packet: Enhance AF_PACKET implementation to not require high order contiguous memory...

[net-next-2.6.git] / net / packet / af_packet.c

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8298e676f5a015f58d1b6005cf85938f8c8e142a..20964560a0ed49834dc9975a57457a442be39171 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -61,6 +61,7 @@
 #include <linux/kernel.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/protocol.h>
@@ -163,8 +164,14 @@ struct packet_mreq_max {
 static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
                int closing, int tx_ring);
 
+#define PGV_FROM_VMALLOC 1
+struct pgv {
+       char *buffer;
+       unsigned char flags;
+};
+
 struct packet_ring_buffer {
-       char                    **pg_vec;
+       struct pgv              *pg_vec;
        unsigned int            head;
        unsigned int            frames_per_block;
        unsigned int            frame_size;
@@ -283,7 +290,8 @@ static void *packet_lookup_frame(struct packet_sock *po,
        pg_vec_pos = position / rb->frames_per_block;
        frame_offset = position % rb->frames_per_block;
 
-       h.raw = rb->pg_vec[pg_vec_pos] + (frame_offset * rb->frame_size);
+       h.raw = rb->pg_vec[pg_vec_pos].buffer +
+               (frame_offset * rb->frame_size);
 
        if (status != __packet_get_status(po, h.raw))
                return NULL;
@@ -2325,37 +2333,74 @@ static const struct vm_operations_struct packet_mmap_ops = {
        .close  =       packet_mm_close,
 };
 
-static void free_pg_vec(char **pg_vec, unsigned int order, 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]))
-                       free_pages((unsigned long) pg_vec[i], order);
+               if (likely(pg_vec[i].buffer)) {
+                       if (pg_vec[i].flags & PGV_FROM_VMALLOC)
+                               vfree(pg_vec[i].buffer);
+                       else
+                               free_pages((unsigned long)pg_vec[i].buffer,
+                                          order);
+                       pg_vec[i].buffer = NULL;
+               }
        }
        kfree(pg_vec);
 }
 
-static inline char *alloc_one_pg_vec_page(unsigned long order)
+static inline char *alloc_one_pg_vec_page(unsigned long order,
+                                         unsigned char *flags)
 {
-       gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN;
+       char *buffer = NULL;
+       gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
+                         __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
+
+       buffer = (char *) __get_free_pages(gfp_flags, order);
+
+       if (buffer)
+               return buffer;
+
+       /*
+        * __get_free_pages failed, fall back to vmalloc
+        */
+       *flags |= PGV_FROM_VMALLOC;
+       buffer = vmalloc((1 << order) * PAGE_SIZE);
 
-       return (char *) __get_free_pages(gfp_flags, order);
+       if (buffer)
+               return buffer;
+
+       /*
+        * vmalloc failed, lets dig into swap here
+        */
+       *flags = 0;
+       gfp_flags &= ~__GFP_NORETRY;
+       buffer = (char *)__get_free_pages(gfp_flags, order);
+       if (buffer)
+               return buffer;
+
+       /*
+        * complete and utter failure
+        */
+       return NULL;
 }
 
-static char **alloc_pg_vec(struct tpacket_req *req, int order)
+static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 {
        unsigned int block_nr = req->tp_block_nr;
-       char **pg_vec;
+       struct pgv *pg_vec;
        int i;
 
-       pg_vec = kzalloc(block_nr * sizeof(char *), GFP_KERNEL);
+       pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL);
        if (unlikely(!pg_vec))
                goto out;
 
        for (i = 0; i < block_nr; i++) {
-               pg_vec[i] = alloc_one_pg_vec_page(order);
-               if (unlikely(!pg_vec[i]))
+               pg_vec[i].buffer = alloc_one_pg_vec_page(order,
+                                                        &pg_vec[i].flags);
+               if (unlikely(!pg_vec[i].buffer))
                        goto out_free_pgvec;
        }
 
@@ -2364,6 +2409,7 @@ out:
 
 out_free_pgvec:
        free_pg_vec(pg_vec, order, block_nr);
+       kfree(pg_vec);
        pg_vec = NULL;
        goto out;
 }
@@ -2371,7 +2417,7 @@ out_free_pgvec:
 static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
                int closing, int tx_ring)
 {
-       char **pg_vec = NULL;
+       struct pgv *pg_vec = NULL;
        struct packet_sock *po = pkt_sk(sk);
        int was_running, order = 0;
        struct packet_ring_buffer *rb;
@@ -2533,15 +2579,22 @@ static int packet_mmap(struct file *file, struct socket *sock,
                        continue;
 
                for (i = 0; i < rb->pg_vec_len; i++) {
-                       struct page *page = virt_to_page(rb->pg_vec[i]);
+                       struct page *page;
+                       void *kaddr = rb->pg_vec[i].buffer;
                        int pg_num;
 
                        for (pg_num = 0; pg_num < rb->pg_vec_pages;
-                                       pg_num++, page++) {
+                                       pg_num++) {
+                               if (rb->pg_vec[i].flags & PGV_FROM_VMALLOC)
+                                       page = vmalloc_to_page(kaddr);
+                               else
+                                       page = virt_to_page(kaddr);
+
                                err = vm_insert_page(vma, start, page);
                                if (unlikely(err))
                                        goto out;
                                start += PAGE_SIZE;
+                               kaddr += PAGE_SIZE;
                        }
                }
        }