diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2009-09-17 13:30:15 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2009-09-17 13:30:15 +1000 |
commit | 4a92b1a8e35d68eb17351a9fc138e29284b2afda (patch) | |
tree | 686cca59f1b1ddd153c3906f93d466fef475572d /drivers | |
parent | ccdca83306e60de0452459d39a6be9935a2a5ba7 (diff) | |
parent | 1bd0e3809cd71567bb19059bb4818a9324771a40 (diff) |
Merge commit 'refs/next/20090908/rr'
Conflicts:
drivers/net/virtio_net.c
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/acpi/osl.c | 2 | ||||
-rw-r--r-- | drivers/acpi/processor_perflib.c | 3 | ||||
-rw-r--r-- | drivers/acpi/processor_throttling.c | 3 | ||||
-rw-r--r-- | drivers/block/virtio_blk.c | 3 | ||||
-rw-r--r-- | drivers/char/hw_random/virtio-rng.c | 3 | ||||
-rw-r--r-- | drivers/char/virtio_console.c | 5 | ||||
-rw-r--r-- | drivers/lguest/core.c | 5 | ||||
-rw-r--r-- | drivers/lguest/page_tables.c | 45 | ||||
-rw-r--r-- | drivers/net/sfc/efx.c | 3 | ||||
-rw-r--r-- | drivers/net/virtio_net.c | 236 | ||||
-rw-r--r-- | drivers/oprofile/buffer_sync.c | 3 | ||||
-rw-r--r-- | drivers/virtio/virtio_balloon.c | 3 | ||||
-rw-r--r-- | drivers/virtio/virtio_pci.c | 125 | ||||
-rw-r--r-- | drivers/virtio/virtio_ring.c | 6 |
14 files changed, 202 insertions, 243 deletions
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index c5b4f1ed9b71..d2eb6a4ba9f1 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -192,7 +192,7 @@ acpi_status __init acpi_os_initialize(void) static void bind_to_cpu0(struct work_struct *work) { - set_cpus_allowed(current, cpumask_of_cpu(0)); + set_cpus_allowed_ptr(current, cpumask_of(0)); kfree(work); } diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 11088cf10319..8ba0ed0b9ddb 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -511,7 +511,7 @@ int acpi_processor_preregister_performance( struct acpi_processor *match_pr; struct acpi_psd_package *match_pdomain; - if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL)) return -ENOMEM; mutex_lock(&performance_mutex); @@ -558,7 +558,6 @@ int acpi_processor_preregister_performance( * Now that we have _PSD data from all CPUs, lets setup P-state * domain info. */ - cpumask_clear(covered_cpus); for_each_possible_cpu(i) { pr = per_cpu(processors, i); if (!pr) diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index ce7cf3bc5101..4c6c14c1e307 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -77,7 +77,7 @@ static int acpi_processor_update_tsd_coord(void) struct acpi_tsd_package *pdomain, *match_pdomain; struct acpi_processor_throttling *pthrottling, *match_pthrottling; - if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL)) return -ENOMEM; /* @@ -105,7 +105,6 @@ static int acpi_processor_update_tsd_coord(void) if (retval) goto err_ret; - cpumask_clear(covered_cpus); for_each_possible_cpu(i) { pr = per_cpu(processors, i); if (!pr) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index aa1a3d5a3e2b..73de7532fcf5 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -3,6 +3,7 @@ #include <linux/blkdev.h> #include <linux/hdreg.h> #include <linux/virtio.h> +#include <linux/virtio_ids.h> #include <linux/virtio_blk.h> #include <linux/scatterlist.h> @@ -139,7 +140,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, } } - if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) { + if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr) < 0) { mempool_free(vbr, vblk->pool); return false; } diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 32216b623248..962968f05b94 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -21,6 +21,7 @@ #include <linux/scatterlist.h> #include <linux/spinlock.h> #include <linux/virtio.h> +#include <linux/virtio_ids.h> #include <linux/virtio_rng.h> /* The host will fill any buffer we give it with sweet, sweet randomness. We @@ -51,7 +52,7 @@ static void register_buffer(void) sg_init_one(&sg, random_data+data_left, RANDOM_DATA_SIZE-data_left); /* There should always be room for one buffer. */ - if (vq->vq_ops->add_buf(vq, &sg, 0, 1, random_data) != 0) + if (vq->vq_ops->add_buf(vq, &sg, 0, 1, random_data) < 0) BUG(); vq->vq_ops->kick(vq); } diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index c74dacfa6795..0d328b59568d 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -31,6 +31,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/virtio.h> +#include <linux/virtio_ids.h> #include <linux/virtio_console.h> #include "hvc_console.h" @@ -65,7 +66,7 @@ static int put_chars(u32 vtermno, const char *buf, int count) /* add_buf wants a token to identify this buffer: we hand it any * non-NULL pointer, since there's only ever one buffer. */ - if (out_vq->vq_ops->add_buf(out_vq, sg, 1, 0, (void *)1) == 0) { + if (out_vq->vq_ops->add_buf(out_vq, sg, 1, 0, (void *)1) >= 0) { /* Tell Host to go! */ out_vq->vq_ops->kick(out_vq); /* Chill out until it's done with the buffer. */ @@ -85,7 +86,7 @@ static void add_inbuf(void) sg_init_one(sg, inbuf, PAGE_SIZE); /* We should always be able to add one buffer to an empty queue. */ - if (in_vq->vq_ops->add_buf(in_vq, sg, 0, 1, inbuf) != 0) + if (in_vq->vq_ops->add_buf(in_vq, sg, 0, 1, inbuf) < 0) BUG(); in_vq->vq_ops->kick(in_vq); } diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 1e2cb846b3c9..8744d24ac6e6 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -67,12 +67,11 @@ static __init int map_switcher(void) * so we make sure they're zeroed. */ for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) { - unsigned long addr = get_zeroed_page(GFP_KERNEL); - if (!addr) { + switcher_page[i] = alloc_page(GFP_KERNEL|__GFP_ZERO); + if (!switcher_page[i]) { err = -ENOMEM; goto free_some_pages; } - switcher_page[i] = virt_to_page(addr); } /* diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c index a8d0aee3bc0e..bf37a31c0e05 100644 --- a/drivers/lguest/page_tables.c +++ b/drivers/lguest/page_tables.c @@ -380,7 +380,7 @@ bool demand_page(struct lg_cpu *cpu, unsigned long vaddr, int errcode) * And we copy the flags to the shadow PMD entry. The page * number in the shadow PMD is the page we just allocated. */ - native_set_pmd(spmd, __pmd(__pa(ptepage) | pmd_flags(gpmd))); + set_pmd(spmd, __pmd(__pa(ptepage) | pmd_flags(gpmd))); } /* @@ -447,7 +447,7 @@ bool demand_page(struct lg_cpu *cpu, unsigned long vaddr, int errcode) * we will come back here when a write does actually occur, so * we can update the Guest's _PAGE_DIRTY flag. */ - native_set_pte(spte, gpte_to_spte(cpu, pte_wrprotect(gpte), 0)); + set_pte(spte, gpte_to_spte(cpu, pte_wrprotect(gpte), 0)); /* * Finally, we write the Guest PTE entry back: we've set the @@ -528,7 +528,7 @@ static void release_pmd(pmd_t *spmd) /* Now we can free the page of PTEs */ free_page((long)ptepage); /* And zero out the PMD entry so we never release it twice. */ - native_set_pmd(spmd, __pmd(0)); + set_pmd(spmd, __pmd(0)); } } @@ -833,15 +833,15 @@ static void do_set_pte(struct lg_cpu *cpu, int idx, */ if (pte_flags(gpte) & (_PAGE_DIRTY | _PAGE_ACCESSED)) { check_gpte(cpu, gpte); - native_set_pte(spte, - gpte_to_spte(cpu, gpte, + set_pte(spte, + gpte_to_spte(cpu, gpte, pte_flags(gpte) & _PAGE_DIRTY)); } else { /* * Otherwise kill it and we can demand_page() * it in later. */ - native_set_pte(spte, __pte(0)); + set_pte(spte, __pte(0)); } #ifdef CONFIG_X86_PAE } @@ -983,25 +983,22 @@ static unsigned long setup_pagetables(struct lguest *lg, */ for (i = j = 0; i < mapped_pages && j < PTRS_PER_PMD; i += PTRS_PER_PTE, j++) { - /* FIXME: native_set_pmd is overkill here. */ - native_set_pmd(&pmd, __pmd(((unsigned long)(linear + i) - - mem_base) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER)); + pmd = pfn_pmd(((unsigned long)&linear[i] - mem_base)/PAGE_SIZE, + __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER)); if (copy_to_user(&pmds[j], &pmd, sizeof(pmd)) != 0) return -EFAULT; } /* One PGD entry, pointing to that PMD page. */ - set_pgd(&pgd, __pgd(((u32)pmds - mem_base) | _PAGE_PRESENT)); + pgd = __pgd(((unsigned long)pmds - mem_base) | _PAGE_PRESENT); /* Copy it in as the first PGD entry (ie. addresses 0-1G). */ if (copy_to_user(&pgdir[0], &pgd, sizeof(pgd)) != 0) return -EFAULT; /* - * And the third PGD entry (ie. addresses 3G-4G). - * - * FIXME: This assumes that PAGE_OFFSET for the Guest is 0xC0000000. + * And the other PGD entry to make the linear mapping at PAGE_OFFSET */ - if (copy_to_user(&pgdir[3], &pgd, sizeof(pgd)) != 0) + if (copy_to_user(&pgdir[KERNEL_PGD_BOUNDARY], &pgd, sizeof(pgd))) return -EFAULT; #else /* @@ -1141,15 +1138,13 @@ void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages) { pte_t *switcher_pte_page = __get_cpu_var(switcher_pte_pages); pte_t regs_pte; - unsigned long pfn; #ifdef CONFIG_X86_PAE pmd_t switcher_pmd; pmd_t *pmd_table; - /* FIXME: native_set_pmd is overkill here. */ - native_set_pmd(&switcher_pmd, pfn_pmd(__pa(switcher_pte_page) >> - PAGE_SHIFT, PAGE_KERNEL_EXEC)); + switcher_pmd = pfn_pmd(__pa(switcher_pte_page) >> PAGE_SHIFT, + PAGE_KERNEL_EXEC); /* Figure out where the pmd page is, by reading the PGD, and converting * it to a virtual address. */ @@ -1157,7 +1152,7 @@ void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages) pgdirs[cpu->cpu_pgd].pgdir[SWITCHER_PGD_INDEX]) << PAGE_SHIFT); /* Now write it into the shadow page table. */ - native_set_pmd(&pmd_table[SWITCHER_PMD_INDEX], switcher_pmd); + set_pmd(&pmd_table[SWITCHER_PMD_INDEX], switcher_pmd); #else pgd_t switcher_pgd; @@ -1179,10 +1174,8 @@ void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages) * page is already mapped there, we don't have to copy them out * again. */ - pfn = __pa(cpu->regs_page) >> PAGE_SHIFT; - native_set_pte(®s_pte, pfn_pte(pfn, PAGE_KERNEL)); - native_set_pte(&switcher_pte_page[pte_index((unsigned long)pages)], - regs_pte); + regs_pte = pfn_pte(__pa(cpu->regs_page) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte(&switcher_pte_page[pte_index((unsigned long)pages)], regs_pte); } /*:*/ @@ -1209,7 +1202,7 @@ static __init void populate_switcher_pte_page(unsigned int cpu, /* The first entries are easy: they map the Switcher code. */ for (i = 0; i < pages; i++) { - native_set_pte(&pte[i], mk_pte(switcher_page[i], + set_pte(&pte[i], mk_pte(switcher_page[i], __pgprot(_PAGE_PRESENT|_PAGE_ACCESSED))); } @@ -1217,14 +1210,14 @@ static __init void populate_switcher_pte_page(unsigned int cpu, i = pages + cpu*2; /* First page (Guest registers) is writable from the Guest */ - native_set_pte(&pte[i], pfn_pte(page_to_pfn(switcher_page[i]), + set_pte(&pte[i], pfn_pte(page_to_pfn(switcher_page[i]), __pgprot(_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_RW))); /* * The second page contains the "struct lguest_ro_state", and is * read-only. */ - native_set_pte(&pte[i+1], pfn_pte(page_to_pfn(switcher_page[i+1]), + set_pte(&pte[i+1], pfn_pte(page_to_pfn(switcher_page[i+1]), __pgprot(_PAGE_PRESENT|_PAGE_ACCESSED))); } diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index 07a7e4b8f8fc..cc4b2f99989d 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -884,13 +884,12 @@ static int efx_wanted_rx_queues(void) int count; int cpu; - if (unlikely(!alloc_cpumask_var(&core_mask, GFP_KERNEL))) { + if (unlikely(!zalloc_cpumask_var(&core_mask, GFP_KERNEL))) { printk(KERN_WARNING "sfc: RSS disabled due to allocation failure\n"); return 1; } - cpumask_clear(core_mask); count = 0; for_each_online_cpu(cpu) { if (!cpumask_test_cpu(cpu, core_mask)) { diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 32266fb89c20..d445845f2779 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1,4 +1,4 @@ -/* A simple network driver using virtio. +/* A network driver using virtio. * * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation * @@ -22,6 +22,7 @@ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/virtio.h> +#include <linux/virtio_ids.h> #include <linux/virtio_net.h> #include <linux/scatterlist.h> #include <linux/if_vlan.h> @@ -47,19 +48,9 @@ struct virtnet_info struct napi_struct napi; unsigned int status; - /* The skb we couldn't send because buffers were full. */ - struct sk_buff *last_xmit_skb; - - /* If we need to free in a timer, this is it. */ - struct timer_list xmit_free_timer; - /* Number of input buffers, and max we've ever had. */ unsigned int num, max; - /* For cleaning up after transmission. */ - struct tasklet_struct tasklet; - bool free_in_tasklet; - /* I like... big packets and I cannot lie! */ bool big_packets; @@ -77,9 +68,17 @@ struct virtnet_info struct page *pages; }; -static inline void *skb_vnet_hdr(struct sk_buff *skb) +struct skb_vnet_hdr { + union { + struct virtio_net_hdr hdr; + struct virtio_net_hdr_mrg_rxbuf mhdr; + }; + unsigned int num_sg; +}; + +static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb) { - return (struct virtio_net_hdr *)skb->cb; + return (struct skb_vnet_hdr *)skb->cb; } static void give_a_page(struct virtnet_info *vi, struct page *page) @@ -118,17 +117,13 @@ static void skb_xmit_done(struct virtqueue *svq) /* We were probably waiting for more output buffers. */ netif_wake_queue(vi->dev); - - /* Make sure we re-xmit last_xmit_skb: if there are no more packets - * queued, start_xmit won't be called. */ - tasklet_schedule(&vi->tasklet); } static void receive_skb(struct net_device *dev, struct sk_buff *skb, unsigned len) { struct virtnet_info *vi = netdev_priv(dev); - struct virtio_net_hdr *hdr = skb_vnet_hdr(skb); + struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb); int err; int i; @@ -139,7 +134,6 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, } if (vi->mergeable_rx_bufs) { - struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb); unsigned int copy; char *p = page_address(skb_shinfo(skb)->frags[0].page); @@ -147,8 +141,8 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, len = PAGE_SIZE; len -= sizeof(struct virtio_net_hdr_mrg_rxbuf); - memcpy(hdr, p, sizeof(*mhdr)); - p += sizeof(*mhdr); + memcpy(&hdr->mhdr, p, sizeof(hdr->mhdr)); + p += sizeof(hdr->mhdr); copy = len; if (copy > skb_tailroom(skb)) @@ -163,13 +157,13 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, skb_shinfo(skb)->nr_frags--; } else { skb_shinfo(skb)->frags[0].page_offset += - sizeof(*mhdr) + copy; + sizeof(hdr->mhdr) + copy; skb_shinfo(skb)->frags[0].size = len; skb->data_len += len; skb->len += len; } - while (--mhdr->num_buffers) { + while (--hdr->mhdr.num_buffers) { struct sk_buff *nskb; i = skb_shinfo(skb)->nr_frags; @@ -183,7 +177,7 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, nskb = vi->rvq->vq_ops->get_buf(vi->rvq, &len); if (!nskb) { pr_debug("%s: rx error: %d buffers missing\n", - dev->name, mhdr->num_buffers); + dev->name, hdr->mhdr.num_buffers); dev->stats.rx_length_errors++; goto drop; } @@ -204,7 +198,7 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, skb->len += len; } } else { - len -= sizeof(struct virtio_net_hdr); + len -= sizeof(hdr->hdr); if (len <= MAX_PACKET_LEN) trim_pages(vi, skb); @@ -222,9 +216,11 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, dev->stats.rx_bytes += skb->len; dev->stats.rx_packets++; - if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { pr_debug("Needs csum!\n"); - if (!skb_partial_csum_set(skb,hdr->csum_start,hdr->csum_offset)) + if (!skb_partial_csum_set(skb, + hdr->hdr.csum_start, + hdr->hdr.csum_offset)) goto frame_err; } @@ -232,9 +228,9 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, pr_debug("Receiving skb proto 0x%04x len %i type %i\n", ntohs(skb->protocol), skb->len, skb->pkt_type); - if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); - switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; @@ -247,14 +243,14 @@ static void receive_skb(struct net_device *dev, struct sk_buff *skb, default: if (net_ratelimit()) printk(KERN_WARNING "%s: bad gso type %u.\n", - dev->name, hdr->gso_type); + dev->name, hdr->hdr.gso_type); goto frame_err; } - if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) + if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - skb_shinfo(skb)->gso_size = hdr->gso_size; + skb_shinfo(skb)->gso_size = hdr->hdr.gso_size; if (skb_shinfo(skb)->gso_size == 0) { if (net_ratelimit()) printk(KERN_WARNING "%s: zero gso size.\n", @@ -284,8 +280,8 @@ static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t gfp) bool oom = false; sg_init_table(sg, 2+MAX_SKB_FRAGS); - for (;;) { - struct virtio_net_hdr *hdr; + do { + struct skb_vnet_hdr *hdr; skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN + NET_IP_ALIGN); if (unlikely(!skb)) { @@ -297,7 +293,7 @@ static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t gfp) skb_put(skb, MAX_PACKET_LEN); hdr = skb_vnet_hdr(skb); - sg_set_buf(sg, hdr, sizeof(*hdr)); + sg_set_buf(sg, &hdr->hdr, sizeof(hdr->hdr)); if (vi->big_packets) { for (i = 0; i < MAX_SKB_FRAGS; i++) { @@ -320,14 +316,14 @@ static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t gfp) skb_queue_head(&vi->recv, skb); err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, num, skb); - if (err) { + if (err < 0) { skb_unlink(skb, &vi->recv); trim_pages(vi, skb); kfree_skb(skb); break; } vi->num++; - } + } while (err >= num); if (unlikely(vi->num > vi->max)) vi->max = vi->num; vi->rvq->vq_ops->kick(vi->rvq); @@ -345,7 +341,7 @@ static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp) if (!vi->mergeable_rx_bufs) return try_fill_recv_maxbufs(vi, gfp); - for (;;) { + do { skb_frag_t *f; skb = netdev_alloc_skb(vi->dev, GOOD_COPY_LEN + NET_IP_ALIGN); @@ -373,13 +369,13 @@ static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp) skb_queue_head(&vi->recv, skb); err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, 1, skb); - if (err) { + if (err < 0) { skb_unlink(skb, &vi->recv); kfree_skb(skb); break; } vi->num++; - } + } while (err > 0); if (unlikely(vi->num > vi->max)) vi->max = vi->num; vi->rvq->vq_ops->kick(vi->rvq); @@ -447,42 +443,26 @@ again: return received; } -static void free_old_xmit_skbs(struct virtnet_info *vi) +static unsigned int free_old_xmit_skbs(struct virtnet_info *vi) { struct sk_buff *skb; - unsigned int len; + unsigned int len, tot_sgs = 0; while ((skb = vi->svq->vq_ops->get_buf(vi->svq, &len)) != NULL) { pr_debug("Sent skb %p\n", skb); __skb_unlink(skb, &vi->send); vi->dev->stats.tx_bytes += skb->len; vi->dev->stats.tx_packets++; + tot_sgs += skb_vnet_hdr(skb)->num_sg; kfree_skb(skb); } -} - -/* If the virtio transport doesn't always notify us when all in-flight packets - * are consumed, we fall back to using this function on a timer to free them. */ -static void xmit_free(unsigned long data) -{ - struct virtnet_info *vi = (void *)data; - - netif_tx_lock(vi->dev); - - free_old_xmit_skbs(vi); - - if (!skb_queue_empty(&vi->send)) - mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10)); - - netif_tx_unlock(vi->dev); + return tot_sgs; } static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb) { - int num, err; struct scatterlist sg[2+MAX_SKB_FRAGS]; - struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb); - struct virtio_net_hdr *hdr = skb_vnet_hdr(skb); + struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb); const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; sg_init_table(sg, 2+MAX_SKB_FRAGS); @@ -490,108 +470,89 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb) pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); if (skb->ip_summed == CHECKSUM_PARTIAL) { - hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - hdr->csum_start = skb->csum_start - skb_headroom(skb); - hdr->csum_offset = skb->csum_offset; + hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + hdr->hdr.csum_start = skb->csum_start - skb_headroom(skb); + hdr->hdr.csum_offset = skb->csum_offset; } else { - hdr->flags = 0; - hdr->csum_offset = hdr->csum_start = 0; + hdr->hdr.flags = 0; + hdr->hdr.csum_offset = hdr->hdr.csum_start = 0; } if (skb_is_gso(skb)) { - hdr->hdr_len = skb_headlen(skb); - hdr->gso_size = skb_shinfo(skb)->gso_size; + hdr->hdr.hdr_len = skb_headlen(skb); + hdr->hdr.gso_size = skb_shinfo(skb)->gso_size; if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) - hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) - hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) - hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN) - hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; + hdr->hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else { - hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; - hdr->gso_size = hdr->hdr_len = 0; + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE; + hdr->hdr.gso_size = hdr->hdr.hdr_len = 0; } - mhdr->num_buffers = 0; + hdr->mhdr.num_buffers = 0; /* Encode metadata header at front. */ if (vi->mergeable_rx_bufs) - sg_set_buf(sg, mhdr, sizeof(*mhdr)); + sg_set_buf(sg, &hdr->mhdr, sizeof(hdr->mhdr)); else - sg_set_buf(sg, hdr, sizeof(*hdr)); - - num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1; - - err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb); - if (!err && !vi->free_in_tasklet) - mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10)); + sg_set_buf(sg, &hdr->hdr, sizeof(hdr->hdr)); - return err; -} - -static void xmit_tasklet(unsigned long data) -{ - struct virtnet_info *vi = (void *)data; - - netif_tx_lock_bh(vi->dev); - if (vi->last_xmit_skb && xmit_skb(vi, vi->last_xmit_skb) == 0) { - vi->svq->vq_ops->kick(vi->svq); - vi->last_xmit_skb = NULL; - } - if (vi->free_in_tasklet) - free_old_xmit_skbs(vi); - netif_tx_unlock_bh(vi->dev); + hdr->num_sg = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1; + return vi->svq->vq_ops->add_buf(vi->svq, sg, hdr->num_sg, 0, skb); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); + int capacity; again: /* Free up any pending old buffers before queueing new ones. */ free_old_xmit_skbs(vi); - /* If we has a buffer left over from last time, send it now. */ - if (unlikely(vi->last_xmit_skb) && - xmit_skb(vi, vi->last_xmit_skb) != 0) - goto stop_queue; - - vi->last_xmit_skb = NULL; - /* Put new one in send queue and do transmit */ - if (likely(skb)) { - __skb_queue_head(&vi->send, skb); - if (xmit_skb(vi, skb) != 0) { - vi->last_xmit_skb = skb; - skb = NULL; - goto stop_queue; + __skb_queue_head(&vi->send, skb); + capacity = xmit_skb(vi, skb); + + /* This can happen with OOM and indirect buffers. */ + if (unlikely(capacity < 0)) { + netif_stop_queue(dev); + dev_warn(&dev->dev, "Unexpected full queue\n"); + if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) { + vi->svq->vq_ops->disable_cb(vi->svq); + netif_start_queue(dev); + goto again; } + return NETDEV_TX_BUSY; } -done: - vi->svq->vq_ops->kick(vi->svq); - return NETDEV_TX_OK; -stop_queue: - pr_debug("%s: virtio not prepared to send\n", dev->name); - netif_stop_queue(dev); - - /* Activate callback for using skbs: if this returns false it - * means some were used in the meantime. */ - if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) { - vi->svq->vq_ops->disable_cb(vi->svq); - netif_start_queue(dev); - goto again; - } - if (skb) { - /* Drop this skb: we only queue one. */ - vi->dev->stats.tx_dropped++; - kfree_skb(skb); + vi->svq->vq_ops->kick(vi->svq); + /* Don't wait up for transmitted skbs to be freed. */ + skb_orphan(skb); + nf_reset(skb); + + /* Apparently nice girls don't return TX_BUSY; stop the queue + * before it gets out of hand. Naturally, this wastes entries. */ + if (capacity < 2+MAX_SKB_FRAGS) { + netif_stop_queue(dev); + if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) { + /* More just got used, free them then recheck. */ + capacity += free_old_xmit_skbs(vi); + if (capacity >= 2+MAX_SKB_FRAGS) { + netif_start_queue(dev); + vi->svq->vq_ops->disable_cb(vi->svq); + } + } } - goto done; + + return NETDEV_TX_OK; } static int virtnet_set_mac_address(struct net_device *dev, void *p) @@ -668,7 +629,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, sg_set_buf(&sg[i + 1], sg_virt(s), s->length); sg_set_buf(&sg[out + in - 1], &status, sizeof(status)); - BUG_ON(vi->cvq->vq_ops->add_buf(vi->cvq, sg, out, in, vi)); + BUG_ON(vi->cvq->vq_ops->add_buf(vi->cvq, sg, out, in, vi) < 0); vi->cvq->vq_ops->kick(vi->cvq); @@ -924,10 +885,6 @@ static int virtnet_probe(struct virtio_device *vdev) vi->pages = NULL; INIT_DELAYED_WORK(&vi->refill, refill_work); - /* If they give us a callback when all buffers are done, we don't need - * the timer. */ - vi->free_in_tasklet = virtio_has_feature(vdev,VIRTIO_F_NOTIFY_ON_EMPTY); - /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) @@ -959,11 +916,6 @@ static int virtnet_probe(struct virtio_device *vdev) skb_queue_head_init(&vi->recv); skb_queue_head_init(&vi->send); - tasklet_init(&vi->tasklet, xmit_tasklet, (unsigned long)vi); - - if (!vi->free_in_tasklet) - setup_timer(&vi->xmit_free_timer, xmit_free, (unsigned long)vi); - err = register_netdev(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); @@ -1004,9 +956,6 @@ static void virtnet_remove(struct virtio_device *vdev) /* Stop all the virtqueues. */ vdev->config->reset(vdev); - if (!vi->free_in_tasklet) - del_timer_sync(&vi->xmit_free_timer); - /* Free our skbs in send and recv queues, if any. */ while ((skb = __skb_dequeue(&vi->recv)) != NULL) { kfree_skb(skb); @@ -1040,7 +989,6 @@ static unsigned int features[] = { VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, - VIRTIO_F_NOTIFY_ON_EMPTY, }; static struct virtio_driver virtio_net = { diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index 8574622e36a5..c9e2ae90f195 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -154,9 +154,8 @@ int sync_start(void) { int err; - if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL)) return -ENOMEM; - cpumask_clear(marked_cpus); start_cpu_work(); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 26b278264796..200c22f55130 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -19,6 +19,7 @@ */ //#define DEBUG #include <linux/virtio.h> +#include <linux/virtio_ids.h> #include <linux/virtio_balloon.h> #include <linux/swap.h> #include <linux/kthread.h> @@ -84,7 +85,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) init_completion(&vb->acked); /* We should always be able to add one buffer to an empty queue. */ - if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) != 0) + if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0) BUG(); vq->vq_ops->kick(vq); diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index 248e00ec4dc1..4a1f1ebff7bf 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -84,7 +84,7 @@ struct virtio_pci_vq_info struct list_head node; /* MSI-X vector (or none) */ - unsigned vector; + unsigned msix_vector; }; /* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */ @@ -280,25 +280,14 @@ static void vp_free_vectors(struct virtio_device *vdev) vp_dev->msix_entries = NULL; } -static int vp_request_vectors(struct virtio_device *vdev, int nvectors, - bool per_vq_vectors) +static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, + bool per_vq_vectors) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); const char *name = dev_name(&vp_dev->vdev.dev); unsigned i, v; int err = -ENOMEM; - if (!nvectors) { - /* Can't allocate MSI-X vectors, use regular interrupt */ - vp_dev->msix_vectors = 0; - err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, - IRQF_SHARED, name, vp_dev); - if (err) - return err; - vp_dev->intx_enabled = 1; - return 0; - } - vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries, GFP_KERNEL); if (!vp_dev->msix_entries) @@ -311,6 +300,7 @@ static int vp_request_vectors(struct virtio_device *vdev, int nvectors, for (i = 0; i < nvectors; ++i) vp_dev->msix_entries[i].entry = i; + /* pci_enable_msix returns positive if we can't get this many. */ err = pci_enable_msix(vp_dev->pci_dev, vp_dev->msix_entries, nvectors); if (err > 0) err = -ENOSPC; @@ -356,10 +346,22 @@ error: return err; } -static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index, - void (*callback)(struct virtqueue *vq), - const char *name, - u16 vector) +static int vp_request_intx(struct virtio_device *vdev) +{ + int err; + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, + IRQF_SHARED, dev_name(&vdev->dev), vp_dev); + if (!err) + vp_dev->intx_enabled = 1; + return err; +} + +static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index, + void (*callback)(struct virtqueue *vq), + const char *name, + u16 msix_vec) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info; @@ -384,7 +386,7 @@ static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index, info->queue_index = index; info->num = num; - info->vector = vector; + info->msix_vector = msix_vec; size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN)); info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO); @@ -408,10 +410,10 @@ static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index, vq->priv = info; info->vq = vq; - if (vector != VIRTIO_MSI_NO_VECTOR) { - iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); - vector = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); - if (vector == VIRTIO_MSI_NO_VECTOR) { + if (msix_vec != VIRTIO_MSI_NO_VECTOR) { + iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); + msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); + if (msix_vec == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto out_assign; } @@ -472,7 +474,8 @@ static void vp_del_vqs(struct virtio_device *vdev) list_for_each_entry_safe(vq, n, &vdev->vqs, list) { info = vq->priv; if (vp_dev->per_vq_vectors) - free_irq(vp_dev->msix_entries[info->vector].vector, vq); + free_irq(vp_dev->msix_entries[info->msix_vector].vector, + vq); vp_del_vq(vq); } vp_dev->per_vq_vectors = false; @@ -484,38 +487,58 @@ static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], const char *names[], - int nvectors, + bool use_msix, bool per_vq_vectors) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - u16 vector; - int i, err, allocated_vectors; + u16 msix_vec; + int i, err, nvectors, allocated_vectors; - err = vp_request_vectors(vdev, nvectors, per_vq_vectors); - if (err) - goto error_request; + if (!use_msix) { + /* Old style: one normal interrupt for change and all vqs. */ + err = vp_request_intx(vdev); + if (err) + goto error_request; + } else { + if (per_vq_vectors) { + /* Best option: one for change interrupt, one per vq. */ + nvectors = 1; + for (i = 0; i < nvqs; ++i) + if (callbacks[i]) + ++nvectors; + } else { + /* Second best: one for change, shared for all vqs. */ + nvectors = 2; + } + + err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors); + if (err) + goto error_request; + } vp_dev->per_vq_vectors = per_vq_vectors; allocated_vectors = vp_dev->msix_used_vectors; for (i = 0; i < nvqs; ++i) { if (!callbacks[i] || !vp_dev->msix_enabled) - vector = VIRTIO_MSI_NO_VECTOR; + msix_vec = VIRTIO_MSI_NO_VECTOR; else if (vp_dev->per_vq_vectors) - vector = allocated_vectors++; + msix_vec = allocated_vectors++; else - vector = VP_MSIX_VQ_VECTOR; - vqs[i] = vp_find_vq(vdev, i, callbacks[i], names[i], vector); + msix_vec = VP_MSIX_VQ_VECTOR; + vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto error_find; } /* allocate per-vq irq if available and necessary */ - if (vp_dev->per_vq_vectors && vector != VIRTIO_MSI_NO_VECTOR) { - snprintf(vp_dev->msix_names[vector], sizeof *vp_dev->msix_names, - "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]); - err = request_irq(vp_dev->msix_entries[vector].vector, - vring_interrupt, 0, - vp_dev->msix_names[vector], vqs[i]); + if (vp_dev->per_vq_vectors) { + snprintf(vp_dev->msix_names[msix_vec], + sizeof *vp_dev->msix_names, + "%s-%s", + dev_name(&vp_dev->vdev.dev), names[i]); + err = request_irq(msix_vec, vring_interrupt, 0, + vp_dev->msix_names[msix_vec], + vqs[i]); if (err) { vp_del_vq(vqs[i]); goto error_find; @@ -537,28 +560,20 @@ static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, vq_callback_t *callbacks[], const char *names[]) { - int vectors = 0; - int i, uninitialized_var(err); - - /* How many vectors would we like? */ - for (i = 0; i < nvqs; ++i) - if (callbacks[i]) - ++vectors; + int err; - /* We want at most one vector per queue and one for config changes. */ - err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, - vectors + 1, true); + /* Try MSI-X with one vector per queue. */ + err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true); if (!err) return 0; - /* Fallback to separate vectors for config and a shared for queues. */ + /* Fallback: MSI-X with one vector for config, one shared for queues. */ err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, - 2, false); + true, false); if (!err) return 0; /* Finally fall back to regular interrupts. */ - err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, - 0, false); - return err; + return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, + false, false); } static struct virtio_config_ops virtio_pci_config_ops = { diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index a882f2606515..f53600580726 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -208,7 +208,11 @@ add_head: pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); - return 0; + + /* If we're indirect, we can fit many (assuming not OOM). */ + if (vq->indirect) + return vq->num_free ? vq->vring.num : 0; + return vq->num_free; } static void vring_kick(struct virtqueue *_vq) |