Merge branch 'bpf-riscv-jit'

Björn Töpel says:

====================
This v2 series adds an RV64G BPF JIT to the kernel.

At the moment the RISC-V Linux port does not support
CONFIG_HAVE_KPROBES (Patrick Stählin sent out an RFC last year), which
means that CONFIG_BPF_EVENTS is not supported. Thus, no tests
involving BPF_PROG_TYPE_TRACEPOINT, BPF_PROG_TYPE_PERF_EVENT,
BPF_PROG_TYPE_KPROBE and BPF_PROG_TYPE_RAW_TRACEPOINT passes.

The implementation does not support "far branching" (>4KiB).

Test results:
  # modprobe test_bpf
  test_bpf: Summary: 378 PASSED, 0 FAILED, [366/366 JIT'ed]

  # echo 1 > /proc/sys/kernel/unprivileged_bpf_disabled
  # ./test_verifier
  ...
  Summary: 761 PASSED, 507 SKIPPED, 2 FAILED

Note that "test_verifier" was run with one build with
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y and one without, otherwise
many of the the tests that require unaligned access were skipped.

CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y:
  # echo 1 > /proc/sys/kernel/unprivileged_bpf_disabled
  # ./test_verifier | grep -c 'NOTE.*unknown align'
  0

No CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS:
  # echo 1 > /proc/sys/kernel/unprivileged_bpf_disabled
  # ./test_verifier | grep -c 'NOTE.*unknown align'
  59

The two failing test_verifier tests are:
  "ld_abs: vlan + abs, test 1"
  "ld_abs: jump around ld_abs"

This is due to that "far branching" involved in those tests.
All tests where done on QEMU emulator version 3.1.50
(v3.1.0-688-g8ae951fbc106). I'll test it on real hardware, when I get
access to it.

I'm routing this patch via bpf-next/netdev mailing list (after a
conversation with Palmer at FOSDEM), mainly because the other JITs
went that path.

Again, thanks for all the comments!

Cheers,
Björn

v1 -> v2:
* Added JMP32 support. (Daniel)
* Add RISC-V to Documentation/sysctl/net.txt. (Daniel)
* Fixed seen_call() asymmetry. (Daniel)
* Fixed broken bpf_flush_icache() range. (Daniel)
* Added alignment annotations to some selftests.

RFCv1 -> v1:
* Cleaned up the Kconfig and net/Makefile. (Christoph)
* Removed the entry-stub and squashed the build/config changes to be
  part of the JIT implementation. (Christoph)
* Simplified the register tracking code. (Daniel)
* Removed unused macros. (Daniel)
* Added myself as maintainer and updated documentation. (Daniel)
* Removed HAVE_EFFICIENT_UNALIGNED_ACCESS. (Christoph, Palmer)
* Added tail-calls and cleaned up the code.
====================

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Documentation/networking/filter.txt

@@ -464,10 +464,11 @@ breakpoints: 0 1
 JIT compiler
 ------------
 
-The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC,
+The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC,
-ARM, ARM64, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT
+PowerPC, ARM, ARM64, MIPS, RISC-V and s390 and can be enabled through
-compiler is transparently invoked for each attached filter from user space
+CONFIG_BPF_JIT. The JIT compiler is transparently invoked for each
-or for internal kernel users if it has been previously enabled by root:
+attached filter from user space or for internal kernel users if it has
+been previously enabled by root:
 
   echo 1 > /proc/sys/net/core/bpf_jit_enable
 
@@ -603,9 +604,10 @@ got from bpf_prog_create(), and 'ctx' the given context (e.g.
 skb pointer). All constraints and restrictions from bpf_check_classic() apply
 before a conversion to the new layout is being done behind the scenes!
 
-Currently, the classic BPF format is being used for JITing on most 32-bit
+Currently, the classic BPF format is being used for JITing on most
-architectures, whereas x86-64, aarch64, s390x, powerpc64, sparc64, arm32 perform
+32-bit architectures, whereas x86-64, aarch64, s390x, powerpc64,
-JIT compilation from eBPF instruction set.
+sparc64, arm32, riscv (RV64G) perform JIT compilation from eBPF
+instruction set.
 
 Some core changes of the new internal format:
 

Documentation/sysctl/net.txt

@@ -52,6 +52,7 @@ two flavors of JITs, the newer eBPF JIT currently supported on:
   - sparc64
   - mips64
   - s390x
+  - riscv
 
 And the older cBPF JIT supported on the following archs:
   - mips

MAINTAINERS

@@ -2907,6 +2907,12 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	arch/powerpc/net/
 
+BPF JIT for RISC-V (RV64G)
+M:	Björn Töpel <bjorn.topel@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/riscv/net/
+
 BPF JIT for S390
 M:	Martin Schwidefsky <schwidefsky@de.ibm.com>
 M:	Heiko Carstens <heiko.carstens@de.ibm.com>

arch/riscv/Kconfig

@@ -49,6 +49,7 @@ config RISCV
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
 	select ARCH_HAS_PTE_SPECIAL
+	select HAVE_EBPF_JIT if 64BIT
 
 config MMU
 	def_bool y

arch/riscv/Makefile

@@ -77,7 +77,7 @@ KBUILD_IMAGE	:= $(boot)/Image.gz
 
 head-y := arch/riscv/kernel/head.o
 
-core-y += arch/riscv/kernel/ arch/riscv/mm/
+core-y += arch/riscv/kernel/ arch/riscv/mm/ arch/riscv/net/
 
 libs-y += arch/riscv/lib/
 

arch/riscv/net/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o

tools/testing/selftests/bpf/verifier/ctx_sk_msg.c

@@ -100,6 +100,7 @@
 	.errstr = "invalid bpf_context access",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_MSG,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid read past end of SK_MSG",

tools/testing/selftests/bpf/verifier/ctx_skb.c

@@ -687,6 +687,7 @@
 	},
 	.errstr = "invalid bpf_context access",
 	.result = REJECT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"check skb->hash half load not permitted, unaligned 3",

tools/testing/selftests/bpf/verifier/jmp32.c

@@ -27,6 +27,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset32: BPF_X",
@@ -58,6 +59,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset32: min/max deduction",
@@ -93,6 +95,7 @@
 		  .data64 = { -1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jeq32: BPF_X",
@@ -119,6 +122,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jeq32: min/max deduction",
@@ -154,6 +158,7 @@
 		  .data64 = { -1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jne32: BPF_X",
@@ -180,6 +185,7 @@
 		  .data64 = { 1ULL << 63 | 2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jne32: min/max deduction",
@@ -218,6 +224,7 @@
 		  .data64 = { 0, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jge32: BPF_X",
@@ -244,6 +251,7 @@
 		  .data64 = { (UINT_MAX - 1) | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jge32: min/max deduction",
@@ -284,6 +292,7 @@
 		  .data64 = { 0, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: BPF_X",
@@ -310,6 +319,7 @@
 		  .data64 = { (UINT_MAX - 1) | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: min/max deduction",
@@ -350,6 +360,7 @@
 		  .data64 = { INT_MAX, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: BPF_X",
@@ -376,6 +387,7 @@
 		  .data64 = { UINT_MAX, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: min/max deduction",
@@ -416,6 +428,7 @@
 		  .data64 = { INT_MAX - 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: BPF_X",
@@ -442,6 +455,7 @@
 		  .data64 = { (INT_MAX - 1) | 3ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: min/max deduction",
@@ -482,6 +496,7 @@
 		  .data64 = { -2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: BPF_X",
@@ -508,6 +523,7 @@
 		  .data64 = { -2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: min/max deduction",
@@ -548,6 +564,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: BPF_X",
@@ -574,6 +591,7 @@
 		  .data64 = { 0x7fffffff, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: min/max deduction",
@@ -614,6 +632,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: BPF_X",
@@ -640,6 +659,7 @@
 		  .data64 = { 0x7fffffff | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: min/max deduction",
@@ -680,6 +700,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: BPF_X",
@@ -706,6 +727,7 @@
 		  .data64 = { 0x7fffffff | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: min/max deduction",

tools/testing/selftests/bpf/verifier/jset.c

@@ -53,6 +53,7 @@
 		  .data64 = { ~0ULL, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset: sign-extend",
@@ -70,6 +71,7 @@
 	.result = ACCEPT,
 	.retval = 2,
 	.data = { 1, 0, 0, 0, 0, 0, 0, 1, },
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset: known const compare",

tools/testing/selftests/bpf/verifier/spill_fill.c

@@ -46,6 +46,7 @@
 	.errstr_unpriv = "attempt to corrupt spilled",
 	.errstr = "R0 invalid mem access 'inv",
 	.result = REJECT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"check corrupted spill/fill, LSB",

tools/testing/selftests/bpf/verifier/spin_lock.c

@@ -83,6 +83,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "",
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"spin_lock: test4 direct ld/st",
@@ -112,6 +113,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "",
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"spin_lock: test5 call within a locked region",

tools/testing/selftests/bpf/verifier/value_ptr_arith.c

@@ -512,6 +512,7 @@
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: unknown scalar += value_ptr, 3",
@@ -537,6 +538,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: unknown scalar += value_ptr, 4",
@@ -559,6 +561,7 @@
 	.result = REJECT,
 	.errstr = "R1 max value is outside of the array range",
 	.errstr_unpriv = "R1 pointer arithmetic of map value goes out of range",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: value_ptr += unknown scalar, 1",
@@ -598,6 +601,7 @@
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: value_ptr += unknown scalar, 3",