diff options
Diffstat (limited to 'drivers/net/xen-netback/netback.c')
| -rw-r--r-- | drivers/net/xen-netback/netback.c | 2101 |
1 files changed, 1219 insertions, 882 deletions
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 59effac15f3..c65b636bcab 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -37,186 +37,94 @@ #include <linux/kthread.h> #include <linux/if_vlan.h> #include <linux/udp.h> +#include <linux/highmem.h> #include <net/tcp.h> +#include <xen/xen.h> #include <xen/events.h> #include <xen/interface/memory.h> #include <asm/xen/hypercall.h> #include <asm/xen/page.h> -struct pending_tx_info { - struct xen_netif_tx_request req; - struct xenvif *vif; -}; -typedef unsigned int pending_ring_idx_t; - -struct netbk_rx_meta { - int id; - int size; - int gso_size; -}; - -#define MAX_PENDING_REQS 256 - -/* Discriminate from any valid pending_idx value. */ -#define INVALID_PENDING_IDX 0xFFFF - -#define MAX_BUFFER_OFFSET PAGE_SIZE - -/* extra field used in struct page */ -union page_ext { - struct { -#if BITS_PER_LONG < 64 -#define IDX_WIDTH 8 -#define GROUP_WIDTH (BITS_PER_LONG - IDX_WIDTH) - unsigned int group:GROUP_WIDTH; - unsigned int idx:IDX_WIDTH; -#else - unsigned int group, idx; -#endif - } e; - void *mapping; -}; - -struct xen_netbk { - wait_queue_head_t wq; - struct task_struct *task; - - struct sk_buff_head rx_queue; - struct sk_buff_head tx_queue; - - struct timer_list net_timer; - - struct page *mmap_pages[MAX_PENDING_REQS]; - - pending_ring_idx_t pending_prod; - pending_ring_idx_t pending_cons; - struct list_head net_schedule_list; - - /* Protect the net_schedule_list in netif. */ - spinlock_t net_schedule_list_lock; - - atomic_t netfront_count; - - struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; - struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS]; - - u16 pending_ring[MAX_PENDING_REQS]; - - /* - * Given MAX_BUFFER_OFFSET of 4096 the worst case is that each - * head/fragment page uses 2 copy operations because it - * straddles two buffers in the frontend. - */ - struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE]; - struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE]; -}; +/* Provide an option to disable split event channels at load time as + * event channels are limited resource. Split event channels are + * enabled by default. + */ +bool separate_tx_rx_irq = 1; +module_param(separate_tx_rx_irq, bool, 0644); -static struct xen_netbk *xen_netbk; -static int xen_netbk_group_nr; +/* When guest ring is filled up, qdisc queues the packets for us, but we have + * to timeout them, otherwise other guests' packets can get stuck there + */ +unsigned int rx_drain_timeout_msecs = 10000; +module_param(rx_drain_timeout_msecs, uint, 0444); +unsigned int rx_drain_timeout_jiffies; -void xen_netbk_add_xenvif(struct xenvif *vif) -{ - int i; - int min_netfront_count; - int min_group = 0; - struct xen_netbk *netbk; - - min_netfront_count = atomic_read(&xen_netbk[0].netfront_count); - for (i = 0; i < xen_netbk_group_nr; i++) { - int netfront_count = atomic_read(&xen_netbk[i].netfront_count); - if (netfront_count < min_netfront_count) { - min_group = i; - min_netfront_count = netfront_count; - } - } +unsigned int xenvif_max_queues; +module_param_named(max_queues, xenvif_max_queues, uint, 0644); +MODULE_PARM_DESC(max_queues, + "Maximum number of queues per virtual interface"); - netbk = &xen_netbk[min_group]; +/* + * This is the maximum slots a skb can have. If a guest sends a skb + * which exceeds this limit it is considered malicious. + */ +#define FATAL_SKB_SLOTS_DEFAULT 20 +static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT; +module_param(fatal_skb_slots, uint, 0444); - vif->netbk = netbk; - atomic_inc(&netbk->netfront_count); -} +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, + u8 status); -void xen_netbk_remove_xenvif(struct xenvif *vif) -{ - struct xen_netbk *netbk = vif->netbk; - vif->netbk = NULL; - atomic_dec(&netbk->netfront_count); -} - -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx); -static void make_tx_response(struct xenvif *vif, +static void make_tx_response(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, s8 st); -static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, + +static inline int tx_work_todo(struct xenvif_queue *queue); +static inline int rx_work_todo(struct xenvif_queue *queue); + +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, s8 st, u16 offset, u16 size, u16 flags); -static inline unsigned long idx_to_pfn(struct xen_netbk *netbk, +static inline unsigned long idx_to_pfn(struct xenvif_queue *queue, u16 idx) { - return page_to_pfn(netbk->mmap_pages[idx]); + return page_to_pfn(queue->mmap_pages[idx]); } -static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk, +static inline unsigned long idx_to_kaddr(struct xenvif_queue *queue, u16 idx) { - return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx)); + return (unsigned long)pfn_to_kaddr(idx_to_pfn(queue, idx)); } -/* extra field used in struct page */ -static inline void set_page_ext(struct page *pg, struct xen_netbk *netbk, - unsigned int idx) -{ - unsigned int group = netbk - xen_netbk; - union page_ext ext = { .e = { .group = group + 1, .idx = idx } }; - - BUILD_BUG_ON(sizeof(ext) > sizeof(ext.mapping)); - pg->mapping = ext.mapping; -} +#define callback_param(vif, pending_idx) \ + (vif->pending_tx_info[pending_idx].callback_struct) -static int get_page_ext(struct page *pg, - unsigned int *pgroup, unsigned int *pidx) +/* Find the containing VIF's structure from a pointer in pending_tx_info array + */ +static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf) { - union page_ext ext = { .mapping = pg->mapping }; - struct xen_netbk *netbk; - unsigned int group, idx; - - group = ext.e.group - 1; - - if (group < 0 || group >= xen_netbk_group_nr) - return 0; - - netbk = &xen_netbk[group]; - - idx = ext.e.idx; - - if ((idx < 0) || (idx >= MAX_PENDING_REQS)) - return 0; - - if (netbk->mmap_pages[idx] != pg) - return 0; - - *pgroup = group; - *pidx = idx; - - return 1; + u16 pending_idx = ubuf->desc; + struct pending_tx_info *temp = + container_of(ubuf, struct pending_tx_info, callback_struct); + return container_of(temp - pending_idx, + struct xenvif_queue, + pending_tx_info[0]); } -/* - * This is the amount of packet we copy rather than map, so that the - * guest can't fiddle with the contents of the headers while we do - * packet processing on them (netfilter, routing, etc). +/* This is a miniumum size for the linear area to avoid lots of + * calls to __pskb_pull_tail() as we set up checksum offsets. The + * value 128 was chosen as it covers all IPv4 and most likely + * IPv6 headers. */ -#define PKT_PROT_LEN (ETH_HLEN + \ - VLAN_HLEN + \ - sizeof(struct iphdr) + MAX_IPOPTLEN + \ - sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE) +#define PKT_PROT_LEN 128 static u16 frag_get_pending_idx(skb_frag_t *frag) { @@ -233,46 +141,26 @@ static inline pending_ring_idx_t pending_index(unsigned i) return i & (MAX_PENDING_REQS-1); } -static inline pending_ring_idx_t nr_pending_reqs(struct xen_netbk *netbk) +bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed) { - return MAX_PENDING_REQS - - netbk->pending_prod + netbk->pending_cons; -} - -static void xen_netbk_kick_thread(struct xen_netbk *netbk) -{ - wake_up(&netbk->wq); -} - -static int max_required_rx_slots(struct xenvif *vif) -{ - int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE); - - if (vif->can_sg || vif->gso || vif->gso_prefix) - max += MAX_SKB_FRAGS + 1; /* extra_info + frags */ + RING_IDX prod, cons; - return max; -} + do { + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; -int xen_netbk_rx_ring_full(struct xenvif *vif) -{ - RING_IDX peek = vif->rx_req_cons_peek; - RING_IDX needed = max_required_rx_slots(vif); + if (prod - cons >= needed) + return true; - return ((vif->rx.sring->req_prod - peek) < needed) || - ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed); -} - -int xen_netbk_must_stop_queue(struct xenvif *vif) -{ - if (!xen_netbk_rx_ring_full(vif)) - return 0; + queue->rx.sring->req_event = prod + 1; - vif->rx.sring->req_event = vif->rx_req_cons_peek + - max_required_rx_slots(vif); - mb(); /* request notification /then/ check the queue */ + /* Make sure event is visible before we check prod + * again. + */ + mb(); + } while (queue->rx.sring->req_prod != prod); - return xen_netbk_rx_ring_full(vif); + return false; } /* @@ -280,7 +168,8 @@ int xen_netbk_must_stop_queue(struct xenvif *vif) * adding 'size' bytes to a buffer which currently contains 'offset' * bytes. */ -static bool start_new_rx_buffer(int offset, unsigned long size, int head) +static bool start_new_rx_buffer(int offset, unsigned long size, int head, + bool full_coalesce) { /* simple case: we have completely filled the current buffer. */ if (offset == MAX_BUFFER_OFFSET) @@ -292,6 +181,7 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head) * (i) this frag would fit completely in the next buffer * and (ii) there is already some data in the current buffer * and (iii) this is not the head buffer. + * and (iv) there is no need to fully utilize the buffers * * Where: * - (i) stops us splitting a frag into two copies @@ -302,77 +192,41 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head) * by (ii) but is explicitly checked because * netfront relies on the first buffer being * non-empty and can crash otherwise. + * - (iv) is needed for skbs which can use up more than MAX_SKB_FRAGS + * slot * * This means we will effectively linearise small * frags but do not needlessly split large buffers * into multiple copies tend to give large frags their * own buffers as before. */ - if ((offset + size > MAX_BUFFER_OFFSET) && - (size <= MAX_BUFFER_OFFSET) && offset && !head) + BUG_ON(size > MAX_BUFFER_OFFSET); + if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head && + !full_coalesce) return true; return false; } -/* - * Figure out how many ring slots we're going to need to send @skb to - * the guest. This function is essentially a dry run of - * netbk_gop_frag_copy. - */ -unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb) -{ - unsigned int count; - int i, copy_off; - - count = DIV_ROUND_UP( - offset_in_page(skb->data)+skb_headlen(skb), PAGE_SIZE); - - copy_off = skb_headlen(skb) % PAGE_SIZE; - - if (skb_shinfo(skb)->gso_size) - count++; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]); - unsigned long bytes; - while (size > 0) { - BUG_ON(copy_off > MAX_BUFFER_OFFSET); - - if (start_new_rx_buffer(copy_off, size, 0)) { - count++; - copy_off = 0; - } - - bytes = size; - if (copy_off + bytes > MAX_BUFFER_OFFSET) - bytes = MAX_BUFFER_OFFSET - copy_off; - - copy_off += bytes; - size -= bytes; - } - } - return count; -} - struct netrx_pending_operations { unsigned copy_prod, copy_cons; unsigned meta_prod, meta_cons; struct gnttab_copy *copy; - struct netbk_rx_meta *meta; + struct xenvif_rx_meta *meta; int copy_off; grant_ref_t copy_gref; }; -static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif, - struct netrx_pending_operations *npo) +static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, + struct netrx_pending_operations *npo) { - struct netbk_rx_meta *meta; + struct xenvif_rx_meta *meta; struct xen_netif_rx_request *req; - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; meta->size = 0; meta->id = req->id; @@ -383,69 +237,81 @@ static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif, return meta; } +struct xenvif_rx_cb { + int meta_slots_used; + bool full_coalesce; +}; + +#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) + /* * Set up the grant operations for this fragment. If it's a flipping * interface, we also set up the unmap request from here. */ -static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, - struct netrx_pending_operations *npo, - struct page *page, unsigned long size, - unsigned long offset, int *head) +static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb, + struct netrx_pending_operations *npo, + struct page *page, unsigned long size, + unsigned long offset, int *head, + struct xenvif_queue *foreign_queue, + grant_ref_t foreign_gref) { struct gnttab_copy *copy_gop; - struct netbk_rx_meta *meta; - /* - * These variables are used iff get_page_ext returns true, - * in which case they are guaranteed to be initialized. - */ - unsigned int uninitialized_var(group), uninitialized_var(idx); - int foreign = get_page_ext(page, &group, &idx); + struct xenvif_rx_meta *meta; unsigned long bytes; + int gso_type = XEN_NETIF_GSO_TYPE_NONE; /* Data must not cross a page boundary. */ - BUG_ON(size + offset > PAGE_SIZE); + BUG_ON(size + offset > PAGE_SIZE<<compound_order(page)); meta = npo->meta + npo->meta_prod - 1; + /* Skip unused frames from start of page */ + page += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; + while (size > 0) { + BUG_ON(offset >= PAGE_SIZE); BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET); - if (start_new_rx_buffer(npo->copy_off, size, *head)) { + bytes = PAGE_SIZE - offset; + + if (bytes > size) + bytes = size; + + if (start_new_rx_buffer(npo->copy_off, + bytes, + *head, + XENVIF_RX_CB(skb)->full_coalesce)) { /* * Netfront requires there to be some data in the head * buffer. */ BUG_ON(*head); - meta = get_next_rx_buffer(vif, npo); + meta = get_next_rx_buffer(queue, npo); } - bytes = size; if (npo->copy_off + bytes > MAX_BUFFER_OFFSET) bytes = MAX_BUFFER_OFFSET - npo->copy_off; copy_gop = npo->copy + npo->copy_prod++; copy_gop->flags = GNTCOPY_dest_gref; - if (foreign) { - struct xen_netbk *netbk = &xen_netbk[group]; - struct pending_tx_info *src_pend; - - src_pend = &netbk->pending_tx_info[idx]; + copy_gop->len = bytes; - copy_gop->source.domid = src_pend->vif->domid; - copy_gop->source.u.ref = src_pend->req.gref; + if (foreign_queue) { + copy_gop->source.domid = foreign_queue->vif->domid; + copy_gop->source.u.ref = foreign_gref; copy_gop->flags |= GNTCOPY_source_gref; } else { - void *vaddr = page_address(page); copy_gop->source.domid = DOMID_SELF; - copy_gop->source.u.gmfn = virt_to_mfn(vaddr); + copy_gop->source.u.gmfn = + virt_to_mfn(page_address(page)); } copy_gop->source.offset = offset; - copy_gop->dest.domid = vif->domid; + copy_gop->dest.domid = queue->vif->domid; copy_gop->dest.offset = npo->copy_off; copy_gop->dest.u.ref = npo->copy_gref; - copy_gop->len = bytes; npo->copy_off += bytes; meta->size += bytes; @@ -453,9 +319,23 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, offset += bytes; size -= bytes; + /* Next frame */ + if (offset == PAGE_SIZE && size) { + BUG_ON(!PageCompound(page)); + page++; + offset = 0; + } + /* Leave a gap for the GSO descriptor. */ - if (*head && skb_shinfo(skb)->gso_size && !vif->gso_prefix) - vif->rx.req_cons++; + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + } + + if (*head && ((1 << gso_type) & queue->vif->gso_mask)) + queue->rx.req_cons++; *head = 0; /* There must be something in this buffer now. */ @@ -463,6 +343,35 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, } /* + * Find the grant ref for a given frag in a chain of struct ubuf_info's + * skb: the skb itself + * i: the frag's number + * ubuf: a pointer to an element in the chain. It should not be NULL + * + * Returns a pointer to the element in the chain where the page were found. If + * not found, returns NULL. + * See the definition of callback_struct in common.h for more details about + * the chain. + */ +static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb, + const int i, + const struct ubuf_info *ubuf) +{ + struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf); + + do { + u16 pending_idx = ubuf->desc; + + if (skb_shinfo(skb)->frags[i].page.p == + foreign_queue->mmap_pages[pending_idx]) + break; + ubuf = (struct ubuf_info *) ubuf->ctx; + } while (ubuf); + + return ubuf; +} + +/* * Prepare an SKB to be transmitted to the frontend. * * This function is responsible for allocating grant operations, meta @@ -474,36 +383,52 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, * zero GSO descriptors (for non-GSO packets) or one descriptor (for * frontend-side LRO). */ -static int netbk_gop_skb(struct sk_buff *skb, - struct netrx_pending_operations *npo) +static int xenvif_gop_skb(struct sk_buff *skb, + struct netrx_pending_operations *npo, + struct xenvif_queue *queue) { struct xenvif *vif = netdev_priv(skb->dev); int nr_frags = skb_shinfo(skb)->nr_frags; int i; struct xen_netif_rx_request *req; - struct netbk_rx_meta *meta; + struct xenvif_rx_meta *meta; unsigned char *data; int head = 1; int old_meta_prod; + int gso_type; + const struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg; + const struct ubuf_info *const head_ubuf = ubuf; old_meta_prod = npo->meta_prod; + gso_type = XEN_NETIF_GSO_TYPE_NONE; + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + } + /* Set up a GSO prefix descriptor, if necessary */ - if (skb_shinfo(skb)->gso_size && vif->gso_prefix) { - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + if ((1 << gso_type) & vif->gso_prefix_mask) { + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; + meta->gso_type = gso_type; meta->gso_size = skb_shinfo(skb)->gso_size; meta->size = 0; meta->id = req->id; } - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; - if (!vif->gso_prefix) + if ((1 << gso_type) & vif->gso_mask) { + meta->gso_type = gso_type; meta->gso_size = skb_shinfo(skb)->gso_size; - else + } else { + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; + } meta->size = 0; meta->id = req->id; @@ -518,30 +443,82 @@ static int netbk_gop_skb(struct sk_buff *skb, if (data + len > skb_tail_pointer(skb)) len = skb_tail_pointer(skb) - data; - netbk_gop_frag_copy(vif, skb, npo, - virt_to_page(data), len, offset, &head); + xenvif_gop_frag_copy(queue, skb, npo, + virt_to_page(data), len, offset, &head, + NULL, + 0); data += len; } for (i = 0; i < nr_frags; i++) { - netbk_gop_frag_copy(vif, skb, npo, - skb_frag_page(&skb_shinfo(skb)->frags[i]), - skb_frag_size(&skb_shinfo(skb)->frags[i]), - skb_shinfo(skb)->frags[i].page_offset, - &head); + /* This variable also signals whether foreign_gref has a real + * value or not. + */ + struct xenvif_queue *foreign_queue = NULL; + grant_ref_t foreign_gref; + + if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) && + (ubuf->callback == &xenvif_zerocopy_callback)) { + const struct ubuf_info *const startpoint = ubuf; + + /* Ideally ubuf points to the chain element which + * belongs to this frag. Or if frags were removed from + * the beginning, then shortly before it. + */ + ubuf = xenvif_find_gref(skb, i, ubuf); + + /* Try again from the beginning of the list, if we + * haven't tried from there. This only makes sense in + * the unlikely event of reordering the original frags. + * For injected local pages it's an unnecessary second + * run. + */ + if (unlikely(!ubuf) && startpoint != head_ubuf) + ubuf = xenvif_find_gref(skb, i, head_ubuf); + + if (likely(ubuf)) { + u16 pending_idx = ubuf->desc; + + foreign_queue = ubuf_to_queue(ubuf); + foreign_gref = + foreign_queue->pending_tx_info[pending_idx].req.gref; + /* Just a safety measure. If this was the last + * element on the list, the for loop will + * iterate again if a local page were added to + * the end. Using head_ubuf here prevents the + * second search on the chain. Or the original + * frags changed order, but that's less likely. + * In any way, ubuf shouldn't be NULL. + */ + ubuf = ubuf->ctx ? + (struct ubuf_info *) ubuf->ctx : + head_ubuf; + } else + /* This frag was a local page, added to the + * array after the skb left netback. + */ + ubuf = head_ubuf; + } + xenvif_gop_frag_copy(queue, skb, npo, + skb_frag_page(&skb_shinfo(skb)->frags[i]), + skb_frag_size(&skb_shinfo(skb)->frags[i]), + skb_shinfo(skb)->frags[i].page_offset, + &head, + foreign_queue, + foreign_queue ? foreign_gref : UINT_MAX); } return npo->meta_prod - old_meta_prod; } /* - * This is a twin to netbk_gop_skb. Assume that netbk_gop_skb was + * This is a twin to xenvif_gop_skb. Assume that xenvif_gop_skb was * used to set up the operations on the top of * netrx_pending_operations, which have since been done. Check that * they didn't give any errors and advance over them. */ -static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots, - struct netrx_pending_operations *npo) +static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots, + struct netrx_pending_operations *npo) { struct gnttab_copy *copy_op; int status = XEN_NETIF_RSP_OKAY; @@ -560,9 +537,9 @@ static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots, return status; } -static void netbk_add_frag_responses(struct xenvif *vif, int status, - struct netbk_rx_meta *meta, - int nr_meta_slots) +static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status, + struct xenvif_rx_meta *meta, + int nr_meta_slots) { int i; unsigned long offset; @@ -581,91 +558,134 @@ static void netbk_add_frag_responses(struct xenvif *vif, int status, flags = XEN_NETRXF_more_data; offset = 0; - make_rx_response(vif, meta[i].id, status, offset, + make_rx_response(queue, meta[i].id, status, offset, meta[i].size, flags); } } -struct skb_cb_overlay { - int meta_slots_used; -}; +void xenvif_kick_thread(struct xenvif_queue *queue) +{ + wake_up(&queue->wq); +} -static void xen_netbk_rx_action(struct xen_netbk *netbk) +static void xenvif_rx_action(struct xenvif_queue *queue) { - struct xenvif *vif = NULL, *tmp; s8 status; - u16 irq, flags; + u16 flags; struct xen_netif_rx_response *resp; struct sk_buff_head rxq; struct sk_buff *skb; LIST_HEAD(notify); int ret; - int nr_frags; - int count; unsigned long offset; - struct skb_cb_overlay *sco; + bool need_to_notify = false; struct netrx_pending_operations npo = { - .copy = netbk->grant_copy_op, - .meta = netbk->meta, + .copy = queue->grant_copy_op, + .meta = queue->meta, }; skb_queue_head_init(&rxq); - count = 0; + while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) { + RING_IDX max_slots_needed; + RING_IDX old_req_cons; + RING_IDX ring_slots_used; + int i; - while ((skb = skb_dequeue(&netbk->rx_queue)) != NULL) { - vif = netdev_priv(skb->dev); - nr_frags = skb_shinfo(skb)->nr_frags; + /* We need a cheap worse case estimate for the number of + * slots we'll use. + */ - sco = (struct skb_cb_overlay *)skb->cb; - sco->meta_slots_used = netbk_gop_skb(skb, &npo); + max_slots_needed = DIV_ROUND_UP(offset_in_page(skb->data) + + skb_headlen(skb), + PAGE_SIZE); + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + unsigned int size; + unsigned int offset; - count += nr_frags + 1; + size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + offset = skb_shinfo(skb)->frags[i].page_offset; - __skb_queue_tail(&rxq, skb); + /* For a worse-case estimate we need to factor in + * the fragment page offset as this will affect the + * number of times xenvif_gop_frag_copy() will + * call start_new_rx_buffer(). + */ + max_slots_needed += DIV_ROUND_UP(offset + size, + PAGE_SIZE); + } + + /* To avoid the estimate becoming too pessimal for some + * frontends that limit posted rx requests, cap the estimate + * at MAX_SKB_FRAGS. In this case netback will fully coalesce + * the skb into the provided slots. + */ + if (max_slots_needed > MAX_SKB_FRAGS) { + max_slots_needed = MAX_SKB_FRAGS; + XENVIF_RX_CB(skb)->full_coalesce = true; + } else { + XENVIF_RX_CB(skb)->full_coalesce = false; + } - /* Filled the batch queue? */ - if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE) + /* We may need one more slot for GSO metadata */ + if (skb_is_gso(skb) && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || + skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) + max_slots_needed++; + + /* If the skb may not fit then bail out now */ + if (!xenvif_rx_ring_slots_available(queue, max_slots_needed)) { + skb_queue_head(&queue->rx_queue, skb); + need_to_notify = true; + queue->rx_last_skb_slots = max_slots_needed; break; + } else + queue->rx_last_skb_slots = 0; + + old_req_cons = queue->rx.req_cons; + XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue); + ring_slots_used = queue->rx.req_cons - old_req_cons; + + BUG_ON(ring_slots_used > max_slots_needed); + + __skb_queue_tail(&rxq, skb); } - BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta)); + BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->meta)); if (!npo.copy_prod) - return; + goto done; - BUG_ON(npo.copy_prod > ARRAY_SIZE(netbk->grant_copy_op)); - ret = HYPERVISOR_grant_table_op(GNTTABOP_copy, &netbk->grant_copy_op, - npo.copy_prod); - BUG_ON(ret != 0); + BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); + gnttab_batch_copy(queue->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { - sco = (struct skb_cb_overlay *)skb->cb; - - vif = netdev_priv(skb->dev); - if (netbk->meta[npo.meta_cons].gso_size && vif->gso_prefix) { - resp = RING_GET_RESPONSE(&vif->rx, - vif->rx.rsp_prod_pvt++); + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_prefix_mask) { + resp = RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data; - resp->offset = netbk->meta[npo.meta_cons].gso_size; - resp->id = netbk->meta[npo.meta_cons].id; - resp->status = sco->meta_slots_used; + resp->offset = queue->meta[npo.meta_cons].gso_size; + resp->id = queue->meta[npo.meta_cons].id; + resp->status = XENVIF_RX_CB(skb)->meta_slots_used; npo.meta_cons++; - sco->meta_slots_used--; + XENVIF_RX_CB(skb)->meta_slots_used--; } - vif->dev->stats.tx_bytes += skb->len; - vif->dev->stats.tx_packets++; + queue->stats.tx_bytes += skb->len; + queue->stats.tx_packets++; - status = netbk_check_gop(vif, sco->meta_slots_used, &npo); + status = xenvif_check_gop(queue->vif, + XENVIF_RX_CB(skb)->meta_slots_used, + &npo); - if (sco->meta_slots_used == 1) + if (XENVIF_RX_CB(skb)->meta_slots_used == 1) flags = 0; else flags = XEN_NETRXF_more_data; @@ -677,21 +697,22 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk) flags |= XEN_NETRXF_data_validated; offset = 0; - resp = make_rx_response(vif, netbk->meta[npo.meta_cons].id, + resp = make_rx_response(queue, queue->meta[npo.meta_cons].id, status, offset, - netbk->meta[npo.meta_cons].size, + queue->meta[npo.meta_cons].size, flags); - if (netbk->meta[npo.meta_cons].gso_size && !vif->gso_prefix) { + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_mask) { struct xen_netif_extra_info *gso = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&vif->rx, - vif->rx.rsp_prod_pvt++); + RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); resp->flags |= XEN_NETRXF_extra_info; - gso->u.gso.size = netbk->meta[npo.meta_cons].gso_size; - gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4; + gso->u.gso.type = queue->meta[npo.meta_cons].gso_type; + gso->u.gso.size = queue->meta[npo.meta_cons].gso_size; gso->u.gso.pad = 0; gso->u.gso.features = 0; @@ -699,125 +720,34 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk) gso->flags = 0; } - netbk_add_frag_responses(vif, status, - netbk->meta + npo.meta_cons + 1, - sco->meta_slots_used); + xenvif_add_frag_responses(queue, status, + queue->meta + npo.meta_cons + 1, + XENVIF_RX_CB(skb)->meta_slots_used); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); - irq = vif->irq; - if (ret && list_empty(&vif->notify_list)) - list_add_tail(&vif->notify_list, ¬ify); + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret); - xenvif_notify_tx_completion(vif); + need_to_notify |= !!ret; - xenvif_put(vif); - npo.meta_cons += sco->meta_slots_used; + npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used; dev_kfree_skb(skb); } - list_for_each_entry_safe(vif, tmp, ¬ify, notify_list) { - notify_remote_via_irq(vif->irq); - list_del_init(&vif->notify_list); - } - - /* More work to do? */ - if (!skb_queue_empty(&netbk->rx_queue) && - !timer_pending(&netbk->net_timer)) - xen_netbk_kick_thread(netbk); -} - -void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb) -{ - struct xen_netbk *netbk = vif->netbk; - - skb_queue_tail(&netbk->rx_queue, skb); - - xen_netbk_kick_thread(netbk); +done: + if (need_to_notify) + notify_remote_via_irq(queue->rx_irq); } -static void xen_netbk_alarm(unsigned long data) -{ - struct xen_netbk *netbk = (struct xen_netbk *)data; - xen_netbk_kick_thread(netbk); -} - -static int __on_net_schedule_list(struct xenvif *vif) -{ - return !list_empty(&vif->schedule_list); -} - -/* Must be called with net_schedule_list_lock held */ -static void remove_from_net_schedule_list(struct xenvif *vif) -{ - if (likely(__on_net_schedule_list(vif))) { - list_del_init(&vif->schedule_list); - xenvif_put(vif); - } -} - -static struct xenvif *poll_net_schedule_list(struct xen_netbk *netbk) -{ - struct xenvif *vif = NULL; - - spin_lock_irq(&netbk->net_schedule_list_lock); - if (list_empty(&netbk->net_schedule_list)) - goto out; - - vif = list_first_entry(&netbk->net_schedule_list, - struct xenvif, schedule_list); - if (!vif) - goto out; - - xenvif_get(vif); - - remove_from_net_schedule_list(vif); -out: - spin_unlock_irq(&netbk->net_schedule_list_lock); - return vif; -} - -void xen_netbk_schedule_xenvif(struct xenvif *vif) -{ - unsigned long flags; - struct xen_netbk *netbk = vif->netbk; - - if (__on_net_schedule_list(vif)) - goto kick; - - spin_lock_irqsave(&netbk->net_schedule_list_lock, flags); - if (!__on_net_schedule_list(vif) && - likely(xenvif_schedulable(vif))) { - list_add_tail(&vif->schedule_list, &netbk->net_schedule_list); - xenvif_get(vif); - } - spin_unlock_irqrestore(&netbk->net_schedule_list_lock, flags); - -kick: - smp_mb(); - if ((nr_pending_reqs(netbk) < (MAX_PENDING_REQS/2)) && - !list_empty(&netbk->net_schedule_list)) - xen_netbk_kick_thread(netbk); -} - -void xen_netbk_deschedule_xenvif(struct xenvif *vif) -{ - struct xen_netbk *netbk = vif->netbk; - spin_lock_irq(&netbk->net_schedule_list_lock); - remove_from_net_schedule_list(vif); - spin_unlock_irq(&netbk->net_schedule_list_lock); -} - -void xen_netbk_check_rx_xenvif(struct xenvif *vif) +void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) { int more_to_do; - RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do); + RING_FINAL_CHECK_FOR_REQUESTS(&queue->tx, more_to_do); if (more_to_do) - xen_netbk_schedule_xenvif(vif); + napi_schedule(&queue->napi); } -static void tx_add_credit(struct xenvif *vif) +static void tx_add_credit(struct xenvif_queue *queue) { unsigned long max_burst, max_credit; @@ -825,217 +755,405 @@ static void tx_add_credit(struct xenvif *vif) * Allow a burst big enough to transmit a jumbo packet of up to 128kB. * Otherwise the interface can seize up due to insufficient credit. */ - max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size; + max_burst = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size; max_burst = min(max_burst, 131072UL); - max_burst = max(max_burst, vif->credit_bytes); + max_burst = max(max_burst, queue->credit_bytes); /* Take care that adding a new chunk of credit doesn't wrap to zero. */ - max_credit = vif->remaining_credit + vif->credit_bytes; - if (max_credit < vif->remaining_credit) + max_credit = queue->remaining_credit + queue->credit_bytes; + if (max_credit < queue->remaining_credit) max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */ - vif->remaining_credit = min(max_credit, max_burst); + queue->remaining_credit = min(max_credit, max_burst); } static void tx_credit_callback(unsigned long data) { - struct xenvif *vif = (struct xenvif *)data; - tx_add_credit(vif); - xen_netbk_check_rx_xenvif(vif); + struct xenvif_queue *queue = (struct xenvif_queue *)data; + tx_add_credit(queue); + xenvif_napi_schedule_or_enable_events(queue); } -static void netbk_tx_err(struct xenvif *vif, - struct xen_netif_tx_request *txp, RING_IDX end) +static void xenvif_tx_err(struct xenvif_queue *queue, + struct xen_netif_tx_request *txp, RING_IDX end) { - RING_IDX cons = vif->tx.req_cons; + RING_IDX cons = queue->tx.req_cons; + unsigned long flags; do { - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - if (cons >= end) + spin_lock_irqsave(&queue->response_lock, flags); + make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR); + spin_unlock_irqrestore(&queue->response_lock, flags); + if (cons == end) break; - txp = RING_GET_REQUEST(&vif->tx, cons++); + txp = RING_GET_REQUEST(&queue->tx, cons++); } while (1); - vif->tx.req_cons = cons; - xen_netbk_check_rx_xenvif(vif); - xenvif_put(vif); + queue->tx.req_cons = cons; } -static int netbk_count_requests(struct xenvif *vif, - struct xen_netif_tx_request *first, - struct xen_netif_tx_request *txp, - int work_to_do) +static void xenvif_fatal_tx_err(struct xenvif *vif) { - RING_IDX cons = vif->tx.req_cons; - int frags = 0; + netdev_err(vif->dev, "fatal error; disabling device\n"); + vif->disabled = true; + /* Disable the vif from queue 0's kthread */ + if (vif->queues) + xenvif_kick_thread(&vif->queues[0]); +} + +static int xenvif_count_requests(struct xenvif_queue *queue, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txp, + int work_to_do) +{ + RING_IDX cons = queue->tx.req_cons; + int slots = 0; + int drop_err = 0; + int more_data; if (!(first->flags & XEN_NETTXF_more_data)) return 0; do { - if (frags >= work_to_do) { - netdev_dbg(vif->dev, "Need more frags\n"); - return -frags; + struct xen_netif_tx_request dropped_tx = { 0 }; + + if (slots >= work_to_do) { + netdev_err(queue->vif->dev, + "Asked for %d slots but exceeds this limit\n", + work_to_do); + xenvif_fatal_tx_err(queue->vif); + return -ENODATA; } - if (unlikely(frags >= MAX_SKB_FRAGS)) { - netdev_dbg(vif->dev, "Too many frags\n"); - return -frags; + /* This guest is really using too many slots and + * considered malicious. + */ + if (unlikely(slots >= fatal_skb_slots)) { + netdev_err(queue->vif->dev, + "Malicious frontend using %d slots, threshold %u\n", + slots, fatal_skb_slots); + xenvif_fatal_tx_err(queue->vif); + return -E2BIG; } - memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags), + /* Xen network protocol had implicit dependency on + * MAX_SKB_FRAGS. XEN_NETBK_LEGACY_SLOTS_MAX is set to + * the historical MAX_SKB_FRAGS value 18 to honor the + * same behavior as before. Any packet using more than + * 18 slots but less than fatal_skb_slots slots is + * dropped + */ + if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) { + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Too many slots (%d) exceeding limit (%d), dropping packet\n", + slots, XEN_NETBK_LEGACY_SLOTS_MAX); + drop_err = -E2BIG; + } + + if (drop_err) + txp = &dropped_tx; + + memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots), sizeof(*txp)); - if (txp->size > first->size) { - netdev_dbg(vif->dev, "Frags galore\n"); - return -frags; + + /* If the guest submitted a frame >= 64 KiB then + * first->size overflowed and following slots will + * appear to be larger than the frame. + * + * This cannot be fatal error as there are buggy + * frontends that do this. + * + * Consume all slots and drop the packet. + */ + if (!drop_err && txp->size > first->size) { + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Invalid tx request, slot size %u > remaining size %u\n", + txp->size, first->size); + drop_err = -EIO; } first->size -= txp->size; - frags++; + slots++; if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n", + netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n", txp->offset, txp->size); - return -frags; + xenvif_fatal_tx_err(queue->vif); + return -EINVAL; } - } while ((txp++)->flags & XEN_NETTXF_more_data); - return frags; + + more_data = txp->flags & XEN_NETTXF_more_data; + + if (!drop_err) + txp++; + + } while (more_data); + + if (drop_err) { + xenvif_tx_err(queue, first, cons + slots); + return drop_err; + } + + return slots; } -static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk, - struct sk_buff *skb, - u16 pending_idx) + +struct xenvif_tx_cb { + u16 pending_idx; +}; + +#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) + +static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, + u16 pending_idx, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *mop) +{ + queue->pages_to_map[mop-queue->tx_map_ops] = queue->mmap_pages[pending_idx]; + gnttab_set_map_op(mop, idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map | GNTMAP_readonly, + txp->gref, queue->vif->domid); + + memcpy(&queue->pending_tx_info[pending_idx].req, txp, + sizeof(*txp)); +} + +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) { - struct page *page; - page = alloc_page(GFP_KERNEL|__GFP_COLD); - if (!page) + struct sk_buff *skb = + alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(skb == NULL)) return NULL; - set_page_ext(page, netbk, pending_idx); - netbk->mmap_pages[pending_idx] = page; - return page; + + /* Packets passed to netif_rx() must have some headroom. */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + /* Initialize it here to avoid later surprises */ + skb_shinfo(skb)->destructor_arg = NULL; + + return skb; } -static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk, - struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_copy *gop) +static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, + struct sk_buff *skb, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = *((u16 *)skb->data); - int i, start; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + int start; + pending_ring_idx_t index; + unsigned int nr_slots, frag_overflow = 0; + + /* At this point shinfo->nr_frags is in fact the number of + * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. + */ + if (shinfo->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + shinfo->nr_frags = MAX_SKB_FRAGS; + } + nr_slots = shinfo->nr_frags; /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); - for (i = start; i < shinfo->nr_frags; i++, txp++) { - struct page *page; - pending_ring_idx_t index; - struct pending_tx_info *pending_tx_info = - netbk->pending_tx_info; + for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + } - index = pending_index(netbk->pending_cons++); - pending_idx = netbk->pending_ring[index]; - page = xen_netbk_alloc_page(netbk, skb, pending_idx); - if (!page) + if (frag_overflow) { + struct sk_buff *nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + if (net_ratelimit()) + netdev_err(queue->vif->dev, + "Can't allocate the frag_list skb.\n"); return NULL; + } - gop->source.u.ref = txp->gref; - gop->source.domid = vif->domid; - gop->source.offset = txp->offset; + shinfo = skb_shinfo(nskb); + frags = shinfo->frags; - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - gop->dest.domid = DOMID_SELF; - gop->dest.offset = txp->offset; + for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], + pending_idx); + } - gop->len = txp->size; - gop->flags = GNTCOPY_source_gref; + skb_shinfo(skb)->frag_list = nskb; + } - gop++; + return gop; +} - memcpy(&pending_tx_info[pending_idx].req, txp, sizeof(*txp)); - xenvif_get(vif); - pending_tx_info[pending_idx].vif = vif; - frag_set_pending_idx(&frags[i], pending_idx); +static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, + u16 pending_idx, + grant_handle_t handle) +{ + if (unlikely(queue->grant_tx_handle[pending_idx] != + NETBACK_INVALID_HANDLE)) { + netdev_err(queue->vif->dev, + "Trying to overwrite active handle! pending_idx: %x\n", + pending_idx); + BUG(); } + queue->grant_tx_handle[pending_idx] = handle; +} - return gop; +static inline void xenvif_grant_handle_reset(struct xenvif_queue *queue, + u16 pending_idx) +{ + if (unlikely(queue->grant_tx_handle[pending_idx] == + NETBACK_INVALID_HANDLE)) { + netdev_err(queue->vif->dev, + "Trying to unmap invalid handle! pending_idx: %x\n", + pending_idx); + BUG(); + } + queue->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; } -static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, - struct sk_buff *skb, - struct gnttab_copy **gopp) +static int xenvif_tx_check_gop(struct xenvif_queue *queue, + struct sk_buff *skb, + struct gnttab_map_grant_ref **gopp_map, + struct gnttab_copy **gopp_copy) { - struct gnttab_copy *gop = *gopp; - u16 pending_idx = *((u16 *)skb->data); - struct pending_tx_info *pending_tx_info = netbk->pending_tx_info; - struct xenvif *vif = pending_tx_info[pending_idx].vif; - struct xen_netif_tx_request *txp; + struct gnttab_map_grant_ref *gop_map = *gopp_map; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + /* This always points to the shinfo of the skb being checked, which + * could be either the first or the one on the frag_list + */ struct skb_shared_info *shinfo = skb_shinfo(skb); + /* If this is non-NULL, we are currently checking the frag_list skb, and + * this points to the shinfo of the first one + */ + struct skb_shared_info *first_shinfo = NULL; int nr_frags = shinfo->nr_frags; - int i, err, start; + const bool sharedslot = nr_frags && + frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; + int i, err; /* Check status of header. */ - err = gop->status; + err = (*gopp_copy)->status; if (unlikely(err)) { - pending_ring_idx_t index; - index = pending_index(netbk->pending_prod++); - txp = &pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", + (*gopp_copy)->status, + pending_idx, + (*gopp_copy)->source.u.ref); + /* The first frag might still have this slot mapped */ + if (!sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); } + (*gopp_copy)++; - /* Skip first skb fragment if it is on same page as header fragment. */ - start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); - - for (i = start; i < nr_frags; i++) { +check_frags: + for (i = 0; i < nr_frags; i++, gop_map++) { int j, newerr; - pending_ring_idx_t index; pending_idx = frag_get_pending_idx(&shinfo->frags[i]); /* Check error status: if okay then remember grant handle. */ - newerr = (++gop)->status; + newerr = gop_map->status; + if (likely(!newerr)) { + xenvif_grant_handle_set(queue, + pending_idx, + gop_map->handle); /* Had a previous error? Invalidate this fragment. */ - if (unlikely(err)) - xen_netbk_idx_release(netbk, pending_idx); + if (unlikely(err)) { + xenvif_idx_unmap(queue, pending_idx); + /* If the mapping of the first frag was OK, but + * the header's copy failed, and they are + * sharing a slot, send an error + */ + if (i == 0 && sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + else + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } continue; } /* Error on this fragment: respond to client with an error. */ - txp = &netbk->pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - index = pending_index(netbk->pending_prod++); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n", + i, + gop_map->status, + pending_idx, + gop_map->ref); + + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) continue; - /* First error: invalidate header and preceding fragments. */ - pending_idx = *((u16 *)skb->data); - xen_netbk_idx_release(netbk, pending_idx); - for (j = start; j < i; j++) { + /* First error: if the header haven't shared a slot with the + * first frag, release it as well. + */ + if (!sharedslot) + xenvif_idx_release(queue, + XENVIF_TX_CB(skb)->pending_idx, + XEN_NETIF_RSP_OKAY); + + /* Invalidate preceding fragments of this skb. */ + for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xen_netbk_idx_release(netbk, pending_idx); + xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } + + /* And if we found the error while checking the frag_list, unmap + * the first skb's frags + */ + if (first_shinfo) { + for (j = 0; j < first_shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&first_shinfo->frags[j]); + xenvif_idx_unmap(queue, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } } /* Remember the error: invalidate all subsequent fragments. */ err = newerr; } - *gopp = gop + 1; + if (skb_has_frag_list(skb) && !first_shinfo) { + first_shinfo = skb_shinfo(skb); + shinfo = skb_shinfo(skb_shinfo(skb)->frag_list); + nr_frags = shinfo->nr_frags; + + goto check_frags; + } + + *gopp_map = gop_map; return err; } -static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb) +static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; int i; + u16 prev_pending_idx = INVALID_PENDING_IDX; for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = shinfo->frags + i; @@ -1045,169 +1163,143 @@ static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb) pending_idx = frag_get_pending_idx(frag); - txp = &netbk->pending_tx_info[pending_idx].req; - page = virt_to_page(idx_to_kaddr(netbk, pending_idx)); + /* If this is not the first frag, chain it to the previous*/ + if (prev_pending_idx == INVALID_PENDING_IDX) + skb_shinfo(skb)->destructor_arg = + &callback_param(queue, pending_idx); + else + callback_param(queue, prev_pending_idx).ctx = + &callback_param(queue, pending_idx); + + callback_param(queue, pending_idx).ctx = NULL; + prev_pending_idx = pending_idx; + + txp = &queue->pending_tx_info[pending_idx].req; + page = virt_to_page(idx_to_kaddr(queue, pending_idx)); __skb_fill_page_desc(skb, i, page, txp->offset, txp->size); skb->len += txp->size; skb->data_len += txp->size; skb->truesize += txp->size; - /* Take an extra reference to offset xen_netbk_idx_release */ - get_page(netbk->mmap_pages[pending_idx]); - xen_netbk_idx_release(netbk, pending_idx); + /* Take an extra reference to offset network stack's put_page */ + get_page(queue->mmap_pages[pending_idx]); } + /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc + * overlaps with "index", and "mapping" is not set. I think mapping + * should be set. If delivered to local stack, it would drop this + * skb in sk_filter unless the socket has the right to use it. + */ + skb->pfmemalloc = false; } -static int xen_netbk_get_extras(struct xenvif *vif, +static int xenvif_get_extras(struct xenvif_queue *queue, struct xen_netif_extra_info *extras, int work_to_do) { struct xen_netif_extra_info extra; - RING_IDX cons = vif->tx.req_cons; + RING_IDX cons = queue->tx.req_cons; do { if (unlikely(work_to_do-- <= 0)) { - netdev_dbg(vif->dev, "Missing extra info\n"); + netdev_err(queue->vif->dev, "Missing extra info\n"); + xenvif_fatal_tx_err(queue->vif); return -EBADR; } - memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons), + memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons), sizeof(extra)); if (unlikely(!extra.type || extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { - vif->tx.req_cons = ++cons; - netdev_dbg(vif->dev, + queue->tx.req_cons = ++cons; + netdev_err(queue->vif->dev, "Invalid extra type: %d\n", extra.type); + xenvif_fatal_tx_err(queue->vif); return -EINVAL; } memcpy(&extras[extra.type - 1], &extra, sizeof(extra)); - vif->tx.req_cons = ++cons; + queue->tx.req_cons = ++cons; } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE); return work_to_do; } -static int netbk_set_skb_gso(struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_extra_info *gso) +static int xenvif_set_skb_gso(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_extra_info *gso) { if (!gso->u.gso.size) { - netdev_dbg(vif->dev, "GSO size must not be zero.\n"); + netdev_err(vif->dev, "GSO size must not be zero.\n"); + xenvif_fatal_tx_err(vif); return -EINVAL; } - /* Currently only TCPv4 S.O. is supported. */ - if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { - netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + switch (gso->u.gso.type) { + case XEN_NETIF_GSO_TYPE_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case XEN_NETIF_GSO_TYPE_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + default: + netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + xenvif_fatal_tx_err(vif); return -EINVAL; } skb_shinfo(skb)->gso_size = gso->u.gso.size; - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; - - /* Header must be checked, and gso_segs computed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + /* gso_segs will be calculated later */ return 0; } -static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) +static int checksum_setup(struct xenvif_queue *queue, struct sk_buff *skb) { - struct iphdr *iph; - unsigned char *th; - int err = -EPROTO; - int recalculate_partial_csum = 0; + bool recalculate_partial_csum = false; - /* - * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy + /* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy * peers can fail to set NETRXF_csum_blank when sending a GSO * frame. In this case force the SKB to CHECKSUM_PARTIAL and * recalculate the partial checksum. */ if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { - vif->rx_gso_checksum_fixup++; + queue->stats.rx_gso_checksum_fixup++; skb->ip_summed = CHECKSUM_PARTIAL; - recalculate_partial_csum = 1; + recalculate_partial_csum = true; } /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; - if (skb->protocol != htons(ETH_P_IP)) - goto out; - - iph = (void *)skb->data; - th = skb->data + 4 * iph->ihl; - if (th >= skb_tail_pointer(skb)) - goto out; - - skb->csum_start = th - skb->head; - switch (iph->protocol) { - case IPPROTO_TCP: - skb->csum_offset = offsetof(struct tcphdr, check); - - if (recalculate_partial_csum) { - struct tcphdr *tcph = (struct tcphdr *)th; - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_TCP, 0); - } - break; - case IPPROTO_UDP: - skb->csum_offset = offsetof(struct udphdr, check); - - if (recalculate_partial_csum) { - struct udphdr *udph = (struct udphdr *)th; - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_UDP, 0); - } - break; - default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n", - iph->protocol); - goto out; - } - - if ((th + skb->csum_offset + 2) > skb_tail_pointer(skb)) - goto out; - - err = 0; - -out: - return err; + return skb_checksum_setup(skb, recalculate_partial_csum); } -static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) +static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) { - unsigned long now = jiffies; - unsigned long next_credit = - vif->credit_timeout.expires + - msecs_to_jiffies(vif->credit_usec / 1000); + u64 now = get_jiffies_64(); + u64 next_credit = queue->credit_window_start + + msecs_to_jiffies(queue->credit_usec / 1000); /* Timer could already be pending in rare cases. */ - if (timer_pending(&vif->credit_timeout)) + if (timer_pending(&queue->credit_timeout)) return true; /* Passed the point where we can replenish credit? */ - if (time_after_eq(now, next_credit)) { - vif->credit_timeout.expires = now; - tx_add_credit(vif); + if (time_after_eq64(now, next_credit)) { + queue->credit_window_start = now; + tx_add_credit(queue); } /* Still too big to send right now? Set a callback. */ - if (size > vif->remaining_credit) { - vif->credit_timeout.data = - (unsigned long)vif; - vif->credit_timeout.function = + if (size > queue->remaining_credit) { + queue->credit_timeout.data = + (unsigned long)queue; + queue->credit_timeout.function = tx_credit_callback; - mod_timer(&vif->credit_timeout, + mod_timer(&queue->credit_timeout, next_credit); + queue->credit_window_start = next_credit; return true; } @@ -1215,18 +1307,18 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return false; } -static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) +static void xenvif_tx_build_gops(struct xenvif_queue *queue, + int budget, + unsigned *copy_ops, + unsigned *map_ops) { - struct gnttab_copy *gop = netbk->tx_copy_ops, *request_gop; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop; struct sk_buff *skb; int ret; - while (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) && - !list_empty(&netbk->net_schedule_list)) { - struct xenvif *vif; + while (skb_queue_len(&queue->tx_queue) < budget) { struct xen_netif_tx_request txreq; - struct xen_netif_tx_request txfrags[MAX_SKB_FRAGS]; - struct page *page; + struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; u16 pending_idx; RING_IDX idx; @@ -1234,193 +1326,255 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) unsigned int data_len; pending_ring_idx_t index; - /* Get a netif from the list with work to do. */ - vif = poll_net_schedule_list(netbk); - if (!vif) - continue; - - RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do); - if (!work_to_do) { - xenvif_put(vif); - continue; + if (queue->tx.sring->req_prod - queue->tx.req_cons > + XEN_NETIF_TX_RING_SIZE) { + netdev_err(queue->vif->dev, + "Impossible number of requests. " + "req_prod %d, req_cons %d, size %ld\n", + queue->tx.sring->req_prod, queue->tx.req_cons, + XEN_NETIF_TX_RING_SIZE); + xenvif_fatal_tx_err(queue->vif); + break; } - idx = vif->tx.req_cons; + work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx); + if (!work_to_do) + break; + + idx = queue->tx.req_cons; rmb(); /* Ensure that we see the request before we copy it. */ - memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq)); + memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq)); /* Credit-based scheduling. */ - if (txreq.size > vif->remaining_credit && - tx_credit_exceeded(vif, txreq.size)) { - xenvif_put(vif); - continue; - } + if (txreq.size > queue->remaining_credit && + tx_credit_exceeded(queue, txreq.size)) + break; - vif->remaining_credit -= txreq.size; + queue->remaining_credit -= txreq.size; work_to_do--; - vif->tx.req_cons = ++idx; + queue->tx.req_cons = ++idx; memset(extras, 0, sizeof(extras)); if (txreq.flags & XEN_NETTXF_extra_info) { - work_to_do = xen_netbk_get_extras(vif, extras, - work_to_do); - idx = vif->tx.req_cons; - if (unlikely(work_to_do < 0)) { - netbk_tx_err(vif, &txreq, idx); - continue; - } + work_to_do = xenvif_get_extras(queue, extras, + work_to_do); + idx = queue->tx.req_cons; + if (unlikely(work_to_do < 0)) + break; } - ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do); - if (unlikely(ret < 0)) { - netbk_tx_err(vif, &txreq, idx - ret); - continue; - } + ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do); + if (unlikely(ret < 0)) + break; + idx += ret; if (unlikely(txreq.size < ETH_HLEN)) { - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Bad packet size: %d\n", txreq.size); - netbk_tx_err(vif, &txreq, idx); - continue; + xenvif_tx_err(queue, &txreq, idx); + break; } /* No crossing a page as the payload mustn't fragment. */ if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, + netdev_err(queue->vif->dev, "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, (txreq.offset&~PAGE_MASK) + txreq.size); - netbk_tx_err(vif, &txreq, idx); - continue; + xenvif_fatal_tx_err(queue->vif); + break; } - index = pending_index(netbk->pending_cons); - pending_idx = netbk->pending_ring[index]; + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; data_len = (txreq.size > PKT_PROT_LEN && - ret < MAX_SKB_FRAGS) ? + ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? PKT_PROT_LEN : txreq.size; - skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN, - GFP_ATOMIC | __GFP_NOWARN); + skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Can't allocate a skb in start_xmit.\n"); - netbk_tx_err(vif, &txreq, idx); + xenvif_tx_err(queue, &txreq, idx); break; } - /* Packets passed to netif_rx() must have some headroom. */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; - if (netbk_set_skb_gso(vif, skb, gso)) { + if (xenvif_set_skb_gso(queue->vif, skb, gso)) { + /* Failure in xenvif_set_skb_gso is fatal. */ kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); - continue; + break; } } - /* XXX could copy straight to head */ - page = xen_netbk_alloc_page(netbk, skb, pending_idx); - if (!page) { - kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); - continue; - } + XENVIF_TX_CB(skb)->pending_idx = pending_idx; - gop->source.u.ref = txreq.gref; - gop->source.domid = vif->domid; - gop->source.offset = txreq.offset; - - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - gop->dest.domid = DOMID_SELF; - gop->dest.offset = txreq.offset; - - gop->len = txreq.size; - gop->flags = GNTCOPY_source_gref; + __skb_put(skb, data_len); + queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; + queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; + queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; - gop++; + queue->tx_copy_ops[*copy_ops].dest.u.gmfn = + virt_to_mfn(skb->data); + queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; + queue->tx_copy_ops[*copy_ops].dest.offset = + offset_in_page(skb->data); - memcpy(&netbk->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - netbk->pending_tx_info[pending_idx].vif = vif; - *((u16 *)skb->data) = pending_idx; + queue->tx_copy_ops[*copy_ops].len = data_len; + queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; - __skb_put(skb, data_len); + (*copy_ops)++; skb_shinfo(skb)->nr_frags = ret; if (data_len < txreq.size) { skb_shinfo(skb)->nr_frags++; frag_set_pending_idx(&skb_shinfo(skb)->frags[0], pending_idx); + xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop); + gop++; } else { frag_set_pending_idx(&skb_shinfo(skb)->frags[0], INVALID_PENDING_IDX); + memcpy(&queue->pending_tx_info[pending_idx].req, &txreq, + sizeof(txreq)); } - __skb_queue_tail(&netbk->tx_queue, skb); - - netbk->pending_cons++; + queue->pending_cons++; - request_gop = xen_netbk_get_requests(netbk, vif, - skb, txfrags, gop); + request_gop = xenvif_get_requests(queue, skb, txfrags, gop); if (request_gop == NULL) { kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); - continue; + xenvif_tx_err(queue, &txreq, idx); + break; } gop = request_gop; - vif->tx.req_cons = idx; - xen_netbk_check_rx_xenvif(vif); + __skb_queue_tail(&queue->tx_queue, skb); + + queue->tx.req_cons = idx; - if ((gop-netbk->tx_copy_ops) >= ARRAY_SIZE(netbk->tx_copy_ops)) + if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) break; } - return gop - netbk->tx_copy_ops; + (*map_ops) = gop - queue->tx_map_ops; + return; } -static void xen_netbk_tx_submit(struct xen_netbk *netbk) +/* Consolidate skb with a frag_list into a brand new one with local pages on + * frags. Returns 0 or -ENOMEM if can't allocate new pages. + */ +static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb) { - struct gnttab_copy *gop = netbk->tx_copy_ops; + unsigned int offset = skb_headlen(skb); + skb_frag_t frags[MAX_SKB_FRAGS]; + int i; + struct ubuf_info *uarg; + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + + queue->stats.tx_zerocopy_sent += 2; + queue->stats.tx_frag_overflow++; + + xenvif_fill_frags(queue, nskb); + /* Subtract frags size, we will correct it later */ + skb->truesize -= skb->data_len; + skb->len += nskb->len; + skb->data_len += nskb->len; + + /* create a brand new frags array and coalesce there */ + for (i = 0; offset < skb->len; i++) { + struct page *page; + unsigned int len; + + BUG_ON(i >= MAX_SKB_FRAGS); + page = alloc_page(GFP_ATOMIC|__GFP_COLD); + if (!page) { + int j; + skb->truesize += skb->data_len; + for (j = 0; j < i; j++) + put_page(frags[j].page.p); + return -ENOMEM; + } + + if (offset + PAGE_SIZE < skb->len) + len = PAGE_SIZE; + else + len = skb->len - offset; + if (skb_copy_bits(skb, offset, page_address(page), len)) + BUG(); + + offset += len; + frags[i].page.p = page; + frags[i].page_offset = 0; + skb_frag_size_set(&frags[i], len); + } + /* swap out with old one */ + memcpy(skb_shinfo(skb)->frags, + frags, + i * sizeof(skb_frag_t)); + skb_shinfo(skb)->nr_frags = i; + skb->truesize += i * PAGE_SIZE; + + /* remove traces of mapped pages and frag_list */ + skb_frag_list_init(skb); + uarg = skb_shinfo(skb)->destructor_arg; + uarg->callback(uarg, true); + skb_shinfo(skb)->destructor_arg = NULL; + + skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(nskb); + + return 0; +} + +static int xenvif_tx_submit(struct xenvif_queue *queue) +{ + struct gnttab_map_grant_ref *gop_map = queue->tx_map_ops; + struct gnttab_copy *gop_copy = queue->tx_copy_ops; struct sk_buff *skb; + int work_done = 0; - while ((skb = __skb_dequeue(&netbk->tx_queue)) != NULL) { + while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; - struct xenvif *vif; u16 pending_idx; unsigned data_len; - pending_idx = *((u16 *)skb->data); - vif = netbk->pending_tx_info[pending_idx].vif; - txp = &netbk->pending_tx_info[pending_idx].req; + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + txp = &queue->pending_tx_info[pending_idx].req; /* Check the remap error code. */ - if (unlikely(xen_netbk_tx_check_gop(netbk, skb, &gop))) { - netdev_dbg(vif->dev, "netback grant failed.\n"); + if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) { + /* If there was an error, xenvif_tx_check_gop is + * expected to release all the frags which were mapped, + * so kfree_skb shouldn't do it again + */ skb_shinfo(skb)->nr_frags = 0; + if (skb_has_frag_list(skb)) { + struct sk_buff *nskb = + skb_shinfo(skb)->frag_list; + skb_shinfo(nskb)->nr_frags = 0; + } kfree_skb(skb); continue; } data_len = skb->len; - memcpy(skb->data, - (void *)(idx_to_kaddr(netbk, pending_idx)|txp->offset), - data_len); + callback_param(queue, pending_idx).ctx = NULL; if (data_len < txp->size) { /* Append the packet payload as a fragment. */ txp->offset += data_len; txp->size -= data_len; } else { /* Schedule a response immediately. */ - xen_netbk_idx_release(netbk, pending_idx); + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1428,111 +1582,253 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk) else if (txp->flags & XEN_NETTXF_data_validated) skb->ip_summed = CHECKSUM_UNNECESSARY; - xen_netbk_fill_frags(netbk, skb); + xenvif_fill_frags(queue, skb); - /* - * If the initial fragment was < PKT_PROT_LEN then - * pull through some bytes from the other fragments to - * increase the linear region to PKT_PROT_LEN bytes. - */ - if (skb_headlen(skb) < PKT_PROT_LEN && skb_is_nonlinear(skb)) { + if (unlikely(skb_has_frag_list(skb))) { + if (xenvif_handle_frag_list(queue, skb)) { + if (net_ratelimit()) + netdev_err(queue->vif->dev, + "Not enough memory to consolidate frag_list!\n"); + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(skb); + continue; + } + } + + if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) { int target = min_t(int, skb->len, PKT_PROT_LEN); __pskb_pull_tail(skb, target - skb_headlen(skb)); } - skb->dev = vif->dev; + skb->dev = queue->vif->dev; skb->protocol = eth_type_trans(skb, skb->dev); + skb_reset_network_header(skb); - if (checksum_setup(vif, skb)) { - netdev_dbg(vif->dev, + if (checksum_setup(queue, skb)) { + netdev_dbg(queue->vif->dev, "Can't setup checksum in net_tx_action\n"); + /* We have to set this flag to trigger the callback */ + if (skb_shinfo(skb)->destructor_arg) + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; kfree_skb(skb); continue; } - vif->dev->stats.rx_bytes += skb->len; - vif->dev->stats.rx_packets++; + skb_probe_transport_header(skb, 0); + + /* If the packet is GSO then we will have just set up the + * transport header offset in checksum_setup so it's now + * straightforward to calculate gso_segs. + */ + if (skb_is_gso(skb)) { + int mss = skb_shinfo(skb)->gso_size; + int hdrlen = skb_transport_header(skb) - + skb_mac_header(skb) + + tcp_hdrlen(skb); + + skb_shinfo(skb)->gso_segs = + DIV_ROUND_UP(skb->len - hdrlen, mss); + } + + queue->stats.rx_bytes += skb->len; + queue->stats.rx_packets++; + + work_done++; + + /* Set this flag right before netif_receive_skb, otherwise + * someone might think this packet already left netback, and + * do a skb_copy_ubufs while we are still in control of the + * skb. E.g. the __pskb_pull_tail earlier can do such thing. + */ + if (skb_shinfo(skb)->destructor_arg) { + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + queue->stats.tx_zerocopy_sent++; + } - xenvif_receive_skb(vif, skb); + netif_receive_skb(skb); } + + return work_done; } -/* Called after netfront has transmitted */ -static void xen_netbk_tx_action(struct xen_netbk *netbk) +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) { - unsigned nr_gops; - int ret; + unsigned long flags; + pending_ring_idx_t index; + struct xenvif_queue *queue = ubuf_to_queue(ubuf); - nr_gops = xen_netbk_tx_build_gops(netbk); + /* This is the only place where we grab this lock, to protect callbacks + * from each other. + */ + spin_lock_irqsave(&queue->callback_lock, flags); + do { + u16 pending_idx = ubuf->desc; + ubuf = (struct ubuf_info *) ubuf->ctx; + BUG_ON(queue->dealloc_prod - queue->dealloc_cons >= + MAX_PENDING_REQS); + index = pending_index(queue->dealloc_prod); + queue->dealloc_ring[index] = pending_idx; + /* Sync with xenvif_tx_dealloc_action: + * insert idx then incr producer. + */ + smp_wmb(); + queue->dealloc_prod++; + } while (ubuf); + wake_up(&queue->dealloc_wq); + spin_unlock_irqrestore(&queue->callback_lock, flags); + + if (likely(zerocopy_success)) + queue->stats.tx_zerocopy_success++; + else + queue->stats.tx_zerocopy_fail++; +} - if (nr_gops == 0) - return; - ret = HYPERVISOR_grant_table_op(GNTTABOP_copy, - netbk->tx_copy_ops, nr_gops); - BUG_ON(ret); +static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) +{ + struct gnttab_unmap_grant_ref *gop; + pending_ring_idx_t dc, dp; + u16 pending_idx, pending_idx_release[MAX_PENDING_REQS]; + unsigned int i = 0; - xen_netbk_tx_submit(netbk); + dc = queue->dealloc_cons; + gop = queue->tx_unmap_ops; + /* Free up any grants we have finished using */ + do { + dp = queue->dealloc_prod; + + /* Ensure we see all indices enqueued by all + * xenvif_zerocopy_callback(). + */ + smp_rmb(); + + while (dc != dp) { + BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS); + pending_idx = + queue->dealloc_ring[pending_index(dc++)]; + + pending_idx_release[gop-queue->tx_unmap_ops] = + pending_idx; + queue->pages_to_unmap[gop-queue->tx_unmap_ops] = + queue->mmap_pages[pending_idx]; + gnttab_set_unmap_op(gop, + idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map, + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); + ++gop; + } + + } while (dp != queue->dealloc_prod); + + queue->dealloc_cons = dc; + + if (gop - queue->tx_unmap_ops > 0) { + int ret; + ret = gnttab_unmap_refs(queue->tx_unmap_ops, + NULL, + queue->pages_to_unmap, + gop - queue->tx_unmap_ops); + if (ret) { + netdev_err(queue->vif->dev, "Unmap fail: nr_ops %tx ret %d\n", + gop - queue->tx_unmap_ops, ret); + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) { + if (gop[i].status != GNTST_okay) + netdev_err(queue->vif->dev, + " host_addr: %llx handle: %x status: %d\n", + gop[i].host_addr, + gop[i].handle, + gop[i].status); + } + BUG(); + } + } + + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) + xenvif_idx_release(queue, pending_idx_release[i], + XEN_NETIF_RSP_OKAY); } -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx) + +/* Called after netfront has transmitted */ +int xenvif_tx_action(struct xenvif_queue *queue, int budget) { - struct xenvif *vif; - struct pending_tx_info *pending_tx_info; - pending_ring_idx_t index; + unsigned nr_mops, nr_cops = 0; + int work_done, ret; - /* Already complete? */ - if (netbk->mmap_pages[pending_idx] == NULL) - return; + if (unlikely(!tx_work_todo(queue))) + return 0; - pending_tx_info = &netbk->pending_tx_info[pending_idx]; + xenvif_tx_build_gops(queue, budget, &nr_cops, &nr_mops); - vif = pending_tx_info->vif; + if (nr_cops == 0) + return 0; - make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY); + gnttab_batch_copy(queue->tx_copy_ops, nr_cops); + if (nr_mops != 0) { + ret = gnttab_map_refs(queue->tx_map_ops, + NULL, + queue->pages_to_map, + nr_mops); + BUG_ON(ret); + } - index = pending_index(netbk->pending_prod++); - netbk->pending_ring[index] = pending_idx; + work_done = xenvif_tx_submit(queue); - xenvif_put(vif); + return work_done; +} - netbk->mmap_pages[pending_idx]->mapping = 0; - put_page(netbk->mmap_pages[pending_idx]); - netbk->mmap_pages[pending_idx] = NULL; +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, + u8 status) +{ + struct pending_tx_info *pending_tx_info; + pending_ring_idx_t index; + unsigned long flags; + + pending_tx_info = &queue->pending_tx_info[pending_idx]; + spin_lock_irqsave(&queue->response_lock, flags); + make_tx_response(queue, &pending_tx_info->req, status); + index = pending_index(queue->pending_prod); + queue->pending_ring[index] = pending_idx; + /* TX shouldn't use the index before we give it back here */ + mb(); + queue->pending_prod++; + spin_unlock_irqrestore(&queue->response_lock, flags); } -static void make_tx_response(struct xenvif *vif, + +static void make_tx_response(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, s8 st) { - RING_IDX i = vif->tx.rsp_prod_pvt; + RING_IDX i = queue->tx.rsp_prod_pvt; struct xen_netif_tx_response *resp; int notify; - resp = RING_GET_RESPONSE(&vif->tx, i); + resp = RING_GET_RESPONSE(&queue->tx, i); resp->id = txp->id; resp->status = st; if (txp->flags & XEN_NETTXF_extra_info) - RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL; + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; - vif->tx.rsp_prod_pvt = ++i; - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify); + queue->tx.rsp_prod_pvt = ++i; + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) - notify_remote_via_irq(vif->irq); + notify_remote_via_irq(queue->tx_irq); } -static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, s8 st, u16 offset, u16 size, u16 flags) { - RING_IDX i = vif->rx.rsp_prod_pvt; + RING_IDX i = queue->rx.rsp_prod_pvt; struct xen_netif_rx_response *resp; - resp = RING_GET_RESPONSE(&vif->rx, i); + resp = RING_GET_RESPONSE(&queue->rx, i); resp->offset = offset; resp->flags = flags; resp->id = id; @@ -1540,62 +1836,69 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, if (st < 0) resp->status = (s16)st; - vif->rx.rsp_prod_pvt = ++i; + queue->rx.rsp_prod_pvt = ++i; return resp; } -static inline int rx_work_todo(struct xen_netbk *netbk) +void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) { - return !skb_queue_empty(&netbk->rx_queue); + int ret; + struct gnttab_unmap_grant_ref tx_unmap_op; + + gnttab_set_unmap_op(&tx_unmap_op, + idx_to_kaddr(queue, pending_idx), + GNTMAP_host_map, + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); + + ret = gnttab_unmap_refs(&tx_unmap_op, NULL, + &queue->mmap_pages[pending_idx], 1); + if (ret) { + netdev_err(queue->vif->dev, + "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n", + ret, + pending_idx, + tx_unmap_op.host_addr, + tx_unmap_op.handle, + tx_unmap_op.status); + BUG(); + } } -static inline int tx_work_todo(struct xen_netbk *netbk) +static inline int rx_work_todo(struct xenvif_queue *queue) { + return (!skb_queue_empty(&queue->rx_queue) && + xenvif_rx_ring_slots_available(queue, queue->rx_last_skb_slots)) || + queue->rx_queue_purge; +} - if (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) && - !list_empty(&netbk->net_schedule_list)) +static inline int tx_work_todo(struct xenvif_queue *queue) +{ + if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))) return 1; return 0; } -static int xen_netbk_kthread(void *data) +static inline bool tx_dealloc_work_todo(struct xenvif_queue *queue) { - struct xen_netbk *netbk = data; - while (!kthread_should_stop()) { - wait_event_interruptible(netbk->wq, - rx_work_todo(netbk) || - tx_work_todo(netbk) || - kthread_should_stop()); - cond_resched(); - - if (kthread_should_stop()) - break; - - if (rx_work_todo(netbk)) - xen_netbk_rx_action(netbk); - - if (tx_work_todo(netbk)) - xen_netbk_tx_action(netbk); - } - - return 0; + return queue->dealloc_cons != queue->dealloc_prod; } -void xen_netbk_unmap_frontend_rings(struct xenvif *vif) +void xenvif_unmap_frontend_rings(struct xenvif_queue *queue) { - if (vif->tx.sring) - xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), - vif->tx.sring); - if (vif->rx.sring) - xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), - vif->rx.sring); + if (queue->tx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->tx.sring); + if (queue->rx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->rx.sring); } -int xen_netbk_map_frontend_rings(struct xenvif *vif, - grant_ref_t tx_ring_ref, - grant_ref_t rx_ring_ref) +int xenvif_map_frontend_rings(struct xenvif_queue *queue, + grant_ref_t tx_ring_ref, + grant_ref_t rx_ring_ref) { void *addr; struct xen_netif_tx_sring *txs; @@ -1603,106 +1906,140 @@ int xen_netbk_map_frontend_rings(struct xenvif *vif, int err = -ENOMEM; - err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif), + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), tx_ring_ref, &addr); if (err) goto err; txs = (struct xen_netif_tx_sring *)addr; - BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE); + BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE); - err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif), + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), rx_ring_ref, &addr); if (err) goto err; rxs = (struct xen_netif_rx_sring *)addr; - BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE); - - vif->rx_req_cons_peek = 0; + BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE); return 0; err: - xen_netbk_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(queue); return err; } -static int __init netback_init(void) +static void xenvif_start_queue(struct xenvif_queue *queue) { - int i; - int rc = 0; - int group; + if (xenvif_schedulable(queue->vif)) + xenvif_wake_queue(queue); +} - if (!xen_domain()) - return -ENODEV; +int xenvif_kthread_guest_rx(void *data) +{ + struct xenvif_queue *queue = data; + struct sk_buff *skb; - xen_netbk_group_nr = num_online_cpus(); - xen_netbk = vzalloc(sizeof(struct xen_netbk) * xen_netbk_group_nr); - if (!xen_netbk) { - printk(KERN_ALERT "%s: out of memory\n", __func__); - return -ENOMEM; - } + while (!kthread_should_stop()) { + wait_event_interruptible(queue->wq, + rx_work_todo(queue) || + queue->vif->disabled || + kthread_should_stop()); + + /* This frontend is found to be rogue, disable it in + * kthread context. Currently this is only set when + * netback finds out frontend sends malformed packet, + * but we cannot disable the interface in softirq + * context so we defer it here, if this thread is + * associated with queue 0. + */ + if (unlikely(queue->vif->disabled && netif_carrier_ok(queue->vif->dev) && queue->id == 0)) + xenvif_carrier_off(queue->vif); - for (group = 0; group < xen_netbk_group_nr; group++) { - struct xen_netbk *netbk = &xen_netbk[group]; - skb_queue_head_init(&netbk->rx_queue); - skb_queue_head_init(&netbk->tx_queue); - - init_timer(&netbk->net_timer); - netbk->net_timer.data = (unsigned long)netbk; - netbk->net_timer.function = xen_netbk_alarm; - - netbk->pending_cons = 0; - netbk->pending_prod = MAX_PENDING_REQS; - for (i = 0; i < MAX_PENDING_REQS; i++) - netbk->pending_ring[i] = i; - - init_waitqueue_head(&netbk->wq); - netbk->task = kthread_create(xen_netbk_kthread, - (void *)netbk, - "netback/%u", group); - - if (IS_ERR(netbk->task)) { - printk(KERN_ALERT "kthread_create() fails at netback\n"); - del_timer(&netbk->net_timer); - rc = PTR_ERR(netbk->task); - goto failed_init; + if (kthread_should_stop()) + break; + + if (queue->rx_queue_purge) { + skb_queue_purge(&queue->rx_queue); + queue->rx_queue_purge = false; } - kthread_bind(netbk->task, group); + if (!skb_queue_empty(&queue->rx_queue)) + xenvif_rx_action(queue); + + if (skb_queue_empty(&queue->rx_queue) && + xenvif_queue_stopped(queue)) { + del_timer_sync(&queue->wake_queue); + xenvif_start_queue(queue); + } + + cond_resched(); + } + + /* Bin any remaining skbs */ + while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) + dev_kfree_skb(skb); + + return 0; +} + +int xenvif_dealloc_kthread(void *data) +{ + struct xenvif_queue *queue = data; + + while (!kthread_should_stop()) { + wait_event_interruptible(queue->dealloc_wq, + tx_dealloc_work_todo(queue) || + kthread_should_stop()); + if (kthread_should_stop()) + break; - INIT_LIST_HEAD(&netbk->net_schedule_list); + xenvif_tx_dealloc_action(queue); + cond_resched(); + } - spin_lock_init(&netbk->net_schedule_list_lock); + /* Unmap anything remaining*/ + if (tx_dealloc_work_todo(queue)) + xenvif_tx_dealloc_action(queue); - atomic_set(&netbk->netfront_count, 0); + return 0; +} - wake_up_process(netbk->task); +static int __init netback_init(void) +{ + int rc = 0; + + if (!xen_domain()) + return -ENODEV; + + /* Allow as many queues as there are CPUs, by default */ + xenvif_max_queues = num_online_cpus(); + + if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) { + pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n", + fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX); + fatal_skb_slots = XEN_NETBK_LEGACY_SLOTS_MAX; } rc = xenvif_xenbus_init(); if (rc) goto failed_init; + rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs); + return 0; failed_init: - while (--group >= 0) { - struct xen_netbk *netbk = &xen_netbk[group]; - for (i = 0; i < MAX_PENDING_REQS; i++) { - if (netbk->mmap_pages[i]) - __free_page(netbk->mmap_pages[i]); - } - del_timer(&netbk->net_timer); - kthread_stop(netbk->task); - } - vfree(xen_netbk); return rc; - } module_init(netback_init); +static void __exit netback_fini(void) +{ + xenvif_xenbus_fini(); +} +module_exit(netback_fini); + MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("xen-backend:vif"); |