mm: allow per-VMA locks on file-backed VMAs

Remove the TCP layering violation by allowing per-VMA locks on all VMAs.
The fault path will immediately fail in handle_mm_fault().  There may be a
small performance reduction from this patch as a little unnecessary work
will be done on each page fault.  See later patches for the improvement.

Link: https://lkml.kernel.org/r/20230724185410.1124082-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/MAINTAINERS b/MAINTAINERS
index 53b7ca8044659f9bb6ffa44ce4a61f09b73c84d5..9e4cfcd7998a01e02e95c7f35fc90b9d00ae6e86 100644 (file)
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14829,7 +14829,6 @@ NETWORKING [TCP]
 M:     Eric Dumazet <edumazet@google.com>
 L:     netdev@vger.kernel.org
 S:     Maintained
-F:     include/linux/net_mm.h
 F:     include/linux/tcp.h
 F:     include/net/tcp.h
 F:     include/trace/events/tcp.h

diff --git a/include/linux/net_mm.h b/include/linux/net_mm.h
deleted file mode 100644 (file)
index b298998..0000000
--- a/include/linux/net_mm.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifdef CONFIG_MMU
-
-#ifdef CONFIG_INET
-extern const struct vm_operations_struct tcp_vm_ops;
-static inline bool vma_is_tcp(const struct vm_area_struct *vma)
-{
-       return vma->vm_ops == &tcp_vm_ops;
-}
-#else
-static inline bool vma_is_tcp(const struct vm_area_struct *vma)
-{
-       return false;
-}
-#endif /* CONFIG_INET*/
-
-#endif /* CONFIG_MMU */

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0ca972ebd3dd0f2f2a342a4feedaa2131fe05d79..3a818fe1a8a513922f988ef92ad764cb9fdcc4d6 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -45,7 +45,6 @@
 #include <linux/memcontrol.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/siphash.h>
-#include <linux/net_mm.h>
 
 extern struct inet_hashinfo tcp_hashinfo;
 

diff --git a/mm/memory.c b/mm/memory.c
index ed4807deec893bbcb1797fbb241067ac5cccaa30..b2b17c66f87a6bfdfb968a659137f803c6d6a5f1 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -77,7 +77,6 @@
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/sysctl.h>
-#include <linux/net_mm.h>
 
 #include <trace/events/kmem.h>
 
@@ -5223,6 +5222,11 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
                goto out;
        }
 
+       if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma)) {
+               vma_end_read(vma);
+               return VM_FAULT_RETRY;
+       }
+
        /*
         * Enable the memcg OOM handling for faults triggered in user
         * space.  Kernel faults are handled more gracefully.
@@ -5394,10 +5398,6 @@ retry:
        if (!vma)
                goto inval;
 
-       /* Only anonymous and tcp vmas are supported for now */
-       if (!vma_is_anonymous(vma) && !vma_is_tcp(vma))
-               goto inval;
-
        if (!vma_start_read(vma))
                goto inval;
 

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8ed52e1e3c99a334a47964d8fd05c720a8f683f9..b9d49803e77f031481c4555c8e85bbab3aa7e49b 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1739,7 +1739,7 @@ void tcp_update_recv_tstamps(struct sk_buff *skb,
 }
 
 #ifdef CONFIG_MMU
-const struct vm_operations_struct tcp_vm_ops = {
+static const struct vm_operations_struct tcp_vm_ops = {
 };
 
 int tcp_mmap(struct file *file, struct socket *sock,
@@ -2042,13 +2042,10 @@ static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
                                           unsigned long address,
                                           bool *mmap_locked)
 {
-       struct vm_area_struct *vma = NULL;
+       struct vm_area_struct *vma = lock_vma_under_rcu(mm, address);
 
-#ifdef CONFIG_PER_VMA_LOCK
-       vma = lock_vma_under_rcu(mm, address);
-#endif
        if (vma) {
-               if (!vma_is_tcp(vma)) {
+               if (vma->vm_ops != &tcp_vm_ops) {
                        vma_end_read(vma);
                        return NULL;
                }
@@ -2058,7 +2055,7 @@ static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
 
        mmap_read_lock(mm);
        vma = vma_lookup(mm, address);
-       if (!vma || !vma_is_tcp(vma)) {
+       if (!vma || vma->vm_ops != &tcp_vm_ops) {
                mmap_read_unlock(mm);
                return NULL;
        }