Merge tag 'mm-hotfixes-stable-2024-04-05-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "8 hotfixes, 3 are cc:stable

  There are a couple of fixups for this cycle's vmalloc changes and one
  for the stackdepot changes. And a fix for a very old x86 PAT issue
  which can cause a warning splat"

* tag 'mm-hotfixes-stable-2024-04-05-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  stackdepot: rename pool_index to pool_index_plus_1
  x86/mm/pat: fix VM_PAT handling in COW mappings
  MAINTAINERS: change vmware.com addresses to broadcom.com
  selftests/mm: include strings.h for ffsl
  mm: vmalloc: fix lockdep warning
  mm: vmalloc: bail out early in find_vmap_area() if vmap is not init
  init: open output files from cpio unpacking with O_LARGEFILE
  mm/secretmem: fix GUP-fast succeeding on secretmem folios

10 files changed, 122 insertions, 76 deletions

diff --git a/.mailmap b/.mailmap
index 59c9a841bf7149..8284692f961071 100644
--- a/.mailmap
+++ b/.mailmap
@@ -20,6 +20,7 @@ Adam Oldham <oldhamca@gmail.com>
 Adam Radford <aradford@gmail.com>
 Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com>
 Adrian Bunk <bunk@stusta.de>
+Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com>
 Akhil P Oommen <quic_akhilpo@quicinc.com> <akhilpo@codeaurora.org>
 Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
@@ -36,6 +37,7 @@ Alexei Avshalom Lazar <quic_ailizaro@quicinc.com> <ailizaro@codeaurora.org>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
 Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alexey Makhalov <alexey.amakhalov@broadcom.com> <amakhalov@vmware.com>
 Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com>
 Alex Shi <alexs@kernel.org> <alex.shi@intel.com>
 Alex Shi <alexs@kernel.org> <alex.shi@linaro.org>
@@ -110,6 +112,7 @@ Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com>
 Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
 Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com>
+Bryan Tan <bryan-bt.tan@broadcom.com> <bryantan@vmware.com>
 Cai Huoqing <cai.huoqing@linux.dev> <caihuoqing@baidu.com>
 Can Guo <quic_cang@quicinc.com> <cang@codeaurora.org>
 Carl Huang <quic_cjhuang@quicinc.com> <cjhuang@codeaurora.org>
@@ -529,6 +532,7 @@ Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
+Ronak Doshi <ronak.doshi@broadcom.com> <doshir@vmware.com>
 Muchun Song <muchun.song@linux.dev> <songmuchun@bytedance.com>
 Muchun Song <muchun.song@linux.dev> <smuchun@gmail.com>
 Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
@@ -651,6 +655,7 @@ Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
 Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.org>
 Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.com>
+Vishnu Dasa <vishnu.dasa@broadcom.com> <vdasa@vmware.com>
 Vivek Aknurwar <quic_viveka@quicinc.com> <viveka@codeaurora.org>
 Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 75381386fe4c38..793926018188f2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16733,9 +16733,9 @@ F:	include/uapi/linux/ppdev.h
 
 PARAVIRT_OPS INTERFACE
 M:	Juergen Gross <jgross@suse.com>
-R:	Ajay Kaher <akaher@vmware.com>
-R:	Alexey Makhalov <amakhalov@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+R:	Ajay Kaher <ajay.kaher@broadcom.com>
+R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
 S:	Supported
@@ -23654,9 +23654,9 @@ S:	Supported
 F:	drivers/misc/vmw_balloon.c
 
 VMWARE HYPERVISOR INTERFACE
-M:	Ajay Kaher <akaher@vmware.com>
-M:	Alexey Makhalov <amakhalov@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Ajay Kaher <ajay.kaher@broadcom.com>
+M:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
 S:	Supported
@@ -23665,33 +23665,34 @@ F:	arch/x86/include/asm/vmware.h
 F:	arch/x86/kernel/cpu/vmware.c
 
 VMWARE PVRDMA DRIVER
-M:	Bryan Tan <bryantan@vmware.com>
-M:	Vishnu Dasa <vdasa@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Bryan Tan <bryan-bt.tan@broadcom.com>
+M:	Vishnu Dasa <vishnu.dasa@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/vmw_pvrdma/
 
 VMWARE PVSCSI DRIVER
-M:	Vishal Bhakta <vbhakta@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Vishal Bhakta <vishal.bhakta@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/vmw_pvscsi.c
 F:	drivers/scsi/vmw_pvscsi.h
 
 VMWARE VIRTUAL PTP CLOCK DRIVER
-R:	Ajay Kaher <akaher@vmware.com>
-R:	Alexey Makhalov <amakhalov@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Nick Shi <nick.shi@broadcom.com>
+R:	Ajay Kaher <ajay.kaher@broadcom.com>
+R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/ptp/ptp_vmw.c
 
 VMWARE VMCI DRIVER
-M:	Bryan Tan <bryantan@vmware.com>
-M:	Vishnu Dasa <vdasa@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Bryan Tan <bryan-bt.tan@broadcom.com>
+M:	Vishnu Dasa <vishnu.dasa@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	drivers/misc/vmw_vmci/
@@ -23706,16 +23707,16 @@ F:	drivers/input/mouse/vmmouse.c
 F:	drivers/input/mouse/vmmouse.h
 
 VMWARE VMXNET3 ETHERNET DRIVER
-M:	Ronak Doshi <doshir@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Ronak Doshi <ronak.doshi@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/vmxnet3/
 
 VMWARE VSOCK VMCI TRANSPORT DRIVER
-M:	Bryan Tan <bryantan@vmware.com>
-M:	Vishnu Dasa <vdasa@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Bryan Tan <bryan-bt.tan@broadcom.com>
+M:	Vishnu Dasa <vishnu.dasa@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	net/vmw_vsock/vmci_transport*
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0d72183b5dd028..36b603d0cddefc 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+		pgprot_t *pgprot)
+{
+	unsigned long prot;
+
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+	/*
+	 * We need the starting PFN and cachemode used for track_pfn_remap()
+	 * that covered the whole VMA. For most mappings, we can obtain that
+	 * information from the page tables. For COW mappings, we might now
+	 * suddenly have anon folios mapped and follow_phys() will fail.
+	 *
+	 * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+	 * detect the PFN. If we need the cachemode as well, we're out of luck
+	 * for now and have to fail fork().
+	 */
+	if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+		if (pgprot)
+			*pgprot = __pgprot(prot);
+		return 0;
+	}
+	if (is_cow_mapping(vma->vm_flags)) {
+		if (pgprot)
+			return -EINVAL;
+		*paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
 /*
  * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
@@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 int track_pfn_copy(struct vm_area_struct *vma)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (vma->vm_flags & VM_PAT) {
-		/*
-		 * reserve the whole chunk covered by vma. We need the
-		 * starting address and protection from pte.
-		 */
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, &pgprot))
 			return -EINVAL;
-		}
-		pgprot = __pgprot(prot);
+		/* reserve the whole chunk covered by vma. */
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
@@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		 unsigned long size, bool mm_wr_locked)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 
 	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
@@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	/* free the chunk starting from pfn or the whole chunk */
 	paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	if (!paddr && !size) {
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, NULL))
 			return;
-		}
-
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
index 35f3a4a8ceb1e3..acf7e1a3f3def9 100644
--- a/include/linux/secretmem.h
+++ b/include/linux/secretmem.h
@@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio)
 	/*
 	 * Using folio_mapping() is quite slow because of the actual call
 	 * instruction.
-	 * We know that secretmem pages are not compound and LRU so we can
+	 * We know that secretmem pages are not compound, so we can
 	 * save a couple of cycles here.
 	 */
-	if (folio_test_large(folio) || !folio_test_lru(folio))
+	if (folio_test_large(folio))
 		return false;
 
 	mapping = (struct address_space *)
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 3c6caa5abc7c42..e9ec32fb97d4a7 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t;
 union handle_parts {
 	depot_stack_handle_t handle;
 	struct {
-		/* pool_index is offset by 1 */
-		u32 pool_index	: DEPOT_POOL_INDEX_BITS;
-		u32 offset	: DEPOT_OFFSET_BITS;
-		u32 extra	: STACK_DEPOT_EXTRA_BITS;
+		u32 pool_index_plus_1	: DEPOT_POOL_INDEX_BITS;
+		u32 offset		: DEPOT_OFFSET_BITS;
+		u32 extra		: STACK_DEPOT_EXTRA_BITS;
 	};
 };
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 3127e0bf7bbd15..a298a3854a8018 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -367,7 +367,7 @@ static int __init do_name(void)
 	if (S_ISREG(mode)) {
 		int ml = maybe_link();
 		if (ml >= 0) {
-			int openflags = O_WRONLY|O_CREAT;
+			int openflags = O_WRONLY|O_CREAT|O_LARGEFILE;
 			if (ml != 1)
 				openflags |= O_TRUNC;
 			wfile = filp_open(collected, openflags, mode);
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index af6cc19a200331..68c97387aa54e2 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -330,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
 	stack = current_pool + pool_offset;
 
 	/* Pre-initialize handle once. */
-	stack->handle.pool_index = pool_index + 1;
+	stack->handle.pool_index_plus_1 = pool_index + 1;
 	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
 	stack->handle.extra = 0;
 	INIT_LIST_HEAD(&stack->hash_list);
@@ -441,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 	const int pools_num_cached = READ_ONCE(pools_num);
 	union handle_parts parts = { .handle = handle };
 	void *pool;
-	u32 pool_index = parts.pool_index - 1;
+	u32 pool_index = parts.pool_index_plus_1 - 1;
 	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
 
diff --git a/mm/memory.c b/mm/memory.c
index 904f70b994985a..d2155ced45f8f8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5973,6 +5973,10 @@ int follow_phys(struct vm_area_struct *vma,
 		goto out;
 	pte = ptep_get(ptep);
 
+	/* Never return PFNs of anon folios in COW mappings. */
+	if (vm_normal_folio(vma, address, pte))
+		goto unlock;
+
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 22aa63f4ef6322..68fa001648cc1c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -989,6 +989,27 @@ unsigned long vmalloc_nr_pages(void)
 	return atomic_long_read(&nr_vmalloc_pages);
 }
 
+static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
+{
+	struct rb_node *n = root->rb_node;
+
+	addr = (unsigned long)kasan_reset_tag((void *)addr);
+
+	while (n) {
+		struct vmap_area *va;
+
+		va = rb_entry(n, struct vmap_area, rb_node);
+		if (addr < va->va_start)
+			n = n->rb_left;
+		else if (addr >= va->va_end)
+			n = n->rb_right;
+		else
+			return va;
+	}
+
+	return NULL;
+}
+
 /* Look up the first VA which satisfies addr < va_end, NULL if none. */
 static struct vmap_area *
 __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
@@ -1025,47 +1046,39 @@ __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
 static struct vmap_node *
 find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
 {
-	struct vmap_node *vn, *va_node = NULL;
-	struct vmap_area *va_lowest;
+	unsigned long va_start_lowest;
+	struct vmap_node *vn;
 	int i;
 
-	for (i = 0; i < nr_vmap_nodes; i++) {
+repeat:
+	for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) {
 		vn = &vmap_nodes[i];
 
 		spin_lock(&vn->busy.lock);
-		va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
-		if (va_lowest) {
-			if (!va_node || va_lowest->va_start < (*va)->va_start) {
-				if (va_node)
-					spin_unlock(&va_node->busy.lock);
-
-				*va = va_lowest;
-				va_node = vn;
-				continue;
-			}
-		}
+		*va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
+
+		if (*va)
+			if (!va_start_lowest || (*va)->va_start < va_start_lowest)
+				va_start_lowest = (*va)->va_start;
 		spin_unlock(&vn->busy.lock);
 	}
 
-	return va_node;
-}
-
-static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
-{
-	struct rb_node *n = root->rb_node;
+	/*
+	 * Check if found VA exists, it might have gone away.  In this case we
+	 * repeat the search because a VA has been removed concurrently and we
+	 * need to proceed to the next one, which is a rare case.
+	 */
+	if (va_start_lowest) {
+		vn = addr_to_node(va_start_lowest);
 
-	addr = (unsigned long)kasan_reset_tag((void *)addr);
+		spin_lock(&vn->busy.lock);
+		*va = __find_vmap_area(va_start_lowest, &vn->busy.root);
 
-	while (n) {
-		struct vmap_area *va;
+		if (*va)
+			return vn;
 
-		va = rb_entry(n, struct vmap_area, rb_node);
-		if (addr < va->va_start)
-			n = n->rb_left;
-		else if (addr >= va->va_end)
-			n = n->rb_right;
-		else
-			return va;
+		spin_unlock(&vn->busy.lock);
+		goto repeat;
 	}
 
 	return NULL;
@@ -2343,6 +2356,9 @@ struct vmap_area *find_vmap_area(unsigned long addr)
 	struct vmap_area *va;
 	int i, j;
 
+	if (unlikely(!vmap_initialized))
+		return NULL;
+
 	/*
 	 * An addr_to_node_id(addr) converts an address to a node index
 	 * where a VA is located. If VA spans several zones and passed
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index c02990bbd56f4c..9007c420d52c52 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -3,7 +3,7 @@
 #include <stdbool.h>
 #include <sys/mman.h>
 #include <err.h>
-#include <string.h> /* ffsl() */
+#include <strings.h> /* ffsl() */
 #include <unistd.h> /* _SC_PAGESIZE */
 
 #define BIT_ULL(nr)                   (1ULL << (nr))