Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 270 insertions, 22 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index f4b6b3b9ed..fdbf88ca8b 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -81,6 +81,8 @@ struct rv_jit_context {
 	int nexentries;
 	unsigned long flags;
 	int stack_size;
+	u64 arena_vm_start;
+	u64 user_vm_start;
 };
 
 /* Convert from ninsns to bytes. */
@@ -606,7 +608,7 @@ static inline u32 rv_nop(void)
 	return rv_i_insn(0, 0, 0, 0, 0x13);
 }
 
-/* RVC instrutions. */
+/* RVC instructions. */
 
 static inline u16 rvc_addi4spn(u8 rd, u32 imm10)
 {
@@ -735,7 +737,7 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
-/* RVZBB instrutions. */
+/* RVZBB instructions. */
 static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
 {
 	return rv_i_insn(0x604, rs1, 1, rd, 0x13);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index fb5d195004..212b015e09 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -12,12 +12,16 @@
 #include <linux/stop_machine.h>
 #include <asm/patch.h>
 #include <asm/cfi.h>
+#include <asm/percpu.h>
 #include "bpf_jit.h"
 
 #define RV_FENTRY_NINSNS 2
+/* imm that allows emit_imm to emit max count insns */
+#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF
 
 #define RV_REG_TCC RV_REG_A6
 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
+#define RV_REG_ARENA RV_REG_S7 /* For storing arena_vm_start */
 
 static const int regmap[] = {
 	[BPF_REG_0] =	RV_REG_A5,
@@ -255,6 +259,10 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
 		emit_ld(RV_REG_S6, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
+	if (ctx->arena_vm_start) {
+		emit_ld(RV_REG_ARENA, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
 
 	emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx);
 	/* Set return value. */
@@ -548,6 +556,7 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 
 #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
 #define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
+#define REG_DONT_CLEAR_MARKER	0	/* RV_REG_ZERO unused in pt_regmap */
 
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs)
@@ -555,7 +564,8 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
 	int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
 
-	*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
+	if (regs_offset != REG_DONT_CLEAR_MARKER)
+		*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
 	regs->epc = (unsigned long)&ex->fixup - offset;
 
 	return true;
@@ -572,7 +582,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	off_t fixup_offset;
 
 	if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable ||
-	    (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX))
+	    (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
+	     BPF_MODE(insn->code) != BPF_PROBE_MEM32))
 		return 0;
 
 	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
@@ -906,7 +917,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 		orig_call += RV_FENTRY_NINSNS * 4;
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		emit_imm(RV_REG_A0, (const s64)im, ctx);
+		emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx);
 		ret = emit_call((const u64)__bpf_tramp_enter, true, ctx);
 		if (ret)
 			return ret;
@@ -967,7 +978,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		im->ip_epilogue = ctx->insns + ctx->ninsns;
-		emit_imm(RV_REG_A0, (const s64)im, ctx);
+		emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx);
 		ret = emit_call((const u64)__bpf_tramp_exit, true, ctx);
 		if (ret)
 			goto out;
@@ -1036,6 +1047,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 {
 	int ret;
 	struct rv_jit_context ctx;
+	u32 size = image_end - image;
 
 	ctx.ninsns = 0;
 	/*
@@ -1049,11 +1061,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	ctx.ro_insns = image;
 	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns);
+	if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) {
+		ret = -E2BIG;
+		goto out;
+	}
 
-	return ninsns_rvoff(ret);
+	bpf_flush_icache(image, image_end);
+out:
+	return ret < 0 ? ret : size;
 }
 
 int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
@@ -1073,6 +1090,33 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (insn_is_cast_user(insn)) {
+			emit_mv(RV_REG_T1, rs, ctx);
+			emit_zextw(RV_REG_T1, RV_REG_T1, ctx);
+			emit_imm(rd, (ctx->user_vm_start >> 32) << 32, ctx);
+			emit(rv_beq(RV_REG_T1, RV_REG_ZERO, 4), ctx);
+			emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
+			emit_mv(rd, RV_REG_T1, ctx);
+			break;
+		} else if (insn_is_mov_percpu_addr(insn)) {
+			if (rd != rs)
+				emit_mv(rd, rs, ctx);
+#ifdef CONFIG_SMP
+			/* Load current CPU number in T1 */
+			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
+				RV_REG_TP, ctx);
+			/* << 3 because offsets are 8 bytes */
+			emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
+			/* Load address of __per_cpu_offset array in T2 */
+			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
+			/* Add offset of current CPU to  __per_cpu_offset */
+			emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+			/* Load __per_cpu_offset[cpu] in T1 */
+			emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
+			/* Add the offset to Rd */
+			emit_add(rd, rd, RV_REG_T1, ctx);
+#endif
+		}
 		if (imm == 1) {
 			/* Special mov32 for zext */
 			emit_zextw(rd, rd, ctx);
@@ -1457,6 +1501,22 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		bool fixed_addr;
 		u64 addr;
 
+		/* Inline calls to bpf_get_smp_processor_id()
+		 *
+		 * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is
+		 * at offset 0 in task_struct.
+		 * Load cpu from thread_info:
+		 *     Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu
+		 *
+		 * This replicates the implementation of raw_smp_processor_id() on RISCV
+		 */
+		if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+			/* Load current CPU number in R0 */
+			emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
+				RV_REG_TP, ctx);
+			break;
+		}
+
 		mark_call(ctx);
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &addr, &fixed_addr);
@@ -1539,6 +1599,11 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
+	/* LDX | PROBE_MEM32: dst = *(unsigned size *)(src + RV_REG_ARENA + off) */
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
 	{
 		int insn_len, insns_start;
 		bool sign_ext;
@@ -1546,6 +1611,11 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
 			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
 
+		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+			emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx);
+			rs = RV_REG_T2;
+		}
+
 		switch (BPF_SIZE(code)) {
 		case BPF_B:
 			if (is_12b_int(off)) {
@@ -1682,6 +1752,86 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
 		break;
 
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+	{
+		int insn_len, insns_start;
+
+		emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx);
+		rd = RV_REG_T3;
+
+		/* Load imm to a register then store it */
+		emit_imm(RV_REG_T1, imm, ctx);
+
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_sb(rd, off, RV_REG_T1), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T2, off, ctx);
+			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_H:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_sh(rd, off, RV_REG_T1), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T2, off, ctx);
+			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_W:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_sw(rd, off, RV_REG_T1, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T2, off, ctx);
+			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_DW:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_sd(rd, off, RV_REG_T1, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T2, off, ctx);
+			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		}
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
+					    insn_len);
+		if (ret)
+			return ret;
+
+		break;
+	}
+
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_B:
 		if (is_12b_int(off)) {
@@ -1728,6 +1878,84 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_atomic(rd, rs, off, imm,
 			    BPF_SIZE(code) == BPF_DW, ctx);
 		break;
+
+	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
+	case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
+	{
+		int insn_len, insns_start;
+
+		emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx);
+		rd = RV_REG_T2;
+
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_sb(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_H:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_sh(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_W:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_sw(rd, off, rs, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit_sw(RV_REG_T1, 0, rs, ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		case BPF_DW:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_sd(rd, off, rs, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+			insns_start = ctx->ninsns;
+			emit_sd(RV_REG_T1, 0, rs, ctx);
+			insn_len = ctx->ninsns - insns_start;
+			break;
+		}
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
+					    insn_len);
+		if (ret)
+			return ret;
+
+		break;
+	}
+
 	default:
 		pr_err("bpf-jit: unknown opcode %02x\n", code);
 		return -EINVAL;
@@ -1759,6 +1987,8 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		stack_adjust += 8;
 	if (seen_reg(RV_REG_S6, ctx))
 		stack_adjust += 8;
+	if (ctx->arena_vm_start)
+		stack_adjust += 8;
 
 	stack_adjust = round_up(stack_adjust, 16);
 	stack_adjust += bpf_stack_adjust;
@@ -1810,6 +2040,10 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		emit_sd(RV_REG_SP, store_offset, RV_REG_S6, ctx);
 		store_offset -= 8;
 	}
+	if (ctx->arena_vm_start) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_ARENA, ctx);
+		store_offset -= 8;
+	}
 
 	emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx);
 
@@ -1823,6 +2057,9 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		emit_mv(RV_REG_TCC_SAVED, RV_REG_TCC, ctx);
 
 	ctx->stack_size = stack_adjust;
+
+	if (ctx->arena_vm_start)
+		emit_imm(RV_REG_ARENA, ctx->arena_vm_start, ctx);
 }
 
 void bpf_jit_build_epilogue(struct rv_jit_context *ctx)
@@ -1839,3 +2076,23 @@ bool bpf_jit_supports_ptr_xchg(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_arena(void)
+{
+	return true;
+}
+
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return true;
+}
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+	switch (imm) {
+	case BPF_FUNC_get_smp_processor_id:
+		return true;
+	default:
+		return false;
+	}
+}
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 6b3acac30c..0a96abdaca 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -80,6 +80,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto skip_init_ctx;
 	}
 
+	ctx->arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena);
+	ctx->user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
 	ctx->prog = prog;
 	ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (!ctx->offset) {
@@ -219,19 +221,6 @@ u64 bpf_jit_alloc_exec_limit(void)
 	return BPF_JIT_REGION_SIZE;
 }
 
-void *bpf_jit_alloc_exec(unsigned long size)
-{
-	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
-				    BPF_JIT_REGION_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
-				    __builtin_return_address(0));
-}
-
-void bpf_jit_free_exec(void *addr)
-{
-	return vfree(addr);
-}
-
 void *bpf_arch_text_copy(void *dst, void *src, size_t len)
 {
 	int ret;