB stub, which is activated
+by passing ``-s`` to QEMU.
+
+It is preferable to turn KASLR off, so that gdb would know where to find the
+kernel image in memory, by building the kernel with::
+
+ RANDOMIZE_BASE=n
+
+GDB can then be attached using the following command::
+
+ gdb-multiarch -ex 'target remote localhost:1234' ./vmlinux
+
+6. Network
+**********
+
+In case one needs to use the network in the virtual machine in order to e.g.
+install additional packages, it can be configured using::
+
+ dhclient eth0
+
+7. Links
+********
+
+This document is a compilation of techniques, whose more comprehensive
+descriptions can be found by following these links:
+
+- `Debootstrap <https://wiki.debian.org/EmDebian/CrossDebootstrap>`_
+- `Multiarch <https://wiki.debian.org/Multiarch/HOWTO>`_
+- `Building LLVM <https://llvm.org/docs/CMake.html>`_
+- `Cross-compiling the kernel <https://wiki.gentoo.org/wiki/Embedded_Handbook/General/Cross-compiling_the_kernel>`_
+- `QEMU s390x Guest Support <https://wiki.qemu.org/Documentation/Platforms/S390X>`_
+- `Plan 9 folder sharing over Virtio <https://wiki.qemu.org/Documentation/9psetup>`_
+- `Using GDB with QEMU <https://wiki.osdev.org/Kernel_Debugging#Use_GDB_with_QEMU>`_
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 84373dc9b341..bbc68a54795e 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -13,7 +13,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg
endif
obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
- pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
+ pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
# Make sure __phys_addr has no stackprotector
nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
new file mode 100644
index 000000000000..f5b85bdc0535
--- /dev/null
+++ b/arch/x86/mm/maccess.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+
+#ifdef CONFIG_X86_64
+static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+ return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+ /*
+ * Range covering the highest possible canonical userspace address
+ * as well as non-canonical address range. For the canonical range
+ * we also need to include the userspace guard page.
+ */
+ return vaddr < TASK_SIZE_MAX + PAGE_SIZE ||
+ canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr;
+}
+#else
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+ return vaddr < TASK_SIZE_MAX;
+}
+#endif
+
+long probe_kernel_read_strict(void *dst, const void *src, size_t size)
+{
+ if (unlikely(invalid_probe_range((unsigned long)src)))
+ return -EFAULT;
+
+ return __probe_kernel_read(dst, src, size);
+}
+
+long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count)
+{
+ if (unlikely(invalid_probe_range((unsigned long)unsafe_addr)))
+ return -EFAULT;
+
+ return __strncpy_from_unsafe(dst, unsafe_addr, count);
+}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 171be30fe0ae..7c7f518811a6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -373,6 +373,11 @@ enum bpf_cgroup_storage_type {
#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
+/* The longest tracepoint has 12 args.
+ * See include/trace/bpf_probe.h
+ */
+#define MAX_BPF_FUNC_ARGS 12
+
struct bpf_prog_stats {
u64 cnt;
u64 nsecs;
@@ -1004,31 +1009,6 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
}
#endif
-#if defined(CONFIG_XDP_SOCKETS)
-struct xdp_sock;
-struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
-int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
- struct xdp_sock *xs);
-void __xsk_map_flush(struct bpf_map *map);
-#else
-struct xdp_sock;
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
- u32 key)
-{
- return NULL;
-}
-
-static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
- struct xdp_sock *xs)
-{
- return -EOPNOTSUPP;
-}
-
-static inline void __xsk_map_flush(struct bpf_map *map)
-{
-}
-#endif
-
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
void bpf_sk_reuseport_detach(struct sock *sk);
int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 36a9c2325176..de14872b01ba 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -26,6 +26,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing)
#endif
#ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d4ee6e942562..67f016010aad 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -311,6 +311,7 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
* happens, handle that and return -EFAULT.
*/
extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
extern long __probe_kernel_read(void *dst, const void *src, size_t size);
/*
@@ -337,7 +338,22 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size);
extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
+/*
+ * probe_user_write(): safely attempt to write to a location in user space
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src. If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
+
extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+ long count);
+extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
long count);
extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9398ce7960f..e3780e4b74e1 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -69,7 +69,14 @@ struct xdp_umem {
/* Nodes are linked in the struct xdp_sock map_list field, and used to
* track which maps a certain socket reside in.
*/
-struct xsk_map;
+
+struct xsk_map {
+ struct bpf_map map;
+ struct list_head __percpu *flush_list;
+ spinlock_t lock; /* Synchronize map updates */
+ struct xdp_sock *xsk_map[];
+};
+
struct xsk_map_node {
struct list_head node;
struct xsk_map *map;
@@ -109,8 +116,6 @@ struct xdp_sock {
struct xdp_buff;
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-void xsk_flush(struct xdp_sock *xs);
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
/* Used from netdev driver */
bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
@@ -134,6 +139,22 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
struct xdp_sock **map_entry);
int xsk_map_inc(struct xsk_map *map);
void xsk_map_put(struct xsk_map *map);
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs);
+void __xsk_map_flush(struct bpf_map *map);
+
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+ u32 key)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct xdp_sock *xs;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ xs = READ_ONCE(m->xsk_map[key]);
+ return xs;
+}
static inline u64 xsk_umem_extract_addr(u64 addr)
{
@@ -224,15 +245,6 @@ static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
return -ENOTSUPP;
}
-static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
-{
- return -ENOTSUPP;
-}
-
-static inline void xsk_flush(struct xdp_sock *xs)
-{
-}
-
static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
return false;
@@ -357,6 +369,21 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
return 0;
}
+static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void __xsk_map_flush(struct bpf_map *map)
+{
+}
+
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+ u32 key)
+{
+ return NULL;
+}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4af8b0819a32..df6809a76404 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -173,6 +173,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_PROG_TYPE_TRACING,
};
enum bpf_attach_type {
@@ -199,6 +200,7 @@ enum bpf_attach_type {
BPF_CGROUP_UDP6_RECVMSG,
BPF_CGROUP_GETSOCKOPT,
BPF_CGROUP_SETSOCKOPT,
+ BPF_TRACE_RAW_TP,
__MAX_BPF_ATTACH_TYPE
};
@@ -561,10 +563,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
- * address *src* and store the data in *dst*.
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -1426,45 +1431,14 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
- * Copy a NUL terminated string from an unsafe address
- * *unsafe_ptr* to *dst*. The *size* should include the
- * terminating NUL byte. In case the string length is smaller than
- * *size*, the target is not padded with further NUL bytes. If the
- * string length is larger than *size*, just *size*-1 bytes are
- * copied and the last byte is set to NUL.
- *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
- *
- * ::
- *
- * SEC("kprobe/sys_open")
- * void bpf_sys_open(struct pt_regs *ctx)
- * {
- * char buf[PATHLEN]; // PATHLEN is defined to 256
- * int res = bpf_probe_read_str(buf, sizeof(buf),
- * ctx->di);
- *
- * // Consume buf, for example push it to
- * // userspace via bpf_perf_event_output(); we
- * // can use res (the string length) as event
- * // size, after checking its boundaries.
- * }
- *
- * In comparison, using **bpf_probe_read()** helper here instead
- * to read the string would require to estimate the length at
- * compile time, and would often result in copying more memory
- * than necessary.
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * more details.
*
- * Another useful use case is when parsing individual process
- * arguments or individual environment variables navigating
- * *current*\ **->mm->arg_start** and *current*\
- * **->mm->env_start**: using this helper and the return value,
- * one can quickly iterate at the right offset of the memory area.
+ * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -2775,6 +2749,72 @@ union bpf_attr {
* restricted to raw_tracepoint bpf programs.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from user space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from kernel space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe user address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read_user()** helper here
+ * instead to read the string would require to estimate the length
+ * at compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * Return
+ * On success, the strictly positive length of the string, including
+ * the trailing NUL character. On error, a negative value.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2888,7 +2928,11 @@ union bpf_attr {
FN(sk_storage_delete), \
FN(send_signal), \
FN(tcp_gen_syncookie), \
- FN(skb_output),
+ FN(skb_output), \
+ FN(probe_read_user), \
+ FN(probe_read_kernel), \
+ FN(probe_read_user_str), \
+ FN(probe_read_kernel_str),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 658d68d409a4..97e37d82a1cc 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -668,9 +668,6 @@ static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
{
struct latch_tree_node *n;
- if (!bpf_jit_kallsyms_enabled())
- return NULL;
-
n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
return n ?
container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
@@ -1309,11 +1306,12 @@ bool bpf_opcode_in_insntable(u8 code)
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read(void * dst, u32 size, const void * unsafe_ptr)
+u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
{
memset(dst, 0, size);
return -EFAULT;
}
+
/**
* __bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1569,9 +1567,9 @@ out:
LDST(W, u32)
LDST(DW, u64)
#undef LDST
-#define LDX_PROBE(SIZEOP, SIZE) \
- LDX_PROBE_MEM_##SIZEOP: \
- bpf_probe_read(&DST, SIZE, (const void *)(long) SRC); \
+#define LDX_PROBE(SIZEOP, SIZE) \
+ LDX_PROBE_MEM_##SIZEOP: \
+ bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) SRC); \
CONT;
LDX_PROBE(B, 1)
LDX_PROBE(H, 2)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 57eacd5fc24a..6d9ce95e5a8d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1579,7 +1579,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
u32 btf_id)
{
switch (prog_type) {
- case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_TRACING:
if (btf_id > BTF_MAX_TYPE)
return -EINVAL;
break;
@@ -1842,13 +1842,13 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
return PTR_ERR(prog);
if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+ prog->type != BPF_PROG_TYPE_TRACING &&
prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
err = -EINVAL;
goto out_put_prog;
}
- if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT &&
- prog->aux->attach_btf_id) {
+ if (prog->type == BPF_PROG_TYPE_TRACING) {
if (attr->raw_tracepoint.name) {
/* raw_tp name should not be specified in raw_tp
* programs that were verified via in-kernel BTF info
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c59778c0fc4d..2f2374967b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6279,6 +6279,11 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
break;
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ if (!env->prog->aux->attach_btf_id)
+ return 0;
+ range = tnum_const(0);
+ break;
default:
return 0;
}
@@ -9376,24 +9381,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
u32 btf_id = prog->aux->attach_btf_id;
+ const char prefix[] = "btf_trace_";
const struct btf_type *t;
const char *tname;
- if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) {
- const char prefix[] = "btf_trace_";
+ if (prog->type != BPF_PROG_TYPE_TRACING)
+ return 0;
- t = btf_type_by_id(btf_vmlinux, btf_id);
- if (!t) {
- verbose(env, "attach_btf_id %u is invalid\n", btf_id);
- return -EINVAL;
- }
+ if (!btf_id) {
+ verbose(env, "Tracing programs must provide btf_id\n");
+ return -EINVAL;
+ }
+ t = btf_type_by_id(btf_vmlinux, btf_id);
+ if (!t) {
+ verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+ return -EINVAL;
+ }
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ if (!tname) {
+ verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
+ return -EINVAL;
+ }
+
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_RAW_TP:
if (!btf_type_is_typedef(t)) {
verbose(env, "attach_btf_id %u is not a typedef\n",
btf_id);
return -EINVAL;
}
- tname = btf_name_by_offset(btf_vmlinux, t->name_off);
- if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) {
+ if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
verbose(env, "attach_btf_id %u points to wrong type name %s\n",
btf_id, tname);
return -EINVAL;
@@ -9414,8 +9431,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
prog->aux->attach_func_name = tname;
prog->aux->attach_func_proto = t;
prog->aux->attach_btf_trace = true;
+ return 0;
+ default:
+ return -EINVAL;
}
- return 0;
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 82a1ffe15dfa..da16c30868f3 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -9,13 +9,6 @@
#include <linux/slab.h>
#include <linux/sched.h>
-struct xsk_map {
- struct bpf_map map;
- struct xdp_sock **xsk_map;
- struct list_head __percpu *flush_list;
- spinlock_t lock; /* Synchronize map updates */
-};
-
int xsk_map_inc(struct xsk_map *map)
{
struct bpf_map *m = &map->map;
@@ -80,9 +73,10 @@ static void xsk_map_sock_delete(struct xdp_sock *xs,
static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
{
+ struct bpf_map_memory mem;
+ int cpu, err, numa_node;
struct xsk_map *m;
- int cpu, err;
- u64 cost;
+ u64 cost, size;
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
@@ -92,44 +86,35 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
return ERR_PTR(-EINVAL);
- m = kzalloc(sizeof(*m), GFP_USER);
- if (!m)
+ numa_node = bpf_map_attr_numa_node(attr);
+ size = struct_size(m, xsk_map, attr->max_entries);
+ cost = size + array_size(sizeof(*m->flush_list), num_possible_cpus());
+
+ err = bpf_map_charge_init(&mem, cost);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ m = bpf_map_area_alloc(size, numa_node);
+ if (!m) {
+ bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
+ }
bpf_map_init_from_attr(&m->map, attr);
+ bpf_map_charge_move(&m->map.memory, &mem);
spin_lock_init(&m->lock);
- cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
- cost += sizeof(struct list_head) * num_possible_cpus();
-
- /* Notice returns -EPERM on if map size is larger than memlock limit */
- err = bpf_map_charge_init(&m->map.memory, cost);
- if (err)
- goto free_m;
-
- err = -ENOMEM;
-
m->flush_list = alloc_percpu(struct list_head);
- if (!m->flush_list)
- goto free_charge;
+ if (!m->flush_list) {
+ bpf_map_charge_finish(&m->map.memory);
+ bpf_map_area_free(m);
+ return ERR_PTR(-ENOMEM);
+ }
for_each_possible_cpu(cpu)
INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
- m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
- sizeof(struct xdp_sock *),
- m->map.numa_node);
- if (!m->xsk_map)
- goto free_percpu;
return &m->map;
-
-free_percpu:
- free_percpu(m->flush_list);
-free_charge:
- bpf_map_charge_finish(&m->map.memory);
-free_m:
- kfree(m);
- return ERR_PTR(err);
}
static void xsk_map_free(struct bpf_map *map)
@@ -139,8 +124,7 @@ static void xsk_map_free(struct bpf_map *map)
bpf_clear_redirect_map(map);
synchronize_net();
free_percpu(m->flush_list);
- bpf_map_area_free(m->xsk_map);
- kfree(m);
+ bpf_map_area_free(m);
}
static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -160,45 +144,20 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
return 0;
}
-struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
-{
- struct xsk_map *m = container_of(map, struct xsk_map, map);
- struct xdp_sock *xs;
-
- if (key >= map->max_entries)
- return NULL;
-
- xs = READ_ONCE(m->xsk_map[key]);
- return xs;
-}
-
-int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
- struct xdp_sock *xs)
-{
- struct xsk_map *m = container_of(map, struct xsk_map, map);
- struct list_head *flush_list = this_cpu_ptr(m->flush_list);
- int err;
-
- err = xsk_rcv(xs, xdp);
- if (err)
- return err;
-
- if (!xs->flush_node.prev)
- list_add(&xs->flush_node, flush_list);
-
- return 0;
-}
-
-void __xsk_map_flush(struct bpf_map *map)
+static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
- struct xsk_map *m = container_of(map, struct xsk_map, map);
- struct list_head *flush_list = this_cpu_ptr(m->flush_list);
- struct xdp_sock *xs, *tmp;
-
- list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
- xsk_flush(xs);
- __list_del_clearprev(&xs->flush_node);
- }
+ const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
+ struct bpf_insn *insn = insn_buf;
+
+ *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+ *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
+ *insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
+ *insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0);
+ *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+ *insn++ = BPF_MOV64_IMM(ret, 0);
+ return insn - insn_buf;
}
static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
@@ -312,6 +271,7 @@ const struct bpf_map_ops xsk_map_ops = {
.map_free = xsk_map_free,
.map_get_next_key = xsk_map_get_next_key,
.map_lookup_elem = xsk_map_lookup_elem,
+ .map_gen_lookup = xsk_map_gen_lookup,
.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
.map_update_elem = xsk_map_update_elem,
.map_delete_elem = xsk_map_delete_elem,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 571c25d60710..ffc91d4935ac 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -138,24 +138,125 @@ static const struct bpf_func_proto bpf_override_return_proto = {
};
#endif
-BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
+ const void __user *, unsafe_ptr)
{
- int ret;
+ int ret = probe_user_read(dst, unsafe_ptr, size);
- ret = security_locked_down(LOCKDOWN_BPF_READ);
- if (ret < 0)
- goto out;
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_proto = {
+ .func = bpf_probe_read_user,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
+ const void __user *, unsafe_ptr)
+{
+ int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);
- ret = probe_kernel_read(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+ .func = bpf_probe_read_user_str,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
+ const bool compat)
+{
+ int ret = security_locked_down(LOCKDOWN_BPF_READ);
+
+ if (unlikely(ret < 0))
+ goto out;
+ ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
+ probe_kernel_read_strict(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
out:
memset(dst, 0, size);
+ return ret;
+}
+BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+ .func = bpf_probe_read_kernel,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_proto = {
+ .func = bpf_probe_read_compat,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static __always_inline int
+bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
+ const bool compat)
+{
+ int ret = security_locked_down(LOCKDOWN_BPF_READ);
+
+ if (unlikely(ret < 0))
+ goto out;
+ /*
+ * The strncpy_from_unsafe_*() call will likely not fill the entire
+ * buffer, but that's okay in this circumstance as we're probing
+ * arbitrary memory anyway similar to bpf_probe_read_*() and might
+ * as well probe the stack. Thus, memory is explicitly cleared
+ * only in error case, so that improper users ignoring return
+ * code altogether don't copy garbage; otherwise length of string
+ * is returned that can be used for bpf_perf_event_output() et al.
+ */
+ ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
+ strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+out:
+ memset(dst, 0, size);
return ret;
}
-static const struct bpf_func_proto bpf_probe_read_proto = {
- .func = bpf_probe_read,
+BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+ .func = bpf_probe_read_kernel_str,
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
@@ -163,7 +264,22 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
.arg3_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
+BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
+ const void *, unsafe_ptr)
+{
+ return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
+ .func = bpf_probe_read_compat_str,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
u32, size)
{
/*
@@ -186,10 +302,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
- if (!access_ok(unsafe_ptr, size))
- return -EPERM;
- return probe_kernel_write(unsafe_ptr, src, size);
+ return probe_user_write(unsafe_ptr, src, size);
}
static const struct bpf_func_proto bpf_probe_write_user_proto = {
@@ -585,41 +699,6 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
.arg2_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
- const void *, unsafe_ptr)
-{
- int ret;
-
- ret = security_locked_down(LOCKDOWN_BPF_READ);
- if (ret < 0)
- goto out;
-
- /*
- * The strncpy_from_unsafe() call will likely not fill the entire
- * buffer, but that's okay in this circumstance as we're probing
- * arbitrary memory anyway similar to bpf_probe_read() and might
- * as well probe the stack. Thus, memory is explicitly cleared
- * only in error case, so that improper users ignoring return
- * code altogether don't copy garbage; otherwise length of string
- * is returned that can be used for bpf_perf_event_output() et al.
- */
- ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
-out:
- memset(dst, 0, size);
-
- return ret;
-}
-
-static const struct bpf_func_proto bpf_probe_read_str_proto = {
- .func = bpf_probe_read_str,
- .gpl_only = true,
- .ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_UNINIT_MEM,
- .arg2_type = ARG_CONST_SIZE_OR_ZERO,
- .arg3_type = ARG_ANYTHING,
-};
-
struct send_signal_irq_work {
struct irq_work irq_work;
struct task_struct *task;
@@ -699,8 +778,6 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_pop_elem_proto;
case BPF_FUNC_map_peek_elem:
return &bpf_map_peek_elem_proto;
- case BPF_FUNC_probe_read:
- return &bpf_probe_read_proto;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_tail_call:
@@ -727,8 +804,18 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_current_task_under_cgroup_proto;
case BPF_FUNC_get_prandom_u32:
return &bpf_get_prandom_u32_proto;
+ case BPF_FUNC_probe_read_user:
+ return &bpf_probe_read_user_proto;
+ case BPF_FUNC_probe_read_kernel:
+ return &bpf_probe_read_kernel_proto;
+ case BPF_FUNC_probe_read:
+ return &bpf_probe_read_compat_proto;
+ case BPF_FUNC_probe_read_user_str:
+ return &bpf_probe_read_user_str_proto;
+ case BPF_FUNC_probe_read_kernel_str:
+ return &bpf_probe_read_kernel_str_proto;
case BPF_FUNC_probe_read_str:
- return &bpf_probe_read_str_proto;
+ return &bpf_probe_read_compat_str_proto;
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
@@ -1055,10 +1142,6 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
switch (func_id) {
case BPF_FUNC_perf_event_output:
return &bpf_perf_event_output_proto_raw_tp;
-#ifdef CONFIG_NET
- case BPF_FUNC_skb_output:
- return &bpf_skb_output_proto;
-#endif
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_raw_tp;
case BPF_FUNC_get_stack:
@@ -1068,20 +1151,44 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
}
+static const struct bpf_func_proto *
+tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+#ifdef CONFIG_NET
+ case BPF_FUNC_skb_output:
+ return &bpf_skb_output_proto;
+#endif
+ default:
+ return raw_tp_prog_func_proto(func_id, prog);
+ }
+}
+
static bool raw_tp_prog_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
- /* largest tracepoint in the kernel has 12 args */
- if (off < 0 || off >= sizeof(__u64) * 12)
+ if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+static bool tracing_prog_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
return false;
if (type != BPF_READ)
return false;
if (off % size != 0)
return false;
- if (!prog->aux->attach_btf_id)
- return true;
return btf_ctx_access(off, size, type, prog, info);
}
@@ -1093,6 +1200,14 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
const struct bpf_prog_ops raw_tracepoint_prog_ops = {
};
+const struct bpf_verifier_ops tracing_verifier_ops = {
+ .get_func_proto = tracing_prog_func_proto,
+ .is_valid_access = tracing_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops tracing_prog_ops = {
+};
+
static bool raw_tp_writable_prog_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 5ef3eccee27c..cecb230833be 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -6859,34 +6859,128 @@ err_page0:
return NULL;
}
-static __init int test_skb_segment(void)
+static __init struct sk_buff *build_test_skb_linear_no_head_frag(void)
{
+ unsigned int alloc_size = 2000;
+ unsigned int headroom = 102, doffset = 72, data_size = 1308;
+ struct sk_buff *skb[2];
+ int i;
+
+ /* skbs linked in a frag_list, both with linear data, with head_frag=0
+ * (data allocated by kmalloc), both have tcp data of 1308 bytes
+ * (total payload is 2616 bytes).
+ * Data offset is 72 bytes (40 ipv6 hdr, 32 tcp hdr). Some headroom.
+ */
+ for (i = 0; i < 2; i++) {
+ skb[i] = alloc_skb(alloc_size, GFP_KERNEL);
+ if (!skb[i]) {
+ if (i == 0)
+ goto err_skb0;
+ else
+ goto err_skb1;
+ }
+
+ skb[i]->protocol = htons(ETH_P_IPV6);
+ skb_reserve(skb[i], headroom);
+ skb_put(skb[i], doffset + data_size);
+ skb_reset_network_header(skb[i]);
+ if (i == 0)
+ skb_reset_mac_header(skb[i]);
+ else
+ skb_set_mac_header(skb[i], -ETH_HLEN);
+ __skb_pull(skb[i], doffset);
+ }
+
+ /* setup shinfo.
+ * mimic bpf_skb_proto_4_to_6, which resets gso_segs and assigns a
+ * reduced gso_size.
+ */
+ skb_shinfo(skb[0])->gso_size = 1288;
+ skb_shinfo(skb[0])->gso_type = SKB_GSO_TCPV6 | SKB_GSO_DODGY;
+ skb_shinfo(skb[0])->gso_segs = 0;
+ skb_shinfo(skb[0])->frag_list = skb[1];
+
+ /* adjust skb[0]'s len */
+ skb[0]->len += skb[1]->len;
+ skb[0]->data_len += skb[1]->len;
+ skb[0]->truesize += skb[1]->truesize;
+
+ return skb[0];
+
+err_skb1:
+ kfree_skb(skb[0]);
+err_skb0:
+ return NULL;
+}
+
+struct skb_segment_test {
+ const char *descr;
+ struct sk_buff *(*build_skb)(void);
netdev_features_t features;
+};
+
+static struct skb_segment_test skb_segment_tests[] __initconst = {
+ {
+ .descr = "gso_with_rx_frags",
+ .build_skb = build_test_skb,
+ .features = NETIF_F_SG | NETIF_F_GSO_PARTIAL | NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM
+ },
+ {
+ .descr = "gso_linear_no_head_frag",
+ .build_skb = build_test_skb_linear_no_head_frag,
+ .features = NETIF_F_SG | NETIF_F_FRAGLIST |
+ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_GSO |
+ NETIF_F_LLTX_BIT | NETIF_F_GRO |
+ NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+ NETIF_F_HW_VLAN_STAG_TX_BIT
+ }
+};
+
+static __init int test_skb_segment_single(const struct skb_segment_test *test)
+{
struct sk_buff *skb, *segs;
int ret = -1;
- features = NETIF_F_SG | NETIF_F_GSO_PARTIAL | NETIF_F_IP_CSUM |
- NETIF_F_IPV6_CSUM;
- features |= NETIF_F_RXCSUM;
- skb = build_test_skb();
+ skb = test->build_skb();
if (!skb) {
pr_info("%s: failed to build_test_skb", __func__);
goto done;
}
- segs = skb_segment(skb, features);
+ segs = skb_segment(skb, test->features);
if (!IS_ERR(segs)) {
kfree_skb_list(segs);
ret = 0;
- pr_info("%s: success in skb_segment!", __func__);
- } else {
- pr_info("%s: failed in skb_segment!", __func__);
}
kfree_skb(skb);
done:
return ret;
}
+static __init int test_skb_segment(void)
+{
+ int i, err_cnt = 0, pass_cnt = 0;
+
+ for (i = 0; i < ARRAY_SIZE(skb_segment_tests); i++) {
+ const struct skb_segment_test *test = &skb_segment_tests[i];
+
+ pr_info("#%d %s ", i, test->descr);
+
+ if (test_skb_segment_single(test)) {
+ pr_cont("FAIL\n");
+ err_cnt++;
+ } else {
+ pr_cont("PASS\n");
+ pass_cnt++;
+ }
+ }
+
+ pr_info("%s: Summary: %d PASSED, %d FAILED\n", __func__,
+ pass_cnt, err_cnt);
+ return err_cnt ? -EINVAL : 0;
+}
+
static __init int test_bpf(void)
{
int i, err_cnt = 0, pass_cnt = 0;
diff --git a/mm/maccess.c b/mm/maccess.c
index d065736f6b87..3ca8d97e5010 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -18,6 +18,18 @@ probe_read_common(void *dst, const void __user *src, size_t size)
return ret ? -EFAULT : 0;
}
+static __always_inline long
+probe_write_common(void __user *dst, const void *src, size_t size)
+{
+ long ret;
+
+ pagefault_disable();
+ ret = __copy_to_user_inatomic(dst, src, size);
+ pagefault_enable();
+
+ return ret ? -EFAULT : 0;
+}
+
/**
* probe_kernel_read(): safely attempt to read from a kernel-space location
* @dst: pointer to the buffer that shall take the data
@@ -31,11 +43,20 @@ probe_read_common(void *dst, const void __user *src, size_t size)
* do_page_fault() doesn't attempt to take mmap_sem. This makes
* probe_kernel_read() suitable for use within regions where the caller
* already holds mmap_sem, or other locks which nest inside mmap_sem.
+ *
+ * probe_kernel_read_strict() is the same as probe_kernel_read() except for
+ * the case where architectures have non-overlapping user and kernel address
+ * ranges: probe_kernel_read_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where probe_user_read() is supposed
+ * to be used instead.
*/
long __weak probe_kernel_read(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_read")));
+long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size)
+ __attribute__((alias("__probe_kernel_read")));
+
long __probe_kernel_read(void *dst, const void *src, size_t size)
{
long ret;
@@ -85,6 +106,7 @@ EXPORT_SYMBOL_GPL(probe_user_read);
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
+
long __weak probe_kernel_write(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_write")));
@@ -94,15 +116,39 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
- pagefault_disable();
- ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
- pagefault_enable();
+ ret = probe_write_common((__force void __user *)dst, src, size);
set_fs(old_fs);
- return ret ? -EFAULT : 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(probe_kernel_write);
+/**
+ * probe_user_write(): safely attempt to write to a user-space location
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src. If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_user_write(void __user *dst, const void *src, size_t size)
+ __attribute__((alias("__probe_user_write")));
+
+long __probe_user_write(void __user *dst, const void *src, size_t size)
+{
+ long ret = -EFAULT;
+ mm_segment_t old_fs = get_fs();
+
+ set_fs(USER_DS);
+ if (access_ok(dst, size))
+ ret = probe_write_common(dst, src, size);
+ set_fs(old_fs);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(probe_user_write);
/**
* strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
@@ -120,8 +166,22 @@ EXPORT_SYMBOL_GPL(probe_kernel_write);
*
* If @count is smaller than the length of the string, copies @count-1 bytes,
* sets the last byte of @dst buffer to NUL and returns @count.
+ *
+ * strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except
+ * for the case where architectures have non-overlapping user and kernel address
+ * ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where strncpy_from_unsafe_user() is
+ * supposed to be used instead.
*/
-long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+
+long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+ __attribute__((alias("__strncpy_from_unsafe")));
+
+long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+ long count)
+ __attribute__((alias("__strncpy_from_unsafe")));
+
+long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
{
mm_segment_t old_fs = get_fs();
const void *src = unsafe_addr;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9044073fbf22..6040bc2b0088 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -196,7 +196,7 @@ static bool xsk_is_bound(struct xdp_sock *xs)
return false;
}
-int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
u32 len;
@@ -212,7 +212,7 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
__xsk_rcv_zc(xs, xdp, len) : __xsk_rcv(xs, xdp, len);
}
-void xsk_flush(struct xdp_sock *xs)
+static void xsk_flush(struct xdp_sock *xs)
{
xskq_produce_flush_desc(xs->rx);
xs->sk.sk_data_ready(&xs->sk);
@@ -264,6 +264,35 @@ out_unlock:
return err;
}
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+ int err;
+
+ err = xsk_rcv(xs, xdp);
+ if (err)
+ return err;
+
+ if (!xs->flush_node.prev)
+ list_add(&xs->flush_node, flush_list);
+
+ return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+ struct xdp_sock *xs, *tmp;
+
+ list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
+ xsk_flush(xs);
+ __list_del_clearprev(&xs->flush_node);
+ }
+}
+
void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
{
xskq_produce_flush_addr_n(umem->cq, nb_entries);
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 5c11aefbc489..281bcdaee58e 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -181,8 +181,8 @@ int stress_lru_hmap_alloc(struct pt_regs *ctx)
if (addrlen != sizeof(*in6))
return 0;
- ret = bpf_probe_read(test_params.dst6, sizeof(test_params.dst6),
- &in6->sin6_addr);
+ ret = bpf_probe_read_user(test_params.dst6, sizeof(test_params.dst6),
+ &in6->sin6_addr);
if (ret)
goto done;
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 4f80cbe74c72..32ee752f19df 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -118,7 +118,7 @@ int trace_sys_connect(struct pt_regs *ctx)
if (addrlen != sizeof(*in6))
return 0;
- ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+ ret = bpf_probe_read_user(dst6, sizeof(dst6), &in6->sin6_addr);
if (ret) {
inline_ret = ret;
goto done;
@@ -129,7 +129,7 @@ int trace_sys_connect(struct pt_regs *ctx)
test_case = dst6[7];
- ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+ ret = bpf_probe_read_user(&port, sizeof(port), &in6->sin6_port);
if (ret) {
inline_ret = ret;
goto done;
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c
index a543358218e6..b7c48f37132c 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user_kern.c
@@ -37,7 +37,7 @@ int bpf_prog1(struct pt_regs *ctx)
if (sockaddr_len > sizeof(orig_addr))
return 0;
- if (bpf_probe_read(&orig_addr, sizeof(orig_addr), sockaddr_arg) != 0)
+ if (bpf_probe_read_user(&orig_addr, sizeof(orig_addr), sockaddr_arg) != 0)
return 0;
mapped_addr = bpf_map_lookup_elem(&dnat_map, &orig_addr);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4af8b0819a32..df6809a76404 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -173,6 +173,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_PROG_TYPE_TRACING,
};
enum bpf_attach_type {
@@ -199,6 +200,7 @@ enum bpf_attach_type {
BPF_CGROUP_UDP6_RECVMSG,
BPF_CGROUP_GETSOCKOPT,
BPF_CGROUP_SETSOCKOPT,
+ BPF_TRACE_RAW_TP,
__MAX_BPF_ATTACH_TYPE
};
@@ -561,10 +563,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
- * address *src* and store the data in *dst*.
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -1426,45 +1431,14 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
- * Copy a NUL terminated string from an unsafe address
- * *unsafe_ptr* to *dst*. The *size* should include the
- * terminating NUL byte. In case the string length is smaller than
- * *size*, the target is not padded with further NUL bytes. If the
- * string length is larger than *size*, just *size*-1 bytes are
- * copied and the last byte is set to NUL.
- *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
- *
- * ::
- *
- * SEC("kprobe/sys_open")
- * void bpf_sys_open(struct pt_regs *ctx)
- * {
- * char buf[PATHLEN]; // PATHLEN is defined to 256
- * int res = bpf_probe_read_str(buf, sizeof(buf),
- * ctx->di);
- *
- * // Consume buf, for example push it to
- * // userspace via bpf_perf_event_output(); we
- * // can use res (the string length) as event
- * // size, after checking its boundaries.
- * }
- *
- * In comparison, using **bpf_probe_read()** helper here instead
- * to read the string would require to estimate the length at
- * compile time, and would often result in copying more memory
- * than necessary.
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * more details.
*
- * Another useful use case is when parsing individual process
- * arguments or individual environment variables navigating
- * *current*\ **->mm->arg_start** and *current*\
- * **->mm->env_start**: using this helper and the return value,
- * one can quickly iterate at the right offset of the memory area.
+ * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -2775,6 +2749,72 @@ union bpf_attr {
* restricted to raw_tracepoint bpf programs.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from user space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from kernel space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe user address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read_user()** helper here
+ * instead to read the string would require to estimate the length
+ * at compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * Return
+ * On success, the strictly positive length of the string, including
+ * the trailing NUL character. On error, a negative value.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2888,7 +2928,11 @@ union bpf_attr {
FN(sk_storage_delete), \
FN(send_signal), \
FN(tcp_gen_syncookie), \
- FN(skb_output),
+ FN(skb_output), \
+ FN(probe_read_user), \
+ FN(probe_read_kernel), \
+ FN(probe_read_user_str), \
+ FN(probe_read_kernel_str),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 79046067720f..ca0d635b1d5e 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -228,9 +228,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
- if (attr.prog_type == BPF_PROG_TYPE_RAW_TRACEPOINT)
- /* expected_attach_type is ignored for tracing progs */
- attr.attach_btf_id = attr.expected_attach_type;
+ if (attr.prog_type == BPF_PROG_TYPE_TRACING)
+ attr.attach_btf_id = load_attr->attach_btf_id;
+ else
+ attr.prog_ifindex = load_attr->prog_ifindex;
attr.insn_cnt = (__u32)load_attr->insns_cnt;
attr.insns = ptr_to_u64(load_attr->insns);
attr.license = ptr_to_u64(load_attr->license);
@@ -245,7 +246,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
}
attr.kern_version = load_attr->kern_version;
- attr.prog_ifindex = load_attr->prog_ifindex;
attr.prog_btf_fd = load_attr->prog_btf_fd;
attr.func_info_rec_size = load_attr->func_info_rec_size;
attr.func_info_cnt = load_attr->func_info_cnt;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 0db01334740f..1c53bc5b4b3c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -78,7 +78,10 @@ struct bpf_load_program_attr {
size_t insns_cnt;
const char *license;
__u32 kern_version;
- __u32 prog_ifindex;
+ union {
+ __u32 prog_ifindex;
+ __u32 attach_btf_id;
+ };
__u32 prog_btf_fd;
__u32 func_info_rec_size;
const void *func_info;
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 2203595f38c3..0c7d28292898 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -38,4 +38,10 @@ struct bpf_map_def {
unsigned int map_flags;
};
+enum libbpf_pin_type {
+ LIBBPF_PIN_NONE,
+ /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+ LIBBPF_PIN_BY_NAME,
+};
+
#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d71631a01926..7aa2a2a22cef 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -188,6 +188,7 @@ struct bpf_program {
bpf_program_clear_priv_t clear_priv;
enum bpf_attach_type expected_attach_type;
+ __u32 attach_btf_id;
void *func_info;
__u32 func_info_rec_size;
__u32 func_info_cnt;
@@ -226,6 +227,8 @@ struct bpf_map {
void *priv;
bpf_map_clear_priv_t clear_priv;
enum libbpf_map_type libbpf_type;
+ char *pin_path;
+ bool pinned;
};
struct bpf_secdata {
@@ -1090,10 +1093,32 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf,
return true;
}
+static int build_map_pin_path(struct bpf_map *map, const char *path)
+{
+ char buf[PATH_MAX];
+ int err, len;
+
+ if (!path)
+ path = "/sys/fs/bpf";
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_map__set_pin_path(map, buf);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static int bpf_object__init_user_btf_map(struct bpf_object *obj,
const struct btf_type *sec,
int var_idx, int sec_idx,
- const Elf_Data *data, bool strict)
+ const Elf_Data *data, bool strict,
+ const char *pin_root_path)
{
const struct btf_type *var, *def, *t;
const struct btf_var_secinfo *vi;
@@ -1268,6 +1293,30 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
}
map->def.value_size = sz;
map->btf_value_type_id = t->type;
+ } else if (strcmp(name, "pinning") == 0) {
+ __u32 val;
+ int err;
+
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &val))
+ return -EINVAL;
+ pr_debug("map '%s': found pinning = %u.\n",
+ map_name, val);
+
+ if (val != LIBBPF_PIN_NONE &&
+ val != LIBBPF_PIN_BY_NAME) {
+ pr_warn("map '%s': invalid pinning value %u.\n",
+ map_name, val);
+ return -EINVAL;
+ }
+ if (val == LIBBPF_PIN_BY_NAME) {
+ err = build_map_pin_path(map, pin_root_path);
+ if (err) {
+ pr_warn("map '%s': couldn't build pin path.\n",
+ map_name);
+ return err;
+ }
+ }
} else {
if (strict) {
pr_warn("map '%s': unknown field '%s'.\n",
@@ -1287,7 +1336,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
return 0;
}
-static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
+static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
+ const char *pin_root_path)
{
const struct btf_type *sec = NULL;
int nr_types, i, vlen, err;
@@ -1329,7 +1379,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
for (i = 0; i < vlen; i++) {
err = bpf_object__init_user_btf_map(obj, sec, i,
obj->efile.btf_maps_shndx,
- data, strict);
+ data, strict, pin_root_path);
if (err)
return err;
}
@@ -1337,7 +1387,8 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
return 0;
}
-static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps)
+static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps,
+ const char *pin_root_path)
{
bool strict = !relaxed_maps;
int err;
@@ -1346,7 +1397,7 @@ static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps)
if (err)
return err;
- err = bpf_object__init_user_btf_maps(obj, strict);
+ err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
if (err)
return err;
@@ -1535,7 +1586,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
return 0;
}
-static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps)
+static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps,
+ const char *pin_root_path)
{
Elf *elf = obj->efile.elf;
GElf_Ehdr *ep = &obj->efile.ehdr;
@@ -1664,13 +1716,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps)
}
}
- if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
+ if (!obj->efile.strtabidx || obj->efile.strtabidx > idx) {
pr_warn("Corrupted ELF file: index of strtab invalid\n");
return -LIBBPF_ERRNO__FORMAT;
}
err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
if (!err)
- err = bpf_object__init_maps(obj, relaxed_maps);
+ err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path);
if (!err)
err = bpf_object__sanitize_and_load_btf(obj);
if (!err)
@@ -1916,16 +1968,22 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
return -errno;
new_fd = open("/", O_RDONLY | O_CLOEXEC);
- if (new_fd < 0)
+ if (new_fd < 0) {
+ err = -errno;
goto err_free_new_name;
+ }
new_fd = dup3(fd, new_fd, O_CLOEXEC);
- if (new_fd < 0)
+ if (new_fd < 0) {
+ err = -errno;
goto err_close_new_fd;
+ }
err = zclose(map->fd);
- if (err)
+ if (err) {
+ err = -errno;
goto err_close_new_fd;
+ }
free(map->name);
map->fd = new_fd;
@@ -1944,7 +2002,7 @@ err_close_new_fd:
close(new_fd);
err_free_new_name:
free(new_name);
- return -errno;
+ return err;
}
int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
@@ -2120,6 +2178,66 @@ bpf_object__probe_caps(struct bpf_object *obj)
return 0;
}
+static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
+{
+ struct bpf_map_info map_info = {};
+ char msg[STRERR_BUFSIZE];
+ __u32 map_info_len;
+
+ map_info_len = sizeof(map_info);
+
+ if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) {
+ pr_warn("failed to get map info for map FD %d: %s\n",
+ map_fd, libbpf_strerror_r(errno, msg, sizeof(msg)));
+ return false;
+ }
+
+ return (map_info.type == map->def.type &&
+ map_info.key_size == map->def.key_size &&
+ map_info.value_size == map->def.value_size &&
+ map_info.max_entries == map->def.max_entries &&
+ map_info.map_flags == map->def.map_flags);
+}
+
+static int
+bpf_object__reuse_map(struct bpf_map *map)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ int err, pin_fd;
+
+ pin_fd = bpf_obj_get(map->pin_path);
+ if (pin_fd < 0) {
+ err = -errno;
+ if (err == -ENOENT) {
+ pr_debug("found no pinned map to reuse at '%s'\n",
+ map->pin_path);
+ return 0;
+ }
+
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("couldn't retrieve pinned map '%s': %s\n",
+ map->pin_path, cp);
+ return err;
+ }
+
+ if (!map_is_reuse_compat(map, pin_fd)) {
+ pr_warn("couldn't reuse pinned map at '%s': parameter mismatch\n",
+ map->pin_path);
+ close(pin_fd);
+ return -EINVAL;
+ }
+
+ err = bpf_map__reuse_fd(map, pin_fd);
+ if (err) {
+ close(pin_fd);
+ return err;
+ }
+ map->pinned = true;
+ pr_debug("reused pinned map at '%s'\n", map->pin_path);
+
+ return 0;
+}
+
static int
bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
{
@@ -2162,6 +2280,15 @@ bpf_object__create_maps(struct bpf_object *obj)
char *cp, errmsg[STRERR_BUFSIZE];
int *pfd = &map->fd;
+ if (map->pin_path) {
+ err = bpf_object__reuse_map(map);
+ if (err) {
+ pr_warn("error reusing pinned map %s\n",
+ map->name);
+ return err;
+ }
+ }
+
if (map->fd >= 0) {
pr_debug("skip map create (preset) %s: fd=%d\n",
map->name, map->fd);
@@ -2240,6 +2367,15 @@ err_out:
}
}
+ if (map->pin_path && !map->pinned) {
+ err = bpf_map__pin(map, NULL);
+ if (err) {
+ pr_warn("failed to auto-pin map name '%s' at '%s'\n",
+ map->name, map->pin_path);
+ return err;
+ }
+ }
+
pr_debug("created map %s: fd=%d\n", map->name, *pfd);
}
@@ -3446,6 +3582,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.line_info_cnt = prog->line_info_cnt;
load_attr.log_level = prog->log_level;
load_attr.prog_flags = prog->prog_flags;
+ load_attr.attach_btf_id = prog->attach_btf_id;
retry_load:
log_buf = malloc(log_buf_size);
@@ -3607,10 +3744,13 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
return 0;
}
+static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id);
+
static struct bpf_object *
__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
struct bpf_object_open_opts *opts)
{
+ const char *pin_root_path;
struct bpf_program *prog;
struct bpf_object *obj;
const char *obj_name;
@@ -3645,17 +3785,20 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false);
relaxed_maps = OPTS_GET(opts, relaxed_maps, false);
+ pin_root_path = OPTS_GET(opts, pin_root_path, NULL);
CHECK_ERR(bpf_object__elf_init(obj), err, out);
CHECK_ERR(bpf_object__check_endianness(obj), err, out);
CHECK_ERR(bpf_object__probe_caps(obj), err, out);
- CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps), err, out);
+ CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path),
+ err, out);
CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
bpf_object__elf_finish(obj);
bpf_object__for_each_program(prog, obj) {
enum bpf_prog_type prog_type;
enum bpf_attach_type attach_type;
+ __u32 btf_id;
err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
&attach_type);
@@ -3667,6 +3810,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
bpf_program__set_type(prog, prog_type);
bpf_program__set_expected_attach_type(prog, attach_type);
+ if (prog_type == BPF_PROG_TYPE_TRACING) {
+ err = libbpf_attach_btf_id_by_name(prog->section_name, &btf_id);
+ if (err)
+ goto out;
+ prog->attach_btf_id = btf_id;
+ }
}
return obj;
@@ -3797,6 +3946,28 @@ int bpf_object__load(struct bpf_object *obj)
return bpf_object__load_xattr(&attr);
}
+static int make_parent_dir(const char *path)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ char *dname, *dir;
+ int err = 0;
+
+ dname = strdup(path);
+ if (dname == NULL)
+ return -ENOMEM;
+
+ dir = dirname(dname);
+ if (mkdir(dir, 0700) && errno != EEXIST)
+ err = -errno;
+
+ free(dname);
+ if (err) {
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("failed to mkdir %s: %s\n", path, cp);
+ }
+ return err;
+}
+
static int check_path(const char *path)
{
char *cp, errmsg[STRERR_BUFSIZE];
@@ -3833,6 +4004,10 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
char *cp, errmsg[STRERR_BUFSIZE];
int err;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+
err = check_path(path);
if (err)
return err;
@@ -3886,25 +4061,14 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
return 0;
}
-static int make_dir(const char *path)
-{
- char *cp, errmsg[STRERR_BUFSIZE];
- int err = 0;
-
- if (mkdir(path, 0700) && errno != EEXIST)
- err = -errno;
-
- if (err) {
- cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
- pr_warn("failed to mkdir %s: %s\n", path, cp);
- }
- return err;
-}
-
int bpf_program__pin(struct bpf_program *prog, const char *path)
{
int i, err;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+
err = check_path(path);
if (err)
return err;
@@ -3925,10 +4089,6 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
return bpf_program__pin_instance(prog, path, 0);
}
- err = make_dir(path);
- if (err)
- return err;
-
for (i = 0; i < prog->instances.nr; i++) {
char buf[PATH_MAX];
int len;
@@ -4019,47 +4179,123 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
char *cp, errmsg[STRERR_BUFSIZE];
int err;
- err = check_path(path);
- if (err)
- return err;
-
if (map == NULL) {
pr_warn("invalid map pointer\n");
return -EINVAL;
}
- if (bpf_obj_pin(map->fd, path)) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warn("failed to pin map: %s\n", cp);
- return -errno;
+ if (map->pin_path) {
+ if (path && strcmp(path, map->pin_path)) {
+ pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
+ bpf_map__name(map), map->pin_path, path);
+ return -EINVAL;
+ } else if (map->pinned) {
+ pr_debug("map '%s' already pinned at '%s'; not re-pinning\n",
+ bpf_map__name(map), map->pin_path);
+ return 0;
+ }
+ } else {
+ if (!path) {
+ pr_warn("missing a path to pin map '%s' at\n",
+ bpf_map__name(map));
+ return -EINVAL;
+ } else if (map->pinned) {
+ pr_warn("map '%s' already pinned\n", bpf_map__name(map));
+ return -EEXIST;
+ }
+
+ map->pin_path = strdup(path);
+ if (!map->pin_path) {
+ err = -errno;
+ goto out_err;
+ }
+ }
+
+ err = make_parent_dir(map->pin_path);
+ if (err)
+ return err;
+
+ err = check_path(map->pin_path);
+ if (err)
+ return err;
+
+ if (bpf_obj_pin(map->fd, map->pin_path)) {
+ err = -errno;
+ goto out_err;
}
- pr_debug("pinned map '%s'\n", path);
+ map->pinned = true;
+ pr_debug("pinned map '%s'\n", map->pin_path);
return 0;
+
+out_err:
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("failed to pin map: %s\n", cp);
+ return err;
}
int bpf_map__unpin(struct bpf_map *map, const char *path)
{
int err;
- err = check_path(path);
- if (err)
- return err;
-
if (map == NULL) {
pr_warn("invalid map pointer\n");
return -EINVAL;
}
+ if (map->pin_path) {
+ if (path && strcmp(path, map->pin_path)) {
+ pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
+ bpf_map__name(map), map->pin_path, path);
+ return -EINVAL;
+ }
+ path = map->pin_path;
+ } else if (!path) {
+ pr_warn("no path to unpin map '%s' from\n",
+ bpf_map__name(map));
+ return -EINVAL;
+ }
+
+ err = check_path(path);
+ if (err)
+ return err;
+
err = unlink(path);
if (err != 0)
return -errno;
- pr_debug("unpinned map '%s'\n", path);
+
+ map->pinned = false;
+ pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path);
return 0;
}
+int bpf_map__set_pin_path(struct bpf_map *map, const char *path)
+{
+ char *new = NULL;
+
+ if (path) {
+ new = strdup(path);
+ if (!new)
+ return -errno;
+ }
+
+ free(map->pin_path);
+ map->pin_path = new;
+ return 0;
+}
+
+const char *bpf_map__get_pin_path(const struct bpf_map *map)
+{
+ return map->pin_path;
+}
+
+bool bpf_map__is_pinned(const struct bpf_map *map)
+{
+ return map->pinned;
+}
+
int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
{
struct bpf_map *map;
@@ -4073,25 +4309,28 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
return -ENOENT;
}
- err = make_dir(path);
- if (err)
- return err;
-
bpf_object__for_each_map(map, obj) {
+ char *pin_path = NULL;
char buf[PATH_MAX];
- int len;
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0) {
- err = -EINVAL;
- goto err_unpin_maps;
- } else if (len >= PATH_MAX) {
- err = -ENAMETOOLONG;
- goto err_unpin_maps;
+ if (path) {
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_maps;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_maps;
+ }
+ pin_path = buf;
+ } else if (!map->pin_path) {
+ continue;
}
- err = bpf_map__pin(map, buf);
+ err = bpf_map__pin(map, pin_path);
if (err)
goto err_unpin_maps;
}
@@ -4100,17 +4339,10 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
err_unpin_maps:
while ((map = bpf_map__prev(map, obj))) {
- char buf[PATH_MAX];
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0)
- continue;
- else if (len >= PATH_MAX)
+ if (!map->pin_path)
continue;
- bpf_map__unpin(map, buf);
+ bpf_map__unpin(map, NULL);
}
return err;
@@ -4125,17 +4357,24 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
return -ENOENT;
bpf_object__for_each_map(map, obj) {
+ char *pin_path = NULL;
char buf[PATH_MAX];
- int len;
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0)
- return -EINVAL;
- else if (len >= PATH_MAX)
- return -ENAMETOOLONG;
+ if (path) {
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+ pin_path = buf;
+ } else if (!map->pin_path) {
+ continue;
+ }
- err = bpf_map__unpin(map, buf);
+ err = bpf_map__unpin(map, pin_path);
if (err)
return err;
}
@@ -4156,10 +4395,6 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
return -ENOENT;
}
- err = make_dir(path);
- if (err)
- return err;
-
bpf_object__for_each_program(prog, obj) {
char buf[PATH_MAX];
int len;
@@ -4260,6 +4495,7 @@ void bpf_object__close(struct bpf_object *obj)
for (i = 0; i < obj->nr_maps; i++) {
zfree(&obj->maps[i].name);
+ zfree(&obj->maps[i].pin_path);
if (obj->maps[i].clear_priv)
obj->maps[i].clear_priv(&obj->maps[i],
obj->maps[i].priv);
@@ -4518,6 +4754,7 @@ BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
+BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
enum bpf_attach_type
bpf_program__get_expected_attach_type(struct bpf_program *prog)
@@ -4546,7 +4783,8 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype)
/* Programs that use BTF to identify attach point */
-#define BPF_PROG_BTF(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 1, 0)
+#define BPF_PROG_BTF(string, ptype, eatype) \
+ BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0)
/* Programs that can be attached but attach type can't be identified by section
* name. Kept for backward compatibility.
@@ -4573,7 +4811,8 @@ static const struct {
BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT),
BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT),
BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT),
- BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_RAW_TRACEPOINT),
+ BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING,
+ BPF_TRACE_RAW_TP),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
@@ -4678,27 +4917,6 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
continue;
*prog_type = section_names[i].prog_type;
*expected_attach_type = section_names[i].expected_attach_type;
- if (section_names[i].is_attach_btf) {
- struct btf *btf = bpf_core_find_kernel_btf();
- char raw_tp_btf_name[128] = "btf_trace_";
- char *dst = raw_tp_btf_name + sizeof("btf_trace_") - 1;
- int ret;
-
- if (IS_ERR(btf)) {
- pr_warn("vmlinux BTF is not found\n");
- return -EINVAL;
- }
- /* prepend "btf_trace_" prefix per kernel convention */
- strncat(dst, name + section_names[i].len,
- sizeof(raw_tp_btf_name) - sizeof("btf_trace_"));
- ret = btf__find_by_name(btf, raw_tp_btf_name);
- btf__free(btf);
- if (ret <= 0) {
- pr_warn("%s is not found in vmlinux BTF\n", dst);
- return -EINVAL;
- }
- *expected_attach_type = ret;
- }
return 0;
}
pr_warn("failed to guess program type based on ELF section name '%s'\n", name);
@@ -4711,6 +4929,46 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
return -ESRCH;
}
+#define BTF_PREFIX "btf_trace_"
+static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id)
+{
+ struct btf *btf = bpf_core_find_kernel_btf();
+ char raw_tp_btf_name[128] = BTF_PREFIX;
+ char *dst = raw_tp_btf_name + sizeof(BTF_PREFIX) - 1;
+ int ret, i, err = -EINVAL;
+
+ if (IS_ERR(btf)) {
+ pr_warn("vmlinux BTF is not found\n");
+ return -EINVAL;
+ }
+
+ if (!name)
+ goto out;
+
+ for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+ if (!section_names[i].is_attach_btf)
+ continue;
+ if (strncmp(name, section_names[i].sec, section_names[i].len))
+ continue;
+ /* prepend "btf_trace_" prefix per kernel convention */
+ strncat(dst, name + section_names[i].len,
+ sizeof(raw_tp_btf_name) - sizeof(BTF_PREFIX));
+ ret = btf__find_by_name(btf, raw_tp_btf_name);
+ if (ret <= 0) {
+ pr_warn("%s is not found in vmlinux BTF\n", dst);
+ goto out;
+ }
+ *btf_id = ret;
+ err = 0;
+ goto out;
+ }
+ pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
+ err = -ESRCH;
+out:
+ btf__free(btf);
+ return err;
+}
+
int libbpf_attach_type_by_name(const char *name,
enum bpf_attach_type *attach_type)
{
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c63e2ff84abc..6ddc0419337b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -103,8 +103,13 @@ struct bpf_object_open_opts {
bool relaxed_maps;
/* process CO-RE relocations non-strictly, allowing them to fail */
bool relaxed_core_relocs;
+ /* maps that set the 'pinning' attribute in their definition will have
+ * their pin_path attribute set to a file in this directory, and be
+ * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
+ */
+ const char *pin_root_path;
};
-#define bpf_object_open_opts__last_field relaxed_core_relocs
+#define bpf_object_open_opts__last_field pin_root_path
LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
LIBBPF_API struct bpf_object *
@@ -124,6 +129,17 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
__u32 *size);
int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
__u32 *off);
+
+enum libbpf_pin_type {
+ LIBBPF_PIN_NONE,
+ /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+ LIBBPF_PIN_BY_NAME,
+};
+
+/* pin_maps and unpin_maps can both be called with a NULL path, in which case
+ * they will use the pin_path attribute of each map (and ignore all maps that
+ * don't have a pin_path set).
+ */
LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
const char *path);
@@ -307,6 +323,7 @@ LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
@@ -326,6 +343,7 @@ LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -385,6 +403,9 @@ LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
+LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map);
LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index d1473ea4d7a5..86173cbb159d 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -193,8 +193,13 @@ LIBBPF_0.0.5 {
LIBBPF_0.0.6 {
global:
+ bpf_map__get_pin_path;
+ bpf_map__is_pinned;
+ bpf_map__set_pin_path;
bpf_object__open_file;
bpf_object__open_mem;
bpf_program__get_expected_attach_type;
bpf_program__get_type;
+ bpf_program__is_tracing;
+ bpf_program__set_tracing;
} LIBBPF_0.0.5;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 4b0b0364f5fc..a9eb8b322671 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -102,6 +102,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_TRACING:
default:
break;
}
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 0b6287d1b15e..74d84f36a5b2 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -73,6 +73,21 @@ struct xsk_nl_info {
int fd;
};
+/* Up until and including Linux 5.3 */
+struct xdp_ring_offset_v1 {
+ __u64 producer;
+ __u64 consumer;
+ __u64 desc;
+};
+
+/* Up until and including Linux 5.3 */
+struct xdp_mmap_offsets_v1 {
+ struct xdp_ring_offset_v1 rx;
+ struct xdp_ring_offset_v1 tx;
+ struct xdp_ring_offset_v1 fr;
+ struct xdp_ring_offset_v1 cr;
+};
+
int xsk_umem__fd(const struct xsk_umem *umem)
{
return umem ? umem->fd : -EINVAL;
@@ -133,6 +148,58 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
return 0;
}
+static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off)
+{
+ struct xdp_mmap_offsets_v1 off_v1;
+
+ /* getsockopt on a kernel <= 5.3 has no flags fields.
+ * Copy over the offsets to the correct places in the >=5.4 format
+ * and put the flags where they would have been on that kernel.
+ */
+ memcpy(&off_v1, off, sizeof(off_v1));
+
+ off->rx.producer = off_v1.rx.producer;
+ off->rx.consumer = off_v1.rx.consumer;
+ off->rx.desc = off_v1.rx.desc;
+ off->rx.flags = off_v1.rx.consumer + sizeof(__u32);
+
+ off->tx.producer = off_v1.tx.producer;
+ off->tx.consumer = off_v1.tx.consumer;
+ off->tx.desc = off_v1.tx.desc;
+ off->tx.flags = off_v1.tx.consumer + sizeof(__u32);
+
+ off->fr.producer = off_v1.fr.producer;
+ off->fr.consumer = off_v1.fr.consumer;
+ off->fr.desc = off_v1.fr.desc;
+ off->fr.flags = off_v1.fr.consumer + sizeof(__u32);
+
+ off->cr.producer = off_v1.cr.producer;
+ off->cr.consumer = off_v1.cr.consumer;
+ off->cr.desc = off_v1.cr.desc;
+ off->cr.flags = off_v1.cr.consumer + sizeof(__u32);
+}
+
+static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
+{
+ socklen_t optlen;
+ int err;
+
+ optlen = sizeof(*off);
+ err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen);
+ if (err)
+ return err;
+
+ if (optlen == sizeof(*off))
+ return 0;
+
+ if (optlen == sizeof(struct xdp_mmap_offsets_v1)) {
+ xsk_mmap_offsets_v1(off);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
__u64 size, struct xsk_ring_prod *fill,
struct xsk_ring_cons *comp,
@@ -141,7 +208,6 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
struct xdp_mmap_offsets off;
struct xdp_umem_reg mr;
struct xsk_umem *umem;
- socklen_t optlen;
void *map;
int err;
@@ -190,8 +256,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
goto out_socket;
}
- optlen = sizeof(off);
- err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ err = xsk_get_mmap_offsets(umem->fd, &off);
if (err) {
err = -errno;
goto out_socket;
@@ -514,7 +579,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
struct xsk_socket *xsk;
- socklen_t optlen;
int err;
if (!umem || !xsk_ptr || !rx || !tx)
@@ -573,8 +637,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
}
- optlen = sizeof(off);
- err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ err = xsk_get_mmap_offsets(xsk->fd, &off);
if (err) {
err = -errno;
goto out_socket;
@@ -660,7 +723,6 @@ out_xsk_alloc:
int xsk_umem__delete(struct xsk_umem *umem)
{
struct xdp_mmap_offsets off;
- socklen_t optlen;
int err;
if (!umem)
@@ -669,8 +731,7 @@ int xsk_umem__delete(struct xsk_umem *umem)
if (umem->refcount)
return -EBUSY;
- optlen = sizeof(off);
- err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ err = xsk_get_mmap_offsets(umem->fd, &off);
if (!err) {
munmap(umem->fill->ring - off.fr.desc,
off.fr.desc + umem->config.fill_size * sizeof(__u64));
@@ -688,7 +749,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
{
size_t desc_sz = sizeof(struct xdp_desc);
struct xdp_mmap_offsets off;
- socklen_t optlen;
int err;
if (!xsk)
@@ -699,8 +759,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
close(xsk->prog_fd);
}
- optlen = sizeof(off);
- err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ err = xsk_get_mmap_offsets(xsk->fd, &off);
if (!err) {
if (xsk->rx) {
munmap(xsk->rx->ring - off.rx.desc,
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 933f39381039..b334a6db15c1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -89,6 +89,9 @@ $(notdir $(TEST_GEN_PROGS) \
$(OUTPUT)/urandom_read: urandom_read.c
$(CC) -o $@ $< -Wl,--build-id
+$(OUTPUT)/test_stub.o: test_stub.c
+ $(CC) -c $(CFLAGS) -o $@ $<
+
BPFOBJ := $(OUTPUT)/libbpf.a
$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
@@ -131,8 +134,13 @@ $(shell $(1) -v -E - </dev/null 2>&1 \
| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
endef
+# Determine target endianness.
+IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \
+ grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
+MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
+
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
-BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
-I. -I./include/uapi -I$(APIDIR) \
-I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include)
@@ -271,12 +279,8 @@ $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
# Define test_progs BPF-GCC-flavored test runner.
ifneq ($(BPF_GCC),)
-IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \
- grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
-MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
-
TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
-TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(call get_sys_includes,gcc) $(MENDIAN)
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(call get_sys_includes,gcc)
TRUNNER_BPF_LDFLAGS :=
$(eval $(call DEFINE_TEST_RUNNER,test_progs,bpf_gcc))
endif
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c
new file mode 100644
index 000000000000..525388971e08
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <test_progs.h>
+
+__u32 get_map_id(struct bpf_object *obj, const char *name)
+{
+ struct bpf_map_info map_info = {};
+ __u32 map_info_len, duration = 0;
+ struct bpf_map *map;
+ int err;
+
+ map_info_len = sizeof(map_info);
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (CHECK(!map, "find map", "NULL map"))
+ return 0;
+
+ err = bpf_obj_get_info_by_fd(bpf_map__fd(map),
+ &map_info, &map_info_len);
+ CHECK(err, "get map info", "err %d errno %d", err, errno);
+ return map_info.id;
+}
+
+void test_pinning(void)
+{
+ const char *file_invalid = "./test_pinning_invalid.o";
+ const char *custpinpath = "/sys/fs/bpf/custom/pinmap";
+ const char *nopinpath = "/sys/fs/bpf/nopinmap";
+ const char *nopinpath2 = "/sys/fs/bpf/nopinmap2";
+ const char *custpath = "/sys/fs/bpf/custom";
+ const char *pinpath = "/sys/fs/bpf/pinmap";
+ const char *file = "./test_pinning.o";
+ __u32 map_id, map_id2, duration = 0;
+ struct stat statbuf = {};
+ struct bpf_object *obj;
+ struct bpf_map *map;
+ int err;
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
+ .pin_root_path = custpath,
+ );
+
+ /* check that opening fails with invalid pinning value in map def */
+ obj = bpf_object__open_file(file_invalid, NULL);
+ err = libbpf_get_error(obj);
+ if (CHECK(err != -EINVAL, "invalid open", "err %d errno %d\n", err, errno)) {
+ obj = NULL;
+ goto out;
+ }
+
+ /* open the valid object file */
+ obj = bpf_object__open_file(file, NULL);
+ err = libbpf_get_error(obj);
+ if (CHECK(err, "default open", "err %d errno %d\n", err, errno)) {
+ obj = NULL;
+ goto out;
+ }
+
+ err = bpf_object__load(obj);
+ if (CHECK(err, "default load", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that pinmap was pinned */
+ err = stat(pinpath, &statbuf);
+ if (CHECK(err, "stat pinpath", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that nopinmap was *not* pinned */
+ err = stat(nopinpath, &statbuf);
+ if (CHECK(!err || errno != ENOENT, "stat nopinpath",
+ "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that nopinmap2 was *not* pinned */
+ err = stat(nopinpath2, &statbuf);
+ if (CHECK(!err || errno != ENOENT, "stat nopinpath2",
+ "err %d errno %d\n", err, errno))
+ goto out;
+
+ map_id = get_map_id(obj, "pinmap");
+ if (!map_id)
+ goto out;
+
+ bpf_object__close(obj);
+
+ obj = bpf_object__open_file(file, NULL);
+ if (CHECK_FAIL(libbpf_get_error(obj))) {
+ obj = NULL;
+ goto out;
+ }
+
+ err = bpf_object__load(obj);
+ if (CHECK(err, "default load", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that same map ID was reused for second load */
+ map_id2 = get_map_id(obj, "pinmap");
+ if (CHECK(map_id != map_id2, "check reuse",
+ "err %d errno %d id %d id2 %d\n", err, errno, map_id, map_id2))
+ goto out;
+
+ /* should be no-op to re-pin same map */
+ map = bpf_object__find_map_by_name(obj, "pinmap");
+ if (CHECK(!map, "find map", "NULL map"))
+ goto out;
+
+ err = bpf_map__pin(map, NULL);
+ if (CHECK(err, "re-pin map", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* but error to pin at different location */
+ err = bpf_map__pin(map, "/sys/fs/bpf/other");
+ if (CHECK(!err, "pin map different", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* unpin maps with a pin_path set */
+ err = bpf_object__unpin_maps(obj, NULL);
+ if (CHECK(err, "unpin maps", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* and re-pin them... */
+ err = bpf_object__pin_maps(obj, NULL);
+ if (CHECK(err, "pin maps", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* set pinning path of other map and re-pin all */
+ map = bpf_object__find_map_by_name(obj, "nopinmap");
+ if (CHECK(!map, "find map", "NULL map"))
+ goto out;
+
+ err = bpf_map__set_pin_path(map, custpinpath);
+ if (CHECK(err, "set pin path", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* should only pin the one unpinned map */
+ err = bpf_object__pin_maps(obj, NULL);
+ if (CHECK(err, "pin maps", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that nopinmap was pinned at the custom path */
+ err = stat(custpinpath, &statbuf);
+ if (CHECK(err, "stat custpinpath", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* remove the custom pin path to re-test it with auto-pinning below */
+ err = unlink(custpinpath);
+ if (CHECK(err, "unlink custpinpath", "err %d errno %d\n", err, errno))
+ goto out;
+
+ err = rmdir(custpath);
+ if (CHECK(err, "rmdir custpindir", "err %d errno %d\n", err, errno))
+ goto out;
+
+ bpf_object__close(obj);
+
+ /* open the valid object file again */
+ obj = bpf_object__open_file(file, NULL);
+ err = libbpf_get_error(obj);
+ if (CHECK(err, "default open", "err %d errno %d\n", err, errno)) {
+ obj = NULL;
+ goto out;
+ }
+
+ /* swap pin paths of the two maps */
+ bpf_object__for_each_map(map, obj) {
+ if (!strcmp(bpf_map__name(map), "nopinmap"))
+ err = bpf_map__set_pin_path(map, pinpath);
+ else if (!strcmp(bpf_map__name(map), "pinmap"))
+ err = bpf_map__set_pin_path(map, NULL);
+ else
+ continue;
+
+ if (CHECK(err, "set pin path", "err %d errno %d\n", err, errno))
+ goto out;
+ }
+
+ /* should fail because of map parameter mismatch */
+ err = bpf_object__load(obj);
+ if (CHECK(err != -EINVAL, "param mismatch load", "err %d errno %d\n", err, errno))
+ goto out;
+
+ bpf_object__close(obj);
+
+ /* test auto-pinning at custom path with open opt */
+ obj = bpf_object__open_file(file, &opts);
+ if (CHECK_FAIL(libbpf_get_error(obj))) {
+ obj = NULL;
+ goto out;
+ }
+
+ err = bpf_object__load(obj);
+ if (CHECK(err, "custom load", "err %d errno %d\n", err, errno))
+ goto out;
+
+ /* check that pinmap was pinned at the custom path */
+ err = stat(custpinpath, &statbuf);
+ if (CHECK(err, "stat custpinpath", "err %d errno %d\n", err, errno))
+ goto out;
+
+out:
+ unlink(pinpath);
+ unlink(nopinpath);
+ unlink(nopinpath2);
+ unlink(custpinpath);
+ rmdir(custpath);
+ if (obj)
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
new file mode 100644
index 000000000000..8a3187dec048
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_probe_user(void)
+{
+#define kprobe_name "__sys_connect"
+ const char *prog_name = "kprobe/" kprobe_name;
+ const char *obj_file = "./test_probe_user.o";
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, );
+ int err, results_map_fd, sock_fd, duration = 0;
+ struct sockaddr curr, orig, tmp;
+ struct sockaddr_in *in = (struct sockaddr_in *)&curr;
+ struct bpf_link *kprobe_link = NULL;
+ struct bpf_program *kprobe_prog;
+ struct bpf_object *obj;
+ static const int zero = 0;
+
+ obj = bpf_object__open_file(obj_file, &opts);
+ if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+ return;
+
+ kprobe_prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (CHECK(!kprobe_prog, "find_probe",
+ "prog '%s' not found\n", prog_name))
+ goto cleanup;
+
+ err = bpf_object__load(obj);
+ if (CHECK(err, "obj_load", "err %d\n", err))
+ goto cleanup;
+
+ results_map_fd = bpf_find_map(__func__, obj, "test_pro.bss");
+ if (CHECK(results_map_fd < 0, "find_bss_map",
+ "err %d\n", results_map_fd))
+ goto cleanup;
+
+ kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false,
+ kprobe_name);
+ if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
+ "err %ld\n", PTR_ERR(kprobe_link))) {
+ kprobe_link = NULL;
+ goto cleanup;
+ }
+
+ memset(&curr, 0, sizeof(curr));
+ in->sin_family = AF_INET;
+ in->sin_port = htons(5555);
+ in->sin_addr.s_addr = inet_addr("255.255.255.255");
+ memcpy(&orig, &curr, sizeof(curr));
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (CHECK(sock_fd < 0, "create_sock_fd", "err %d\n", sock_fd))
+ goto cleanup;
+
+ connect(sock_fd, &curr, sizeof(curr));
+ close(sock_fd);
+
+ err = bpf_map_lookup_elem(results_map_fd, &zero, &tmp);
+ if (CHECK(err, "get_kprobe_res",
+ "failed to get kprobe res: %d\n", err))
+ goto cleanup;
+
+ in = (struct sockaddr_in *)&tmp;
+ if (CHECK(memcmp(&tmp, &orig, sizeof(orig)), "check_kprobe_res",
+ "wrong kprobe res from probe read: %s:%u\n",
+ inet_ntoa(in->sin_addr), ntohs(in->sin_port)))
+ goto cleanup;
+
+ memset(&tmp, 0xab, sizeof(tmp));
+
+ in = (struct sockaddr_in *)&curr;
+ if (CHECK(memcmp(&curr, &tmp, sizeof(tmp)), "check_kprobe_res",
+ "wrong kprobe res from probe write: %s:%u\n",
+ inet_ntoa(in->sin_addr), ntohs(in->sin_port)))
+ goto cleanup;
+cleanup:
+ bpf_link__destroy(kprobe_link);
+ bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 89af8a921ee4..489319ea1d6a 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -79,11 +79,11 @@ int trace_kfree_skb(struct trace_kfree_skb *ctx)
func = ptr->func;
}));
- bpf_probe_read(&pkt_type, sizeof(pkt_type), _(&skb->__pkt_type_offset));
+ bpf_probe_read_kernel(&pkt_type, sizeof(pkt_type), _(&skb->__pkt_type_offset));
pkt_type &= 7;
/* read eth proto */
- bpf_probe_read(&pkt_data, sizeof(pkt_data), data + 12);
+ bpf_probe_read_kernel(&pkt_data, sizeof(pkt_data), data + 12);
bpf_printk("rcuhead.next %llx func %llx\n", ptr, func);
bpf_printk("skb->len %d users %d pkt_type %x\n",
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 003fe106fc70..71d383cc9b85 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -72,9 +72,9 @@ static __always_inline void *get_thread_state(void *tls_base, PidData *pidData)
void* thread_state;
int key;
- bpf_probe_read(&key, sizeof(key), (void*)(long)pidData->tls_key_addr);
- bpf_probe_read(&thread_state, sizeof(thread_state),
- tls_base + 0x310 + key * 0x10 + 0x08);
+ bpf_probe_read_user(&key, sizeof(key), (void*)(long)pidData->tls_key_addr);
+ bpf_probe_read_user(&thread_state, sizeof(thread_state),
+ tls_base + 0x310 + key * 0x10 + 0x08);
return thread_state;
}
@@ -82,31 +82,33 @@ static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData,
FrameData *frame, Symbol *symbol)
{
// read data from PyFrameObject
- bpf_probe_read(&frame->f_back,
- sizeof(frame->f_back),
- frame_ptr + pidData->offsets.PyFrameObject_back);
- bpf_probe_read(&frame->f_code,
- sizeof(frame->f_code),
- frame_ptr + pidData->offsets.PyFrameObject_code);
+ bpf_probe_read_user(&frame->f_back,
+ sizeof(frame->f_back),
+ frame_ptr + pidData->offsets.PyFrameObject_back);
+ bpf_probe_read_user(&frame->f_code,
+ sizeof(frame->f_code),
+ frame_ptr + pidData->offsets.PyFrameObject_code);
// read data from PyCodeObject
if (!frame->f_code)
return false;
- bpf_probe_read(&frame->co_filename,
- sizeof(frame->co_filename),
- frame->f_code + pidData->offsets.PyCodeObject_filename);
- bpf_probe_read(&frame->co_name,
- sizeof(frame->co_name),
- frame->f_code + pidData->offsets.PyCodeObject_name);
+ bpf_probe_read_user(&frame->co_filename,
+ sizeof(frame->co_filename),
+ frame->f_code + pidData->offsets.PyCodeObject_filename);
+ bpf_probe_read_user(&frame->co_name,
+ sizeof(frame->co_name),
+ frame->f_code + pidData->offsets.PyCodeObject_name);
// read actual names into symbol
if (frame->co_filename)
- bpf_probe_read_str(&symbol->file,
- sizeof(symbol->file),
- frame->co_filename + pidData->offsets.String_data);
+ bpf_probe_read_user_str(&symbol->file,
+ sizeof(symbol->file),
+ frame->co_filename +
+ pidData->offsets.String_data);
if (frame->co_name)
- bpf_probe_read_str(&symbol->name,
- sizeof(symbol->name),
- frame->co_name + pidData->offsets.String_data);
+ bpf_probe_read_user_str(&symbol->name,
+ sizeof(symbol->name),
+ frame->co_name +
+ pidData->offsets.String_data);
return true;
}
@@ -174,9 +176,9 @@ static __always_inline int __on_event(struct pt_regs *ctx)
event->kernel_stack_id = bpf_get_stackid(ctx, &stackmap, 0);
void* thread_state_current = (void*)0;
- bpf_probe_read(&thread_state_current,
- sizeof(thread_state_current),
- (void*)(long)pidData->current_state_addr);
+ bpf_probe_read_user(&thread_state_current,
+ sizeof(thread_state_current),
+ (void*)(long)pidData->current_state_addr);
struct task_struct* task = (struct task_struct*)bpf_get_current_task();
void* tls_base = (void*)task;
@@ -188,11 +190,13 @@ static __always_inline int __on_event(struct pt_regs *ctx)
if (pidData->use_tls) {
uint64_t pthread_created;
uint64_t pthread_self;
- bpf_probe_read(&pthread_self, sizeof(pthread_self), tls_base + 0x10);
+ bpf_probe_read_user(&pthread_self, sizeof(pthread_self),
+ tls_base + 0x10);
- bpf_probe_read(&pthread_created,
- sizeof(pthread_created),
- thread_state + pidData->offsets.PyThreadState_thread);
+ bpf_probe_read_user(&pthread_created,
+ sizeof(pthread_created),
+ thread_state +
+ pidData->offsets.PyThreadState_thread);
event->pthread_match = pthread_created == pthread_self;
} else {
event->pthread_match = 1;
@@ -204,9 +208,10 @@ static __always_inline int __on_event(struct pt_regs *ctx)
Symbol sym = {};
int cur_cpu = bpf_get_smp_processor_id();
- bpf_probe_read(&frame_ptr,
- sizeof(frame_ptr),
- thread_state + pidData->offsets.PyThreadState_frame);
+ bpf_probe_read_user(&frame_ptr,
+ sizeof(frame_ptr),
+ thread_state +
+ pidData->offsets.PyThreadState_frame);
int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym);
if (symbol_counter == NULL)
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 067eb625d01c..4bf16e0a1b0e 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -98,7 +98,7 @@ struct strobe_map_raw {
/*
* having volatile doesn't change anything on BPF side, but clang
* emits warnings for passing `volatile const char *` into
- * bpf_probe_read_str that expects just `const char *`
+ * bpf_probe_read_user_str that expects just `const char *`
*/
const char* tag;
/*
@@ -309,18 +309,18 @@ static __always_inline void *calc_location(struct strobe_value_loc *loc,
dtv_t *dtv;
void *tls_ptr;
- bpf_probe_read(&tls_index, sizeof(struct tls_index),
- (void *)loc->offset);
+ bpf_probe_read_user(&tls_index, sizeof(struct tls_index),
+ (void *)loc->offset);
/* valid module index is always positive */
if (tls_index.module > 0) {
/* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */
- bpf_probe_read(&dtv, sizeof(dtv),
- &((struct tcbhead *)tls_base)->dtv);
+ bpf_probe_read_user(&dtv, sizeof(dtv),
+ &((struct tcbhead *)tls_base)->dtv);
dtv += tls_index.module;
} else {
dtv = NULL;
}
- bpf_probe_read(&tls_ptr, sizeof(void *), dtv);
+ bpf_probe_read_user(&tls_ptr, sizeof(void *), dtv);
/* if pointer has (void *)-1 value, then TLS wasn't initialized yet */
return tls_ptr && tls_ptr != (void *)-1
? tls_ptr + tls_index.offset
@@ -336,7 +336,7 @@ static __always_inline void read_int_var(struct strobemeta_cfg *cfg,
if (!location)
return;
- bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
+ bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
data->int_vals[idx] = value->val;
if (value->header.len)
data->int_vals_set_mask |= (1 << idx);
@@ -356,13 +356,13 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
if (!location)
return 0;
- bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
- len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, value->ptr);
+ bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
+ len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr);
/*
- * if bpf_probe_read_str returns error (<0), due to casting to
+ * if bpf_probe_read_user_str returns error (<0), due to casting to
* unsinged int, it will become big number, so next check is
* sufficient to check for errors AND prove to BPF verifier, that
- * bpf_probe_read_str won't return anything bigger than
+ * bpf_probe_read_user_str won't return anything bigger than
* STROBE_MAX_STR_LEN
*/
if (len > STROBE_MAX_STR_LEN)
@@ -391,8 +391,8 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
if (!location)
return payload;
- bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
- if (bpf_probe_read(&map, sizeof(struct strobe_map_raw), value->ptr))
+ bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
+ if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr))
return payload;
descr->id = map.id;
@@ -402,7 +402,7 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
data->req_meta_valid = 1;
}
- len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, map.tag);
+ len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
if (len <= STROBE_MAX_STR_LEN) {
descr->tag_len = len;
payload += len;
@@ -418,15 +418,15 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
break;
descr->key_lens[i] = 0;
- len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
- map.entries[i].key);
+ len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+ map.entries[i].key);
if (len <= STROBE_MAX_STR_LEN) {
descr->key_lens[i] = len;
payload += len;
}
descr->val_lens[i] = 0;
- len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
- map.entries[i].val);
+ len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+ map.entries[i].val);
if (len <= STROBE_MAX_STR_LEN) {
descr->val_lens[i] = len;
payload += len;
diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c
new file mode 100644
index 000000000000..f69a4a50d056
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(pinning, LIBBPF_PIN_BY_NAME);
+} pinmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} nopinmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(pinning, LIBBPF_PIN_NONE);
+} nopinmap2 SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
new file mode 100644
index 000000000000..51b38abe7ba1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(pinning, 2); /* invalid */
+} nopinmap3 SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
new file mode 100644
index 000000000000..1871e2ece0c4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+
+#include <netinet/in.h>
+
+#include "bpf_helpers.h"
+#include "bpf_tracing.h"
+
+static struct sockaddr_in old;
+
+SEC("kprobe/__sys_connect")
+int handle_sys_connect(struct pt_regs *ctx)
+{
+ void *ptr = (void *)PT_REGS_PARM2(ctx);
+ struct sockaddr_in new;
+
+ bpf_probe_read_user(&old, sizeof(old), ptr);
+ __builtin_memset(&new, 0xab, sizeof(new));
+ bpf_probe_write_user(ptr, &new, sizeof(new));
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index c8c595da38d4..87b7d934ce73 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@@ -38,7 +38,7 @@
#include <sys/socket.h>
#include "bpf_helpers.h"
-#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
+#define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;})
#define TCP_ESTATS_MAGIC 0xBAADBEEF
/* This test case needs "sock" and "pt_regs" data structure.
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index d1645cc5ecbb..fc8a4319c1b2 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -314,9 +314,6 @@ class DebugfsDir:
continue
p = os.path.join(path, f)
- if not os.stat(p).st_mode & stat.S_IRUSR:
- continue
-
if os.path.isfile(p) and os.access(p, os.R_OK):
_, out = cmd('cat %s/%s' % (path, f))
dfs[f] = out.strip()
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index a320e3844b17..7aff907003d3 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -121,6 +121,29 @@ static struct sysctl_test tests[] = {
.result = OP_EPERM,
},
{
+ .descr = "ctx:write sysctl:write read ok narrow",
+ .insns = {
+ /* u64 w = (u16)write & 1; */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write)),
+#else
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write) + 2),
+#endif
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_7, 1),
+ /* return 1 - w; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/domainname",
+ .open_flags = O_WRONLY,
+ .newval = "(none)", /* same as default, should fail anyway */
+ .result = OP_EPERM,
+ },
+ {
.descr = "ctx:write sysctl:read write reject",
.insns = {
/* write = X */