Various arm64 fixes:

- suspicious RCU usage warning
 - BPF (out of bounds array read and endianness conversion)
 - perf (of_node usage after of_node_put, cpu_pmu->plat_device
   assignment)
 - huge pmd/pud check for value 0
 - rate-limiting should only take unhandled signals into account
 
 Clean-up:
 
 - incorrect use of pgprot_t type
 - unused header include
 - __init annotation to arm_cpuidle_init
 - pr_debug instead of pr_error for disabled GICC entries in ACPI/MADT
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJVlrS4AAoJEGvWsS0AyF7x/TUQAK1o3/jlyAOY2eFRZPR9CJrU
 xBB3bFs1TcYGyl5TvSssyAHS9RgpsagS+ZHbSaWTR9zjrtkJ5/kAFS0JY3Y3/oOy
 4cPACISX8ps+YcekCIF0PLsznmvKstpXasvfEVr+QlspzF0utxZa/koP2ofzK+J4
 IuTIMvXjym4x8GnV4FzkyFSOtJLEmtFpeW8GbzbrhjrIiCYP7Hx5zsn2PNfpdsQj
 2UqE0JdMsCS42fmjzmX+MTTiQBIzfDXR9BSxUtbarR/wLEZbcN8cfQGIm/mrj69Y
 1S6TuQVCskUC+8Ue2jKPJEb18igUZcbNulBPEEyMt1dNQxHrvicdgK/bthwmGlxb
 sp5W82BT1ws3E4IHFB1tY89mp4j7GpvWf19su6xLmcbgYAh+/bQZHB0OR6iBnPHI
 Zyp3BotBAk7zvf7hpdV2l9a3RkNR0tjI6eD7L1I7trxvPqq46DedxqpnBwXzElI8
 xfTm8G4EaOBK65LnvPXnWDRawKhOcfEEAFEzJYZoO5g0gw4fA4+dRMsXBF/ENPde
 FTv9afGMDy1uK7s449x+F4XwcZiiCaXBjtxAbXKNbfqPmMgv3v05/oE66LyTyYYM
 lcEdQLMJ62zrKASPfKS3Iw5BChLoFFDKnnZRryGuYt5h5fGyMBlGYoe3y9K8zTV6
 iGYFzZ6cQfv/7HvYIZqB
 =R+XU
 -----END PGP SIGNATURE-----

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

Pull arm64 fixes (and cleanups) from Catalin Marinas:
 "Various arm64 fixes:

   - suspicious RCU usage warning
   - BPF (out of bounds array read and endianness conversion)
   - perf (of_node usage after of_node_put, cpu_pmu->plat_device
     assignment)
   - huge pmd/pud check for value 0
   - rate-limiting should only take unhandled signals into account

  Clean-up:

   - incorrect use of pgprot_t type
   - unused header include
   - __init annotation to arm_cpuidle_init
   - pr_debug instead of pr_error for disabled GICC entries in
     ACPI/MADT"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Fix show_unhandled_signal_ratelimited usage
  ARM64 / SMP: Switch pr_err() to pr_debug() for disabled GICC entry
  arm64: cpuidle: add __init section marker to arm_cpuidle_init
  arm64: Don't report clear pmds and puds as huge
  arm64: perf: fix unassigned cpu_pmu->plat_device when probing PMU PPIs
  arm64: perf: Don't use of_node after putting it
  arm64: fix incorrect use of pgprot_t variable
  arm64/hw_breakpoint.c: remove unnecessary header
  arm64: bpf: fix endianness conversion bugs
  arm64: bpf: fix out-of-bounds read in bpf2a64_offset()
  ARM64: smp: Fix suspicious RCU usage with ipi tracepoints

arch/arm64/kernel/cpuidle.c

@@ -15,7 +15,7 @@
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
 
-int arm_cpuidle_init(unsigned int cpu)
+int __init arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
 

arch/arm64/kernel/hw_breakpoint.c

@@ -31,7 +31,6 @@
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
-#include <asm/kdebug.h>
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>

arch/arm64/kernel/perf_event.c

@@ -1318,7 +1318,7 @@ static int armpmu_device_probe(struct platform_device *pdev)
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0 && irq_is_percpu(irq))
-		return 0;
+		goto out;
 
 	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
@@ -1340,12 +1340,13 @@ static int armpmu_device_probe(struct platform_device *pdev)
 			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
 				break;
 
-		of_node_put(dn);
 		if (cpu >= nr_cpu_ids) {
 			pr_warn("Failed to find logical CPU for %s\n",
 				dn->name);
+			of_node_put(dn);
 			break;
 		}
+		of_node_put(dn);
 
 		irqs[i] = cpu;
 	}
@@ -1355,6 +1356,7 @@ static int armpmu_device_probe(struct platform_device *pdev)
 	else
 		kfree(irqs);
 
+out:
 	cpu_pmu->plat_device = pdev;
 	return 0;
 }

arch/arm64/kernel/smp.c

@@ -396,13 +396,13 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 {
 	u64 hwid = processor->arm_mpidr;
 
-	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
-		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
+	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+		pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
 		return;
 	}
 
-	if (!(processor->flags & ACPI_MADT_ENABLED)) {
-		pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
+	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
+		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
 		return;
 	}
 
@@ -693,7 +693,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
@@ -736,7 +736,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 

arch/arm64/kernel/traps.c

@@ -335,7 +335,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (call_undef_hook(regs) == 0)
 		return;
 
-	if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) {
+	if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
 		dump_instr(KERN_INFO, regs);

arch/arm64/mm/fault.c

@@ -115,7 +115,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 {
 	struct siginfo si;
 
-	if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) {
+	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
 			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
 			addr, esr);

arch/arm64/mm/hugetlbpage.c

@@ -33,13 +33,13 @@
 
 int pmd_huge(pmd_t pmd)
 {
-	return !(pmd_val(pmd) & PMD_TABLE_BIT);
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
 
 int pud_huge(pud_t pud)
 {
 #ifndef __PAGETABLE_PMD_FOLDED
-	return !(pud_val(pud) & PUD_TABLE_BIT);
+	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
 #else
 	return 0;
 #endif

arch/arm64/mm/mmu.c

@@ -117,7 +117,7 @@ void split_pud(pud_t *old_pud, pmd_t *pmd)
 	int i = 0;
 
 	do {
-		set_pmd(pmd, __pmd(addr | prot));
+		set_pmd(pmd, __pmd(addr | pgprot_val(prot)));
 		addr += PMD_SIZE;
 	} while (pmd++, i++, i < PTRS_PER_PMD);
 }

arch/arm64/net/bpf_jit.h

@@ -110,6 +110,10 @@
 /* Rd = Rn >> shift; signed */
 #define A64_ASR(sf, Rd, Rn, shift) A64_SBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31)
 
+/* Zero extend */
+#define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15)
+#define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31)
+
 /* Move wide (immediate) */
 #define A64_MOVEW(sf, Rd, imm16, shift, type) \
 	aarch64_insn_gen_movewide(Rd, imm16, shift, \

arch/arm64/net/bpf_jit_comp.c

@@ -113,9 +113,9 @@ static inline void emit_a64_mov_i(const int is64, const int reg,
 static inline int bpf2a64_offset(int bpf_to, int bpf_from,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to + 1];
+	int to = ctx->offset[bpf_to];
 	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from + 1] - 1;
+	int from = ctx->offset[bpf_from] - 1;
 
 	return to - from;
 }
@@ -289,23 +289,41 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		if (BPF_SRC(code) == BPF_FROM_BE)
-			break;
+			goto emit_bswap_uxt;
 #else /* !CONFIG_CPU_BIG_ENDIAN */
 		if (BPF_SRC(code) == BPF_FROM_LE)
-			break;
+			goto emit_bswap_uxt;
 #endif
 		switch (imm) {
 		case 16:
 			emit(A64_REV16(is64, dst, dst), ctx);
+			/* zero-extend 16 bits into 64 bits */
+			emit(A64_UXTH(is64, dst, dst), ctx);
 			break;
 		case 32:
 			emit(A64_REV32(is64, dst, dst), ctx);
+			/* upper 32 bits already cleared */
 			break;
 		case 64:
 			emit(A64_REV64(dst, dst), ctx);
 			break;
 		}
 		break;
+emit_bswap_uxt:
+		switch (imm) {
+		case 16:
+			/* zero-extend 16 bits into 64 bits */
+			emit(A64_UXTH(is64, dst, dst), ctx);
+			break;
+		case 32:
+			/* zero-extend 32 bits into 64 bits */
+			emit(A64_UXTW(is64, dst, dst), ctx);
+			break;
+		case 64:
+			/* nop */
+			break;
+		}
+		break;
 	/* dst = imm */
 	case BPF_ALU | BPF_MOV | BPF_K:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
@@ -640,10 +658,11 @@ static int build_body(struct jit_ctx *ctx)
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
+		ret = build_insn(insn, ctx);
+
 		if (ctx->image == NULL)
 			ctx->offset[i] = ctx->idx;
 
-		ret = build_insn(insn, ctx);
 		if (ret > 0) {
 			i++;
 			continue;