Skip to contentSkip to conversation

fs/proc/kcore: avoid bounce buffer for ktext data

PATCH Superseded Lorenzo Stoakes 1 participant 4 messages Mar 20, 2023 1 message not in the archive

Subsystems (8)
Memory management VFS Library code Proc filesystem +4 more subsystems

v3 of 8 Superseded Latest is v8 →

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

Lorenzo Stoakes

author
#1 lore raw

PATCH v3 1/4 fs/proc/kcore: avoid bounce buffer for ktext data

Commit df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data") introduced the use of a bounce buffer to retrieve kernel text data for /proc/kcore in order to avoid failures arising from hardened user copies enabled by CONFIG_HARDENED_USERCOPY in check_kernel_text_object().

We can avoid doing this if instead of copy_to_user() we use _copy_to_user() which bypasses the hardening check. This is more efficient than using a bounce buffer and simplifies the code.

We do so as part an overall effort to eliminate bounce buffer usage in the function with an eye to converting it an iterator read.

Signed-off-by Lorenzo Stoakes <[email protected]>
Reviewed-by David Hildenbrand <[email protected]>
---
 fs/proc/kcore.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)
fs/proc/kcore.c +5 -12
index 71157ee35c1a..556f310d6aa4 100644
@@ -541,19 +541,12 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
 			/*
-			 * Using bounce buffer to bypass the
-			 * hardened user copy kernel text checks.
+			 * We use _copy_to_user() to bypass usermode hardening
+			 * which would otherwise prevent this operation.
 			 */
-			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
-				if (clear_user(buffer, tsz)) {
-					ret = -EFAULT;
-					goto out;
-				}
-			} else {
-				if (copy_to_user(buffer, buf, tsz)) {
-					ret = -EFAULT;
-					goto out;
-				}
+			if (_copy_to_user(buffer, (char *)start, tsz)) {
+				ret = -EFAULT;
+				goto out;
 			}
 			break;
 		default:
Signature · 1 line
2.39.2
author
#2 lore raw

PATCH v3 2/4 fs/proc/kcore: convert read_kcore() to read_kcore_iter()

In reply to a message not in the archive

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.

Signed-off-by Lorenzo Stoakes <[email protected]>
---
 fs/proc/kcore.c | 58 ++++++++++++++++++++++++-------------------------
 1 file changed, 29 insertions(+), 29 deletions(-)
fs/proc/kcore.c +29 -29
index 556f310d6aa4..25e0eeb8d498 100644
@@ -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 *notes, size_t *i, const char *name,
 }
 
 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 __user *buffer, size_t buflen, loff_t *fpos)
 	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 __user *buffer, size_t buflen, loff_t *fpos)
 	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 __user *buffer, size_t buflen, loff_t *fpos)
 			.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 __user *buffer, size_t buflen, loff_t *fpos)
 			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 __user *buffer, size_t buflen, loff_t *fpos)
 				  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 __user *buffer, size_t buflen, loff_t *fpos)
 		}
 
 		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 __user *buffer, size_t buflen, loff_t *fpos)
 		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 __user *buffer, size_t buflen, loff_t *fpos)
 			 */
 			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 __user *buffer, size_t buflen, loff_t *fpos)
 		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 *inode, struct file *file)
 }
 
 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,
Signature · 1 line
2.39.2
author
#3 lore raw

PATCH v3 3/4 iov_iter: add copy_page_to_iter_atomic()

In reply to a message not in the archive

Provide an atomic context equivalent for copy_page_to_iter(). This eschews the might_fault() check copies memory in the same way that copy_page_from_iter_atomic() does.

This functions assumes a non-compound page, however this mimics the existing behaviour of copy_page_from_iter_atomic(). I am keeping the behaviour consistent between the two, deferring any such change to an explicit folio-fication effort.

This is being added in order that an iteratable form of vread() can be implemented with known prefaulted pages to avoid the need for mutex locking.

Signed-off-by Lorenzo Stoakes <[email protected]>
---
 include/linux/uio.h |  2 ++
 lib/iov_iter.c      | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)
include/linux/uio.h +2 -0
index 27e3fd942960..fab07103090f 100644
@@ -154,6 +154,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
 
 size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
 				  size_t bytes, struct iov_iter *i);
+size_t copy_page_to_iter_atomic(struct page *page, unsigned offset,
+				size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
 size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
lib/iov_iter.c +28 -0
index 274014e4eafe..48ca1c5dfc04 100644
@@ -821,6 +821,34 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t byt
 }
 EXPORT_SYMBOL(copy_page_from_iter_atomic);
 
+size_t copy_page_to_iter_atomic(struct page *page, unsigned offset, size_t bytes,
+				struct iov_iter *i)
+{
+	char *kaddr = kmap_local_page(page);
+	char *p = kaddr + offset;
+	size_t copied = 0;
+
+	if (!page_copy_sane(page, offset, bytes) ||
+	    WARN_ON_ONCE(i->data_source))
+		goto out;
+
+	if (unlikely(iov_iter_is_pipe(i))) {
+		copied = copy_page_to_iter_pipe(page, offset, bytes, i);
+		goto out;
+	}
+
+	iterate_and_advance(i, bytes, base, len, off,
+		copyout(base, p + off, len),
+		memcpy(base, p + off, len)
+	)
+	copied = bytes;
+
+out:
+	kunmap_local(kaddr);
+	return copied;
+}
+EXPORT_SYMBOL(copy_page_to_iter_atomic);
+
 static void pipe_advance(struct iov_iter *i, size_t size)
 {
 	struct pipe_inode_info *pipe = i->pipe;
Signature · 1 line
2.39.2
author
#4 lore raw

PATCH v3 4/4 mm: vmalloc: convert vread() to vread_iter()

In reply to a message not in the archive

Having previously laid the foundation for converting vread() to an iterator function, pull the trigger and do so.

This patch attempts to provide minimal refactoring and to reflect the existing logic as best we can, for example we continue to zero portions of memory not read, as before.

Overall, there should be no functional difference other than a performance improvement in /proc/kcore access to vmalloc regions.

Now we have eliminated the need for a bounce buffer in read_kcore_iter(), we dispense with it. We need to ensure userland pages are faulted in before proceeding, as we take spin locks.

Additionally, we must account for the fact that at any point a copy may fail if this happens, we exit indicating fewer bytes retrieved than expected.

Signed-off-by Lorenzo Stoakes <[email protected]>
---
 fs/proc/kcore.c         |  26 ++---
 include/linux/vmalloc.h |   3 +-
 mm/nommu.c              |  10 +-
 mm/vmalloc.c            | 234 +++++++++++++++++++++++++---------------
 4 files changed, 160 insertions(+), 113 deletions(-)
fs/proc/kcore.c +7 -19
index 25e0eeb8d498..221e16f75ba5 100644
@@ -307,13 +307,9 @@ static void append_kcore_note(char *notes, size_t *i, const char *name,
 	*i = ALIGN(*i + descsz, 4);
 }
 
-static ssize_t
-read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t 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;

@@ -507,9 +503,12 @@ read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 		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_iter(buf, tsz, iter) != tsz) {
+			/*
+			 * Make sure user pages are faulted in as we acquire
+			 * spinlocks in vread_iter().
+			 */
+			if (fault_in_iov_iter_writeable(iter, tsz) ||
+			    vread_iter(iter, (char *)start, tsz) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}

@@ -582,10 +581,6 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!filp->private_data)
-		return -ENOMEM;
-
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {

@@ -596,16 +591,9 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int release_kcore(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
-	return 0;
-}
-
 static const struct proc_ops kcore_proc_ops = {
 	.proc_read_iter	= read_kcore_iter,
 	.proc_open	= open_kcore,
-	.proc_release	= release_kcore,
 	.proc_lseek	= default_llseek,
 };
include/linux/vmalloc.h +2 -1
index 69250efa03d1..461aa5637f65 100644
@@ -9,6 +9,7 @@
 #include <asm/page.h>		/* pgprot_t */
 #include <linux/rbtree.h>
 #include <linux/overflow.h>
+#include <linux/uio.h>
 
 #include <asm/vmalloc.h>
 

@@ -251,7 +252,7 @@ static inline void set_vm_flush_reset_perms(void *addr)
 #endif
 
 /* for /proc/kcore */
-extern long vread(char *buf, char *addr, unsigned long count);
+extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count);
 
 /*
  *	Internals.  Don't use..
mm/nommu.c +5 -5
index 57ba243c6a37..e0fcd948096e 100644
@@ -36,6 +36,7 @@
 #include <linux/printk.h>
 
 #include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>

@@ -198,14 +199,13 @@ unsigned long vmalloc_to_pfn(const void *addr)
 }
 EXPORT_SYMBOL(vmalloc_to_pfn);
 
-long vread(char *buf, char *addr, unsigned long count)
+long vread_iter(struct iov_iter *iter, char *addr, size_t count)
 {
 	/* Don't allow overflow */
-	if ((unsigned long) buf + count < count)
-		count = -(unsigned long) buf;
+	if ((unsigned long) addr + count < count)
+		count = -(unsigned long) addr;
 
-	memcpy(buf, addr, count);
-	return count;
+	return copy_to_iter(addr, count, iter);
 }
 
 /*
mm/vmalloc.c +146 -88

340 lines not on this page · raw message

Signature · 1 line
2.39.2