The patch titled
Subject: fs/proc/kcore: convert read_kcore() to read_kcore_iter()
has been added to the -mm mm-unstable branch. Its filename is
fs-proc-kcore-convert-read_kcore-to-read_kcore_iter.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/fs-proc-kcore-convert-read_kcore-to-read_kcore_iter.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Subject: fs/proc/kcore: convert read_kcore() to read_kcore_iter()
Date: Sun, 19 Mar 2023 07:09:32 +0000
Now we have eliminated spinlocks from the vread() case, convert
read_kcore() to read_kcore_iter().
For the time being we still use a bounce buffer for vread(), however in
the next patch we will convert this to interact directly with the iterator
and eliminate the bounce buffer altogether.
Link: https://lkml.kernel.org/r/32f8fad50500d0cd0927a66638c5890533725d30.1679209395.git.lstoakes@xxxxxxxxx
Signed-off-by: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Liu Shixin <liushixin2@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/fs/proc/kcore.c~fs-proc-kcore-convert-read_kcore-to-read_kcore_iter
+++ a/fs/proc/kcore.c
@@ -24,7 +24,7 @@
#include <linux/memblock.h>
#include <linux/init.h>
#include <linux/slab.h>
-#include <linux/uaccess.h>
+#include <linux/uio.h>
#include <asm/io.h>
#include <linux/list.h>
#include <linux/ioport.h>
@@ -308,9 +308,12 @@ static void append_kcore_note(char *note
}
static ssize_t
-read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
+read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
{
+ struct file *file = iocb->ki_filp;
char *buf = file->private_data;
+ loff_t *ppos = &iocb->ki_pos;
+
size_t phdrs_offset, notes_offset, data_offset;
size_t page_offline_frozen = 1;
size_t phdrs_len, notes_len;
@@ -318,6 +321,7 @@ read_kcore(struct file *file, char __use
size_t tsz;
int nphdr;
unsigned long start;
+ size_t buflen = iov_iter_count(iter);
size_t orig_buflen = buflen;
int ret = 0;
@@ -333,7 +337,7 @@ read_kcore(struct file *file, char __use
notes_offset = phdrs_offset + phdrs_len;
/* ELF file header. */
- if (buflen && *fpos < sizeof(struct elfhdr)) {
+ if (buflen && *ppos < sizeof(struct elfhdr)) {
struct elfhdr ehdr = {
.e_ident = {
[EI_MAG0] = ELFMAG0,
@@ -355,19 +359,18 @@ read_kcore(struct file *file, char __use
.e_phnum = nphdr,
};
- tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
- if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) {
+ tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *ppos);
+ if (copy_to_iter((char *)&ehdr + *ppos, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
- buffer += tsz;
buflen -= tsz;
- *fpos += tsz;
+ *ppos += tsz;
}
/* ELF program headers. */
- if (buflen && *fpos < phdrs_offset + phdrs_len) {
+ if (buflen && *ppos < phdrs_offset + phdrs_len) {
struct elf_phdr *phdrs, *phdr;
phdrs = kzalloc(phdrs_len, GFP_KERNEL);
@@ -397,22 +400,21 @@ read_kcore(struct file *file, char __use
phdr++;
}
- tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
- if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset,
- tsz)) {
+ tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *ppos);
+ if (copy_to_iter((char *)phdrs + *ppos - phdrs_offset, tsz,
+ iter) != tsz) {
kfree(phdrs);
ret = -EFAULT;
goto out;
}
kfree(phdrs);
- buffer += tsz;
buflen -= tsz;
- *fpos += tsz;
+ *ppos += tsz;
}
/* ELF note segment. */
- if (buflen && *fpos < notes_offset + notes_len) {
+ if (buflen && *ppos < notes_offset + notes_len) {
struct elf_prstatus prstatus = {};
struct elf_prpsinfo prpsinfo = {
.pr_sname = 'R',
@@ -447,24 +449,23 @@ read_kcore(struct file *file, char __use
vmcoreinfo_data,
min(vmcoreinfo_size, notes_len - i));
- tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
- if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) {
+ tsz = min_t(size_t, buflen, notes_offset + notes_len - *ppos);
+ if (copy_to_iter(notes + *ppos - notes_offset, tsz, iter) != tsz) {
kfree(notes);
ret = -EFAULT;
goto out;
}
kfree(notes);
- buffer += tsz;
buflen -= tsz;
- *fpos += tsz;
+ *ppos += tsz;
}
/*
* Check to see if our file offset matches with any of
* the addresses in the elf_phdr on our list.
*/
- start = kc_offset_to_vaddr(*fpos - data_offset);
+ start = kc_offset_to_vaddr(*ppos - data_offset);
if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
tsz = buflen;
@@ -497,7 +498,7 @@ read_kcore(struct file *file, char __use
}
if (!m) {
- if (clear_user(buffer, tsz)) {
+ if (iov_iter_zero(tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
@@ -508,14 +509,14 @@ read_kcore(struct file *file, char __use
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)) {
+ if (copy_to_iter(buf, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
break;
case KCORE_USER:
/* User page is handled prior to normal kernel page: */
- if (copy_to_user(buffer, (char *)start, tsz)) {
+ if (copy_to_iter((char *)start, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
@@ -531,7 +532,7 @@ read_kcore(struct file *file, char __use
*/
if (!page || PageOffline(page) ||
is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
- if (clear_user(buffer, tsz)) {
+ if (iov_iter_zero(tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
@@ -541,25 +542,24 @@ read_kcore(struct file *file, char __use
case KCORE_VMEMMAP:
case KCORE_TEXT:
/*
- * We use _copy_to_user() to bypass usermode hardening
+ * We use _copy_to_iter() to bypass usermode hardening
* which would otherwise prevent this operation.
*/
- if (_copy_to_user(buffer, (char *)start, tsz)) {
+ if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
break;
default:
pr_warn_once("Unhandled KCORE type: %d\n", m->type);
- if (clear_user(buffer, tsz)) {
+ if (iov_iter_zero(tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
}
skip:
buflen -= tsz;
- *fpos += tsz;
- buffer += tsz;
+ *ppos += tsz;
start += tsz;
tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
}
@@ -603,7 +603,7 @@ static int release_kcore(struct inode *i
}
static const struct proc_ops kcore_proc_ops = {
- .proc_read = read_kcore,
+ .proc_read_iter = read_kcore_iter,
.proc_open = open_kcore,
.proc_release = release_kcore,
.proc_lseek = default_llseek,
_
Patches currently in -mm which might be from lstoakes@xxxxxxxxx are
mm-remove-unused-vmf_insert_mixed_prot.patch
mm-remove-vmf_insert_pfn_xxx_prot-for-huge-page-table-entries.patch
drm-ttm-remove-comment-referencing-now-removed-vmf_insert_mixed_prot.patch
mm-prefer-xxx_page-alloc-free-functions-for-order-0-pages.patch
mm-refactor-do_fault_around.patch
mm-pefer-fault_around_pages-to-fault_around_bytes.patch
fs-proc-kcore-avoid-bounce-buffer-for-ktext-data.patch
mm-vmalloc-use-rwsem-mutex-for-vmap_area_lock-and-vmap_block-lock.patch
fs-proc-kcore-convert-read_kcore-to-read_kcore_iter.patch
mm-vmalloc-convert-vread-to-vread_iter.patch
