From b6eb9b45f7307638ff166401721ae6d0401e1d67 Mon Sep 17 00:00:00 2001 From: Paulina Szubarczyk Date: Wed, 14 Sep 2016 21:10:03 +0200 Subject: [PATCH] qdisk - hw/block/xen_disk: grant copy implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Copy data operated on during request from/to local buffers to/from the grant references. Before grant copy operation local buffers must be allocated what is done by calling ioreq_init_copy_buffers. For the 'read' operation, first, the qemu device invokes the read operation on local buffers and on the completion grant copy is called and buffers are freed. For the 'write' operation grant copy is performed before invoking write by qemu device. A new value 'feature_grant_copy' is added to recognize when the grant copy operation is supported by a guest. Signed-off-by: Paulina Szubarczyk Reviewed-by: Stefano Stabellini Acked-by: Anthony PERARD Acked-by: Roger Pau Monné --- configure | 55 +++++++++++++ hw/block/xen_disk.c | 153 ++++++++++++++++++++++++++++++++++-- include/hw/xen/xen_common.h | 14 ++++ 3 files changed, 217 insertions(+), 5 deletions(-) diff --git a/configure b/configure index 8fa62ade57..1fb343ded3 100755 --- a/configure +++ b/configure @@ -1952,6 +1952,61 @@ EOF # Xen unstable elif cat > $TMPC < +#include +#include +#include +#include +#include +#include +#if !defined(HVM_MAX_VCPUS) +# error HVM_MAX_VCPUS not defined +#endif +int main(void) { + xc_interface *xc = NULL; + xenforeignmemory_handle *xfmem; + xenevtchn_handle *xe; + xengnttab_handle *xg; + xen_domain_handle_t handle; + xengnttab_grant_copy_segment_t* seg = NULL; + + xs_daemon_open(); + + xc = xc_interface_open(0, 0, 0); + xc_hvm_set_mem_type(0, 0, HVMMEM_ram_ro, 0, 0); + xc_domain_add_to_physmap(0, 0, XENMAPSPACE_gmfn, 0, 0); + xc_hvm_inject_msi(xc, 0, 0xf0000000, 0x00000000); + xc_hvm_create_ioreq_server(xc, 0, HVM_IOREQSRV_BUFIOREQ_ATOMIC, NULL); + xc_domain_create(xc, 0, handle, 0, NULL, NULL); + + xfmem = xenforeignmemory_open(0, 0); + xenforeignmemory_map(xfmem, 0, 0, 0, 0, 0); + + xe = xenevtchn_open(0, 0); + xenevtchn_fd(xe); + + xg = xengnttab_open(0, 0); + xengnttab_grant_copy(xg, 0, seg); + + return 0; +} +EOF + compile_prog "" "$xen_libs $xen_stable_libs" + then + xen_ctrl_version=480 + xen=yes + elif + cat > $TMPC <= 480 + +static void ioreq_free_copy_buffers(struct ioreq *ioreq) +{ + int i; + + for (i = 0; i < ioreq->v.niov; i++) { + ioreq->page[i] = NULL; + } + + qemu_vfree(ioreq->pages); +} + +static int ioreq_init_copy_buffers(struct ioreq *ioreq) +{ + int i; + + if (ioreq->v.niov == 0) { + return 0; + } + + ioreq->pages = qemu_memalign(XC_PAGE_SIZE, ioreq->v.niov * XC_PAGE_SIZE); + + for (i = 0; i < ioreq->v.niov; i++) { + ioreq->page[i] = ioreq->pages + i * XC_PAGE_SIZE; + ioreq->v.iov[i].iov_base = ioreq->page[i]; + } + + return 0; +} + +static int ioreq_grant_copy(struct ioreq *ioreq) +{ + xengnttab_handle *gnt = ioreq->blkdev->xendev.gnttabdev; + xengnttab_grant_copy_segment_t segs[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + int i, count, rc; + int64_t file_blk = ioreq->blkdev->file_blk; + + if (ioreq->v.niov == 0) { + return 0; + } + + count = ioreq->v.niov; + + for (i = 0; i < count; i++) { + if (ioreq->req.operation == BLKIF_OP_READ) { + segs[i].flags = GNTCOPY_dest_gref; + segs[i].dest.foreign.ref = ioreq->refs[i]; + segs[i].dest.foreign.domid = ioreq->domids[i]; + segs[i].dest.foreign.offset = ioreq->req.seg[i].first_sect * file_blk; + segs[i].source.virt = ioreq->v.iov[i].iov_base; + } else { + segs[i].flags = GNTCOPY_source_gref; + segs[i].source.foreign.ref = ioreq->refs[i]; + segs[i].source.foreign.domid = ioreq->domids[i]; + segs[i].source.foreign.offset = ioreq->req.seg[i].first_sect * file_blk; + segs[i].dest.virt = ioreq->v.iov[i].iov_base; + } + segs[i].len = (ioreq->req.seg[i].last_sect + - ioreq->req.seg[i].first_sect + 1) * file_blk; + } + + rc = xengnttab_grant_copy(gnt, count, segs); + + if (rc) { + xen_be_printf(&ioreq->blkdev->xendev, 0, + "failed to copy data %d\n", rc); + ioreq->aio_errors++; + return -1; + } + + for (i = 0; i < count; i++) { + if (segs[i].status != GNTST_okay) { + xen_be_printf(&ioreq->blkdev->xendev, 3, + "failed to copy data %d for gref %d, domid %d\n", + segs[i].status, ioreq->refs[i], ioreq->domids[i]); + ioreq->aio_errors++; + rc = -1; + } + } + + return rc; +} +#else +static void ioreq_free_copy_buffers(struct ioreq *ioreq) +{ + abort(); +} + +static int ioreq_init_copy_buffers(struct ioreq *ioreq) +{ + abort(); +} + +static int ioreq_grant_copy(struct ioreq *ioreq) +{ + abort(); +} +#endif + static int ioreq_runio_qemu_aio(struct ioreq *ioreq); static void qemu_aio_complete(void *opaque, int ret) @@ -511,8 +614,31 @@ static void qemu_aio_complete(void *opaque, int ret) return; } + if (ioreq->blkdev->feature_grant_copy) { + switch (ioreq->req.operation) { + case BLKIF_OP_READ: + /* in case of failure ioreq->aio_errors is increased */ + if (ret == 0) { + ioreq_grant_copy(ioreq); + } + ioreq_free_copy_buffers(ioreq); + break; + case BLKIF_OP_WRITE: + case BLKIF_OP_FLUSH_DISKCACHE: + if (!ioreq->req.nr_segments) { + break; + } + ioreq_free_copy_buffers(ioreq); + break; + default: + break; + } + } + ioreq->status = ioreq->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY; - ioreq_unmap(ioreq); + if (!ioreq->blkdev->feature_grant_copy) { + ioreq_unmap(ioreq); + } ioreq_finish(ioreq); switch (ioreq->req.operation) { case BLKIF_OP_WRITE: @@ -538,8 +664,18 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq) { struct XenBlkDev *blkdev = ioreq->blkdev; - if (ioreq->req.nr_segments && ioreq_map(ioreq) == -1) { - goto err_no_map; + if (ioreq->blkdev->feature_grant_copy) { + ioreq_init_copy_buffers(ioreq); + if (ioreq->req.nr_segments && (ioreq->req.operation == BLKIF_OP_WRITE || + ioreq->req.operation == BLKIF_OP_FLUSH_DISKCACHE) && + ioreq_grant_copy(ioreq)) { + ioreq_free_copy_buffers(ioreq); + goto err; + } + } else { + if (ioreq->req.nr_segments && ioreq_map(ioreq)) { + goto err; + } } ioreq->aio_inflight++; @@ -582,6 +718,9 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq) } default: /* unknown operation (shouldn't happen -- parse catches this) */ + if (!ioreq->blkdev->feature_grant_copy) { + ioreq_unmap(ioreq); + } goto err; } @@ -590,8 +729,6 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq) return 0; err: - ioreq_unmap(ioreq); -err_no_map: ioreq_finish(ioreq); ioreq->status = BLKIF_RSP_ERROR; return -1; @@ -1034,6 +1171,12 @@ static int blk_connect(struct XenDevice *xendev) xen_be_bind_evtchn(&blkdev->xendev); + blkdev->feature_grant_copy = + (xengnttab_grant_copy(blkdev->xendev.gnttabdev, 0, NULL) == 0); + + xen_be_printf(&blkdev->xendev, 3, "grant copy operation %s\n", + blkdev->feature_grant_copy ? "enabled" : "disabled"); + xen_be_printf(&blkdev->xendev, 1, "ok: proto %s, ring-ref %d, " "remote port %d, local port %d\n", blkdev->xendev.protocol, blkdev->ring_ref, diff --git a/include/hw/xen/xen_common.h b/include/hw/xen/xen_common.h index bd39287b8f..8e1580d526 100644 --- a/include/hw/xen/xen_common.h +++ b/include/hw/xen/xen_common.h @@ -424,4 +424,18 @@ static inline int xen_domain_create(xc_interface *xc, uint32_t ssidref, #endif #endif +/* Xen before 4.8 */ + +#if CONFIG_XEN_CTRL_INTERFACE_VERSION < 480 + + +typedef void *xengnttab_grant_copy_segment_t; + +static inline int xengnttab_grant_copy(xengnttab_handle *xgt, uint32_t count, + xengnttab_grant_copy_segment_t *segs) +{ + return -ENOSYS; +} +#endif + #endif /* QEMU_HW_XEN_COMMON_H */