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

Daniel Borkmann says:

====================
pull-request: bpf-next 2017-12-18

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

The main changes are:

1) Allow arbitrary function calls from one BPF function to another BPF function.
   As of today when writing BPF programs, __always_inline had to be used in
   the BPF C programs for all functions, unnecessarily causing LLVM to inflate
   code size. Handle this more naturally with support for BPF to BPF calls
   such that this __always_inline restriction can be overcome. As a result,
   it allows for better optimized code and finally enables to introduce core
   BPF libraries in the future that can be reused out of different projects.
   x86 and arm64 JIT support was added as well, from Alexei.

2) Add infrastructure for tagging functions as error injectable and allow for
   BPF to return arbitrary error values when BPF is attached via kprobes on
   those. This way of injecting errors generically eases testing and debugging
   without having to recompile or restart the kernel. Tags for opting-in for
   this facility are added with BPF_ALLOW_ERROR_INJECTION(), from Josef.

3) For BPF offload via nfp JIT, add support for bpf_xdp_adjust_head() helper
   call for XDP programs. First part of this work adds handling of BPF
   capabilities included in the firmware, and the later patches add support
   to the nfp verifier part and JIT as well as some small optimizations,
   from Jakub.

4) The bpftool now also gets support for basic cgroup BPF operations such
   as attaching, detaching and listing current BPF programs. As a requirement
   for the attach part, bpftool can now also load object files through
   'bpftool prog load'. This reuses libbpf which we have in the kernel tree
   as well. bpftool-cgroup man page is added along with it, from Roman.

5) Back then commit e87c6bc3852b ("bpf: permit multiple bpf attachments for
   a single perf event") added support for attaching multiple BPF programs
   to a single perf event. Given they are configured through perf's ioctl()
   interface, the interface has been extended with a PERF_EVENT_IOC_QUERY_BPF
   command in this work in order to return an array of one or multiple BPF
   prog ids that are currently attached, from Yonghong.

6) Various minor fixes and cleanups to the bpftool's Makefile as well
   as a new 'uninstall' and 'doc-uninstall' target for removing bpftool
   itself or prior installed documentation related to it, from Quentin.

7) Add CONFIG_CGROUP_BPF=y to the BPF kernel selftest config file which is
   required for the test_dev_cgroup test case to run, from Naresh.

8) Fix reporting of XDP prog_flags for nfp driver, from Jakub.

9) Fix libbpf's exit code from the Makefile when libelf was not found in
   the system, also from Jakub.
====================

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

12 files changed, 142 insertions, 14 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..d3f4aaf9cb7a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,6 +196,9 @@ config HAVE_OPTPROBES
 config HAVE_KPROBES_ON_FTRACE
 	bool
 
+config HAVE_KPROBE_OVERRIDE
+	bool
+
 config HAVE_NMI
 	bool
 
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c199990e12b6..4425189bb24c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1824,7 +1824,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* If BPF JIT was not enabled then we must fall back to
 	 * the interpreter.
 	 */
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	/* If constant blinding was enabled and we failed during blinding
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ba38d403abb2..396490cf7316 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -99,6 +99,20 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 	}
 }
 
+static inline void emit_addr_mov_i64(const int reg, const u64 val,
+				     struct jit_ctx *ctx)
+{
+	u64 tmp = val;
+	int shift = 0;
+
+	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
+	for (;shift < 48;) {
+		tmp >>= 16;
+		shift += 16;
+		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
+	}
+}
+
 static inline void emit_a64_mov_i(const int is64, const int reg,
 				  const s32 val, struct jit_ctx *ctx)
 {
@@ -603,7 +617,10 @@ emit_cond_jmp:
 		const u8 r0 = bpf2a64[BPF_REG_0];
 		const u64 func = (u64)__bpf_call_base + imm;
 
-		emit_a64_mov_i64(tmp, func, ctx);
+		if (ctx->prog->is_func)
+			emit_addr_mov_i64(tmp, func, ctx);
+		else
+			emit_a64_mov_i64(tmp, func, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -835,16 +852,24 @@ static inline void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+struct arm64_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
+	struct arm64_jit_data *jit_data;
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	struct jit_ctx ctx;
 	int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -858,13 +883,29 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		goto skip_init_ctx;
+	}
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
 	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
-		goto out;
+		goto out_off;
 	}
 
 	/* 1. Initial fake pass to compute ctx->idx. */
@@ -895,6 +936,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+skip_init_ctx:
 	ctx.idx = 0;
 
 	build_prologue(&ctx);
@@ -920,13 +962,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
-	bpf_jit_binary_lock_ro(header);
+	if (!prog->is_func || extra_pass) {
+		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
+			pr_err_once("multi-func JIT bug %d != %d\n",
+				    ctx.idx, jit_data->ctx.idx);
+			bpf_jit_binary_free(header);
+			prog->bpf_func = NULL;
+			prog->jited = 0;
+			goto out_off;
+		}
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
 	prog->jited_len = image_size;
 
+	if (!prog->is_func || extra_pass) {
 out_off:
-	kfree(ctx.offset);
+		kfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 962b0259b4b6..97069a1b6f43 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1869,7 +1869,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable || !cpu_has_mips64r2)
+	if (!prog->jit_requested || !cpu_has_mips64r2)
 		return prog;
 
 	tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 46d74e81aff1..d5a5bc43cf8f 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -993,7 +993,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return org_fp;
 
 	tmp_fp = bpf_jit_blind_constants(org_fp);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e81c16838b90..f4baa8c514d3 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1300,7 +1300,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_jit jit;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return orig_fp;
 
 	tmp = bpf_jit_blind_constants(fp);
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 5765e7e711f7..a2f1b5e774a7 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1517,7 +1517,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	u8 *image_ptr;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8eed3f94bfc7..04d66e6fa447 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -154,6 +154,7 @@ config X86
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_KPROBE_OVERRIDE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 9f2e3102e0bb..36abb23a7a35 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -67,6 +67,10 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs);
+#endif
+
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14131dd06b29..6de1fd3d0097 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ax = rc;
+}
+
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..1ea748d682fd 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -97,3 +97,17 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p)
 	p->ainsn.boostable = false;
 	return 0;
 }
+
+asmlinkage void override_func(void);
+asm(
+	".type override_func, @function\n"
+	"override_func:\n"
+	"	ret\n"
+	".size override_func, .-override_func\n"
+);
+
+void arch_ftrace_kprobe_override_function(struct pt_regs *regs)
+{
+	regs->ip = (unsigned long)&override_func;
+}
+NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 0554e8aef4d5..87f214fbe66e 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1109,19 +1109,29 @@ common_load:
 	return proglen;
 }
 
+struct x64_jit_data {
+	struct bpf_binary_header *header;
+	int *addrs;
+	u8 *image;
+	int proglen;
+	struct jit_context ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct x64_jit_data *jit_data;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
 	int i;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1135,10 +1145,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	addrs = jit_data->addrs;
+	if (addrs) {
+		ctx = jit_data->ctx;
+		oldproglen = jit_data->proglen;
+		image = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		goto skip_init_addrs;
+	}
 	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
-		goto out;
+		goto out_addrs;
 	}
 
 	/* Before first pass, make a rough estimation of addrs[]
@@ -1149,6 +1177,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		addrs[i] = proglen;
 	}
 	ctx.cleanup_addr = proglen;
+skip_init_addrs:
 
 	/* JITed image shrinks with every pass and the loop iterates
 	 * until the image stops shrinking. Very large bpf programs
@@ -1189,7 +1218,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
-		bpf_jit_binary_lock_ro(header);
+		if (!prog->is_func || extra_pass) {
+			bpf_jit_binary_lock_ro(header);
+		} else {
+			jit_data->addrs = addrs;
+			jit_data->ctx = ctx;
+			jit_data->proglen = proglen;
+			jit_data->image = image;
+			jit_data->header = header;
+		}
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;
@@ -1197,8 +1234,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = orig_prog;
 	}
 
+	if (!prog->is_func || extra_pass) {
 out_addrs:
-	kfree(addrs);
+		kfree(addrs);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?