Merge tag 'mm-hotfixes-stable-2024-10-09-15-46' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "12 hotfixes, 5 of which are c:stable. All singletons, about half of
  which are MM"

* tag 'mm-hotfixes-stable-2024-10-09-15-46' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm: zswap: delete comments for "value" member of 'struct zswap_entry'.
  CREDITS: sort alphabetically by name
  secretmem: disable memfd_secret() if arch cannot set direct map
  .mailmap: update Fangrui's email
  mm/huge_memory: check pmd_special() only after pmd_present()
  resource, kunit: fix user-after-free in resource_test_region_intersects()
  fs/proc/kcore.c: allow translation of physical memory addresses
  selftests/mm: fix incorrect buffer->mirror size in hmm2 double_map test
  device-dax: correct pgoff align in dax_set_mapping()
  kthread: unpark only parked kthread
  Revert "mm: introduce PF_MEMALLOC_NORECLAIM, PF_MEMALLOC_NOWARN"
  bcachefs: do not use PF_MEMALLOC_NORECLAIM

Author: torvalds

.mailmap

@@ -203,6 +203,7 @@ Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com>
 Faith Ekstrand <faith.ekstrand@collabora.com> <jason@jlekstrand.net>
 Faith Ekstrand <faith.ekstrand@collabora.com> <jason.ekstrand@intel.com>
 Faith Ekstrand <faith.ekstrand@collabora.com> <jason.ekstrand@collabora.com>
+Fangrui Song <i@maskray.me> <maskray@google.com>
 Felipe W Damasio <felipewd@terra.com.br>
 Felix Kuhling <fxkuehl@gmx.de>
 Felix Moeller <felix@derklecks.de>

CREDITS

@@ -1358,10 +1358,6 @@ D: Major kbuild rework during the 2.5 cycle
 D: ISDN Maintainer
 S: USA
 
-N: Gerrit Renker
-E: gerrit@erg.abdn.ac.uk
-D: DCCP protocol support.
-
 N: Philip Gladstone
 E: philip@gladstonefamily.net
 D: Kernel / timekeeping stuff
@@ -1677,11 +1673,6 @@ W: http://www.carumba.com/
 D: bug toaster (A1 sauce makes all the difference)
 D: Random linux hacker
 
-N: James Hogan
-E: jhogan@kernel.org
-D: Metag architecture maintainer
-D: TZ1090 SoC maintainer
-
 N: Tim Hockin
 E: thockin@hockin.org
 W: http://www.hockin.org/~thockin
@@ -1697,6 +1688,11 @@ D: hwmon subsystem maintainer
 D: i2c-sis96x and i2c-stub SMBus drivers
 S: USA
 
+N: James Hogan
+E: jhogan@kernel.org
+D: Metag architecture maintainer
+D: TZ1090 SoC maintainer
+
 N: Dirk Hohndel
 E: hohndel@suse.de
 D: The XFree86[tm] Project
@@ -1872,6 +1868,10 @@ S: K osmidomkum 723
 S: 160 00 Praha 6
 S: Czech Republic
 
+N: Seth Jennings
+E: sjenning@redhat.com
+D: Creation and maintenance of zswap
+
 N: Jeremy Kerr
 D: Maintainer of SPU File System
 
@@ -2188,19 +2188,6 @@ N: Mike Kravetz
 E: mike.kravetz@oracle.com
 D: Maintenance and development of the hugetlb subsystem
 
-N: Seth Jennings
-E: sjenning@redhat.com
-D: Creation and maintenance of zswap
-
-N: Dan Streetman
-E: ddstreet@ieee.org
-D: Maintenance and development of zswap
-D: Creation and maintenance of the zpool API
-
-N: Vitaly Wool
-E: vitaly.wool@konsulko.com
-D: Maintenance and development of zswap
-
 N: Andreas S. Krebs
 E: akrebs@altavista.net
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards
@@ -3191,6 +3178,11 @@ N: Ken Pizzini
 E: ken@halcyon.com
 D: CDROM driver "sonycd535" (Sony CDU-535/531)
 
+N: Mathieu Poirier
+E: mathieu.poirier@linaro.org
+D: CoreSight kernel subsystem, Maintainer 2014-2022
+D: Perf tool support for CoreSight
+
 N: Stelian Pop
 E: stelian@popies.net
 P: 1024D/EDBB6147 7B36 0E07 04BC 11DC A7A0  D3F7 7185 9E7A EDBB 6147
@@ -3300,6 +3292,10 @@ S: Schlossbergring 9
 S: 79098 Freiburg
 S: Germany
 
+N: Gerrit Renker
+E: gerrit@erg.abdn.ac.uk
+D: DCCP protocol support.
+
 N: Thomas Renninger
 E: trenn@suse.de
 D: cpupowerutils
@@ -3576,11 +3572,6 @@ D: several improvements to system programs
 S: Oldenburg
 S: Germany
 
-N: Mathieu Poirier
-E: mathieu.poirier@linaro.org
-D: CoreSight kernel subsystem, Maintainer 2014-2022
-D: Perf tool support for CoreSight
-
 N: Robert Schwebel
 E: robert@schwebel.de
 W: https://www.schwebel.de
@@ -3771,6 +3762,11 @@ S: Chr. Winthersvej 1 B, st.th.
 S: DK-1860 Frederiksberg C
 S: Denmark
 
+N: Dan Streetman
+E: ddstreet@ieee.org
+D: Maintenance and development of zswap
+D: Creation and maintenance of the zpool API
+
 N: Drew Sullivan
 E: drew@ss.org
 W: http://www.ss.org/
@@ -4286,6 +4282,10 @@ S: Pipers Way
 S: Swindon. SN3 1RJ
 S: England
 
+N: Vitaly Wool
+E: vitaly.wool@konsulko.com
+D: Maintenance and development of zswap
+
 N: Chris Wright
 E: chrisw@sous-sol.org
 D: hacking on LSM framework and security modules.

arch/s390/include/asm/io.h

@@ -16,8 +16,10 @@
 #include <asm/pci_io.h>
 
 #define xlate_dev_mem_ptr xlate_dev_mem_ptr
+#define kc_xlate_dev_mem_ptr xlate_dev_mem_ptr
 void *xlate_dev_mem_ptr(phys_addr_t phys);
 #define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+#define kc_unxlate_dev_mem_ptr unxlate_dev_mem_ptr
 void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 #define IO_SPACE_LIMIT 0

drivers/dax/device.c

@@ -86,7 +86,7 @@ static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
 		nr_pages = 1;
 
 	pgoff = linear_page_index(vmf->vma,
-			ALIGN(vmf->address, fault_size));
+			ALIGN_DOWN(vmf->address, fault_size));
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i);

fs/bcachefs/fs.c

@@ -300,10 +300,10 @@ static struct inode *bch2_alloc_inode(struct super_block *sb)
 	BUG();
 }
 
-static struct bch_inode_info *__bch2_new_inode(struct bch_fs *c)
+static struct bch_inode_info *__bch2_new_inode(struct bch_fs *c, gfp_t gfp)
 {
 	struct bch_inode_info *inode = alloc_inode_sb(c->vfs_sb,
-						bch2_inode_cache, GFP_NOFS);
+						bch2_inode_cache, gfp);
 	if (!inode)
 		return NULL;
 
@@ -315,7 +315,7 @@ static struct bch_inode_info *__bch2_new_inode(struct bch_fs *c)
 	mutex_init(&inode->ei_quota_lock);
 	memset(&inode->ei_devs_need_flush, 0, sizeof(inode->ei_devs_need_flush));
 
-	if (unlikely(inode_init_always(c->vfs_sb, &inode->v))) {
+	if (unlikely(inode_init_always_gfp(c->vfs_sb, &inode->v, gfp))) {
 		kmem_cache_free(bch2_inode_cache, inode);
 		return NULL;
 	}
@@ -328,12 +328,10 @@ static struct bch_inode_info *__bch2_new_inode(struct bch_fs *c)
  */
 static struct bch_inode_info *bch2_new_inode(struct btree_trans *trans)
 {
-	struct bch_inode_info *inode =
-		memalloc_flags_do(PF_MEMALLOC_NORECLAIM|PF_MEMALLOC_NOWARN,
-				  __bch2_new_inode(trans->c));
+	struct bch_inode_info *inode = __bch2_new_inode(trans->c, GFP_NOWAIT);
 
 	if (unlikely(!inode)) {
-		int ret = drop_locks_do(trans, (inode = __bch2_new_inode(trans->c)) ? 0 : -ENOMEM);
+		int ret = drop_locks_do(trans, (inode = __bch2_new_inode(trans->c, GFP_NOFS)) ? 0 : -ENOMEM);
 		if (ret && inode) {
 			__destroy_inode(&inode->v);
 			kmem_cache_free(bch2_inode_cache, inode);
@@ -407,7 +405,7 @@ __bch2_create(struct mnt_idmap *idmap,
 	if (ret)
 		return ERR_PTR(ret);
 #endif
-	inode = __bch2_new_inode(c);
+	inode = __bch2_new_inode(c, GFP_NOFS);
 	if (unlikely(!inode)) {
 		inode = ERR_PTR(-ENOMEM);
 		goto err;

fs/inode.c

@@ -146,14 +146,16 @@ static int no_open(struct inode *inode, struct file *file)
 }
 
 /**
- * inode_init_always - perform inode structure initialisation
+ * inode_init_always_gfp - perform inode structure initialisation
  * @sb: superblock inode belongs to
  * @inode: inode to initialise
+ * @gfp: allocation flags
  *
  * These are initializations that need to be done on every inode
  * allocation as the fields are not initialised by slab allocation.
+ * If there are additional allocations required @gfp is used.
  */
-int inode_init_always(struct super_block *sb, struct inode *inode)
+int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp)
 {
 	static const struct inode_operations empty_iops;
 	static const struct file_operations no_open_fops = {.open = no_open};
@@ -230,14 +232,14 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 #endif
 	inode->i_flctx = NULL;
 
-	if (unlikely(security_inode_alloc(inode)))
+	if (unlikely(security_inode_alloc(inode, gfp)))
 		return -ENOMEM;
 
 	this_cpu_inc(nr_inodes);
 
 	return 0;
 }
-EXPORT_SYMBOL(inode_init_always);
+EXPORT_SYMBOL(inode_init_always_gfp);
 
 void free_inode_nonrcu(struct inode *inode)
 {

fs/proc/kcore.c

@@ -50,6 +50,20 @@ static struct proc_dir_entry *proc_root_kcore;
 #define	kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
 #endif
 
+#ifndef kc_xlate_dev_mem_ptr
+#define kc_xlate_dev_mem_ptr kc_xlate_dev_mem_ptr
+static inline void *kc_xlate_dev_mem_ptr(phys_addr_t phys)
+{
+	return __va(phys);
+}
+#endif
+#ifndef kc_unxlate_dev_mem_ptr
+#define kc_unxlate_dev_mem_ptr kc_unxlate_dev_mem_ptr
+static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt)
+{
+}
+#endif
+
 static LIST_HEAD(kclist_head);
 static DECLARE_RWSEM(kclist_lock);
 static int kcore_need_update = 1;
@@ -471,6 +485,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	while (buflen) {
 		struct page *page;
 		unsigned long pfn;
+		phys_addr_t phys;
+		void *__start;
 
 		/*
 		 * If this is the first iteration or the address is not within
@@ -537,7 +553,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 			}
 			break;
 		case KCORE_RAM:
-			pfn = __pa(start) >> PAGE_SHIFT;
+			phys = __pa(start);
+			pfn =  phys >> PAGE_SHIFT;
 			page = pfn_to_online_page(pfn);
 
 			/*
@@ -557,13 +574,28 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 			fallthrough;
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
+			if (m->type == KCORE_RAM) {
+				__start = kc_xlate_dev_mem_ptr(phys);
+				if (!__start) {
+					ret = -ENOMEM;
+					if (iov_iter_zero(tsz, iter) != tsz)
+						ret = -EFAULT;
+					goto out;
+				}
+			} else {
+				__start = (void *)start;
+			}
+
 			/*
 			 * Sadly we must use a bounce buffer here to be able to
 			 * make use of copy_from_kernel_nofault(), as these
 			 * memory regions might not always be mapped on all
 			 * architectures.
 			 */
-			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+			ret = copy_from_kernel_nofault(buf, __start, tsz);
+			if (m->type == KCORE_RAM)
+				kc_unxlate_dev_mem_ptr(phys, __start);
+			if (ret) {
 				if (iov_iter_zero(tsz, iter) != tsz) {
 					ret = -EFAULT;
 					goto out;

include/linux/fs.h

@@ -3082,7 +3082,12 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 
-extern int inode_init_always(struct super_block *, struct inode *);
+extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t);
+static inline int inode_init_always(struct super_block *sb, struct inode *inode)
+{
+	return inode_init_always_gfp(sb, inode, GFP_NOFS);
+}
+
 extern void inode_init_once(struct inode *);
 extern void address_space_init_once(struct address_space *mapping);
 extern struct inode * igrab(struct inode *);

include/linux/sched.h

@@ -1681,8 +1681,8 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF_MEMALLOC_NORECLAIM	0x00800000	/* All allocation requests will clear __GFP_DIRECT_RECLAIM */
-#define PF_MEMALLOC_NOWARN	0x01000000	/* All allocation requests will inherit __GFP_NOWARN */
+#define PF__HOLE__00800000	0x00800000
+#define PF__HOLE__01000000	0x01000000
 #define PF__HOLE__02000000	0x02000000
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */

include/linux/sched/mm.h

@@ -251,25 +251,16 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 {
 	unsigned int pflags = READ_ONCE(current->flags);
 
-	if (unlikely(pflags & (PF_MEMALLOC_NOIO |
-			       PF_MEMALLOC_NOFS |
-			       PF_MEMALLOC_NORECLAIM |
-			       PF_MEMALLOC_NOWARN |
-			       PF_MEMALLOC_PIN))) {
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) {
 		/*
-		 * Stronger flags before weaker flags:
-		 * NORECLAIM implies NOIO, which in turn implies NOFS
+		 * NOIO implies both NOIO and NOFS and it is a weaker context
+		 * so always make sure it makes precedence
 		 */
-		if (pflags & PF_MEMALLOC_NORECLAIM)
-			flags &= ~__GFP_DIRECT_RECLAIM;
-		else if (pflags & PF_MEMALLOC_NOIO)
+		if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
 
-		if (pflags & PF_MEMALLOC_NOWARN)
-			flags |= __GFP_NOWARN;
-
 		if (pflags & PF_MEMALLOC_PIN)
 			flags &= ~__GFP_MOVABLE;
 	}