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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 107 insertions, 89 deletions

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a5227ab8ccb1..ca95abd2bed1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -4,58 +4,24 @@
 #ifndef __LINUX_FILTER_H__
 #define __LINUX_FILTER_H__
 
+#include <stdarg.h>
+
 #include <linux/atomic.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
+#include <linux/linkage.h>
+#include <linux/printk.h>
 #include <linux/workqueue.h>
-#include <uapi/linux/filter.h>
-
-/* Internally used and optimized filter representation with extended
- * instruction set based on top of classic BPF.
- */
 
-/* instruction classes */
-#define BPF_ALU64	0x07	/* alu mode in double word width */
+#include <asm/cacheflush.h>
 
-/* ld/ldx fields */
-#define BPF_DW		0x18	/* double word */
-#define BPF_XADD	0xc0	/* exclusive add */
-
-/* alu/jmp fields */
-#define BPF_MOV		0xb0	/* mov reg to reg */
-#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
-
-/* change endianness of a register */
-#define BPF_END		0xd0	/* flags for endianness conversion: */
-#define BPF_TO_LE	0x00	/* convert to little-endian */
-#define BPF_TO_BE	0x08	/* convert to big-endian */
-#define BPF_FROM_LE	BPF_TO_LE
-#define BPF_FROM_BE	BPF_TO_BE
-
-#define BPF_JNE		0x50	/* jump != */
-#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
-#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
-#define BPF_CALL	0x80	/* function call */
-#define BPF_EXIT	0x90	/* function return */
-
-/* Register numbers */
-enum {
-	BPF_REG_0 = 0,
-	BPF_REG_1,
-	BPF_REG_2,
-	BPF_REG_3,
-	BPF_REG_4,
-	BPF_REG_5,
-	BPF_REG_6,
-	BPF_REG_7,
-	BPF_REG_8,
-	BPF_REG_9,
-	BPF_REG_10,
-	__MAX_BPF_REG,
-};
+#include <uapi/linux/filter.h>
+#include <uapi/linux/bpf.h>
 
-/* BPF has 10 general purpose 64-bit registers and stack frame. */
-#define MAX_BPF_REG	__MAX_BPF_REG
+struct sk_buff;
+struct sock;
+struct seccomp_data;
+struct bpf_prog_aux;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -161,6 +127,30 @@ enum {
 		.off   = 0,					\
 		.imm   = IMM })
 
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM)					\
+	BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = (__u32) (IMM) }),			\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((__u64) (IMM)) >> 32 })
+
+#define BPF_PSEUDO_MAP_FD	1
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD)				\
+	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
 /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
 
 #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)			\
@@ -299,14 +289,6 @@ enum {
 #define SK_RUN_FILTER(filter, ctx) \
 	(*filter->prog->bpf_func)(ctx, filter->prog->insnsi)
 
-struct bpf_insn {
-	__u8	code;		/* opcode */
-	__u8	dst_reg:4;	/* dest register */
-	__u8	src_reg:4;	/* source register */
-	__s16	off;		/* signed offset */
-	__s32	imm;		/* signed immediate constant */
-};
-
 #ifdef CONFIG_COMPAT
 /* A struct sock_filter is architecture independent. */
 struct compat_sock_fprog {
@@ -320,20 +302,23 @@ struct sock_fprog_kern {
 	struct sock_filter	*filter;
 };
 
-struct sk_buff;
-struct sock;
-struct seccomp_data;
+struct bpf_binary_header {
+	unsigned int pages;
+	u8 image[];
+};
 
 struct bpf_prog {
-	u32			jited:1,	/* Is our filter JIT'ed? */
-				len:31;		/* Number of filter blocks */
+	u16			pages;		/* Number of allocated pages */
+	bool			jited;		/* Is our filter JIT'ed? */
+	u32			len;		/* Number of filter blocks */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
+	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct bpf_insn *filter);
+	/* Instructions for interpreter */
 	union {
 		struct sock_filter	insns[0];
 		struct bpf_insn		insnsi[0];
-		struct work_struct	work;
 	};
 };
 
@@ -353,6 +338,26 @@ static inline unsigned int bpf_prog_size(unsigned int proglen)
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
+#ifdef CONFIG_DEBUG_SET_MODULE_RONX
+static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+{
+	set_memory_ro((unsigned long)fp, fp->pages);
+}
+
+static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
+{
+	set_memory_rw((unsigned long)fp, fp->pages);
+}
+#else
+static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+{
+}
+
+static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
+{
+}
+#endif /* CONFIG_DEBUG_SET_MODULE_RONX */
+
 int sk_filter(struct sock *sk, struct sk_buff *skb);
 
 void bpf_prog_select_runtime(struct bpf_prog *fp);
@@ -361,6 +366,17 @@ void bpf_prog_free(struct bpf_prog *fp);
 int bpf_convert_filter(struct sock_filter *prog, int len,
 		       struct bpf_insn *new_prog, int *new_len);
 
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
+struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
+				  gfp_t gfp_extra_flags);
+void __bpf_prog_free(struct bpf_prog *fp);
+
+static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
+{
+	bpf_prog_unlock_ro(fp);
+	__bpf_prog_free(fp);
+}
+
 int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
 void bpf_prog_destroy(struct bpf_prog *fp);
 
@@ -377,6 +393,38 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 void bpf_int_jit_compile(struct bpf_prog *fp);
 
+#ifdef CONFIG_BPF_JIT
+typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
+
+struct bpf_binary_header *
+bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
+		     unsigned int alignment,
+		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
+void bpf_jit_binary_free(struct bpf_binary_header *hdr);
+
+void bpf_jit_compile(struct bpf_prog *fp);
+void bpf_jit_free(struct bpf_prog *fp);
+
+static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
+				u32 pass, void *image)
+{
+	pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
+	       flen, proglen, pass, image);
+	if (image)
+		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
+			       16, 1, image, proglen, false);
+}
+#else
+static inline void bpf_jit_compile(struct bpf_prog *fp)
+{
+}
+
+static inline void bpf_jit_free(struct bpf_prog *fp)
+{
+	bpf_prog_unlock_free(fp);
+}
+#endif /* CONFIG_BPF_JIT */
+
 #define BPF_ANC		BIT(15)
 
 static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
@@ -424,36 +472,6 @@ static inline void *bpf_load_pointer(const struct sk_buff *skb, int k,
 	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
-#ifdef CONFIG_BPF_JIT
-#include <stdarg.h>
-#include <linux/linkage.h>
-#include <linux/printk.h>
-
-void bpf_jit_compile(struct bpf_prog *fp);
-void bpf_jit_free(struct bpf_prog *fp);
-
-static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
-				u32 pass, void *image)
-{
-	pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
-	       flen, proglen, pass, image);
-	if (image)
-		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
-			       16, 1, image, proglen, false);
-}
-#else
-#include <linux/slab.h>
-
-static inline void bpf_jit_compile(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_jit_free(struct bpf_prog *fp)
-{
-	kfree(fp);
-}
-#endif /* CONFIG_BPF_JIT */
-
 static inline int bpf_tell_extensions(void)
 {
 	return SKF_AD_MAX;