search for: sgs

Author: mike_s Repository: /hg/zfs-crypto/gate Revision: e144729d8b901f4092085ea17a31bf10d1089f79 Log message: 6273860 gcc and sgs/gprof don''t get along 6273866 gcc and sgs/prof don''t get along Files: update: usr/src/cmd/sgs/gprof/Makefile.com update: usr/src/cmd/sgs/gprof/common/arcs.c update: usr/src/cmd/sgs/gprof/common/dfn.c update: usr/src/cmd/sgs/gprof/common/gprof.c update: usr/src/cmd/sgs/gprof/...

Author: seizo Repository: /hg/zfs-crypto/gate Revision: 08bf1c2a0376c8a9085fd66f4c8cb2420b8bd82a Log message: 6273855 gcc and sgs/crle don''t get along 6273864 gcc and sgs/libld don''t get along 6273875 gcc and sgs/rtld don''t get along 6272563 gcc and amd64/krtld/doreloc.c don''t get along 6290157 gcc and sgs/librtld_db/rdb_demo don''t get along Files: update: usr/src/cmd/sgs/Makefil...

.../usr/src/tools/build/mk -m /usr/src/share/mk -D WITH_CTF" make -f Makefile.inc1 DESTDIR= BOOTSTRAPPING=603000 -DWITHOUT_HTML -DWITHOUT_INFO -DNO_LINT -DWITHOUT_MAN -DWITHOUT_NLS -DNO_PIC -DWITHOUT_PROFILE -DNO_SHARED -DNO_CPU_CFLAGS -DNO_WARNS -DNO_CTF bootstrap-tools ===> cddl/usr.bin/sgsmsg (obj,depend,all,install) /usr/obj/usr/src/tmp/usr/src/cddl/usr.bin/sgsmsg created for /usr/src/cddl/usr.bin/sgsmsg rm -f .depend mkdep -f .depend -a -DNEED_SOLARIS_BOOLEAN -DNEED_SOLARIS_BOOLEAN -I/usr/src/cddl/usr.bin/sgsmsg/../../../sys/cddl/compat/opensolaris -I/usr/src/cddl/usr.bin/sgsmsg...

OK, so I've spent a few days benchmarking. Turns out 80% of virtio_add_buf cases are uni-directional (including the always-performance-sensitive networking code), and that gets no performance penalty (though tests with real networking would be appreciated!). I'm not reposting all the "convert driver to virtio_add_outbuf()" patches: just the scsi one which I didn't have

OK, so I've spent a few days benchmarking. Turns out 80% of virtio_add_buf cases are uni-directional (including the always-performance-sensitive networking code), and that gets no performance penalty (though tests with real networking would be appreciated!). I'm not reposting all the "convert driver to virtio_add_outbuf()" patches: just the scsi one which I didn't have

...g_next_arr(struct scatterlist *sg, - unsigned int *count) -{ - if (--(*count) == 0) - return NULL; - return sg + 1; -} - /* Set up an indirect table of descriptors and add it to the queue. */ static inline int vring_add_indirect(struct vring_virtqueue *vq, struct scatterlist *sgs[], - struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), unsigned int total_sg, - unsigned int total_out, - unsigned int total_in, unsigned int out_sgs, unsigned int in_sgs, gfp_t gfp) @@ -144,7 +126,7 @@ st...

...ations in the linker space, but I had never actually looked at their iinker (the time I spent interacting with Solaris/illumos was related to DTrace stuff and happened before I started working on linkers). The basic layout seems to be: http://src.illumos.org/source/xref/illumos-gate/usr/src/cmd/ sgs/ld/common/ld.c This is where `main` is. The actual linker has a "main in a library" type interface that is called into from main() by: 718 /* Call the libld entry point for the specified ELFCLASS */ 719 if (class == ELFCLASS64) 720 return (ld64_main(argc, argv, mach)); 721 else 722 retu...

...+} + static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, void *cpu_addr, size_t size, enum dma_data_direction direction) @@ -520,6 +528,80 @@ static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq, return next; } +static void virtqueue_unmap_sgs(struct vring_virtqueue *vq, + struct scatterlist *sgs[], + unsigned int total_sg, + unsigned int out_sgs, + unsigned int in_sgs) +{ + struct scatterlist *sg; + unsigned int n; + + if (!vq->use_dma_api) + return; + + for (n = 0; n < out_sgs; n++) { + for (sg = sgs[n]; sg; sg = sg...

DMA-related logic is separated from the virtqueue_add_vring_split() to prepare for subsequent support for premapped. DMA address will be saved as sg->dma_address, then virtqueue_add_vring_split() will use it directly. If it is a premapped scene, the transmitted sgs should have saved DMA address in dma_address, and in virtio core, we need to pass virtqueue_map_sgs(). Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com> --- drivers/virtio/virtio_ring.c | 116 ++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 36 deletions(-) diff...

...rated from the virtqueue_add_split to prepare > for subsequent support for premapped. The patch seems to do more than what is described here. To simplify reviewers, I'd suggest to split this patch into three: 1) virtqueue_add_split_prepare() (could we have a better name?) 2) virtqueue_map_sgs() 3) virtqueue_add_split_vring() (Or only factor DMA parts out, I haven't gone through the reset of the patches) Thanks > > Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com> > --- > drivers/virtio/virtio_ring.c | 219 ++++++++++++++++++++++++----------- > 1 file...

Add virtqueue_add_sgs which is more general than virtqueue_add_buf, which makes virtio-scsi and virtio-blk nicer, then add virtqueue_add_inbuf and virtqueue_add_outbuf which handle the more general case, and finally delete virtqueue_add_buf(). I'm hoping this will be the final post of the whole series, and it can m...

Add virtqueue_add_sgs which is more general than virtqueue_add_buf, which makes virtio-scsi and virtio-blk nicer, then add virtqueue_add_inbuf and virtqueue_add_outbuf which handle the more general case, and finally delete virtqueue_add_buf(). I'm hoping this will be the final post of the whole series, and it can m...

...phen Hemminger <stephen at networkplumber.org> --- a/drivers/net/virtio_net.c 2013-12-09 16:12:03.897891975 -0800 +++ b/drivers/net/virtio_net.c 2013-12-09 16:12:36.353164803 -0800 @@ -893,7 +893,7 @@ static bool virtnet_send_command(struct sg_init_one(&hdr, &ctrl, sizeof(ctrl)); sgs[out_num++] = &hdr; - if (out) + for (; out; out = sg_next(out)) sgs[out_num++] = out; if (in) sgs[out_num + in_num++] = in;

...phen Hemminger <stephen at networkplumber.org> --- a/drivers/net/virtio_net.c 2013-12-09 16:12:03.897891975 -0800 +++ b/drivers/net/virtio_net.c 2013-12-09 16:12:36.353164803 -0800 @@ -893,7 +893,7 @@ static bool virtnet_send_command(struct sg_init_one(&hdr, &ctrl, sizeof(ctrl)); sgs[out_num++] = &hdr; - if (out) + for (; out; out = sg_next(out)) sgs[out_num++] = out; if (in) sgs[out_num + in_num++] = in;

...to 65535 segments 6317980 coredump elfheader doesn''t reflect the correct number of dumped segments 6343698 p-tools affected by 6317980 : coredump elfheader incorrectly states number of dumped segments 6350070 stub for shmgetid() returns the wrong default value Files: create: usr/src/cmd/sgs/libelf/common/getphnum.c update: usr/src/cmd/mdb/common/mdb/mdb_gelf.c update: usr/src/cmd/mdb/common/mdb/mdb_gelf.h update: usr/src/cmd/sgs/elfdump/common/elfdump.c update: usr/src/cmd/sgs/elfdump/common/elfdump.msg update: usr/src/cmd/sgs/libelf/Makefile.com update: usr/src/cmd/sgs/libelf/c...

...g_next_arr(struct scatterlist *sg, - unsigned int *count) -{ - if (--(*count) == 0) - return NULL; - return sg + 1; -} - /* Set up an indirect table of descriptors and add it to the queue. */ static inline int vring_add_indirect(struct vring_virtqueue *vq, struct scatterlist *sgs[], - struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), unsigned int total_sg, unsigned int total_out, unsigned int total_in, @@ -128,7 +112,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, struct vring_desc *...

OK, this is (ab)uses some of Paolo's patches. The first 7 are candidates for this merge window (maybe), the rest I'm not so sure about. Thanks, Rusty. Paolo Bonzini (3): scatterlist: introduce sg_unmark_end virtio-blk: reorganize virtblk_add_req virtio-blk: use virtqueue_add_sgs on req path Rusty Russell (13): virtio_ring: virtqueue_add_sgs, to add multiple sgs. virtio-blk: use virtqueue_start_buf on bio path virtio_blk: remove nents member. virtio_ring: don't count elements twice for add_buf path. virtio_ring: virtqueue_add_outbuf / virtqueue_add_inbuf. v...

OK, this is (ab)uses some of Paolo's patches. The first 7 are candidates for this merge window (maybe), the rest I'm not so sure about. Thanks, Rusty. Paolo Bonzini (3): scatterlist: introduce sg_unmark_end virtio-blk: reorganize virtblk_add_req virtio-blk: use virtqueue_add_sgs on req path Rusty Russell (13): virtio_ring: virtqueue_add_sgs, to add multiple sgs. virtio-blk: use virtqueue_start_buf on bio path virtio_blk: remove nents member. virtio_ring: don't count elements twice for add_buf path. virtio_ring: virtqueue_add_outbuf / virtqueue_add_inbuf. v...

...+} + static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, void *cpu_addr, size_t size, enum dma_data_direction direction) @@ -520,6 +528,80 @@ static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq, return next; } +static void virtqueue_unmap_sgs(struct vring_virtqueue *vq, + struct scatterlist *sgs[], + unsigned int total_sg, + unsigned int out_sgs, + unsigned int in_sgs) +{ + struct scatterlist *sg; + unsigned int n; + + if (!vq->use_dma_api) + return; + + for (n = 0; n < out_sgs; n++) { + for (sg = sgs[n]; sg; sg = sg...

...+} + static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, void *cpu_addr, size_t size, enum dma_data_direction direction) @@ -520,6 +528,80 @@ static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq, return next; } +static void virtqueue_unmap_sgs(struct vring_virtqueue *vq, + struct scatterlist *sgs[], + unsigned int total_sg, + unsigned int out_sgs, + unsigned int in_sgs) +{ + struct scatterlist *sg; + unsigned int n; + + if (!vq->use_dma_api) + return; + + for (n = 0; n < out_sgs; n++) { + for (sg = sgs[n]; sg; sg = sg...