Revert "packet: switch kvzalloc to allocate memory"

This reverts commit 71e41286203c017d24f041a7cd71abea7ca7b1e0.

mmap()/munmap() can not be backed by kmalloced pages :

We fault in :

    VM_BUG_ON_PAGE(PageSlab(page), page);

    unmap_single_vma+0x8a/0x110
    unmap_vmas+0x4b/0x90
    unmap_region+0xc9/0x140
    do_munmap+0x274/0x360
    vm_munmap+0x81/0xc0
    SyS_munmap+0x2b/0x40
    do_syscall_64+0x13e/0x1c0
    entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 71e41286203c ("packet: switch kvzalloc to allocate memory")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: John Sperbeck <jsperbeck@google.com>
Bisected-by: John Sperbeck <jsperbeck@google.com>
Cc: Zhang Yu <zhangyu31@baidu.com>
Cc: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5610061e7f2e00b935ce44dd9cf82d10eb77a7bf..75c92a87e7b2481141161c8945f5e7eef8e0abf8 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4137,36 +4137,52 @@ static const struct vm_operations_struct packet_mmap_ops = {
        .close  =       packet_mm_close,
 };
 
-static void free_pg_vec(struct pgv *pg_vec, unsigned int len)
+static void free_pg_vec(struct pgv *pg_vec, unsigned int order,
+                       unsigned int len)
 {
        int i;
 
        for (i = 0; i < len; i++) {
                if (likely(pg_vec[i].buffer)) {
-                       kvfree(pg_vec[i].buffer);
+                       if (is_vmalloc_addr(pg_vec[i].buffer))
+                               vfree(pg_vec[i].buffer);
+                       else
+                               free_pages((unsigned long)pg_vec[i].buffer,
+                                          order);
                        pg_vec[i].buffer = NULL;
                }
        }
        kfree(pg_vec);
 }
 
-static char *alloc_one_pg_vec_page(unsigned long size)
+static char *alloc_one_pg_vec_page(unsigned long order)
 {
        char *buffer;
+       gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
+                         __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
 
-       buffer = kvzalloc(size, GFP_KERNEL);
+       buffer = (char *) __get_free_pages(gfp_flags, order);
        if (buffer)
                return buffer;
 
-       buffer = kvzalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+       /* __get_free_pages failed, fall back to vmalloc */
+       buffer = vzalloc(array_size((1 << order), PAGE_SIZE));
+       if (buffer)
+               return buffer;
 
-       return buffer;
+       /* vmalloc failed, lets dig into swap here */
+       gfp_flags &= ~__GFP_NORETRY;
+       buffer = (char *) __get_free_pages(gfp_flags, order);
+       if (buffer)
+               return buffer;
+
+       /* complete and utter failure */
+       return NULL;
 }
 
-static struct pgv *alloc_pg_vec(struct tpacket_req *req)
+static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 {
        unsigned int block_nr = req->tp_block_nr;
-       unsigned long size = req->tp_block_size;
        struct pgv *pg_vec;
        int i;
 
@@ -4175,7 +4191,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req)
                goto out;
 
        for (i = 0; i < block_nr; i++) {
-               pg_vec[i].buffer = alloc_one_pg_vec_page(size);
+               pg_vec[i].buffer = alloc_one_pg_vec_page(order);
                if (unlikely(!pg_vec[i].buffer))
                        goto out_free_pgvec;
        }
@@ -4184,7 +4200,7 @@ out:
        return pg_vec;
 
 out_free_pgvec:
-       free_pg_vec(pg_vec, block_nr);
+       free_pg_vec(pg_vec, order, block_nr);
        pg_vec = NULL;
        goto out;
 }
@@ -4194,9 +4210,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 {
        struct pgv *pg_vec = NULL;
        struct packet_sock *po = pkt_sk(sk);
+       int was_running, order = 0;
        struct packet_ring_buffer *rb;
        struct sk_buff_head *rb_queue;
-       int was_running;
        __be16 num;
        int err = -EINVAL;
        /* Added to avoid minimal code churn */
@@ -4258,7 +4274,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
                        goto out;
 
                err = -ENOMEM;
-               pg_vec = alloc_pg_vec(req);
+               order = get_order(req->tp_block_size);
+               pg_vec = alloc_pg_vec(req, order);
                if (unlikely(!pg_vec))
                        goto out;
                switch (po->tp_version) {
@@ -4312,6 +4329,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
                rb->frame_size = req->tp_frame_size;
                spin_unlock_bh(&rb_queue->lock);
 
+               swap(rb->pg_vec_order, order);
                swap(rb->pg_vec_len, req->tp_block_nr);
 
                rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
@@ -4337,7 +4355,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
        }
 
        if (pg_vec)
-               free_pg_vec(pg_vec, req->tp_block_nr);
+               free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
        return err;
 }

diff --git a/net/packet/internal.h b/net/packet/internal.h
index 8f50036f62f05c76632dea82491d6a60dba39f0f..3bb7c5fb3bff2fd5d91c3d973d006d0cdde29a0b 100644 (file)
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -64,6 +64,7 @@ struct packet_ring_buffer {
        unsigned int            frame_size;
        unsigned int            frame_max;
 
+       unsigned int            pg_vec_order;
        unsigned int            pg_vec_pages;
        unsigned int            pg_vec_len;