summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig15
-rw-r--r--fs/exec.c3
-rw-r--r--fs/hfsplus/inode.c5
-rw-r--r--fs/hfsplus/xattr.c1
-rw-r--r--fs/nfsd/nfs4state.c2
-rw-r--r--fs/nilfs2/btree.c1
-rw-r--r--fs/open.c13
-rw-r--r--fs/proc/base.c6
-rw-r--r--fs/proc/fd.c20
-rw-r--r--fs/proc/kcore.c67
-rw-r--r--fs/proc/task_mmu.c34
-rw-r--r--fs/seq_file.c43
-rw-r--r--fs/userfaultfd.c15
13 files changed, 161 insertions, 64 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 141a856c50e7..a7749c126b8e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -240,6 +240,21 @@ config HUGETLBFS
config HUGETLB_PAGE
def_bool HUGETLBFS
+config HUGETLB_PAGE_FREE_VMEMMAP
+ def_bool HUGETLB_PAGE
+ depends on X86_64
+ depends on SPARSEMEM_VMEMMAP
+
+config HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON
+ bool "Default freeing vmemmap pages of HugeTLB to on"
+ default n
+ depends on HUGETLB_PAGE_FREE_VMEMMAP
+ help
+ When using HUGETLB_PAGE_FREE_VMEMMAP, the freeing unused vmemmap
+ pages associated with each HugeTLB page is default off. Say Y here
+ to enable freeing vmemmap pages of HugeTLB by default. It can then
+ be disabled on the command line via hugetlb_free_vmemmap=off.
+
config MEMFD_CREATE
def_bool TMPFS || HUGETLBFS
diff --git a/fs/exec.c b/fs/exec.c
index f2bcdbeb3afb..38f63451b928 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -84,9 +84,6 @@ static DEFINE_RWLOCK(binfmt_lock);
void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
- BUG_ON(!fmt);
- if (WARN_ON(!fmt->load_binary))
- return;
write_lock(&binfmt_lock);
insert ? list_add(&fmt->lh, &formats) :
list_add_tail(&fmt->lh, &formats);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 70e8374ddac4..6fef67c2a9f0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -281,6 +281,11 @@ int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path,
struct inode *inode = d_inode(path->dentry);
struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ if (request_mask & STATX_BTIME) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime = hfsp_mt2ut(hip->create_date);
+ }
+
if (inode->i_flags & S_APPEND)
stat->attributes |= STATX_ATTR_APPEND;
if (inode->i_flags & S_IMMUTABLE)
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 4d169c5a2673..e2855ceefd39 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -204,7 +204,6 @@ check_attr_tree_state_again:
buf = kzalloc(node_size, GFP_NOFS);
if (!buf) {
- pr_err("failed to allocate memory for header node\n");
err = -ENOMEM;
goto end_attr_file_creation;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b517a8794400..cd5eac2ba054 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2351,7 +2351,7 @@ static struct nfs4_client *get_nfsdfs_clp(struct inode *inode)
static void seq_quote_mem(struct seq_file *m, char *data, int len)
{
seq_printf(m, "\"");
- seq_escape_mem_ascii(m, data, len);
+ seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\");
seq_printf(m, "\"");
}
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index f42ab57201e7..ab9ec073330f 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -738,7 +738,6 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree,
if (ptr2 != ptr + cnt || ++cnt == maxblocks)
goto end;
index++;
- continue;
}
if (level == maxlevel)
break;
diff --git a/fs/open.c b/fs/open.c
index 53bc0573c0ec..1a325b3194df 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -852,8 +852,17 @@ static int do_dentry_open(struct file *f,
* XXX: Huge page cache doesn't support writing yet. Drop all page
* cache for this file before processing writes.
*/
- if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping))
- truncate_pagecache(inode, 0);
+ if (f->f_mode & FMODE_WRITE) {
+ /*
+ * Paired with smp_mb() in collapse_file() to ensure nr_thps
+ * is up to date and the update to i_writecount by
+ * get_write_access() is visible. Ensures subsequent insertion
+ * of THPs into the page cache will fail.
+ */
+ smp_mb();
+ if (filemap_nr_thps(inode->i_mapping))
+ truncate_pagecache(inode, 0);
+ }
return 0;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9cbd915025ad..e5b5f7709d48 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -854,7 +854,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
flags = FOLL_FORCE | (write ? FOLL_WRITE : 0);
while (count > 0) {
- int this_len = min_t(int, count, PAGE_SIZE);
+ size_t this_len = min_t(size_t, count, PAGE_SIZE);
if (write && copy_from_user(page, buf, this_len)) {
copied = -EFAULT;
@@ -3172,7 +3172,7 @@ static const struct pid_entry tgid_base_stuff[] = {
DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
- DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+ DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations),
DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
#ifdef CONFIG_NET
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
@@ -3517,7 +3517,7 @@ static const struct inode_operations proc_tid_comm_inode_operations = {
*/
static const struct pid_entry tid_base_stuff[] = {
DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
- DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+ DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations),
DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
#ifdef CONFIG_NET
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 07fc4fad2602..172c86270b31 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -6,6 +6,7 @@
#include <linux/fdtable.h>
#include <linux/namei.h>
#include <linux/pid.h>
+#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/file.h>
#include <linux/seq_file.h>
@@ -53,9 +54,10 @@ static int seq_show(struct seq_file *m, void *v)
if (ret)
return ret;
- seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
+ seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%lu\n",
(long long)file->f_pos, f_flags,
- real_mount(file->f_path.mnt)->mnt_id);
+ real_mount(file->f_path.mnt)->mnt_id,
+ file_inode(file)->i_ino);
/* show_fd_locks() never deferences files so a stale value is safe */
show_fd_locks(m, file, files);
@@ -72,6 +74,18 @@ out:
static int seq_fdinfo_open(struct inode *inode, struct file *file)
{
+ bool allowed = false;
+ struct task_struct *task = get_proc_task(inode);
+
+ if (!task)
+ return -ESRCH;
+
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+ put_task_struct(task);
+
+ if (!allowed)
+ return -EACCES;
+
return single_open(file, seq_show, inode);
}
@@ -308,7 +322,7 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
struct proc_inode *ei;
struct inode *inode;
- inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR);
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO);
if (!inode)
return ERR_PTR(-ENOENT);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 4d2e64e9016c..982e694aae77 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -313,6 +313,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
{
char *buf = file->private_data;
size_t phdrs_offset, notes_offset, data_offset;
+ size_t page_offline_frozen = 1;
size_t phdrs_len, notes_len;
struct kcore_list *m;
size_t tsz;
@@ -322,6 +323,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
int ret = 0;
down_read(&kclist_lock);
+ /*
+ * Don't race against drivers that set PageOffline() and expect no
+ * further page access.
+ */
+ page_offline_freeze();
get_kcore_size(&nphdr, &phdrs_len, &notes_len, &data_offset);
phdrs_offset = sizeof(struct elfhdr);
@@ -380,11 +386,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R | PF_W | PF_X;
phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
- if (m->type == KCORE_REMAP)
- phdr->p_vaddr = (size_t)m->vaddr;
- else
- phdr->p_vaddr = (size_t)m->addr;
- if (m->type == KCORE_RAM || m->type == KCORE_REMAP)
+ phdr->p_vaddr = (size_t)m->addr;
+ if (m->type == KCORE_RAM)
phdr->p_paddr = __pa(m->addr);
else if (m->type == KCORE_TEXT)
phdr->p_paddr = __pa_symbol(m->addr);
@@ -468,6 +471,9 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
m = NULL;
while (buflen) {
+ struct page *page;
+ unsigned long pfn;
+
/*
* If this is the first iteration or the address is not within
* the previous entry, search for a matching entry.
@@ -480,31 +486,57 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
}
}
+ if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) {
+ page_offline_thaw();
+ cond_resched();
+ page_offline_freeze();
+ }
+
if (&m->list == &kclist_head) {
if (clear_user(buffer, tsz)) {
ret = -EFAULT;
goto out;
}
m = NULL; /* skip the list anchor */
- } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) {
- if (clear_user(buffer, tsz)) {
- ret = -EFAULT;
- goto out;
- }
- } else if (m->type == KCORE_VMALLOC) {
+ goto skip;
+ }
+
+ switch (m->type) {
+ case KCORE_VMALLOC:
vread(buf, (char *)start, tsz);
/* we have to zero-fill user buffer even if no read */
if (copy_to_user(buffer, buf, tsz)) {
ret = -EFAULT;
goto out;
}
- } else if (m->type == KCORE_USER) {
+ break;
+ case KCORE_USER:
/* User page is handled prior to normal kernel page: */
if (copy_to_user(buffer, (char *)start, tsz)) {
ret = -EFAULT;
goto out;
}
- } else {
+ break;
+ case KCORE_RAM:
+ pfn = __pa(start) >> PAGE_SHIFT;
+ page = pfn_to_online_page(pfn);
+
+ /*
+ * Don't read offline sections, logically offline pages
+ * (e.g., inflated in a balloon), hwpoisoned pages,
+ * and explicitly excluded physical ranges.
+ */
+ if (!page || PageOffline(page) ||
+ is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
+ if (clear_user(buffer, tsz)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ break;
+ }
+ fallthrough;
+ case KCORE_VMEMMAP:
+ case KCORE_TEXT:
if (kern_addr_valid(start)) {
/*
* Using bounce buffer to bypass the
@@ -528,7 +560,15 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
goto out;
}
}
+ break;
+ default:
+ pr_warn_once("Unhandled KCORE type: %d\n", m->type);
+ if (clear_user(buffer, tsz)) {
+ ret = -EFAULT;
+ goto out;
+ }
}
+skip:
buflen -= tsz;
*fpos += tsz;
buffer += tsz;
@@ -537,6 +577,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
}
out:
+ page_offline_thaw();
up_read(&kclist_lock);
if (ret)
return ret;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 66965ad88d8b..eb97468dfe4c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -514,10 +514,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
} else {
mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
}
- } else if (is_migration_entry(swpent))
- page = migration_entry_to_page(swpent);
- else if (is_device_private_entry(swpent))
- page = device_private_entry_to_page(swpent);
+ } else if (is_pfn_swap_entry(swpent))
+ page = pfn_swap_entry_to_page(swpent);
} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
&& pte_none(*pte))) {
page = xa_load(&vma->vm_file->f_mapping->i_pages,
@@ -549,7 +547,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
swp_entry_t entry = pmd_to_swp_entry(*pmd);
if (is_migration_entry(entry))
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
}
if (IS_ERR_OR_NULL(page))
return;
@@ -694,10 +692,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
} else if (is_swap_pte(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
- if (is_migration_entry(swpent))
- page = migration_entry_to_page(swpent);
- else if (is_device_private_entry(swpent))
- page = device_private_entry_to_page(swpent);
+ if (is_pfn_swap_entry(swpent))
+ page = pfn_swap_entry_to_page(swpent);
}
if (page) {
int mapcount = page_mapcount(page);
@@ -832,7 +828,7 @@ static int show_smap(struct seq_file *m, void *v)
__show_smap(m, &mss, false);
seq_printf(m, "THPeligible: %d\n",
- transparent_hugepage_enabled(vma));
+ transparent_hugepage_active(vma));
if (arch_pkeys_enabled())
seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma));
@@ -1302,6 +1298,7 @@ struct pagemapread {
#define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
#define PM_SOFT_DIRTY BIT_ULL(55)
#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
+#define PM_UFFD_WP BIT_ULL(57)
#define PM_FILE BIT_ULL(61)
#define PM_SWAP BIT_ULL(62)
#define PM_PRESENT BIT_ULL(63)
@@ -1375,20 +1372,21 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
page = vm_normal_page(vma, addr, pte);
if (pte_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
+ if (pte_uffd_wp(pte))
+ flags |= PM_UFFD_WP;
} else if (is_swap_pte(pte)) {
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
+ if (pte_swp_uffd_wp(pte))
+ flags |= PM_UFFD_WP;
entry = pte_to_swp_entry(pte);
if (pm->show_pfn)
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags |= PM_SWAP;
- if (is_migration_entry(entry))
- page = migration_entry_to_page(entry);
-
- if (is_device_private_entry(entry))
- page = device_private_entry_to_page(entry);
+ if (is_pfn_swap_entry(entry))
+ page = pfn_swap_entry_to_page(entry);
}
if (page && !PageAnon(page))
@@ -1426,6 +1424,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
flags |= PM_PRESENT;
if (pmd_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
+ if (pmd_uffd_wp(pmd))
+ flags |= PM_UFFD_WP;
if (pm->show_pfn)
frame = pmd_pfn(pmd) +
((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1444,8 +1444,10 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
flags |= PM_SWAP;
if (pmd_swp_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
+ if (pmd_swp_uffd_wp(pmd))
+ flags |= PM_UFFD_WP;
VM_BUG_ON(!is_pmd_migration_entry(pmd));
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
}
#endif
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 5059248f2d64..b117b212ef28 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -356,6 +356,31 @@ int seq_release(struct inode *inode, struct file *file)
EXPORT_SYMBOL(seq_release);
/**
+ * seq_escape_mem - print data into buffer, escaping some characters
+ * @m: target buffer
+ * @src: source buffer
+ * @len: size of source buffer
+ * @flags: flags to pass to string_escape_mem()
+ * @esc: set of characters that need escaping
+ *
+ * Puts data into buffer, replacing each occurrence of character from
+ * given class (defined by @flags and @esc) with printable escaped sequence.
+ *
+ * Use seq_has_overflowed() to check for errors.
+ */
+void seq_escape_mem(struct seq_file *m, const char *src, size_t len,
+ unsigned int flags, const char *esc)
+{
+ char *buf;
+ size_t size = seq_get_buf(m, &buf);
+ int ret;
+
+ ret = string_escape_mem(src, len, buf, size, flags, esc);
+ seq_commit(m, ret < size ? ret : -1);
+}
+EXPORT_SYMBOL(seq_escape_mem);
+
+/**
* seq_escape - print string into buffer, escaping some characters
* @m: target buffer
* @s: string
@@ -367,26 +392,10 @@ EXPORT_SYMBOL(seq_release);
*/
void seq_escape(struct seq_file *m, const char *s, const char *esc)
{
- char *buf;
- size_t size = seq_get_buf(m, &buf);
- int ret;
-
- ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc);
- seq_commit(m, ret < size ? ret : -1);
+ seq_escape_str(m, s, ESCAPE_OCTAL, esc);
}
EXPORT_SYMBOL(seq_escape);
-void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz)
-{
- char *buf;
- size_t size = seq_get_buf(m, &buf);
- int ret;
-
- ret = string_escape_mem_ascii(src, isz, buf, size);
- seq_commit(m, ret < size ? ret : -1);
-}
-EXPORT_SYMBOL(seq_escape_mem_ascii);
-
void seq_vprintf(struct seq_file *m, const char *f, va_list args)
{
int len;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index dd7a6c62b56f..f6e0f0c0d0e5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1267,8 +1267,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
}
if (vm_flags & VM_UFFD_MINOR) {
- /* FIXME: Add minor fault interception for shmem. */
- if (!is_vm_hugetlb_page(vma))
+ if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
return false;
}
@@ -1304,8 +1303,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
+ if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+ goto out;
+#endif
vm_flags |= VM_UFFD_WP;
+ }
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
goto out;
@@ -1941,7 +1944,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
- uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+ uffdio_api.features &=
+ ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
+#endif
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+ uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
#endif
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-02 02:36:18 +0300