Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "8 patches.

  Subsystems affected by this patch series: mm (madvise, pagemap,
  readahead, memcg, userfaultfd), kbuild, and vfs"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: fix madvise WILLNEED performance problem
  libfs: fix error cast of negative value in simple_attr_write()
  mm/userfaultfd: do not access vma->vm_mm after calling handle_userfault()
  mm: memcg/slab: fix root memcg vmstats
  mm: fix readahead_page_batch for retry entries
  mm: fix phys_to_target_node() and memory_add_physaddr_to_nid() exports
  compiler-clang: remove version check for BPF Tracing
  mm/madvise: fix memory leak from process_madvise

16 files changed, 75 insertions, 49 deletions

diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
index 336d0570e1fa..dd8c166ffd7b 100644
--- a/arch/ia64/include/asm/sparsemem.h
+++ b/arch/ia64/include/asm/sparsemem.h
@@ -18,4 +18,10 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 addr);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+
 #endif /* _ASM_IA64_SPARSEMEM_H */
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 91c69ff53a8a..6cda76b57c5d 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -46,5 +46,10 @@ u64 memory_hotplug_max(void);
 #define __HAVE_ARCH_RESERVED_KERNEL_PAGES
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern int create_section_mapping(unsigned long start, unsigned long end,
+				  int nid, pgprot_t prot);
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 1e6fa371cc38..d072866842e4 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -13,9 +13,9 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
-				  int nid, pgprot_t prot);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
 
 #ifdef CONFIG_NUMA
 extern int hot_add_scn_to_nid(unsigned long scn_addr);
@@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr)
 }
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_MEMORY_HOTPLUG */
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SPARSEMEM_H */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 01ec2a252f09..3fc325bebe4d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -50,6 +50,7 @@
 #include <asm/rtas.h>
 #include <asm/kasan.h>
 #include <asm/svm.h>
+#include <asm/mmzone.h>
 
 #include <mm/mmu_decl.h>
 
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 6bfc878f6771..6a9ccc1b2be5 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -28,4 +28,14 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+extern int phys_to_target_node(phys_addr_t start);
+#define phys_to_target_node phys_to_target_node
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_X86_SPARSEMEM_H */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 44148691d78b..5eb4dc2b97da 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
+EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {
@@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start)
 		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 567428e10b7b..d2834c2cfa10 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -50,7 +50,6 @@ config DEV_DAX_HMEM
 	  Say M if unsure.
 
 config DEV_DAX_HMEM_DEVICES
-	depends on NUMA_KEEP_MEMINFO # for phys_to_target_node()
 	depends on DEV_DAX_HMEM && DAX=y
 	def_bool y
 
diff --git a/fs/libfs.c b/fs/libfs.c
index fc34361c1489..7124c2e8df2f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -959,7 +959,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 			  size_t len, loff_t *ppos)
 {
 	struct simple_attr *attr;
-	u64 val;
+	unsigned long long val;
 	size_t size;
 	ssize_t ret;
 
@@ -977,7 +977,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 		goto out;
 
 	attr->set_buf[size] = '\0';
-	val = simple_strtoll(attr->set_buf, NULL, 0);
+	ret = kstrtoull(attr->set_buf, 0, &val);
+	if (ret)
+		goto out;
 	ret = attr->set(attr->data, val);
 	if (ret == 0)
 		ret = len; /* on success, claim we got the whole input */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index dd7233c48bf3..98cff1b4b088 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -8,8 +8,10 @@
 		     + __clang_patchlevel__)
 
 #if CLANG_VERSION < 100001
+#ifndef __BPF_TRACING__
 # error Sorry, your version of Clang is too old - please use 10.0.1 or newer.
 #endif
+#endif
 
 /* Compiler specific definitions for Clang compiler */
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d65c6fdc5cfc..551093b74596 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-extern int phys_to_target_node(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-static inline int phys_to_target_node(u64 start)
-{
-	return 0;
-}
-#endif
-
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions
diff --git a/include/linux/numa.h b/include/linux/numa.h
index 8cb33ccfb671..cb44cfe2b725 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -21,13 +21,41 @@
 #endif
 
 #ifdef CONFIG_NUMA
+#include <linux/printk.h>
+#include <asm/sparsemem.h>
+
 /* Generic implementation available */
 int numa_map_to_online_node(int node);
-#else
+
+#ifndef memory_add_physaddr_to_nid
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+#endif
+#ifndef phys_to_target_node
+static inline int phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+#endif
+#else /* !CONFIG_NUMA */
 static inline int numa_map_to_online_node(int node)
 {
 	return NUMA_NO_NODE;
 }
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+static inline int phys_to_target_node(u64 start)
+{
+	return 0;
+}
 #endif
 
 #endif /* _LINUX_NUMA_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e1e19c1f9ec9..d5570deff400 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 	xas_set(&xas, rac->_index);
 	rcu_read_lock();
 	xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
+		if (xas_retry(&xas, page))
+			continue;
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(PageTail(page), page);
 		array[i++] = page;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9474dbc150ed..ec2bb93f7431 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -710,7 +710,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			transparent_hugepage_use_zero_page()) {
 		pgtable_t pgtable;
 		struct page *zero_page;
-		bool set;
 		vm_fault_t ret;
 		pgtable = pte_alloc_one(vma->vm_mm);
 		if (unlikely(!pgtable))
@@ -723,25 +722,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		}
 		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 		ret = 0;
-		set = false;
 		if (pmd_none(*vmf->pmd)) {
 			ret = check_stable_address_space(vma->vm_mm);
 			if (ret) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 			} else if (userfaultfd_missing(vma)) {
 				spin_unlock(vmf->ptl);
+				pte_free(vma->vm_mm, pgtable);
 				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			} else {
 				set_huge_zero_page(pgtable, vma->vm_mm, vma,
 						   haddr, vmf->pmd, zero_page);
 				spin_unlock(vmf->ptl);
-				set = true;
 			}
-		} else
+		} else {
 			spin_unlock(vmf->ptl);
-		if (!set)
 			pte_free(vma->vm_mm, pgtable);
+		}
 		return ret;
 	}
 	gfp = alloc_hugepage_direct_gfpmask(vma);
diff --git a/mm/madvise.c b/mm/madvise.c
index 416a56b8e757..a8d8d48a57fe 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		struct address_space *mapping)
 {
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
-	pgoff_t end_index = end / PAGE_SIZE;
+	pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
 	struct page *page;
 
 	rcu_read_lock();
@@ -1231,8 +1231,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 		ret = total_len - iov_iter_count(&iter);
 
 	mmput(mm);
-	return ret;
-
 release_task:
 	put_task_struct(task);
 put_pid:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dcbf24d2227..29459a6ce1c7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -867,8 +867,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_lock();
 	memcg = mem_cgroup_from_obj(p);
 
-	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!memcg || memcg == root_mem_cgroup) {
+	/*
+	 * Untracked pages have no memcg, no lruvec. Update only the
+	 * node. If we reparent the slab objects to the root memcg,
+	 * when we free the slab object, we need to update the per-memcg
+	 * vmstats to keep it correct for the root memcg.
+	 */
+	if (!memcg) {
 		__mod_node_page_state(pgdat, idx, val);
 	} else {
 		lruvec = mem_cgroup_lruvec(memcg, pgdat);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b44d4c7ba73b..63b2e46b6555 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	return err;
 }
 
-#ifdef CONFIG_NUMA
-int __weak memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
-int __weak phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(phys_to_target_node);
-#endif
-
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
 static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,