Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:

 - Allow CPUs affected by erratum 1418040 to come online late
   (previously we only fixed the other case - CPUs not affected by the
   erratum coming up late).

 - Fix branch offset in BPF JIT.

 - Defer the stolen time initialisation to the CPU online time from the
   CPU starting time to avoid a (sleep-able) memory allocation in an
   atomic context.

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: paravirt: Initialize steal time when cpu is online
  arm64: bpf: Fix branch offset in JIT
  arm64: Allow CPUs unffected by ARM erratum 1418040 to come in late

3 files changed, 52 insertions, 25 deletions

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c332d49780dc..560ba69e13c1 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -910,8 +910,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
-		.type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU |
-			 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU),
+		/*
+		 * We need to allow affected CPUs to come in late, but
+		 * also need the non-affected CPUs to be able to come
+		 * in at any point in time. Wonderful.
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 295d66490584..c07d7a034941 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu)
 	struct pv_time_stolen_time_region *reg;
 
 	reg = per_cpu_ptr(&stolen_time_region, cpu);
-	if (!reg->kaddr) {
-		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
-			     cpu);
+
+	/*
+	 * paravirt_steal_clock() may be called before the CPU
+	 * online notification callback runs. Until the callback
+	 * has run we just return zero.
+	 */
+	if (!reg->kaddr)
 		return 0;
-	}
 
 	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
 }
 
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 	struct arm_smccc_res res;
@@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
-				"hypervisor/arm/pvtime:starting",
-				init_stolen_time_cpu, stolen_time_dying_cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"hypervisor/arm/pvtime:online",
+				stolen_time_cpu_online,
+				stolen_time_cpu_down_prepare);
 	if (ret < 0)
 		return ret;
 	return 0;
 }
 
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f8912e45be7a..ef9f1d5e989d 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -143,14 +143,17 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	}
 }
 
-static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+static inline int bpf2a64_offset(int bpf_insn, int off,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to];
-	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from] - 1;
-
-	return to - from;
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas arm64 branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
 }
 
 static void jit_fill_hole(void *area, unsigned int size)
@@ -642,7 +645,7 @@ emit_bswap_uxt:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm26(jmp_offset);
 		emit(A64_B(jmp_offset), ctx);
 		break;
@@ -669,7 +672,7 @@ emit_bswap_uxt:
 	case BPF_JMP32 | BPF_JSLE | BPF_X:
 		emit(A64_CMP(is64, dst, src), ctx);
 emit_cond_jmp:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm19(jmp_offset);
 		switch (BPF_OP(code)) {
 		case BPF_JEQ:
@@ -908,10 +911,21 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
 
+	/*
+	 * - offset[0] offset of the end of prologue,
+	 *   start of the 1st instruction.
+	 * - offset[1] - offset of the end of 1st instruction,
+	 *   start of the 2nd instruction
+	 * [....]
+	 * - offset[3] - offset of the end of 3rd instruction,
+	 *   start of 4th instruction
+	 */
 	for (i = 0; i < prog->len; i++) {
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
@@ -919,11 +933,16 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 				ctx->offset[i] = ctx->idx;
 			continue;
 		}
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
+	/*
+	 * offset is allocated with prog->len + 1 so fill in
+	 * the last element with the offset after the last
+	 * instruction (end of program)
+	 */
+	if (ctx->image == NULL)
+		ctx->offset[i] = ctx->idx;
 
 	return 0;
 }
@@ -1002,7 +1021,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
@@ -1089,7 +1108,7 @@ skip_init_ctx:
 	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
-		bpf_prog_fill_jited_linfo(prog, ctx.offset);
+		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);