Merge branch 'fixes' into next

Merge in our fixes branch, which brings in clone3() as well as some
implicit fallthrough fixes we want in next.

arch/powerpc/include/asm/cache.h

@@ -107,22 +107,22 @@ extern void _set_L3CR(unsigned long);
 
 static inline void dcbz(void *addr)
 {
-	__asm__ __volatile__ ("dcbz %y0" : : "Z"(*(u8 *)addr) : "memory");
+	__asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory");
 }
 
 static inline void dcbi(void *addr)
 {
-	__asm__ __volatile__ ("dcbi %y0" : : "Z"(*(u8 *)addr) : "memory");
+	__asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory");
 }
 
 static inline void dcbf(void *addr)
 {
-	__asm__ __volatile__ ("dcbf %y0" : : "Z"(*(u8 *)addr) : "memory");
+	__asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory");
 }
 
 static inline void dcbst(void *addr)
 {
-	__asm__ __volatile__ ("dcbst %y0" : : "Z"(*(u8 *)addr) : "memory");
+	__asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory");
 }
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/unistd.h

@@ -49,6 +49,7 @@
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 #endif		/* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_UNISTD_H_ */

arch/powerpc/kernel/align.c

@@ -176,9 +176,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
 			ret |= __get_user_inatomic(temp.v[1], p++);
 			ret |= __get_user_inatomic(temp.v[2], p++);
 			ret |= __get_user_inatomic(temp.v[3], p++);
+			/* fall through */
 		case 4:
 			ret |= __get_user_inatomic(temp.v[4], p++);
 			ret |= __get_user_inatomic(temp.v[5], p++);
+			/* fall through */
 		case 2:
 			ret |= __get_user_inatomic(temp.v[6], p++);
 			ret |= __get_user_inatomic(temp.v[7], p++);
@@ -259,9 +261,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
 			ret |= __put_user_inatomic(data.v[1], p++);
 			ret |= __put_user_inatomic(data.v[2], p++);
 			ret |= __put_user_inatomic(data.v[3], p++);
+			/* fall through */
 		case 4:
 			ret |= __put_user_inatomic(data.v[4], p++);
 			ret |= __put_user_inatomic(data.v[5], p++);
+			/* fall through */
 		case 2:
 			ret |= __put_user_inatomic(data.v[6], p++);
 			ret |= __put_user_inatomic(data.v[7], p++);

arch/powerpc/kernel/entry_32.S

@@ -597,6 +597,14 @@ ppc_clone:
 	stw	r0,_TRAP(r1)		/* register set saved */
 	b	sys_clone
 
+	.globl	ppc_clone3
+ppc_clone3:
+	SAVE_NVGPRS(r1)
+	lwz	r0,_TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,_TRAP(r1)		/* register set saved */
+	b	sys_clone3
+
 	.globl	ppc_swapcontext
 ppc_swapcontext:
 	SAVE_NVGPRS(r1)

arch/powerpc/kernel/entry_64.S

@@ -487,6 +487,11 @@ _GLOBAL(ppc_clone)
 	bl	sys_clone
 	b	.Lsyscall_exit
 
+_GLOBAL(ppc_clone3)
+       bl      save_nvgprs
+       bl      sys_clone3
+       b       .Lsyscall_exit
+
 _GLOBAL(ppc32_swapcontext)
 	bl	save_nvgprs
 	bl	compat_sys_swapcontext

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -516,4 +516,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	nospu	clone3				ppc_clone3

arch/powerpc/kvm/book3s_32_mmu.c

@@ -239,6 +239,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				case 2:
 				case 6:
 					pte->may_write = true;
+					/* fall through */
 				case 3:
 				case 5:
 				case 7:

arch/powerpc/mm/kasan/kasan_init_32.c

@@ -21,7 +21,7 @@ static void kasan_populate_pte(pte_t *ptep, pgprot_t prot)
 		__set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
 }
 
-static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
+static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
 {
 	pmd_t *pmd;
 	unsigned long k_cur, k_next;
@@ -35,7 +35,10 @@ static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_
 		if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
 			continue;
 
-		new = pte_alloc_one_kernel(&init_mm);
+		if (slab_is_available())
+			new = pte_alloc_one_kernel(&init_mm);
+		else
+			new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
 
 		if (!new)
 			return -ENOMEM;

arch/powerpc/mm/nohash/tlb.c

@@ -630,7 +630,6 @@ static void early_init_this_mmu(void)
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
 		unsigned int num_cams;
-		int __maybe_unused cpu = smp_processor_id();
 		bool map = true;
 
 		/* use a quarter of the TLBCAM for bolted linear map */

arch/powerpc/platforms/pseries/papr_scm.c

@@ -275,12 +275,32 @@ static const struct attribute_group *papr_scm_dimm_groups[] = {
 	NULL,
 };
 
+static inline int papr_scm_node(int node)
+{
+	int min_dist = INT_MAX, dist;
+	int nid, min_node;
+
+	if ((node == NUMA_NO_NODE) || node_online(node))
+		return node;
+
+	min_node = first_online_node;
+	for_each_online_node(nid) {
+		dist = node_distance(node, nid);
+		if (dist < min_dist) {
+			min_dist = dist;
+			min_node = nid;
+		}
+	}
+	return min_node;
+}
+
 static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 {
 	struct device *dev = &p->pdev->dev;
 	struct nd_mapping_desc mapping;
 	struct nd_region_desc ndr_desc;
 	unsigned long dimm_flags;
+	int target_nid, online_nid;
 
 	p->bus_desc.ndctl = papr_scm_ndctl;
 	p->bus_desc.module = THIS_MODULE;
@@ -319,8 +339,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	ndr_desc.attr_groups = region_attr_groups;
-	ndr_desc.numa_node = dev_to_node(&p->pdev->dev);
-	ndr_desc.target_node = ndr_desc.numa_node;
+	target_nid = dev_to_node(&p->pdev->dev);
+	online_nid = papr_scm_node(target_nid);
+	ndr_desc.numa_node = online_nid;
+	ndr_desc.target_node = target_nid;
 	ndr_desc.res = &p->res;
 	ndr_desc.of_node = p->dn;
 	ndr_desc.provider_data = p;
@@ -338,6 +360,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 				ndr_desc.res, p->dn);
 		goto err;
 	}
+	if (target_nid != online_nid)
+		dev_info(dev, "Region registered with target node %d and online node %d",
+			 target_nid, online_nid);
 
 	return 0;
 

drivers/macintosh/smu.c

@@ -852,6 +852,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd)
 		break;
 	case SMU_I2C_TRANSFER_COMBINED:
 		cmd->info.devaddr &= 0xfe;
+		/* fall through */
 	case SMU_I2C_TRANSFER_STDSUB:
 		if (cmd->info.sublen > 3)
 			return -EINVAL;