Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-15

The following pull-request contains BPF updates for your *net-next* tree.

We've added 37 non-merge commits during the last 1 day(s) which contain
a total of 67 files changed, 741 insertions(+), 252 deletions(-).

The main changes are:

1) bpf_xdp_adjust_tail() now allows to grow the tail as well, from Jesper.

2) bpftool can probe CONFIG_HZ, from Daniel.

3) CAP_BPF is introduced to isolate user processes that use BPF infra and
   to secure BPF networking services by dropping CAP_SYS_ADMIN requirement
   in certain cases, from Alexei.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 97 insertions, 5 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c45d198ac38c..efe8836b5c48 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
+#include <linux/capability.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -119,7 +120,7 @@ struct bpf_map {
 	struct bpf_map_memory memory;
 	char name[BPF_OBJ_NAME_LEN];
 	u32 btf_vmlinux_value_type_id;
-	bool unpriv_array;
+	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
 	/* 22 bytes hole */
 
@@ -1095,6 +1096,21 @@ struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
+static inline bool bpf_allow_ptr_leaks(void)
+{
+	return perfmon_capable();
+}
+
+static inline bool bpf_bypass_spec_v1(void)
+{
+	return perfmon_capable();
+}
+
+static inline bool bpf_bypass_spec_v4(void)
+{
+	return perfmon_capable();
+}
+
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6abd5a778fcd..ea833087e853 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -375,6 +375,9 @@ struct bpf_verifier_env {
 	u32 used_map_cnt;		/* number of used maps */
 	u32 id_gen;			/* used to generate unique reg IDs */
 	bool allow_ptr_leaks;
+	bool bpf_capable;
+	bool bypass_spec_v1;
+	bool bypass_spec_v4;
 	bool seen_direct_write;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
 	const struct bpf_line_info *prev_linfo;
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 027d7e4a853b..b4345b38a6be 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -256,6 +256,11 @@ static inline bool perfmon_capable(void)
 	return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN);
 }
 
+static inline bool bpf_capable(void)
+{
+	return capable(CAP_BPF) || capable(CAP_SYS_ADMIN);
+}
+
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 3cc6d5d84aa4..3094fccf5a88 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -6,6 +6,8 @@
 #ifndef __LINUX_NET_XDP_H__
 #define __LINUX_NET_XDP_H__
 
+#include <linux/skbuff.h> /* skb_shared_info */
+
 /**
  * DOC: XDP RX-queue information
  *
@@ -70,13 +72,25 @@ struct xdp_buff {
 	void *data_hard_start;
 	unsigned long handle;
 	struct xdp_rxq_info *rxq;
+	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 
+/* Reserve memory area at end-of data area.
+ *
+ * This macro reserves tailroom in the XDP buffer by limiting the
+ * XDP/BPF data access to data_hard_end.  Notice same area (and size)
+ * is used for XDP_PASS, when constructing the SKB via build_skb().
+ */
+#define xdp_data_hard_end(xdp)				\
+	((xdp)->data_hard_start + (xdp)->frame_sz -	\
+	 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
 struct xdp_frame {
 	void *data;
 	u16 len;
 	u16 headroom;
-	u16 metasize;
+	u32 metasize:8;
+	u32 frame_sz:24;
 	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
 	 * while mem info is valid on remote CPU.
 	 */
@@ -91,6 +105,10 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+/* Avoids inlining WARN macro in fast-path */
+void xdp_warn(const char *msg, const char *func, const int line);
+#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
+
 struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
 
 /* Convert xdp_buff to xdp_frame */
@@ -111,6 +129,12 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 	if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
 		return NULL;
 
+	/* Catch if driver didn't reserve tailroom for skb_shared_info */
+	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
+		XDP_WARN("Driver BUG: missing reserved tailroom");
+		return NULL;
+	}
+
 	/* Store info in top of packet */
 	xdp_frame = xdp->data_hard_start;
 
@@ -118,6 +142,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 	xdp_frame->len  = xdp->data_end - xdp->data;
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
+	xdp_frame->frame_sz = xdp->frame_sz;
 
 	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
 	xdp_frame->mem = xdp->rxq->mem;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 67191ccaab85..abd72de25fa4 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -236,6 +236,12 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
 	else
 		return address + offset;
 }
+
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return umem->chunk_size_nohr + umem->headroom;
+}
+
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -366,6 +372,11 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
 	return 0;
 }
 
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return 0;
+}
+
 static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	return -EOPNOTSUPP;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 32cbf36c7729..b9b8a0f63b91 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2015,8 +2015,8 @@ union bpf_attr {
  * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
  * 	Description
  * 		Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
- * 		only possible to shrink the packet as of this writing,
- * 		therefore *delta* must be a negative integer.
+ * 		possible to both shrink and grow the packet tail.
+ * 		Shrink done via *delta* being a negative integer.
  *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index e58c9636741b..c7372180a0a9 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -274,6 +274,7 @@ struct vfs_ns_cap_data {
    arbitrary SCSI commands */
 /* Allow setting encryption key on loopback filesystem */
 /* Allow setting zone reclaim policy */
+/* Allow everything under CAP_BPF and CAP_PERFMON for backward compatibility */
 
 #define CAP_SYS_ADMIN        21
 
@@ -374,7 +375,38 @@ struct vfs_ns_cap_data {
 
 #define CAP_PERFMON		38
 
-#define CAP_LAST_CAP         CAP_PERFMON
+/*
+ * CAP_BPF allows the following BPF operations:
+ * - Creating all types of BPF maps
+ * - Advanced verifier features
+ *   - Indirect variable access
+ *   - Bounded loops
+ *   - BPF to BPF function calls
+ *   - Scalar precision tracking
+ *   - Larger complexity limits
+ *   - Dead code elimination
+ *   - And potentially other features
+ * - Loading BPF Type Format (BTF) data
+ * - Retrieve xlated and JITed code of BPF programs
+ * - Use bpf_spin_lock() helper
+ *
+ * CAP_PERFMON relaxes the verifier checks further:
+ * - BPF progs can use of pointer-to-integer conversions
+ * - speculation attack hardening measures are bypassed
+ * - bpf_probe_read to read arbitrary kernel memory is allowed
+ * - bpf_trace_printk to print kernel memory is allowed
+ *
+ * CAP_SYS_ADMIN is required to use bpf_probe_write_user.
+ *
+ * CAP_SYS_ADMIN is required to iterate system wide loaded
+ * programs, maps, links, BTFs and convert their IDs to file descriptors.
+ *
+ * CAP_PERFMON and CAP_BPF are required to load tracing programs.
+ * CAP_NET_ADMIN and CAP_BPF are required to load networking programs.
+ */
+#define CAP_BPF			39
+
+#define CAP_LAST_CAP         CAP_BPF
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)