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>
mariux64 · Nov 2, 2019 · ae8a76f · ae8a76f
2 parents d31e955 + 358fdb4
commit ae8a76f
Showing 41 changed files with 1,863 additions and 476 deletions.
diff --git 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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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);