Merge tag 'powerpc-5.17-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - A series of bpf fixes, including an oops fix and some codegen fixes.

 - Fix a regression in syscall_get_arch() for compat processes.

 - Fix boot failure on some 32-bit systems with KASAN enabled.

 - A couple of other build/minor fixes.

Thanks to Athira Rajeev, Christophe Leroy, Dmitry V. Levin, Jiri Olsa,
Johan Almbladh, Maxime Bizon, Naveen N. Rao, and Nicholas Piggin.

* tag 'powerpc-5.17-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s: Mask SRR0 before checking against the masked NIP
  powerpc/perf: Only define power_pmu_wants_prompt_pmi() for CONFIG_PPC64
  powerpc/32s: Fix kasan_init_region() for KASAN
  powerpc/time: Fix build failure due to do_hard_irq_enable() on PPC32
  powerpc/audit: Fix syscall_get_arch()
  powerpc64/bpf: Limit 'ldbrx' to processors compliant with ISA v2.06
  tools/bpf: Rename 'struct event' to avoid naming conflict
  powerpc/bpf: Update ldimm64 instructions during extra pass
  powerpc32/bpf: Fix codegen for bpf-to-bpf calls
  bpf: Guard against accessing NULL pt_regs in bpf_get_task_stack()

Author: torvalds

arch/powerpc/include/asm/book3s/32/mmu-hash.h

@@ -223,6 +223,8 @@ static __always_inline void update_user_segments(u32 val)
 	update_user_segment(15, val);
 }
 
+int __init find_free_bat(void);
+unsigned int bat_block_size(unsigned long base, unsigned long top);
 #endif /* !__ASSEMBLY__ */
 
 /* We happily ignore the smaller BATs on 601, we don't actually use

arch/powerpc/include/asm/hw_irq.h

@@ -473,7 +473,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 	return !(regs->msr & MSR_EE);
 }
 
-static inline bool should_hard_irq_enable(void)
+static __always_inline bool should_hard_irq_enable(void)
 {
 	return false;
 }

arch/powerpc/include/asm/ppc-opcode.h

@@ -500,6 +500,7 @@
 #define PPC_RAW_LDX(r, base, b)		(0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_RAW_LHZ(r, base, i)		(0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LHBRX(r, base, b)	(0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_RAW_LWBRX(r, base, b)	(0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_RAW_LDBRX(r, base, b)	(0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_RAW_STWCX(s, a, b)		(0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_CMPWI(a, i)		(0x2c000000 | ___PPC_RA(a) | IMM_L(i))

arch/powerpc/include/asm/syscall.h

@@ -90,7 +90,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	unsigned long val, mask = -1UL;
 	unsigned int n = 6;
 
-	if (is_32bit_task())
+	if (is_tsk_32bit_task(task))
 		mask = 0xffffffff;
 
 	while (n--) {
@@ -105,7 +105,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(struct task_struct *task)
 {
-	if (is_32bit_task())
+	if (is_tsk_32bit_task(task))
 		return AUDIT_ARCH_PPC;
 	else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
 		return AUDIT_ARCH_PPC64LE;

arch/powerpc/include/asm/thread_info.h

@@ -168,8 +168,10 @@ static inline bool test_thread_local_flags(unsigned int flags)
 
 #ifdef CONFIG_COMPAT
 #define is_32bit_task()	(test_thread_flag(TIF_32BIT))
+#define is_tsk_32bit_task(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT))
 #else
 #define is_32bit_task()	(IS_ENABLED(CONFIG_PPC32))
+#define is_tsk_32bit_task(tsk)	(IS_ENABLED(CONFIG_PPC32))
 #endif
 
 #if defined(CONFIG_PPC64)

arch/powerpc/kernel/interrupt_64.S

@@ -30,6 +30,7 @@ COMPAT_SYS_CALL_TABLE:
 	.ifc \srr,srr
 	mfspr	r11,SPRN_SRR0
 	ld	r12,_NIP(r1)
+	clrrdi  r11,r11,2
 	clrrdi  r12,r12,2
 100:	tdne	r11,r12
 	EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
@@ -40,6 +41,7 @@ COMPAT_SYS_CALL_TABLE:
 	.else
 	mfspr	r11,SPRN_HSRR0
 	ld	r12,_NIP(r1)
+	clrrdi  r11,r11,2
 	clrrdi  r12,r12,2
 100:	tdne	r11,r12
 	EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)

arch/powerpc/mm/book3s32/mmu.c

@@ -76,7 +76,7 @@ unsigned long p_block_mapped(phys_addr_t pa)
 	return 0;
 }
 
-static int __init find_free_bat(void)
+int __init find_free_bat(void)
 {
 	int b;
 	int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
@@ -100,7 +100,7 @@ static int __init find_free_bat(void)
  * - block size has to be a power of two. This is calculated by finding the
  *   highest bit set to 1.
  */
-static unsigned int block_size(unsigned long base, unsigned long top)
+unsigned int bat_block_size(unsigned long base, unsigned long top)
 {
 	unsigned int max_size = SZ_256M;
 	unsigned int base_shift = (ffs(base) - 1) & 31;
@@ -145,7 +145,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to
 	int idx;
 
 	while ((idx = find_free_bat()) != -1 && base != top) {
-		unsigned int size = block_size(base, top);
+		unsigned int size = bat_block_size(base, top);
 
 		if (size < 128 << 10)
 			break;
@@ -201,12 +201,12 @@ void mmu_mark_initmem_nx(void)
 	unsigned long size;
 
 	for (i = 0; i < nb - 1 && base < top;) {
-		size = block_size(base, top);
+		size = bat_block_size(base, top);
 		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
 		base += size;
 	}
 	if (base < top) {
-		size = block_size(base, top);
+		size = bat_block_size(base, top);
 		if ((top - base) > size) {
 			size <<= 1;
 			if (strict_kernel_rwx_enabled() && base + size > border)

arch/powerpc/mm/kasan/book3s_32.c

@@ -10,48 +10,51 @@ int __init kasan_init_region(void *start, size_t size)
 {
 	unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start);
 	unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size);
-	unsigned long k_cur = k_start;
-	int k_size = k_end - k_start;
-	int k_size_base = 1 << (ffs(k_size) - 1);
+	unsigned long k_nobat = k_start;
+	unsigned long k_cur;
+	phys_addr_t phys;
 	int ret;
-	void *block;
 
-	block = memblock_alloc(k_size, k_size_base);
-
-	if (block && k_size_base >= SZ_128K && k_start == ALIGN(k_start, k_size_base)) {
-		int shift = ffs(k_size - k_size_base);
-		int k_size_more = shift ? 1 << (shift - 1) : 0;
-
-		setbat(-1, k_start, __pa(block), k_size_base, PAGE_KERNEL);
-		if (k_size_more >= SZ_128K)
-			setbat(-1, k_start + k_size_base, __pa(block) + k_size_base,
-			       k_size_more, PAGE_KERNEL);
-		if (v_block_mapped(k_start))
-			k_cur = k_start + k_size_base;
-		if (v_block_mapped(k_start + k_size_base))
-			k_cur = k_start + k_size_base + k_size_more;
-
-		update_bats();
+	while (k_nobat < k_end) {
+		unsigned int k_size = bat_block_size(k_nobat, k_end);
+		int idx = find_free_bat();
+
+		if (idx == -1)
+			break;
+		if (k_size < SZ_128K)
+			break;
+		phys = memblock_phys_alloc_range(k_size, k_size, 0,
+						 MEMBLOCK_ALLOC_ANYWHERE);
+		if (!phys)
+			break;
+
+		setbat(idx, k_nobat, phys, k_size, PAGE_KERNEL);
+		k_nobat += k_size;
 	}
+	if (k_nobat != k_start)
+		update_bats();
 
-	if (!block)
-		block = memblock_alloc(k_size, PAGE_SIZE);
-	if (!block)
-		return -ENOMEM;
+	if (k_nobat < k_end) {
+		phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0,
+						 MEMBLOCK_ALLOC_ANYWHERE);
+		if (!phys)
+			return -ENOMEM;
+	}
 
 	ret = kasan_init_shadow_page_tables(k_start, k_end);
 	if (ret)
 		return ret;
 
-	kasan_update_early_region(k_start, k_cur, __pte(0));
+	kasan_update_early_region(k_start, k_nobat, __pte(0));
 
-	for (; k_cur < k_end; k_cur += PAGE_SIZE) {
+	for (k_cur = k_nobat; k_cur < k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_off_k(k_cur);
-		void *va = block + k_cur - k_start;
-		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
+		pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_nobat), PAGE_KERNEL);
 
 		__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0);
 	}
 	flush_tlb_kernel_range(k_start, k_end);
+	memset(kasan_mem_to_shadow(start), 0, k_end - k_start);
+
 	return 0;
 }

arch/powerpc/net/bpf_jit_comp.c

@@ -23,15 +23,15 @@ static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
 	memset32(area, BREAKPOINT_INSTRUCTION, size / 4);
 }
 
-/* Fix the branch target addresses for subprog calls */
-static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
-				       struct codegen_context *ctx, u32 *addrs)
+/* Fix updated addresses (for subprog calls, ldimm64, et al) during extra pass */
+static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image,
+				   struct codegen_context *ctx, u32 *addrs)
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	bool func_addr_fixed;
 	u64 func_addr;
 	u32 tmp_idx;
-	int i, ret;
+	int i, j, ret;
 
 	for (i = 0; i < fp->len; i++) {
 		/*
@@ -66,6 +66,23 @@ static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
 			 * of the JITed sequence remains unchanged.
 			 */
 			ctx->idx = tmp_idx;
+		} else if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+			tmp_idx = ctx->idx;
+			ctx->idx = addrs[i] / 4;
+#ifdef CONFIG_PPC32
+			PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm);
+			PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm);
+			for (j = ctx->idx - addrs[i] / 4; j < 4; j++)
+				EMIT(PPC_RAW_NOP());
+#else
+			func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32);
+			PPC_LI64(b2p[insn[i].dst_reg], func_addr);
+			/* overwrite rest with nops */
+			for (j = ctx->idx - addrs[i] / 4; j < 5; j++)
+				EMIT(PPC_RAW_NOP());
+#endif
+			ctx->idx = tmp_idx;
+			i++;
 		}
 	}
 
@@ -200,13 +217,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		/*
 		 * Do not touch the prologue and epilogue as they will remain
 		 * unchanged. Only fix the branch target address for subprog
-		 * calls in the body.
+		 * calls in the body, and ldimm64 instructions.
 		 *
 		 * This does not change the offsets and lengths of the subprog
 		 * call instruction sequences and hence, the size of the JITed
 		 * image as well.
 		 */
-		bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs);
+		bpf_jit_fixup_addresses(fp, code_base, &cgctx, addrs);
 
 		/* There is no need to perform the usual passes. */
 		goto skip_codegen_passes;

arch/powerpc/net/bpf_jit_comp32.c

@@ -191,6 +191,9 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
 		PPC_BL_ABS(func);
+		EMIT(PPC_RAW_NOP());
+		EMIT(PPC_RAW_NOP());
+		EMIT(PPC_RAW_NOP());
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
@@ -290,6 +293,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		bool func_addr_fixed;
 		u64 func_addr;
 		u32 true_cond;
+		u32 tmp_idx;
+		int j;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -905,8 +910,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 * 16 byte instruction that uses two 'struct bpf_insn'
 		 */
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
+			tmp_idx = ctx->idx;
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
+			/* padding to allow full 4 instructions for later patching */
+			for (j = ctx->idx - tmp_idx; j < 4; j++)
+				EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;

arch/powerpc/net/bpf_jit_comp64.c

@@ -319,6 +319,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u64 imm64;
 		u32 true_cond;
 		u32 tmp_idx;
+		int j;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -633,17 +634,21 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1]));
 				break;
 			case 64:
-				/*
-				 * Way easier and faster(?) to store the value
-				 * into stack and then use ldbrx
-				 *
-				 * ctx->seen will be reliable in pass2, but
-				 * the instructions generated will remain the
-				 * same across all passes
-				 */
+				/* Store the value to stack and then use byte-reverse loads */
 				PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
 				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)));
-				EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1]));
+				if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+					EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1]));
+				} else {
+					EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1]));
+					if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
+						EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32));
+					EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4));
+					EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1]));
+					if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+						EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32));
+					EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2]));
+				}
 				break;
 			}
 			break;
@@ -848,9 +853,13 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
 			imm64 = ((u64)(u32) insn[i].imm) |
 				    (((u64)(u32) insn[i+1].imm) << 32);
+			tmp_idx = ctx->idx;
+			PPC_LI64(dst_reg, imm64);
+			/* padding to allow full 5 instructions for later patching */
+			for (j = ctx->idx - tmp_idx; j < 5; j++)
+				EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
-			PPC_LI64(dst_reg, imm64);
 			break;
 
 		/*