diff mbox series

[RFC] Make find_tcp_vma() more efficient

Message ID ZivhG0yrbpFqORDw@casper.infradead.org (mailing list archive)
State RFC
Delegated to: Netdev Maintainers
Headers show
Series [RFC] Make find_tcp_vma() more efficient | expand

Checks

Context Check Description
netdev/series_format warning Single patches do not need cover letters; Target tree name not specified in the subject
netdev/tree_selection success Guessed tree name to be net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 13928 this patch: 13928
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 5 maintainers not CCed: pabeni@redhat.com akpm@linux-foundation.org edumazet@google.com dsahern@kernel.org kuba@kernel.org
netdev/build_clang success Errors and warnings before: 1944 this patch: 1944
netdev/verify_signedoff fail author Signed-off-by missing
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 15037 this patch: 15037
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 87 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 7 this patch: 7
netdev/source_inline success Was 0 now: 0

Commit Message

Matthew Wilcox April 26, 2024, 5:15 p.m. UTC
Liam asked me if we could do away with the "bool *mmap_locked"
parameter, and the problem is that some architctures don't support
CONFIG_PER_VMA_LOCK yet.  But we can abstract it ... something like this
maybe?

(not particularly proposing this for inclusion; just wrote it and want
to get it out of my tree so I can get back to other projects.  If anyone
wants it, they can test it and submit it for inclusion and stick my
S-o-B on it)

Comments

Suren Baghdasaryan May 3, 2024, 10:29 p.m. UTC | #1
On Fri, Apr 26, 2024 at 10:15 AM Matthew Wilcox <willy@infradead.org> wrote:
>
> Liam asked me if we could do away with the "bool *mmap_locked"
> parameter, and the problem is that some architctures don't support
> CONFIG_PER_VMA_LOCK yet.  But we can abstract it ... something like this
> maybe?
>
> (not particularly proposing this for inclusion; just wrote it and want
> to get it out of my tree so I can get back to other projects.  If anyone
> wants it, they can test it and submit it for inclusion and stick my
> S-o-B on it)

I went through all uses of vma_end_read() to convince myself this is
safe with CONFIG_PER_VMA_LOCK=n and the change seems fine from
correctness POV. However the fact that in this configuration
lock_vma_under_mmap_lock()==NOP and vma_end_read()==mmap_read_unlock()
does not feel right to me. Current code is more explicit about which
lock is held and I think it's easier to understand.
A new interface like below might be a bit better but I'm not sure if
it's worth it:

#ifdef CONFIG_PER_VMA_LOCK
static inline void mmap_to_vma_lock(struct vm_area_struct *vma)
{
       down_read(&vma->vm_lock->lock);
       mmap_read_unlock(vma->vm_mm);
}

static inline void mmap_or_vma_unlock(struct vm_area_struct *vma)
{
       vma_end_read(vma);
}

#else /* CONFIG_PER_VMA_LOCK */

static inline void mmap_to_vma_lock(struct vm_area_struct *vma) {}
static inline void mmap_or_vma_unlock(struct vm_area_struct *vma)
{
       mmap_read_unlock(vma->vm_mm);
}
#endif /* CONFIG_PER_VMA_LOCK */

>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 9849dfda44d4..570763351508 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -779,11 +779,22 @@ static inline void assert_fault_locked(struct vm_fault *vmf)
>  struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
>                                           unsigned long address);
>
> +static inline void lock_vma_under_mmap_lock(struct vm_area_struct *vma)
> +{
> +       down_read(&vma->vm_lock->lock);
> +       mmap_read_unlock(vma->vm_mm);
> +}
> +
>  #else /* CONFIG_PER_VMA_LOCK */
>
>  static inline bool vma_start_read(struct vm_area_struct *vma)
>                 { return false; }
> -static inline void vma_end_read(struct vm_area_struct *vma) {}
> +static inline void vma_end_read(struct vm_area_struct *vma)
> +{
> +       mmap_read_unlock(vma->vm_mm);
> +}
> +
> +static inline void lock_vma_under_mmap_lock(struct vm_area_struct *vma) {}
>  static inline void vma_start_write(struct vm_area_struct *vma) {}
>  static inline void vma_assert_write_locked(struct vm_area_struct *vma)
>                 { mmap_assert_write_locked(vma->vm_mm); }
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index f23b97777ea5..e763916e5185 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -2051,27 +2051,25 @@ static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
>  }
>
>  static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
> -                                          unsigned long address,
> -                                          bool *mmap_locked)
> +                                          unsigned long address)
>  {
>         struct vm_area_struct *vma = lock_vma_under_rcu(mm, address);
>
> -       if (vma) {
> -               if (vma->vm_ops != &tcp_vm_ops) {
> -                       vma_end_read(vma);
> +       if (!vma) {
> +               mmap_read_lock(mm);
> +               vma = vma_lookup(mm, address);
> +               if (vma) {
> +                       lock_vma_under_mmap_lock(vma);
> +               } else {
> +                       mmap_read_unlock(mm);
>                         return NULL;
>                 }
> -               *mmap_locked = false;
> -               return vma;
>         }
> -
> -       mmap_read_lock(mm);
> -       vma = vma_lookup(mm, address);
> -       if (!vma || vma->vm_ops != &tcp_vm_ops) {
> -               mmap_read_unlock(mm);
> +       if (vma->vm_ops != &tcp_vm_ops) {
> +               vma_end_read(vma);
>                 return NULL;
>         }
> -       *mmap_locked = true;
> +
>         return vma;
>  }
>
> @@ -2092,7 +2090,6 @@ static int tcp_zerocopy_receive(struct sock *sk,
>         u32 seq = tp->copied_seq;
>         u32 total_bytes_to_map;
>         int inq = tcp_inq(sk);
> -       bool mmap_locked;
>         int ret;
>
>         zc->copybuf_len = 0;
> @@ -2117,7 +2114,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
>                 return 0;
>         }
>
> -       vma = find_tcp_vma(current->mm, address, &mmap_locked);
> +       vma = find_tcp_vma(current->mm, address);
>         if (!vma)
>                 return -EINVAL;
>
> @@ -2194,10 +2191,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
>                                                    zc, total_bytes_to_map);
>         }
>  out:
> -       if (mmap_locked)
> -               mmap_read_unlock(current->mm);
> -       else
> -               vma_end_read(vma);
> +       vma_end_read(vma);
>         /* Try to copy straggler data. */
>         if (!ret)
>                 copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss);
Liam R. Howlett May 14, 2024, 10:12 p.m. UTC | #2
* Suren Baghdasaryan <surenb@google.com> [240503 18:29]:
> On Fri, Apr 26, 2024 at 10:15 AM Matthew Wilcox <willy@infradead.org> wrote:
> >
> > Liam asked me if we could do away with the "bool *mmap_locked"
> > parameter, and the problem is that some architctures don't support
> > CONFIG_PER_VMA_LOCK yet.  But we can abstract it ... something like this
> > maybe?
> >
> > (not particularly proposing this for inclusion; just wrote it and want
> > to get it out of my tree so I can get back to other projects.  If anyone
> > wants it, they can test it and submit it for inclusion and stick my
> > S-o-B on it)
> 
> I went through all uses of vma_end_read() to convince myself this is
> safe with CONFIG_PER_VMA_LOCK=n and the change seems fine from
> correctness POV. However the fact that in this configuration
> lock_vma_under_mmap_lock()==NOP and vma_end_read()==mmap_read_unlock()
> does not feel right to me. Current code is more explicit about which
> lock is held and I think it's easier to understand.
> A new interface like below might be a bit better but I'm not sure if
> it's worth it:
> 
...

We could do something like we do in the release_fault_lock(), but
without using the FAULT flag..

/* Naming is hard. */
static inline void release_vma_modification_lock(
		struct vm_area_struct *vma)
{                                                                                                                                      
#ifdef CONFIG_PER_VMA_LOCK
        if (rwsem_is_locked(&vma->vm_lock->lock))
                vma_end_read(vma);                                                                                                
        else                                                                                                                           
                mmap_read_unlock(vma->vm_mm);                                                                                     
#else
        mmap_read_unlock(vma->vm_mm);                                                                                     
#endif
}
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9849dfda44d4..570763351508 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -779,11 +779,22 @@  static inline void assert_fault_locked(struct vm_fault *vmf)
 struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 					  unsigned long address);
 
+static inline void lock_vma_under_mmap_lock(struct vm_area_struct *vma)
+{
+	down_read(&vma->vm_lock->lock);
+	mmap_read_unlock(vma->vm_mm);
+}
+
 #else /* CONFIG_PER_VMA_LOCK */
 
 static inline bool vma_start_read(struct vm_area_struct *vma)
 		{ return false; }
-static inline void vma_end_read(struct vm_area_struct *vma) {}
+static inline void vma_end_read(struct vm_area_struct *vma)
+{
+	mmap_read_unlock(vma->vm_mm);
+}
+
+static inline void lock_vma_under_mmap_lock(struct vm_area_struct *vma) {}
 static inline void vma_start_write(struct vm_area_struct *vma) {}
 static inline void vma_assert_write_locked(struct vm_area_struct *vma)
 		{ mmap_assert_write_locked(vma->vm_mm); }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f23b97777ea5..e763916e5185 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2051,27 +2051,25 @@  static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
 }
 
 static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
-					   unsigned long address,
-					   bool *mmap_locked)
+					   unsigned long address)
 {
 	struct vm_area_struct *vma = lock_vma_under_rcu(mm, address);
 
-	if (vma) {
-		if (vma->vm_ops != &tcp_vm_ops) {
-			vma_end_read(vma);
+	if (!vma) {
+		mmap_read_lock(mm);
+		vma = vma_lookup(mm, address);
+		if (vma) {
+			lock_vma_under_mmap_lock(vma);
+		} else {
+			mmap_read_unlock(mm);
 			return NULL;
 		}
-		*mmap_locked = false;
-		return vma;
 	}
-
-	mmap_read_lock(mm);
-	vma = vma_lookup(mm, address);
-	if (!vma || vma->vm_ops != &tcp_vm_ops) {
-		mmap_read_unlock(mm);
+	if (vma->vm_ops != &tcp_vm_ops) {
+		vma_end_read(vma);
 		return NULL;
 	}
-	*mmap_locked = true;
+
 	return vma;
 }
 
@@ -2092,7 +2090,6 @@  static int tcp_zerocopy_receive(struct sock *sk,
 	u32 seq = tp->copied_seq;
 	u32 total_bytes_to_map;
 	int inq = tcp_inq(sk);
-	bool mmap_locked;
 	int ret;
 
 	zc->copybuf_len = 0;
@@ -2117,7 +2114,7 @@  static int tcp_zerocopy_receive(struct sock *sk,
 		return 0;
 	}
 
-	vma = find_tcp_vma(current->mm, address, &mmap_locked);
+	vma = find_tcp_vma(current->mm, address);
 	if (!vma)
 		return -EINVAL;
 
@@ -2194,10 +2191,7 @@  static int tcp_zerocopy_receive(struct sock *sk,
 						   zc, total_bytes_to_map);
 	}
 out:
-	if (mmap_locked)
-		mmap_read_unlock(current->mm);
-	else
-		vma_end_read(vma);
+	vma_end_read(vma);
 	/* Try to copy straggler data. */
 	if (!ret)
 		copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss);