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

Pull networking updates from David Miller:

 1) Add WireGuard

 2) Add HE and TWT support to ath11k driver, from John Crispin.

 3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.

 4) Add variable window congestion control to TIPC, from Jon Maloy.

 5) Add BCM84881 PHY driver, from Russell King.

 6) Start adding netlink support for ethtool operations, from Michal
    Kubecek.

 7) Add XDP drop and TX action support to ena driver, from Sameeh
    Jubran.

 8) Add new ipv4 route notifications so that mlxsw driver does not have
    to handle identical routes itself. From Ido Schimmel.

 9) Add BPF dynamic program extensions, from Alexei Starovoitov.

10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.

11) Add support for macsec HW offloading, from Antoine Tenart.

12) Add initial support for MPTCP protocol, from Christoph Paasch,
    Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.

13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
    Cherian, and others.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
  net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
  udp: segment looped gso packets correctly
  netem: change mailing list
  qed: FW 8.42.2.0 debug features
  qed: rt init valid initialization changed
  qed: Debug feature: ilt and mdump
  qed: FW 8.42.2.0 Add fw overlay feature
  qed: FW 8.42.2.0 HSI changes
  qed: FW 8.42.2.0 iscsi/fcoe changes
  qed: Add abstraction for different hsi values per chip
  qed: FW 8.42.2.0 Additional ll2 type
  qed: Use dmae to write to widebus registers in fw_funcs
  qed: FW 8.42.2.0 Parser offsets modified
  qed: FW 8.42.2.0 Queue Manager changes
  qed: FW 8.42.2.0 Expose new registers and change windows
  qed: FW 8.42.2.0 Internal ram offsets modifications
  MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
  Documentation: net: octeontx2: Add RVU HW and drivers overview
  octeontx2-pf: ethtool RSS config support
  octeontx2-pf: Add basic ethtool support
  ...

2 files changed, 158 insertions, 9 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 42bc6fb0d2be..a283336bb5d5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -93,6 +93,7 @@ config X86
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	select ARCH_WANT_DEFAULT_BPF_JIT	if X86_64
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_HUGE_PMD_SHARE
 	select ARCH_WANTS_THP_SWAP		if X86_64
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b8be18427277..9ba08e9abc09 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -10,10 +10,12 @@
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
 #include <linux/memory.h>
+#include <linux/sort.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
+#include <asm/asm-prototypes.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -1326,7 +1328,7 @@ emit_jmp:
 	return proglen;
 }
 
-static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 		      int stack_size)
 {
 	int i;
@@ -1342,7 +1344,7 @@ static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
 			 -(stack_size - i * 8));
 }
 
-static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 			 int stack_size)
 {
 	int i;
@@ -1359,7 +1361,7 @@ static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
 			 -(stack_size - i * 8));
 }
 
-static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
+static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_prog **progs, int prog_cnt, int stack_size)
 {
 	u8 *prog = *pprog;
@@ -1454,7 +1456,8 @@ static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
  * add rsp, 8                      // skip eth_type_trans's frame
  * ret                             // return to its caller
  */
-int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+int arch_prepare_bpf_trampoline(void *image, void *image_end,
+				const struct btf_func_model *m, u32 flags,
 				struct bpf_prog **fentry_progs, int fentry_cnt,
 				struct bpf_prog **fexit_progs, int fexit_cnt,
 				void *orig_call)
@@ -1521,15 +1524,160 @@ int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
 	EMIT1(0xC3); /* ret */
-	/* One half of the page has active running trampoline.
-	 * Another half is an area for next trampoline.
-	 * Make sure the trampoline generation logic doesn't overflow.
-	 */
-	if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
+	/* Make sure the trampoline generation logic doesn't overflow */
+	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY))
 		return -EFAULT;
+	return prog - (u8 *)image;
+}
+
+static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	s64 offset;
+
+	offset = func - (ip + 2 + 4);
+	if (!is_simm32(offset)) {
+		pr_err("Target %p is out of range\n", func);
+		return -EINVAL;
+	}
+	EMIT2_off32(0x0F, jmp_cond + 0x10, offset);
+	*pprog = prog;
+	return 0;
+}
+
+static void emit_nops(u8 **pprog, unsigned int len)
+{
+	unsigned int i, noplen;
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(ideal_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+}
+
+static int emit_fallback_jump(u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int err = 0;
+
+#ifdef CONFIG_RETPOLINE
+	/* Note that this assumes the the compiler uses external
+	 * thunks for indirect calls. Both clang and GCC use the same
+	 * naming convention for external thunks.
+	 */
+	err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog);
+#else
+	int cnt = 0;
+
+	EMIT2(0xFF, 0xE2);	/* jmp rdx */
+#endif
+	*pprog = prog;
+	return err;
+}
+
+static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
+{
+	u8 *jg_reloc, *jg_target, *prog = *pprog;
+	int pivot, err, jg_bytes = 1, cnt = 0;
+	s64 jg_offset;
+
+	if (a == b) {
+		/* Leaf node of recursion, i.e. not a range of indices
+		 * anymore.
+		 */
+		EMIT1(add_1mod(0x48, BPF_REG_3));	/* cmp rdx,func */
+		if (!is_simm32(progs[a]))
+			return -1;
+		EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3),
+			    progs[a]);
+		err = emit_cond_near_jump(&prog,	/* je func */
+					  (void *)progs[a], prog,
+					  X86_JE);
+		if (err)
+			return err;
+
+		err = emit_fallback_jump(&prog);	/* jmp thunk/indirect */
+		if (err)
+			return err;
+
+		*pprog = prog;
+		return 0;
+	}
+
+	/* Not a leaf node, so we pivot, and recursively descend into
+	 * the lower and upper ranges.
+	 */
+	pivot = (b - a) / 2;
+	EMIT1(add_1mod(0x48, BPF_REG_3));		/* cmp rdx,func */
+	if (!is_simm32(progs[a + pivot]))
+		return -1;
+	EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a + pivot]);
+
+	if (pivot > 2) {				/* jg upper_part */
+		/* Require near jump. */
+		jg_bytes = 4;
+		EMIT2_off32(0x0F, X86_JG + 0x10, 0);
+	} else {
+		EMIT2(X86_JG, 0);
+	}
+	jg_reloc = prog;
+
+	err = emit_bpf_dispatcher(&prog, a, a + pivot,	/* emit lower_part */
+				  progs);
+	if (err)
+		return err;
+
+	/* From Intel 64 and IA-32 Architectures Optimization
+	 * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
+	 * Coding Rule 11: All branch targets should be 16-byte
+	 * aligned.
+	 */
+	jg_target = PTR_ALIGN(prog, 16);
+	if (jg_target != prog)
+		emit_nops(&prog, jg_target - prog);
+	jg_offset = prog - jg_reloc;
+	emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes);
+
+	err = emit_bpf_dispatcher(&prog, a + pivot + 1,	/* emit upper_part */
+				  b, progs);
+	if (err)
+		return err;
+
+	*pprog = prog;
 	return 0;
 }
 
+static int cmp_ips(const void *a, const void *b)
+{
+	const s64 *ipa = a;
+	const s64 *ipb = b;
+
+	if (*ipa > *ipb)
+		return 1;
+	if (*ipa < *ipb)
+		return -1;
+	return 0;
+}
+
+int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs)
+{
+	u8 *prog = image;
+
+	sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL);
+	return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs);
+}
+
 struct x64_jit_data {
 	struct bpf_binary_header *header;
 	int *addrs;