Re: [PATCH v4 2/4] fs/proc/kcore: convert read_kcore() to read_kcore_iter()

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Mar 22, 2023 at 09:15:48AM +0800, Baoquan He wrote:
> Hi Lorenzo,
>
> On 03/21/23 at 08:54pm, Lorenzo Stoakes wrote:
> > Now we have eliminated spinlocks from the vread() case, convert
> > read_kcore() to read_kcore_iter().
>
> Sorry for late comment.
>
> Here I could miss something important, I don't get where we have
> eliminated spinlocks from the vread() case. Do I misunderstand this
> sentence?
>

Apologies, I didn't update the commit message after the latest revision! We
can just drop this sentence altogether.

Andrew - could you change the commit message to simply read:-

  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.

Thanks!

> >
> > 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 <lstoakes@xxxxxxxxx>
> > ---
> >  fs/proc/kcore.c | 58 ++++++++++++++++++++++++-------------------------
> >  1 file changed, 29 insertions(+), 29 deletions(-)
> >
> > diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
> > index 556f310d6aa4..25e0eeb8d498 100644
> > --- a/fs/proc/kcore.c
> > +++ b/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 *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,
> > --
> > 2.39.2
> >
>



[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux