Merge branch 'signed-loads-from-arena'

Puranjay Mohan says:

====================
Signed loads from Arena

Changelog:

v3 -> v4:
v3: https://lore.kernel.org/all/20250915162848.54282-1-puranjay@kernel.org/
- Update bpf_jit_supports_insn() in riscv jit to reject signed arena loads (Eduard)
- Fix coding style related to braces usage in an if statement in x86 jit (Eduard)

v2 -> v3:
v2: https://lore.kernel.org/bpf/20250514175415.2045783-1-memxor@gmail.com/
- Fix encoding for the generated instructions in x86 JIT (Eduard)
  The patch in v2 was generating instructions like:
        42 63 44 20 f8     movslq -0x8(%rax,%r12), %eax
  This doesn't make sense because movslq outputs a 64-bit result, but
  the destination register here is set to eax (32-bit). The fix it to
  set the REX.W bit in the opcode, that means changing
  EMIT2(add_3mod(0x40, ...)) to EMIT2(add_3mod(0x48, ...))
- Add arm64 support
- Add selftests signed laods from arena.

v1 -> v2:
v1: https://lore.kernel.org/bpf/20250509194956.1635207-1-memxor@gmail.com
- Use bpf_jit_supports_insn. (Alexei)

Currently, signed load instructions into arena memory are unsupported.
The compiler is free to generate these, and on GCC-14 we see a
corresponding error when it happens. The hurdle in supporting them is
deciding which unused opcode to use to mark them for the JIT's own
consumption. After much thinking, it appears 0xc0 / BPF_NOSPEC can be
combined with load instructions to identify signed arena loads. Use
this to recognize and JIT them appropriately, and remove the verifier
side limitation on the program if the JIT supports them.
====================

Link: https://patch.msgid.link/20250923110157.18326-1-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 176 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index f087ffb79f20..c8494b682c31 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include "bpf_arena_common.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
@@ -10,6 +11,12 @@
 	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1);
+} arena SEC(".maps");
+
 SEC("socket")
 __description("LDSX, S8")
 __success __success_unpriv __retval(-2)
@@ -256,6 +263,175 @@ __naked void ldsx_ctx_8(void)
 	: __clobber_all);
 }
 
+SEC("syscall")
+__description("Arena LDSX Disasm")
+__success
+__arch_x86_64
+__jited("movslq	0x10(%rax,%r12), %r14")
+__jited("movswq	0x18(%rax,%r12), %r14")
+__jited("movsbq	0x20(%rax,%r12), %r14")
+__jited("movslq	0x10(%rdi,%r12), %r15")
+__jited("movswq	0x18(%rdi,%r12), %r15")
+__jited("movsbq	0x20(%rdi,%r12), %r15")
+__arch_arm64
+__jited("add	x11, x7, x28")
+__jited("ldrsw	x21, [x11, #0x10]")
+__jited("add	x11, x7, x28")
+__jited("ldrsh	x21, [x11, #0x18]")
+__jited("add	x11, x7, x28")
+__jited("ldrsb	x21, [x11, #0x20]")
+__jited("add	x11, x0, x28")
+__jited("ldrsw	x22, [x11, #0x10]")
+__jited("add	x11, x0, x28")
+__jited("ldrsh	x22, [x11, #0x18]")
+__jited("add	x11, x0, x28")
+__jited("ldrsb	x22, [x11, #0x20]")
+__naked void arena_ldsx_disasm(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = r0;"
+	"r8 = *(s32 *)(r0 + 16);"
+	"r8 = *(s16 *)(r0 + 24);"
+	"r8 = *(s8  *)(r0 + 32);"
+	"r9 = *(s32 *)(r1 + 16);"
+	"r9 = *(s16 *)(r1 + 24);"
+	"r9 = *(s8  *)(r1 + 32);"
+	"r0 = 0;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX Exception")
+__success __retval(0)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_exception(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r0 = 0xdeadbeef;"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fe;"
+	"*(u64 *)(r0 + 0) = r1;"
+	"r0 = *(s8 *)(r0 + 0);"
+	"exit;"
+	:
+	:  __imm_addr(arena)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S8")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s8(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s8 *)(r0 + 0);"
+#else
+	"r0 = *(s8 *)(r0 + 7);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S16")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s16(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fffe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s16 *)(r0 + 0);"
+#else
+	"r0 = *(s16 *)(r0 + 6);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S32")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s32(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0xfffffffe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s32 *)(r0 + 0);"
+#else
+	"r0 = *(s32 *)(r0 + 4);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+	bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
 #else
 
 SEC("socket")