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

Daniel Borkmann says:

====================
bpf-next 2021-10-02

We've added 85 non-merge commits during the last 15 day(s) which contain
a total of 132 files changed, 13779 insertions(+), 6724 deletions(-).

The main changes are:

1) Massive update on test_bpf.ko coverage for JITs as preparatory work for
   an upcoming MIPS eBPF JIT, from Johan Almbladh.

2) Add a batched interface for RX buffer allocation in AF_XDP buffer pool,
   with driver support for i40e and ice from Magnus Karlsson.

3) Add legacy uprobe support to libbpf to complement recently merged legacy
   kprobe support, from Andrii Nakryiko.

4) Add bpf_trace_vprintk() as variadic printk helper, from Dave Marchevsky.

5) Support saving the register state in verifier when spilling <8byte bounded
   scalar to the stack, from Martin Lau.

6) Add libbpf opt-in for stricter BPF program section name handling as part
   of libbpf 1.0 effort, from Andrii Nakryiko.

7) Add a document to help clarifying BPF licensing, from Alexei Starovoitov.

8) Fix skel_internal.h to propagate errno if the loader indicates an internal
   error, from Kumar Kartikeya Dwivedi.

9) Fix build warnings with -Wcast-function-type so that the option can later
   be enabled by default for the kernel, from Kees Cook.

10) Fix libbpf to ignore STT_SECTION symbols in legacy map definitions as it
    otherwise errors out when encountering them, from Toke Høiland-Jørgensen.

11) Teach libbpf to recognize specialized maps (such as for perf RB) and
    internally remove BTF type IDs when creating them, from Hengqi Chen.

12) Various fixes and improvements to BPF selftests.
====================

Link: https://lore.kernel.org/r/20211002001327.15169-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 95 insertions, 13 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 020a7d5bf470..1c7fd7c4c6d3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -48,6 +48,7 @@ extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
 
+typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
@@ -142,7 +143,8 @@ struct bpf_map_ops {
 	int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env,
 					      struct bpf_func_state *caller,
 					      struct bpf_func_state *callee);
-	int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn,
+	int (*map_for_each_callback)(struct bpf_map *map,
+				     bpf_callback_t callback_fn,
 				     void *callback_ctx, u64 flags);
 
 	/* BTF name and id of struct allocated by map_alloc */
@@ -1089,6 +1091,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void);
 
 typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 					unsigned long off, unsigned long len);
@@ -2217,6 +2220,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 struct btf_id_set;
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
+#define MAX_BPRINTF_VARARGS		12
+
 int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 **bin_buf, u32 num_args);
 void bpf_bprintf_cleanup(void);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12543ee..47f80adbe744 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -360,10 +360,9 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = 0,					\
 		.imm   = TGT })
 
-/* Function call */
+/* Convert function address to BPF immediate */
 
-#define BPF_CAST_CALL(x)					\
-		((u64 (*)(u64, u64, u64, u64, u64))(x))
+#define BPF_CALL_IMM(x)	((void *)(x) - (void *)__bpf_call_base)
 
 #define BPF_EMIT_CALL(FUNC)					\
 	((struct bpf_insn) {					\
@@ -371,7 +370,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.dst_reg = 0,					\
 		.src_reg = 0,					\
 		.off   = 0,					\
-		.imm   = ((FUNC) - __bpf_call_base) })
+		.imm   = BPF_CALL_IMM(FUNC) })
 
 /* Raw code statement block */
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index ad5b02dcb6f4..447f9b1578f3 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -15,13 +15,13 @@
  * level RX-ring queues.  It is information that is specific to how
  * the driver have configured a given RX-ring queue.
  *
- * Each xdp_buff frame received in the driver carry a (pointer)
+ * Each xdp_buff frame received in the driver carries a (pointer)
  * reference to this xdp_rxq_info structure.  This provides the XDP
  * data-path read-access to RX-info for both kernel and bpf-side
  * (limited subset).
  *
  * For now, direct access is only safe while running in NAPI/softirq
- * context.  Contents is read-mostly and must not be updated during
+ * context.  Contents are read-mostly and must not be updated during
  * driver NAPI/softirq poll.
  *
  * The driver usage API is a register and unregister API.
@@ -30,8 +30,8 @@
  * can be attached as long as it doesn't change the underlying
  * RX-ring.  If the RX-ring does change significantly, the NIC driver
  * naturally need to stop the RX-ring before purging and reallocating
- * memory.  In that process the driver MUST call unregistor (which
- * also apply for driver shutdown and unload).  The register API is
+ * memory.  In that process the driver MUST call unregister (which
+ * also applies for driver shutdown and unload).  The register API is
  * also mandatory during RX-ring setup.
  */
 
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 4e295541e396..443d45951564 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -77,6 +77,12 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return xp_alloc(pool);
 }
 
+/* Returns as many entries as possible up to max. 0 <= N <= max. */
+static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	return xp_alloc_batch(pool, xdp, max);
+}
+
 static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return xp_can_alloc(pool, count);
@@ -89,6 +95,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 	xp_free(xskb);
 }
 
+static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
+{
+	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
+	xdp->data_meta = xdp->data;
+	xdp->data_end = xdp->data + size;
+}
+
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
 					      u64 addr)
 {
@@ -212,6 +225,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return NULL;
 }
 
+static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	return 0;
+}
+
 static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return false;
@@ -221,6 +239,10 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
+static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
+{
+}
+
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
 					      u64 addr)
 {
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 7a9a23e7a604..ddeefc4a1040 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -7,6 +7,7 @@
 #include <linux/if_xdp.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
+#include <linux/bpf.h>
 #include <net/xdp.h>
 
 struct xsk_buff_pool;
@@ -23,7 +24,6 @@ struct xdp_buff_xsk {
 	dma_addr_t dma;
 	dma_addr_t frame_dma;
 	struct xsk_buff_pool *pool;
-	bool unaligned;
 	u64 orig_addr;
 	struct list_head free_list_node;
 };
@@ -67,6 +67,7 @@ struct xsk_buff_pool {
 	u32 free_heads_cnt;
 	u32 headroom;
 	u32 chunk_size;
+	u32 chunk_shift;
 	u32 frame_len;
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
@@ -81,6 +82,13 @@ struct xsk_buff_pool {
 	struct xdp_buff_xsk *free_heads[];
 };
 
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
+
 /* AF_XDP core. */
 struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
@@ -89,7 +97,6 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
 			 struct net_device *dev, u16 queue_id);
 void xp_destroy(struct xsk_buff_pool *pool);
-void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
 bool xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
@@ -99,12 +106,28 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
 
+static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				     u64 addr)
+{
+	xskb->orig_addr = addr;
+	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
+}
+
+static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				    dma_addr_t *dma_pages, u64 addr)
+{
+	xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) +
+		(addr & ~PAGE_MASK);
+	xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
+}
+
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
 struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool);
+u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max);
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
 dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
@@ -180,4 +203,25 @@ static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
 		xp_unaligned_extract_offset(addr);
 }
 
+static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr)
+{
+	return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift;
+}
+
+static inline void xp_release(struct xdp_buff_xsk *xskb)
+{
+	if (xskb->pool->unaligned)
+		xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
+}
+
+static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
+{
+	u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+
+	offset += xskb->pool->headroom;
+	if (!xskb->pool->unaligned)
+		return xskb->orig_addr + offset;
+	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+}
+
 #endif /* XSK_BUFF_POOL_H_ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3e9785f1064a..6fc59d61937a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4046,7 +4046,7 @@ union bpf_attr {
  * 		arguments. The *data* are a **u64** array and corresponding format string
  * 		values are stored in the array. For strings and pointers where pointees
  * 		are accessed, only the pointer values are stored in the *data* array.
- * 		The *data_len* is the size of *data* in bytes.
+ * 		The *data_len* is the size of *data* in bytes - must be a multiple of 8.
  *
  *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
  *		Reading kernel memory may fail due to either invalid address or
@@ -4751,7 +4751,8 @@ union bpf_attr {
  *		Each format specifier in **fmt** corresponds to one u64 element
  *		in the **data** array. For strings and pointers where pointees
  *		are accessed, only the pointer values are stored in the *data*
- *		array. The *data_len* is the size of *data* in bytes.
+ *		array. The *data_len* is the size of *data* in bytes - must be
+ *		a multiple of 8.
  *
  *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
  *		memory. Reading kernel memory may fail due to either invalid
@@ -4898,6 +4899,16 @@ union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5088,7 @@ union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper