openkylin
/
qemu
mirror of https://gitee.com/openkylin/qemu.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

RDMA queue 

* Another Clang compilation fix
  * Collect pvrdma debugging statistics
  * Various fixes for the pvrdma device
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJcjQN+AAoJEDbUwPDPL+RtGzkIALjXgQlcb2YjNRkqwKLsfwFS
 OtZ/9nMj/d3HnLrXd9J5X+DTde0NsXhQb/jmrs5IvidxxNlyA9eq38XhfFBxsTFv
 djKWe87ImRoevFRRAoeHN1I/+w4++ThWtkfbGjY0ANincoJGSixDbWecGNLpiaJU
 PHlb3YmrEhmm4tQxFMmK2Ua5Ydh4grTCXE89eHOFvTtafhdtjLYkrVJrUZIIbtVc
 AmaqD/J3z+swZVl4V+6tAFLfcov1rs8GC0wo3QRAHCHGyGWXCMjabZ8ZPM/YDu39
 efhQpan//aWyWiX/XdRx+BTJtZlNUzt3TjjHWdMg4Jdr+J7Z8v3zs9vpY3JGdVY=
 =bcoj
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/marcel/tags/rdma-pull-request' into staging

RDMA queue

 * Another Clang compilation fix
 * Collect pvrdma debugging statistics
 * Various fixes for the pvrdma device

# gpg: Signature made Sat 16 Mar 2019 14:09:02 GMT
# gpg:                using RSA key 36D4C0F0CF2FE46D
# gpg: Good signature from "Marcel Apfelbaum <marcel.apfelbaum@zoho.com>" [marginal]
# gpg:                 aka "Marcel Apfelbaum <marcel@redhat.com>" [marginal]
# gpg:                 aka "Marcel Apfelbaum <marcel.apfelbaum@gmail.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: B1C6 3A57 F92E 08F2 640F  31F5 36D4 C0F0 CF2F E46D

* remotes/marcel/tags/rdma-pull-request:
  hw/rdma: Fix the error prints in create_qp_rings()
  hw/pvrdma: Fix zero-initialization of resp in {query/modify}_qp
  hw/rdma: Use {} instead of {0}
  hw/rdma: Remove unused parameter from rdma_poll_cq()
  hw/rdma: Fix broken paths to docs/devel/tracing.txt
  hw/rdma: another clang compilation fix
  hw/pvrdma: Provide correct value to object_get_typename
  hw/pvrdma: Unregister from shutdown notifier when device goes down
  hw/pvrdma: Delete pvrdma_exit function
  hw/pvrdma: Delete unneeded function argument
  hw/rdma: Free all receive buffers when QP is destroyed
  hw/rdma: Free all MAD receive buffers when device is closed
  {hmp, hw/pvrdma}: Expose device internals via monitor interface
  hw/pvrdma: Collect debugging statistics
  hw/rdma: Protect against concurrent execution of poll_cq
  hw/rdma: Introduce protected qlist
  hw/rdma: Switch to generic error reporting way
  contrib/rdmacm-mux: Fix out-of-bounds risk

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2019-03-16 20:18:48 +00:00
parent 8b088d3f8a cb42a5867e
commit c4b21ed1cf
22 changed files with 865 additions and 649 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
contrib/rdmacm-mux/main.c
View File

@ -300,7 +300,7 @@ static void hash_tbl_remove_fd_ifid_pair(int fd)
pthread_rwlock_unlock(&server.lock);
}
static int get_fd(const char *mad, int *fd, __be64 *gid_ifid)
static int get_fd(const char *mad, int umad_len, int *fd, __be64 *gid_ifid)
{
struct umad_hdr *hdr = (struct umad_hdr *)mad;
char *data = (char *)hdr + sizeof(*hdr);
@ -308,13 +308,35 @@ static int get_fd(const char *mad, int *fd, __be64 *gid_ifid)
uint16_t attr_id = be16toh(hdr->attr_id);
int rc = 0;
if (umad_len <= sizeof(*hdr)) {
rc = -EINVAL;
syslog(LOG_DEBUG, "Ignoring MAD packets with header only\n");
goto out;
}
switch (attr_id) {
case UMAD_CM_ATTR_REQ:
if (unlikely(umad_len < sizeof(*hdr) + CM_REQ_DGID_POS +
sizeof(*gid_ifid))) {
rc = -EINVAL;
syslog(LOG_WARNING,
"Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len,
attr_id);
goto out;
}
memcpy(gid_ifid, data + CM_REQ_DGID_POS, sizeof(*gid_ifid));
rc = hash_tbl_search_fd_by_ifid(fd, gid_ifid);
break;
case UMAD_CM_ATTR_SIDR_REQ:
if (unlikely(umad_len < sizeof(*hdr) + CM_SIDR_REQ_DGID_POS +
sizeof(*gid_ifid))) {
rc = -EINVAL;
syslog(LOG_WARNING,
"Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len,
attr_id);
goto out;
}
memcpy(gid_ifid, data + CM_SIDR_REQ_DGID_POS, sizeof(*gid_ifid));
rc = hash_tbl_search_fd_by_ifid(fd, gid_ifid);
break;
@ -331,6 +353,13 @@ static int get_fd(const char *mad, int *fd, __be64 *gid_ifid)
data += sizeof(comm_id);
/* Fall through */
case UMAD_CM_ATTR_SIDR_REP:
if (unlikely(umad_len < sizeof(*hdr) + sizeof(comm_id))) {
rc = -EINVAL;
syslog(LOG_WARNING,
"Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len,
attr_id);
goto out;
}
memcpy(&comm_id, data, sizeof(comm_id));
if (comm_id) {
rc = hash_tbl_search_fd_by_comm_id(comm_id, fd, gid_ifid);
@ -344,6 +373,7 @@ static int get_fd(const char *mad, int *fd, __be64 *gid_ifid)
syslog(LOG_DEBUG, "mad_to_vm: %d 0x%x 0x%x\n", *fd, attr_id, comm_id);
out:
return rc;
}
@ -372,7 +402,8 @@ static void *umad_recv_thread_func(void *args)
} while (rc && server.run);
if (server.run) {
rc = get_fd(msg.umad.mad, &fd, &msg.hdr.sgid.global.interface_id);
rc = get_fd(msg.umad.mad, msg.umad_len, &fd,
&msg.hdr.sgid.global.interface_id);
if (rc) {
continue;
}

14
hmp-commands-info.hx
View File

@ -202,6 +202,20 @@ STEXI
@item info pic
@findex info pic
Show PIC state.
ETEXI
{
.name = "rdma",
.args_type = "",
.params = "",
.help = "show RDMA state",
.cmd = hmp_info_rdma,
},
STEXI
@item info rdma
@findex info rdma
Show RDMA state.
ETEXI
{

27
hmp.c
View File

@ -51,6 +51,7 @@
#include "qemu/error-report.h"
#include "exec/ramlist.h"
#include "hw/intc/intc.h"
#include "hw/rdma/rdma.h"
#include "migration/snapshot.h"
#include "migration/misc.h"
@ -1013,6 +1014,32 @@ void hmp_info_pic(Monitor *mon, const QDict *qdict)
hmp_info_pic_foreach, mon);
}
static int hmp_info_rdma_foreach(Object *obj, void *opaque)
{
RdmaProvider *rdma;
RdmaProviderClass *k;
Monitor *mon = opaque;
if (object_dynamic_cast(obj, INTERFACE_RDMA_PROVIDER)) {
rdma = RDMA_PROVIDER(obj);
k = RDMA_PROVIDER_GET_CLASS(obj);
if (k->print_statistics) {
k->print_statistics(mon, rdma);
} else {
monitor_printf(mon, "RDMA statistics not available for %s.\n",
object_get_typename(obj));
}
}
return 0;
}
void hmp_info_rdma(Monitor *mon, const QDict *qdict)
{
object_child_foreach_recursive(object_get_root(),
hmp_info_rdma_foreach, mon);
}
void hmp_info_pci(Monitor *mon, const QDict *qdict)
{
PciInfoList *info_list, *info;

1
hmp.h
View File

@ -36,6 +36,7 @@ void hmp_info_spice(Monitor *mon, const QDict *qdict);
void hmp_info_balloon(Monitor *mon, const QDict *qdict);
void hmp_info_irq(Monitor *mon, const QDict *qdict);
void hmp_info_pic(Monitor *mon, const QDict *qdict);
void hmp_info_rdma(Monitor *mon, const QDict *qdict);
void hmp_info_pci(Monitor *mon, const QDict *qdict);
void hmp_info_block_jobs(Monitor *mon, const QDict *qdict);
void hmp_info_tpm(Monitor *mon, const QDict *qdict);

2
hw/rdma/Makefile.objs
View File

@ -1,5 +1,5 @@
ifeq ($(CONFIG_PVRDMA),y)
obj-$(CONFIG_PCI) += rdma_utils.o rdma_backend.o rdma_rm.o
obj-$(CONFIG_PCI) += rdma_utils.o rdma_backend.o rdma_rm.o rdma.o
obj-$(CONFIG_PCI) += vmw/pvrdma_dev_ring.o vmw/pvrdma_cmd.o \
vmw/pvrdma_qp_ops.o vmw/pvrdma_main.o
endif

30
hw/rdma/rdma.c Normal file
View File

@ -0,0 +1,30 @@
/*
* RDMA device interface
*
* Copyright (C) 2018 Oracle
* Copyright (C) 2018 Red Hat Inc
*
* Authors:
* Yuval Shaia <yuval.shaia@oracle.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "hw/rdma/rdma.h"
#include "qemu/module.h"
static const TypeInfo rdma_hmp_info = {
.name = INTERFACE_RDMA_PROVIDER,
.parent = TYPE_INTERFACE,
.class_size = sizeof(RdmaProviderClass),
};
static void rdma_register_types(void)
{
type_register_static(&rdma_hmp_info);
}
type_init(rdma_register_types)

518
hw/rdma/rdma_backend.c
View File

File diff suppressed because it is too large Load Diff

7
hw/rdma/rdma_backend.h
View File

@ -58,8 +58,8 @@ static inline uint32_t rdma_backend_mr_rkey(const RdmaBackendMR *mr)
int rdma_backend_init(RdmaBackendDev *backend_dev, PCIDevice *pdev,
RdmaDeviceResources *rdma_dev_res,
const char *backend_device_name, uint8_t port_num,
struct ibv_device_attr *dev_attr, CharBackend *mad_chr_be,
Error **errp);
struct ibv_device_attr *dev_attr,
CharBackend *mad_chr_be);
void rdma_backend_fini(RdmaBackendDev *backend_dev);
int rdma_backend_add_gid(RdmaBackendDev *backend_dev, const char *ifname,
union ibv_gid *gid);
@ -102,7 +102,7 @@ int rdma_backend_qp_state_rts(RdmaBackendQP *qp, uint8_t qp_type,
uint32_t sq_psn, uint32_t qkey, bool use_qkey);
int rdma_backend_query_qp(RdmaBackendQP *qp, struct ibv_qp_attr *attr,
int attr_mask, struct ibv_qp_init_attr *init_attr);
void rdma_backend_destroy_qp(RdmaBackendQP *qp);
void rdma_backend_destroy_qp(RdmaBackendQP *qp, RdmaDeviceResources *dev_res);
void rdma_backend_post_send(RdmaBackendDev *backend_dev,
RdmaBackendQP *qp, uint8_t qp_type,
@ -111,7 +111,6 @@ void rdma_backend_post_send(RdmaBackendDev *backend_dev,
union ibv_gid *dgid, uint32_t dqpn, uint32_t dqkey,
void *ctx);
void rdma_backend_post_recv(RdmaBackendDev *backend_dev,
RdmaDeviceResources *rdma_dev_res,
RdmaBackendQP *qp, uint8_t qp_type,
struct ibv_sge *sge, uint32_t num_sge, void *ctx);

10
hw/rdma/rdma_backend_defs.h
View File

@ -20,21 +20,16 @@
#include "chardev/char-fe.h"
#include <infiniband/verbs.h>
#include "contrib/rdmacm-mux/rdmacm-mux.h"
#include "rdma_utils.h"
typedef struct RdmaDeviceResources RdmaDeviceResources;
typedef struct RdmaBackendThread {
QemuThread thread;
QemuMutex mutex;
bool run; /* Set by thread manager to let thread know it should exit */
bool is_running; /* Set by the thread to report its status */
} RdmaBackendThread;
typedef struct RecvMadList {
QemuMutex lock;
QList *list;
} RecvMadList;
typedef struct RdmaCmMux {
CharBackend *chr_be;
int can_receive;
@ -48,7 +43,7 @@ typedef struct RdmaBackendDev {
struct ibv_context *context;
struct ibv_comp_channel *channel;
uint8_t port_num;
RecvMadList recv_mads_list;
RdmaProtectedQList recv_mads_list;
RdmaCmMux rdmacm_mux;
} RdmaBackendDev;
@ -70,6 +65,7 @@ typedef struct RdmaBackendQP {
struct ibv_pd *ibpd;
struct ibv_qp *ibqp;
uint8_t sgid_idx;
RdmaProtectedGSList cqe_ctx_list;
} RdmaBackendQP;
#endif

196
hw/rdma/rdma_rm.c
View File

@ -16,7 +16,9 @@
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "cpu.h"
#include "monitor/monitor.h"
#include "trace.h"
#include "rdma_utils.h"
#include "rdma_backend.h"
#include "rdma_rm.h"
@ -25,6 +27,58 @@
#define PG_DIR_SZ { TARGET_PAGE_SIZE / sizeof(__u64) }
#define PG_TBL_SZ { TARGET_PAGE_SIZE / sizeof(__u64) }
void rdma_dump_device_counters(Monitor *mon, RdmaDeviceResources *dev_res)
{
monitor_printf(mon, "\ttx : %" PRId64 "\n",
dev_res->stats.tx);
monitor_printf(mon, "\ttx_len : %" PRId64 "\n",
dev_res->stats.tx_len);
monitor_printf(mon, "\ttx_err : %" PRId64 "\n",
dev_res->stats.tx_err);
monitor_printf(mon, "\trx_bufs : %" PRId64 "\n",
dev_res->stats.rx_bufs);
monitor_printf(mon, "\trx_bufs_len : %" PRId64 "\n",
dev_res->stats.rx_bufs_len);
monitor_printf(mon, "\trx_bufs_err : %" PRId64 "\n",
dev_res->stats.rx_bufs_err);
monitor_printf(mon, "\tcomps : %" PRId64 "\n",
dev_res->stats.completions);
monitor_printf(mon, "\tmissing_comps : %" PRId32 "\n",
dev_res->stats.missing_cqe);
monitor_printf(mon, "\tpoll_cq (bk) : %" PRId64 "\n",
dev_res->stats.poll_cq_from_bk);
monitor_printf(mon, "\tpoll_cq_ppoll_to : %" PRId64 "\n",
dev_res->stats.poll_cq_ppoll_to);
monitor_printf(mon, "\tpoll_cq (fe) : %" PRId64 "\n",
dev_res->stats.poll_cq_from_guest);
monitor_printf(mon, "\tpoll_cq_empty : %" PRId64 "\n",
dev_res->stats.poll_cq_from_guest_empty);
monitor_printf(mon, "\tmad_tx : %" PRId64 "\n",
dev_res->stats.mad_tx);
monitor_printf(mon, "\tmad_tx_err : %" PRId64 "\n",
dev_res->stats.mad_tx_err);
monitor_printf(mon, "\tmad_rx : %" PRId64 "\n",
dev_res->stats.mad_rx);
monitor_printf(mon, "\tmad_rx_err : %" PRId64 "\n",
dev_res->stats.mad_rx_err);
monitor_printf(mon, "\tmad_rx_bufs : %" PRId64 "\n",
dev_res->stats.mad_rx_bufs);
monitor_printf(mon, "\tmad_rx_bufs_err : %" PRId64 "\n",
dev_res->stats.mad_rx_bufs_err);
monitor_printf(mon, "\tPDs : %" PRId32 "\n",
dev_res->pd_tbl.used);
monitor_printf(mon, "\tMRs : %" PRId32 "\n",
dev_res->mr_tbl.used);
monitor_printf(mon, "\tUCs : %" PRId32 "\n",
dev_res->uc_tbl.used);
monitor_printf(mon, "\tQPs : %" PRId32 "\n",
dev_res->qp_tbl.used);
monitor_printf(mon, "\tCQs : %" PRId32 "\n",
dev_res->cq_tbl.used);
monitor_printf(mon, "\tCEQ_CTXs : %" PRId32 "\n",
dev_res->cqe_ctx_tbl.used);
}
static inline void res_tbl_init(const char *name, RdmaRmResTbl *tbl,
uint32_t tbl_sz, uint32_t res_sz)
{
@ -36,6 +90,7 @@ static inline void res_tbl_init(const char *name, RdmaRmResTbl *tbl,
tbl->bitmap = bitmap_new(tbl_sz);
tbl->tbl_sz = tbl_sz;
tbl->res_sz = res_sz;
tbl->used = 0;
qemu_mutex_init(&tbl->lock);
}
@ -49,48 +104,52 @@ static inline void res_tbl_free(RdmaRmResTbl *tbl)
g_free(tbl->bitmap);
}
static inline void *res_tbl_get(RdmaRmResTbl *tbl, uint32_t handle)
static inline void *rdma_res_tbl_get(RdmaRmResTbl *tbl, uint32_t handle)
{
pr_dbg("%s, handle=%d\n", tbl->name, handle);
trace_rdma_res_tbl_get(tbl->name, handle);
if ((handle < tbl->tbl_sz) && (test_bit(handle, tbl->bitmap))) {
return tbl->tbl + handle * tbl->res_sz;
} else {
pr_dbg("Invalid handle %d\n", handle);
rdma_error_report("Table %s, invalid handle %d", tbl->name, handle);
return NULL;
}
}
static inline void *res_tbl_alloc(RdmaRmResTbl *tbl, uint32_t *handle)
static inline void *rdma_res_tbl_alloc(RdmaRmResTbl *tbl, uint32_t *handle)
{
qemu_mutex_lock(&tbl->lock);
*handle = find_first_zero_bit(tbl->bitmap, tbl->tbl_sz);
if (*handle > tbl->tbl_sz) {
pr_dbg("Failed to alloc, bitmap is full\n");
rdma_error_report("Table %s, failed to allocate, bitmap is full",
tbl->name);
qemu_mutex_unlock(&tbl->lock);
return NULL;
}
set_bit(*handle, tbl->bitmap);
tbl->used++;
qemu_mutex_unlock(&tbl->lock);
memset(tbl->tbl + *handle * tbl->res_sz, 0, tbl->res_sz);
pr_dbg("%s, handle=%d\n", tbl->name, *handle);
trace_rdma_res_tbl_alloc(tbl->name, *handle);
return tbl->tbl + *handle * tbl->res_sz;
}
static inline void res_tbl_dealloc(RdmaRmResTbl *tbl, uint32_t handle)
static inline void rdma_res_tbl_dealloc(RdmaRmResTbl *tbl, uint32_t handle)
{
pr_dbg("%s, handle=%d\n", tbl->name, handle);
trace_rdma_res_tbl_dealloc(tbl->name, handle);
qemu_mutex_lock(&tbl->lock);
if (handle < tbl->tbl_sz) {
clear_bit(handle, tbl->bitmap);
tbl->used--;
}
qemu_mutex_unlock(&tbl->lock);
@ -102,7 +161,7 @@ int rdma_rm_alloc_pd(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
RdmaRmPD *pd;
int ret = -ENOMEM;
pd = res_tbl_alloc(&dev_res->pd_tbl, pd_handle);
pd = rdma_res_tbl_alloc(&dev_res->pd_tbl, pd_handle);
if (!pd) {
goto out;
}
@ -118,7 +177,7 @@ int rdma_rm_alloc_pd(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
return 0;
out_tbl_dealloc:
res_tbl_dealloc(&dev_res->pd_tbl, *pd_handle);
rdma_res_tbl_dealloc(&dev_res->pd_tbl, *pd_handle);
out:
return ret;
@ -126,7 +185,7 @@ out:
RdmaRmPD *rdma_rm_get_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle)
{
return res_tbl_get(&dev_res->pd_tbl, pd_handle);
return rdma_res_tbl_get(&dev_res->pd_tbl, pd_handle);
}
void rdma_rm_dealloc_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle)
@ -135,14 +194,14 @@ void rdma_rm_dealloc_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle)
if (pd) {
rdma_backend_destroy_pd(&pd->backend_pd);
res_tbl_dealloc(&dev_res->pd_tbl, pd_handle);
rdma_res_tbl_dealloc(&dev_res->pd_tbl, pd_handle);
}
}
int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
uint64_t guest_start, size_t guest_length, void *host_virt,
int access_flags, uint32_t *mr_handle, uint32_t *lkey,
uint32_t *rkey)
uint64_t guest_start, uint64_t guest_length,
void *host_virt, int access_flags, uint32_t *mr_handle,
uint32_t *lkey, uint32_t *rkey)
{
RdmaRmMR *mr;
int ret = 0;
@ -150,20 +209,15 @@ int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
pd = rdma_rm_get_pd(dev_res, pd_handle);
if (!pd) {
pr_dbg("Invalid PD\n");
return -EINVAL;
}
mr = res_tbl_alloc(&dev_res->mr_tbl, mr_handle);
mr = rdma_res_tbl_alloc(&dev_res->mr_tbl, mr_handle);
if (!mr) {
pr_dbg("Failed to allocate obj in table\n");
return -ENOMEM;
}
pr_dbg("mr_handle=%d\n", *mr_handle);
pr_dbg("host_virt=0x%p\n", host_virt);
pr_dbg("guest_start=0x%" PRIx64 "\n", guest_start);
pr_dbg("length=%zu\n", guest_length);
trace_rdma_rm_alloc_mr(*mr_handle, host_virt, guest_start, guest_length,
access_flags);
if (host_virt) {
mr->virt = host_virt;
@ -174,7 +228,6 @@ int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
ret = rdma_backend_create_mr(&mr->backend_mr, &pd->backend_pd, mr->virt,
mr->length, access_flags);
if (ret) {
pr_dbg("Fail in rdma_backend_create_mr, err=%d\n", ret);
ret = -EIO;
goto out_dealloc_mr;
}
@ -189,14 +242,14 @@ int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
return 0;
out_dealloc_mr:
res_tbl_dealloc(&dev_res->mr_tbl, *mr_handle);
rdma_res_tbl_dealloc(&dev_res->mr_tbl, *mr_handle);
return ret;
}
RdmaRmMR *rdma_rm_get_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle)
{
return res_tbl_get(&dev_res->mr_tbl, mr_handle);
return rdma_res_tbl_get(&dev_res->mr_tbl, mr_handle);
}
void rdma_rm_dealloc_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle)
@ -205,12 +258,12 @@ void rdma_rm_dealloc_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle)
if (mr) {
rdma_backend_destroy_mr(&mr->backend_mr);
pr_dbg("start=0x%" PRIx64 "\n", mr->start);
trace_rdma_rm_dealloc_mr(mr_handle, mr->start);
if (mr->start) {
mr->virt -= (mr->start & (TARGET_PAGE_SIZE - 1));
munmap(mr->virt, mr->length);
}
res_tbl_dealloc(&dev_res->mr_tbl, mr_handle);
rdma_res_tbl_dealloc(&dev_res->mr_tbl, mr_handle);
}
}
@ -222,12 +275,13 @@ int rdma_rm_alloc_uc(RdmaDeviceResources *dev_res, uint32_t pfn,
/* TODO: Need to make sure pfn is between bar start address and
* bsd+RDMA_BAR2_UAR_SIZE
if (pfn > RDMA_BAR2_UAR_SIZE) {
pr_err("pfn out of range (%d > %d)\n", pfn, RDMA_BAR2_UAR_SIZE);
rdma_error_report("pfn out of range (%d > %d)", pfn,
RDMA_BAR2_UAR_SIZE);
return -ENOMEM;
}
*/
uc = res_tbl_alloc(&dev_res->uc_tbl, uc_handle);
uc = rdma_res_tbl_alloc(&dev_res->uc_tbl, uc_handle);
if (!uc) {
return -ENOMEM;
}
@ -237,7 +291,7 @@ int rdma_rm_alloc_uc(RdmaDeviceResources *dev_res, uint32_t pfn,
RdmaRmUC *rdma_rm_get_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle)
{
return res_tbl_get(&dev_res->uc_tbl, uc_handle);
return rdma_res_tbl_get(&dev_res->uc_tbl, uc_handle);
}
void rdma_rm_dealloc_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle)
@ -245,13 +299,13 @@ void rdma_rm_dealloc_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle)
RdmaRmUC *uc = rdma_rm_get_uc(dev_res, uc_handle);
if (uc) {
res_tbl_dealloc(&dev_res->uc_tbl, uc_handle);
rdma_res_tbl_dealloc(&dev_res->uc_tbl, uc_handle);
}
}
RdmaRmCQ *rdma_rm_get_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle)
{
return res_tbl_get(&dev_res->cq_tbl, cq_handle);
return rdma_res_tbl_get(&dev_res->cq_tbl, cq_handle);
}
int rdma_rm_alloc_cq(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
@ -260,7 +314,7 @@ int rdma_rm_alloc_cq(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
int rc;
RdmaRmCQ *cq;
cq = res_tbl_alloc(&dev_res->cq_tbl, cq_handle);
cq = rdma_res_tbl_alloc(&dev_res->cq_tbl, cq_handle);
if (!cq) {
return -ENOMEM;
}
@ -287,8 +341,6 @@ void rdma_rm_req_notify_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle,
{
RdmaRmCQ *cq;
pr_dbg("cq_handle=%d, notify=0x%x\n", cq_handle, notify);
cq = rdma_rm_get_cq(dev_res, cq_handle);
if (!cq) {
return;
@ -297,8 +349,6 @@ void rdma_rm_req_notify_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle,
if (cq->notify != CNT_SET) {
cq->notify = notify ? CNT_ARM : CNT_CLEAR;
}
pr_dbg("notify=%d\n", cq->notify);
}
void rdma_rm_dealloc_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle)
@ -312,7 +362,7 @@ void rdma_rm_dealloc_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle)
rdma_backend_destroy_cq(&cq->backend_cq);
res_tbl_dealloc(&dev_res->cq_tbl, cq_handle);
rdma_res_tbl_dealloc(&dev_res->cq_tbl, cq_handle);
}
RdmaRmQP *rdma_rm_get_qp(RdmaDeviceResources *dev_res, uint32_t qpn)
@ -323,6 +373,10 @@ RdmaRmQP *rdma_rm_get_qp(RdmaDeviceResources *dev_res, uint32_t qpn)
g_bytes_unref(key);
if (!qp) {
rdma_error_report("Invalid QP handle %d", qpn);
}
return qp;
}
@ -338,11 +392,8 @@ int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle,
RdmaRmPD *pd;
uint32_t rm_qpn;
pr_dbg("qp_type=%d\n", qp_type);
pd = rdma_rm_get_pd(dev_res, pd_handle);
if (!pd) {
pr_err("Invalid pd handle (%d)\n", pd_handle);
return -EINVAL;
}
@ -350,8 +401,8 @@ int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle,
rcq = rdma_rm_get_cq(dev_res, recv_cq_handle);
if (!scq || !rcq) {
pr_err("Invalid send_cqn or recv_cqn (%d, %d)\n",
send_cq_handle, recv_cq_handle);
rdma_error_report("Invalid send_cqn or recv_cqn (%d, %d)",
send_cq_handle, recv_cq_handle);
return -EINVAL;
}
@ -360,11 +411,10 @@ int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle,
rcq->notify = CNT_SET;
}
qp = res_tbl_alloc(&dev_res->qp_tbl, &rm_qpn);
qp = rdma_res_tbl_alloc(&dev_res->qp_tbl, &rm_qpn);
if (!qp) {
return -ENOMEM;
}
pr_dbg("rm_qpn=%d\n", rm_qpn);
qp->qpn = rm_qpn;
qp->qp_state = IBV_QPS_RESET;
@ -382,13 +432,13 @@ int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle,
}
*qpn = rdma_backend_qpn(&qp->backend_qp);
pr_dbg("rm_qpn=%d, backend_qpn=0x%x\n", rm_qpn, *qpn);
trace_rdma_rm_alloc_qp(rm_qpn, *qpn, qp_type);
g_hash_table_insert(dev_res->qp_hash, g_bytes_new(qpn, sizeof(*qpn)), qp);
return 0;
out_dealloc_qp:
res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn);
rdma_res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn);
return rc;
}
@ -402,28 +452,22 @@ int rdma_rm_modify_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
RdmaRmQP *qp;
int ret;
pr_dbg("qpn=0x%x\n", qp_handle);
pr_dbg("qkey=0x%x\n", qkey);
qp = rdma_rm_get_qp(dev_res, qp_handle);
if (!qp) {
return -EINVAL;
}
pr_dbg("qp_type=%d\n", qp->qp_type);
pr_dbg("attr_mask=0x%x\n", attr_mask);
if (qp->qp_type == IBV_QPT_SMI) {
pr_dbg("QP0 unsupported\n");
rdma_error_report("Got QP0 request");
return -EPERM;
} else if (qp->qp_type == IBV_QPT_GSI) {
pr_dbg("QP1\n");
return 0;
}
trace_rdma_rm_modify_qp(qp_handle, attr_mask, qp_state, sgid_idx);
if (attr_mask & IBV_QP_STATE) {
qp->qp_state = qp_state;
pr_dbg("qp_state=%d\n", qp->qp_state);
if (qp->qp_state == IBV_QPS_INIT) {
ret = rdma_backend_qp_state_init(backend_dev, &qp->backend_qp,
@ -435,11 +479,11 @@ int rdma_rm_modify_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
if (qp->qp_state == IBV_QPS_RTR) {
/* Get backend gid index */
pr_dbg("Guest sgid_idx=%d\n", sgid_idx);
sgid_idx = rdma_rm_get_backend_gid_index(dev_res, backend_dev,
sgid_idx);
if (sgid_idx <= 0) { /* TODO check also less than bk.max_sgid */
pr_dbg("Fail to get bk sgid_idx for sgid_idx %d\n", sgid_idx);
rdma_error_report("Failed to get bk sgid_idx for sgid_idx %d",
sgid_idx);
return -EIO;
}
@ -471,15 +515,11 @@ int rdma_rm_query_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
{
RdmaRmQP *qp;
pr_dbg("qpn=0x%x\n", qp_handle);
qp = rdma_rm_get_qp(dev_res, qp_handle);
if (!qp) {
return -EINVAL;
}
pr_dbg("qp_type=%d\n", qp->qp_type);
return rdma_backend_query_qp(&qp->backend_qp, attr, attr_mask, init_attr);
}
@ -497,22 +537,20 @@ void rdma_rm_dealloc_qp(RdmaDeviceResources *dev_res, uint32_t qp_handle)
return;
}
rdma_backend_destroy_qp(&qp->backend_qp);
rdma_backend_destroy_qp(&qp->backend_qp, dev_res);
res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn);
rdma_res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn);
}
void *rdma_rm_get_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id)
{
void **cqe_ctx;
cqe_ctx = res_tbl_get(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
cqe_ctx = rdma_res_tbl_get(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
if (!cqe_ctx) {
return NULL;
}
pr_dbg("ctx=%p\n", *cqe_ctx);
return *cqe_ctx;
}
@ -521,12 +559,11 @@ int rdma_rm_alloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t *cqe_ctx_id,
{
void **cqe_ctx;
cqe_ctx = res_tbl_alloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
cqe_ctx = rdma_res_tbl_alloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
if (!cqe_ctx) {
return -ENOMEM;
}
pr_dbg("ctx=%p\n", ctx);
*cqe_ctx = ctx;
return 0;
@ -534,7 +571,7 @@ int rdma_rm_alloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t *cqe_ctx_id,
void rdma_rm_dealloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id)
{
res_tbl_dealloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
rdma_res_tbl_dealloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id);
}
int rdma_rm_add_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
@ -544,7 +581,6 @@ int rdma_rm_add_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
rc = rdma_backend_add_gid(backend_dev, ifname, gid);
if (rc) {
pr_dbg("Fail to add gid\n");
return -EINVAL;
}
@ -565,7 +601,6 @@ int rdma_rm_del_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
rc = rdma_backend_del_gid(backend_dev, ifname,
&dev_res->port.gid_tbl[gid_idx].gid);
if (rc) {
pr_dbg("Fail to delete gid\n");
return -EINVAL;
}
@ -580,7 +615,7 @@ int rdma_rm_get_backend_gid_index(RdmaDeviceResources *dev_res,
RdmaBackendDev *backend_dev, int sgid_idx)
{
if (unlikely(sgid_idx < 0 || sgid_idx >= MAX_PORT_GIDS)) {
pr_dbg("Got invalid sgid_idx %d\n", sgid_idx);
rdma_error_report("Got invalid sgid_idx %d", sgid_idx);
return -EINVAL;
}
@ -590,9 +625,6 @@ int rdma_rm_get_backend_gid_index(RdmaDeviceResources *dev_res,
&dev_res->port.gid_tbl[sgid_idx].gid);
}
pr_dbg("backend_gid_index=%d\n",
dev_res->port.gid_tbl[sgid_idx].backend_gid_index);
return dev_res->port.gid_tbl[sgid_idx].backend_gid_index;
}
@ -624,8 +656,7 @@ static void fini_ports(RdmaDeviceResources *dev_res,
}
}
int rdma_rm_init(RdmaDeviceResources *dev_res, struct ibv_device_attr *dev_attr,
Error **errp)
int rdma_rm_init(RdmaDeviceResources *dev_res, struct ibv_device_attr *dev_attr)
{
dev_res->qp_hash = g_hash_table_new_full(g_bytes_hash, g_bytes_equal,
destroy_qp_hash_key, NULL);
@ -643,12 +674,19 @@ int rdma_rm_init(RdmaDeviceResources *dev_res, struct ibv_device_attr *dev_attr,
init_ports(dev_res);
qemu_mutex_init(&dev_res->lock);
memset(&dev_res->stats, 0, sizeof(dev_res->stats));
atomic_set(&dev_res->stats.missing_cqe, 0);
return 0;
}
void rdma_rm_fini(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
const char *ifname)
{
qemu_mutex_destroy(&dev_res->lock);
fini_ports(dev_res, backend_dev, ifname);
res_tbl_free(&dev_res->uc_tbl);

11
hw/rdma/rdma_rm.h
View File

@ -20,8 +20,8 @@
#include "rdma_backend_defs.h"
#include "rdma_rm_defs.h"
int rdma_rm_init(RdmaDeviceResources *dev_res, struct ibv_device_attr *dev_attr,
Error **errp);
int rdma_rm_init(RdmaDeviceResources *dev_res,
struct ibv_device_attr *dev_attr);
void rdma_rm_fini(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
const char *ifname);
@ -31,9 +31,9 @@ RdmaRmPD *rdma_rm_get_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle);
void rdma_rm_dealloc_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle);
int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
uint64_t guest_start, size_t guest_length, void *host_virt,
int access_flags, uint32_t *mr_handle, uint32_t *lkey,
uint32_t *rkey);
uint64_t guest_start, uint64_t guest_length,
void *host_virt, int access_flags, uint32_t *mr_handle,
uint32_t *lkey, uint32_t *rkey);
RdmaRmMR *rdma_rm_get_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle);
void rdma_rm_dealloc_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle);
@ -81,5 +81,6 @@ static inline union ibv_gid *rdma_rm_get_gid(RdmaDeviceResources *dev_res,
{
return &dev_res->port.gid_tbl[sgid_idx].gid;
}
void rdma_dump_device_counters(Monitor *mon, RdmaDeviceResources *dev_res);
#endif

32
hw/rdma/rdma_rm_defs.h
View File

@ -34,7 +34,9 @@
#define MAX_QP_INIT_RD_ATOM 16
#define MAX_AH 64
#define MAX_RM_TBL_NAME 16
#define MAX_RM_TBL_NAME 16
#define MAX_CONSEQ_EMPTY_POLL_CQ 4096 /* considered as error above this */
typedef struct RdmaRmResTbl {
char name[MAX_RM_TBL_NAME];
QemuMutex lock;
@ -42,6 +44,7 @@ typedef struct RdmaRmResTbl {
size_t tbl_sz;
size_t res_sz;
void *tbl;
uint32_t used; /* number of used entries in the table */
} RdmaRmResTbl;
typedef struct RdmaRmPD {
@ -96,7 +99,28 @@ typedef struct RdmaRmPort {
enum ibv_port_state state;
} RdmaRmPort;
typedef struct RdmaDeviceResources {
typedef struct RdmaRmStats {
uint64_t tx;
uint64_t tx_len;
uint64_t tx_err;
uint64_t rx_bufs;
uint64_t rx_bufs_len;
uint64_t rx_bufs_err;
uint64_t completions;
uint64_t mad_tx;
uint64_t mad_tx_err;
uint64_t mad_rx;
uint64_t mad_rx_err;
uint64_t mad_rx_bufs;
uint64_t mad_rx_bufs_err;
uint64_t poll_cq_from_bk;
uint64_t poll_cq_from_guest;
uint64_t poll_cq_from_guest_empty;
uint64_t poll_cq_ppoll_to;
uint32_t missing_cqe;
} RdmaRmStats;
struct RdmaDeviceResources {
RdmaRmPort port;
RdmaRmResTbl pd_tbl;
RdmaRmResTbl mr_tbl;
@ -105,6 +129,8 @@ typedef struct RdmaDeviceResources {
RdmaRmResTbl cq_tbl;
RdmaRmResTbl cqe_ctx_tbl;
GHashTable *qp_hash; /* Keeps mapping between real and emulated */
} RdmaDeviceResources;
QemuMutex lock;
RdmaRmStats stats;
};
#endif

83
hw/rdma/rdma_utils.c
View File

@ -14,26 +14,25 @@
*/
#include "qemu/osdep.h"
#include "qapi/qmp/qlist.h"
#include "qapi/qmp/qnum.h"
#include "trace.h"
#include "rdma_utils.h"
#ifdef PVRDMA_DEBUG
unsigned long pr_dbg_cnt;
#endif
void *rdma_pci_dma_map(PCIDevice *dev, dma_addr_t addr, dma_addr_t plen)
{
void *p;
hwaddr len = plen;
if (!addr) {
pr_dbg("addr is NULL\n");
rdma_error_report("addr is NULL");
return NULL;
}
p = pci_dma_map(dev, addr, &len, DMA_DIRECTION_TO_DEVICE);
if (!p) {
pr_dbg("Fail in pci_dma_map, addr=0x%" PRIx64 ", len=%" PRId64 "\n",
addr, len);
rdma_error_report("pci_dma_map fail, addr=0x%"PRIx64", len=%"PRId64,
addr, len);
return NULL;
}
@ -42,15 +41,81 @@ void *rdma_pci_dma_map(PCIDevice *dev, dma_addr_t addr, dma_addr_t plen)
return NULL;
}
pr_dbg("0x%" PRIx64 " -> %p (len=% " PRId64 ")\n", addr, p, len);
trace_rdma_pci_dma_map(addr, p, len);
return p;
}
void rdma_pci_dma_unmap(PCIDevice *dev, void *buffer, dma_addr_t len)
{
pr_dbg("%p\n", buffer);
trace_rdma_pci_dma_unmap(buffer);
if (buffer) {
pci_dma_unmap(dev, buffer, len, DMA_DIRECTION_TO_DEVICE, 0);
}
}
void rdma_protected_qlist_init(RdmaProtectedQList *list)
{
qemu_mutex_init(&list->lock);
list->list = qlist_new();
}
void rdma_protected_qlist_destroy(RdmaProtectedQList *list)
{
if (list->list) {
qlist_destroy_obj(QOBJECT(list->list));
qemu_mutex_destroy(&list->lock);
list->list = NULL;
}
}
void rdma_protected_qlist_append_int64(RdmaProtectedQList *list, int64_t value)
{
qemu_mutex_lock(&list->lock);
qlist_append_int(list->list, value);
qemu_mutex_unlock(&list->lock);
}
int64_t rdma_protected_qlist_pop_int64(RdmaProtectedQList *list)
{
QObject *obj;
qemu_mutex_lock(&list->lock);
obj = qlist_pop(list->list);
qemu_mutex_unlock(&list->lock);
if (!obj) {
return -ENOENT;
}
return qnum_get_uint(qobject_to(QNum, obj));
}
void rdma_protected_gslist_init(RdmaProtectedGSList *list)
{
qemu_mutex_init(&list->lock);
}
void rdma_protected_gslist_destroy(RdmaProtectedGSList *list)
{
if (list->list) {
g_slist_free(list->list);
list->list = NULL;
}
}
void rdma_protected_gslist_append_int32(RdmaProtectedGSList *list,
int32_t value)
{
qemu_mutex_lock(&list->lock);
list->list = g_slist_prepend(list->list, GINT_TO_POINTER(value));
qemu_mutex_unlock(&list->lock);
}
void rdma_protected_gslist_remove_int32(RdmaProtectedGSList *list,
int32_t value)
{
qemu_mutex_lock(&list->lock);
list->list = g_slist_remove(list->list, GINT_TO_POINTER(value));
qemu_mutex_unlock(&list->lock);
}

61
hw/rdma/rdma_utils.h
View File

@ -17,51 +17,40 @@
#ifndef RDMA_UTILS_H
#define RDMA_UTILS_H
#include "qemu/error-report.h"
#include "hw/pci/pci.h"
#include "sysemu/dma.h"
#include "stdio.h"
#define pr_info(fmt, ...) \
fprintf(stdout, "%s: %-20s (%3d): " fmt, "rdma", __func__, __LINE__,\
## __VA_ARGS__)
#define rdma_error_report(fmt, ...) \
error_report("%s: " fmt, "rdma", ## __VA_ARGS__)
#define rdma_warn_report(fmt, ...) \
warn_report("%s: " fmt, "rdma", ## __VA_ARGS__)
#define rdma_info_report(fmt, ...) \
info_report("%s: " fmt, "rdma", ## __VA_ARGS__)
#define pr_err(fmt, ...) \
fprintf(stderr, "%s: Error at %-20s (%3d): " fmt, "rdma", __func__, \
__LINE__, ## __VA_ARGS__)
typedef struct RdmaProtectedQList {
QemuMutex lock;
QList *list;
} RdmaProtectedQList;
#ifdef PVRDMA_DEBUG
extern unsigned long pr_dbg_cnt;
#define init_pr_dbg(void) \
{ \
pr_dbg_cnt = 0; \
}
#define pr_dbg(fmt, ...) \
fprintf(stdout, "%lx %ld: %-20s (%3d): " fmt, pthread_self(), pr_dbg_cnt++, \
__func__, __LINE__, ## __VA_ARGS__)
#define pr_dbg_buf(title, buf, len) \
{ \
int i; \
char *b = g_malloc0(len * 3 + 1); \
char b1[4]; \
for (i = 0; i < len; i++) { \
sprintf(b1, "%.2X ", buf[i] & 0x000000FF); \
strcat(b, b1); \
} \
pr_dbg("%s (%d): %s\n", title, len, b); \
g_free(b); \
}
#else
#define init_pr_dbg(void)
#define pr_dbg(fmt, ...)
#define pr_dbg_buf(title, buf, len)
#endif
typedef struct RdmaProtectedGSList {
QemuMutex lock;
GSList *list;
} RdmaProtectedGSList;
void *rdma_pci_dma_map(PCIDevice *dev, dma_addr_t addr, dma_addr_t plen);
void rdma_pci_dma_unmap(PCIDevice *dev, void *buffer, dma_addr_t len);
void rdma_protected_qlist_init(RdmaProtectedQList *list);
void rdma_protected_qlist_destroy(RdmaProtectedQList *list);
void rdma_protected_qlist_append_int64(RdmaProtectedQList *list, int64_t value);
int64_t rdma_protected_qlist_pop_int64(RdmaProtectedQList *list);
void rdma_protected_gslist_init(RdmaProtectedGSList *list);
void rdma_protected_gslist_destroy(RdmaProtectedGSList *list);
void rdma_protected_gslist_append_int32(RdmaProtectedGSList *list,
int32_t value);
void rdma_protected_gslist_remove_int32(RdmaProtectedGSList *list,
int32_t value);
static inline void addrconf_addr_eui48(uint8_t *eui, const char *addr)
{

34
hw/rdma/trace-events
View File

@ -1,5 +1,31 @@
# See docs/tracing.txt for syntax documentation.
# See docs/devel/tracing.txt for syntax documentation.
#hw/rdma/rdma_backend.c
create_ah_cache_hit(uint64_t subnet, uint64_t net_id) "subnet = 0x%"PRIx64" net_id = 0x%"PRIx64
create_ah_cache_miss(uint64_t subnet, uint64_t net_id) "subnet = 0x%"PRIx64" net_id = 0x%"PRIx64
# hw/rdma/rdma_backend.c
rdma_check_dev_attr(const char *name, int max_bk, int max_fe) "%s: be=%d, fe=%d"
rdma_create_ah_cache_hit(uint64_t subnet, uint64_t if_id) "subnet=0x%"PRIx64",if_id=0x%"PRIx64
rdma_create_ah_cache_miss(uint64_t subnet, uint64_t if_id) "subnet=0x%"PRIx64",if_id=0x%"PRIx64
rdma_poll_cq(int ne, void *ibcq) "Got %d completion(s) from cq %p"
rdmacm_mux(const char *title, int msg_type, int op_code) "%s: msg_type=%d, op_code=%d"
rdmacm_mux_check_op_status(int msg_type, int op_code, int err_code) "resp: msg_type=%d, op_code=%d, err_code=%d"
rdma_mad_message(const char *title, int len, char *data) "mad %s (%d): %s"
rdma_backend_rc_qp_state_init(uint32_t qpn) "RC QP 0x%x switch to INIT"
rdma_backend_ud_qp_state_init(uint32_t qpn, uint32_t qkey) "UD QP 0x%x switch to INIT, qkey=0x%x"
rdma_backend_rc_qp_state_rtr(uint32_t qpn, uint64_t subnet, uint64_t ifid, uint8_t sgid_idx, uint32_t dqpn, uint32_t rq_psn) "RC QP 0x%x switch to RTR, subnet = 0x%"PRIx64", ifid = 0x%"PRIx64 ", sgid_idx=%d, dqpn=0x%x, rq_psn=0x%x"
rdma_backend_ud_qp_state_rtr(uint32_t qpn, uint32_t qkey) "UD QP 0x%x switch to RTR, qkey=0x%x"
rdma_backend_rc_qp_state_rts(uint32_t qpn, uint32_t sq_psn) "RC QP 0x%x switch to RTS, sq_psn=0x%x, "
rdma_backend_ud_qp_state_rts(uint32_t qpn, uint32_t sq_psn, uint32_t qkey) "UD QP 0x%x switch to RTS, sq_psn=0x%x, qkey=0x%x"
rdma_backend_get_gid_index(uint64_t subnet, uint64_t ifid, int gid_idx) "subnet=0x%"PRIx64", ifid=0x%"PRIx64 ", gid_idx=%d"
rdma_backend_gid_change(const char *op, uint64_t subnet, uint64_t ifid) "%s subnet=0x%"PRIx64", ifid=0x%"PRIx64
# hw/rdma/rdma_rm.c
rdma_res_tbl_get(char *name, uint32_t handle) "tbl %s, handle %d"
rdma_res_tbl_alloc(char *name, uint32_t handle) "tbl %s, handle %d"
rdma_res_tbl_dealloc(char *name, uint32_t handle) "tbl %s, handle %d"
rdma_rm_alloc_mr(uint32_t mr_handle, void *host_virt, uint64_t guest_start, uint64_t guest_length, int access_flags) "mr_handle=%d, host_virt=%p, guest_start=0x%"PRIx64", length=%" PRId64", access_flags=0x%x"
rdma_rm_dealloc_mr(uint32_t mr_handle, uint64_t guest_start) "mr_handle=%d, guest_start=0x%"PRIx64
rdma_rm_alloc_qp(uint32_t rm_qpn, uint32_t backend_qpn, uint8_t qp_type) "rm_qpn=%d, backend_qpn=0x%x, qp_type=%d"
rdma_rm_modify_qp(uint32_t qpn, uint32_t attr_mask, int qp_state, uint8_t sgid_idx) "qpn=0x%x, attr_mask=0x%x, qp_state=%d, sgid_idx=%d"
# hw/rdma/rdma_utils.c
rdma_pci_dma_map(uint64_t addr, void *vaddr, uint64_t len) "0x%"PRIx64" -> %p (len=%" PRId64")"
rdma_pci_dma_unmap(void *vaddr) "%p"

12
hw/rdma/vmw/pvrdma.h
View File

@ -70,6 +70,14 @@ typedef struct DSRInfo {
PvrdmaRing cq;
} DSRInfo;
typedef struct PVRDMADevStats {
uint64_t commands;
uint64_t regs_reads;
uint64_t regs_writes;
uint64_t uar_writes;
uint64_t interrupts;
} PVRDMADevStats;
typedef struct PVRDMADev {
PCIDevice parent_obj;
MemoryRegion msix;
@ -89,6 +97,7 @@ typedef struct PVRDMADev {
CharBackend mad_chr;
VMXNET3State *func0;
Notifier shutdown_notifier;
PVRDMADevStats stats;
} PVRDMADev;
#define PVRDMA_DEV(dev) OBJECT_CHECK(PVRDMADev, (dev), PVRDMA_HW_NAME)
@ -123,10 +132,11 @@ static inline void post_interrupt(PVRDMADev *dev, unsigned vector)
PCIDevice *pci_dev = PCI_DEVICE(dev);
if (likely(!dev->interrupt_mask)) {
dev->stats.interrupts++;
msix_notify(pci_dev, vector);
}
}
int execute_command(PVRDMADev *dev);
int pvrdma_exec_cmd(PVRDMADev *dev);
#endif

121
hw/rdma/vmw/pvrdma_cmd.c
View File

@ -14,7 +14,6 @@
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "cpu.h"
#include "hw/hw.h"
#include "hw/pci/pci.h"
@ -24,6 +23,7 @@
#include "../rdma_rm.h"
#include "../rdma_utils.h"
#include "trace.h"
#include "pvrdma.h"
#include "standard-headers/rdma/vmw_pvrdma-abi.h"
@ -35,40 +35,38 @@ static void *pvrdma_map_to_pdir(PCIDevice *pdev, uint64_t pdir_dma,
void *host_virt = NULL, *curr_page;
if (!nchunks) {
pr_dbg("nchunks=0\n");
rdma_error_report("Got nchunks=0");
return NULL;
}
dir = rdma_pci_dma_map(pdev, pdir_dma, TARGET_PAGE_SIZE);
if (!dir) {
error_report("PVRDMA: Failed to map to page directory");
rdma_error_report("Failed to map to page directory");
return NULL;
}
tbl = rdma_pci_dma_map(pdev, dir[0], TARGET_PAGE_SIZE);
if (!tbl) {
error_report("PVRDMA: Failed to map to page table 0");
rdma_error_report("Failed to map to page table 0");
goto out_unmap_dir;
}
curr_page = rdma_pci_dma_map(pdev, (dma_addr_t)tbl[0], TARGET_PAGE_SIZE);
if (!curr_page) {
error_report("PVRDMA: Failed to map the first page");
rdma_error_report("Failed to map the page 0");
goto out_unmap_tbl;
}
host_virt = mremap(curr_page, 0, length, MREMAP_MAYMOVE);
pr_dbg("mremap %p -> %p\n", curr_page, host_virt);
if (host_virt == MAP_FAILED) {
host_virt = NULL;
error_report("PVRDMA: Failed to remap memory for host_virt");
rdma_error_report("Failed to remap memory for host_virt");
goto out_unmap_tbl;
}
trace_pvrdma_map_to_pdir_host_virt(curr_page, host_virt);
rdma_pci_dma_unmap(pdev, curr_page, TARGET_PAGE_SIZE);
pr_dbg("host_virt=%p\n", host_virt);
dir_idx = 0;
tbl_idx = 1;
addr_idx = 1;
@ -76,28 +74,28 @@ static void *pvrdma_map_to_pdir(PCIDevice *pdev, uint64_t pdir_dma,
if (tbl_idx == TARGET_PAGE_SIZE / sizeof(uint64_t)) {
tbl_idx = 0;
dir_idx++;
pr_dbg("Mapping to table %d\n", dir_idx);
rdma_pci_dma_unmap(pdev, tbl, TARGET_PAGE_SIZE);
tbl = rdma_pci_dma_map(pdev, dir[dir_idx], TARGET_PAGE_SIZE);
if (!tbl) {
error_report("PVRDMA: Failed to map to page table %d", dir_idx);
rdma_error_report("Failed to map to page table %d", dir_idx);
goto out_unmap_host_virt;
}
}
pr_dbg("guest_dma[%d]=0x%" PRIx64 "\n", addr_idx, tbl[tbl_idx]);
curr_page = rdma_pci_dma_map(pdev, (dma_addr_t)tbl[tbl_idx],
TARGET_PAGE_SIZE);
if (!curr_page) {
error_report("PVRDMA: Failed to map to page %d, dir %d", tbl_idx,
dir_idx);
rdma_error_report("Failed to map to page %d, dir %d", tbl_idx,
dir_idx);
goto out_unmap_host_virt;
}
mremap(curr_page, 0, TARGET_PAGE_SIZE, MREMAP_MAYMOVE | MREMAP_FIXED,
host_virt + TARGET_PAGE_SIZE * addr_idx);
trace_pvrdma_map_to_pdir_next_page(addr_idx, curr_page, host_virt +
TARGET_PAGE_SIZE * addr_idx);
rdma_pci_dma_unmap(pdev, curr_page, TARGET_PAGE_SIZE);
addr_idx++;
@ -125,9 +123,8 @@ static int query_port(PVRDMADev *dev, union pvrdma_cmd_req *req,
{
struct pvrdma_cmd_query_port *cmd = &req->query_port;
struct pvrdma_cmd_query_port_resp *resp = &rsp->query_port_resp;
struct pvrdma_port_attr attrs = {0};
struct pvrdma_port_attr attrs = {};
pr_dbg("port=%d\n", cmd->port_num);
if (cmd->port_num > MAX_PORTS) {
return -EINVAL;
}
@ -159,12 +156,10 @@ static int query_pkey(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct pvrdma_cmd_query_pkey *cmd = &req->query_pkey;
struct pvrdma_cmd_query_pkey_resp *resp = &rsp->query_pkey_resp;
pr_dbg("port=%d\n", cmd->port_num);
if (cmd->port_num > MAX_PORTS) {
return -EINVAL;
}
pr_dbg("index=%d\n", cmd->index);
if (cmd->index > MAX_PKEYS) {
return -EINVAL;
}
@ -172,7 +167,6 @@ static int query_pkey(PVRDMADev *dev, union pvrdma_cmd_req *req,
memset(resp, 0, sizeof(*resp));
resp->pkey = PVRDMA_PKEY;
pr_dbg("pkey=0x%x\n", resp->pkey);
return 0;
}
@ -184,8 +178,6 @@ static int create_pd(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct pvrdma_cmd_create_pd_resp *resp = &rsp->create_pd_resp;
int rc;
pr_dbg("context=0x%x\n", cmd->ctx_handle ? cmd->ctx_handle : 0);
memset(resp, 0, sizeof(*resp));
rc = rdma_rm_alloc_pd(&dev->rdma_dev_res, &dev->backend_dev,
&resp->pd_handle, cmd->ctx_handle);
@ -198,8 +190,6 @@ static int destroy_pd(PVRDMADev *dev, union pvrdma_cmd_req *req,
{
struct pvrdma_cmd_destroy_pd *cmd = &req->destroy_pd;
pr_dbg("pd_handle=%d\n", cmd->pd_handle);
rdma_rm_dealloc_pd(&dev->rdma_dev_res, cmd->pd_handle);
return 0;
@ -216,15 +206,11 @@ static int create_mr(PVRDMADev *dev, union pvrdma_cmd_req *req,
memset(resp, 0, sizeof(*resp));
pr_dbg("pd_handle=%d\n", cmd->pd_handle);
pr_dbg("access_flags=0x%x\n", cmd->access_flags);
pr_dbg("flags=0x%x\n", cmd->flags);
if (!(cmd->flags & PVRDMA_MR_FLAG_DMA)) {
host_virt = pvrdma_map_to_pdir(pci_dev, cmd->pdir_dma, cmd->nchunks,
cmd->length);
if (!host_virt) {
pr_dbg("Failed to map to pdir\n");
rdma_error_report("Failed to map to pdir");
return -EINVAL;
}
}
@ -244,8 +230,6 @@ static int destroy_mr(PVRDMADev *dev, union pvrdma_cmd_req *req,
{
struct pvrdma_cmd_destroy_mr *cmd = &req->destroy_mr;
pr_dbg("mr_handle=%d\n", cmd->mr_handle);
rdma_rm_dealloc_mr(&dev->rdma_dev_res, cmd->mr_handle);
return 0;
@ -260,20 +244,19 @@ static int create_cq_ring(PCIDevice *pci_dev , PvrdmaRing **ring,
char ring_name[MAX_RING_NAME_SZ];
if (!nchunks || nchunks > PVRDMA_MAX_FAST_REG_PAGES) {
pr_dbg("invalid nchunks: %d\n", nchunks);
rdma_error_report("Got invalid nchunks: %d", nchunks);
return rc;
}
pr_dbg("pdir_dma=0x%llx\n", (long long unsigned int)pdir_dma);
dir = rdma_pci_dma_map(pci_dev, pdir_dma, TARGET_PAGE_SIZE);
if (!dir) {
pr_dbg("Failed to map to CQ page directory\n");
rdma_error_report("Failed to map to CQ page directory");
goto out;
}
tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE);
if (!tbl) {
pr_dbg("Failed to map to CQ page table\n");
rdma_error_report("Failed to map to CQ page table");
goto out;
}
@ -284,7 +267,7 @@ static int create_cq_ring(PCIDevice *pci_dev , PvrdmaRing **ring,
rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
if (!r->ring_state) {
pr_dbg("Failed to map to CQ ring state\n");
rdma_error_report("Failed to map to CQ ring state");
goto out_free_ring;
}
@ -339,8 +322,6 @@ static int create_cq(PVRDMADev *dev, union pvrdma_cmd_req *req,
return rc;
}
pr_dbg("ring=%p\n", ring);
rc = rdma_rm_alloc_cq(&dev->rdma_dev_res, &dev->backend_dev, cmd->cqe,
&resp->cq_handle, ring);
if (rc) {
@ -359,11 +340,9 @@ static int destroy_cq(PVRDMADev *dev, union pvrdma_cmd_req *req,
RdmaRmCQ *cq;
PvrdmaRing *ring;
pr_dbg("cq_handle=%d\n", cmd->cq_handle);
cq = rdma_rm_get_cq(&dev->rdma_dev_res, cmd->cq_handle);
if (!cq) {
pr_dbg("Invalid CQ handle\n");
rdma_error_report("Got invalid CQ handle");
return -EINVAL;
}
@ -388,42 +367,33 @@ static int create_qp_rings(PCIDevice *pci_dev, uint64_t pdir_dma,
if (!spages || spages > PVRDMA_MAX_FAST_REG_PAGES
|| !rpages || rpages > PVRDMA_MAX_FAST_REG_PAGES) {
pr_dbg("invalid pages: %d, %d\n", spages, rpages);
rdma_error_report("Got invalid page count for QP ring: %d, %d", spages,
rpages);
return rc;
}
pr_dbg("pdir_dma=0x%llx\n", (long long unsigned int)pdir_dma);
dir = rdma_pci_dma_map(pci_dev, pdir_dma, TARGET_PAGE_SIZE);
if (!dir) {
pr_dbg("Failed to map to CQ page directory\n");
rdma_error_report("Failed to map to QP page directory");
goto out;
}
tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE);
if (!tbl) {
pr_dbg("Failed to map to CQ page table\n");
rdma_error_report("Failed to map to QP page table");
goto out;
}
sr = g_malloc(2 * sizeof(*rr));
rr = &sr[1];
pr_dbg("sring=%p\n", sr);
pr_dbg("rring=%p\n", rr);
*rings = sr;
pr_dbg("scqe=%d\n", scqe);
pr_dbg("smax_sge=%d\n", smax_sge);
pr_dbg("spages=%d\n", spages);
pr_dbg("rcqe=%d\n", rcqe);
pr_dbg("rmax_sge=%d\n", rmax_sge);
pr_dbg("rpages=%d\n", rpages);
/* Create send ring */
sr->ring_state = (struct pvrdma_ring *)
rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
if (!sr->ring_state) {
pr_dbg("Failed to map to CQ ring state\n");
rdma_error_report("Failed to map to QP ring state");
goto out_free_sr_mem;
}
@ -468,9 +438,7 @@ out:
static void destroy_qp_rings(PvrdmaRing *ring)
{
pr_dbg("sring=%p\n", &ring[0]);
pvrdma_ring_free(&ring[0]);
pr_dbg("rring=%p\n", &ring[1]);
pvrdma_ring_free(&ring[1]);
rdma_pci_dma_unmap(ring->dev, ring->ring_state, TARGET_PAGE_SIZE);
@ -487,9 +455,6 @@ static int create_qp(PVRDMADev *dev, union pvrdma_cmd_req *req,
memset(resp, 0, sizeof(*resp));
pr_dbg("total_chunks=%d\n", cmd->total_chunks);
pr_dbg("send_chunks=%d\n", cmd->send_chunks);
rc = create_qp_rings(PCI_DEVICE(dev), cmd->pdir_dma, &rings,
cmd->max_send_wr, cmd->max_send_sge, cmd->send_chunks,
cmd->max_recv_wr, cmd->max_recv_sge,
@ -498,8 +463,6 @@ static int create_qp(PVRDMADev *dev, union pvrdma_cmd_req *req,
return rc;
}
pr_dbg("rings=%p\n", rings);
rc = rdma_rm_alloc_qp(&dev->rdma_dev_res, cmd->pd_handle, cmd->qp_type,
cmd->max_send_wr, cmd->max_send_sge,
cmd->send_cq_handle, cmd->max_recv_wr,
@ -525,10 +488,6 @@ static int modify_qp(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct pvrdma_cmd_modify_qp *cmd = &req->modify_qp;
int rc;
pr_dbg("qp_handle=%d\n", cmd->qp_handle);
memset(rsp, 0, sizeof(*rsp));
/* No need to verify sgid_index since it is u8 */
rc = rdma_rm_modify_qp(&dev->rdma_dev_res, &dev->backend_dev,
@ -551,10 +510,7 @@ static int query_qp(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct ibv_qp_init_attr init_attr;
int rc;
pr_dbg("qp_handle=%d\n", cmd->qp_handle);
pr_dbg("attr_mask=0x%x\n", cmd->attr_mask);
memset(rsp, 0, sizeof(*rsp));
memset(resp, 0, sizeof(*resp));
rc = rdma_rm_query_qp(&dev->rdma_dev_res, &dev->backend_dev, cmd->qp_handle,
(struct ibv_qp_attr *)&resp->attrs, cmd->attr_mask,
@ -572,7 +528,6 @@ static int destroy_qp(PVRDMADev *dev, union pvrdma_cmd_req *req,
qp = rdma_rm_get_qp(&dev->rdma_dev_res, cmd->qp_handle);
if (!qp) {
pr_dbg("Invalid QP handle\n");
return -EINVAL;
}
@ -591,16 +546,10 @@ static int create_bind(PVRDMADev *dev, union pvrdma_cmd_req *req,
int rc;
union ibv_gid *gid = (union ibv_gid *)&cmd->new_gid;
pr_dbg("index=%d\n", cmd->index);
if (cmd->index >= MAX_PORT_GIDS) {
return -EINVAL;
}
pr_dbg("gid[%d]=0x%llx,0x%llx\n", cmd->index,
(long long unsigned int)be64_to_cpu(gid->global.subnet_prefix),
(long long unsigned int)be64_to_cpu(gid->global.interface_id));
rc = rdma_rm_add_gid(&dev->rdma_dev_res, &dev->backend_dev,
dev->backend_eth_device_name, gid, cmd->index);
@ -614,8 +563,6 @@ static int destroy_bind(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct pvrdma_cmd_destroy_bind *cmd = &req->destroy_bind;
pr_dbg("index=%d\n", cmd->index);
if (cmd->index >= MAX_PORT_GIDS) {
return -EINVAL;
}
@ -633,8 +580,6 @@ static int create_uc(PVRDMADev *dev, union pvrdma_cmd_req *req,
struct pvrdma_cmd_create_uc_resp *resp = &rsp->create_uc_resp;
int rc;
pr_dbg("pfn=%d\n", cmd->pfn);
memset(resp, 0, sizeof(*resp));
rc = rdma_rm_alloc_uc(&dev->rdma_dev_res, cmd->pfn, &resp->ctx_handle);
@ -646,8 +591,6 @@ static int destroy_uc(PVRDMADev *dev, union pvrdma_cmd_req *req,
{
struct pvrdma_cmd_destroy_uc *cmd = &req->destroy_uc;
pr_dbg("ctx_handle=%d\n", cmd->ctx_handle);
rdma_rm_dealloc_uc(&dev->rdma_dev_res, cmd->ctx_handle);
return 0;
@ -680,22 +623,21 @@ static struct cmd_handler cmd_handlers[] = {
{PVRDMA_CMD_DESTROY_BIND, PVRDMA_CMD_DESTROY_BIND_RESP_NOOP, destroy_bind},
};
int execute_command(PVRDMADev *dev)
int pvrdma_exec_cmd(PVRDMADev *dev)
{
int err = 0xFFFF;
DSRInfo *dsr_info;
dsr_info = &dev->dsr_info;
pr_dbg("cmd=%d\n", dsr_info->req->hdr.cmd);
if (dsr_info->req->hdr.cmd >= sizeof(cmd_handlers) /
sizeof(struct cmd_handler)) {
pr_dbg("Unsupported command\n");
rdma_error_report("Unsupported command");
goto out;
}
if (!cmd_handlers[dsr_info->req->hdr.cmd].exec) {
pr_dbg("Unsupported command (not implemented yet)\n");
rdma_error_report("Unsupported command (not implemented yet)");
goto out;
}
@ -704,7 +646,10 @@ int execute_command(PVRDMADev *dev)
dsr_info->rsp->hdr.response = dsr_info->req->hdr.response;
dsr_info->rsp->hdr.ack = cmd_handlers[dsr_info->req->hdr.cmd].ack;
dsr_info->rsp->hdr.err = err < 0 ? -err : 0;
pr_dbg("rsp->hdr.err=%d\n", dsr_info->rsp->hdr.err);
trace_pvrdma_exec_cmd(dsr_info->req->hdr.cmd, dsr_info->rsp->hdr.err);
dev->stats.commands++;
out:
set_reg_val(dev, PVRDMA_REG_ERR, err);

26
hw/rdma/vmw/pvrdma_dev_ring.c
View File

@ -17,6 +17,8 @@
#include "hw/pci/pci.h"
#include "cpu.h"
#include "trace.h"
#include "../rdma_utils.h"
#include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h"
#include "pvrdma_dev_ring.h"
@ -30,13 +32,10 @@ int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev,
strncpy(ring->name, name, MAX_RING_NAME_SZ);
ring->name[MAX_RING_NAME_SZ - 1] = 0;
pr_dbg("Initializing %s ring\n", ring->name);
ring->dev = dev;
ring->ring_state = ring_state;
ring->max_elems = max_elems;
ring->elem_sz = elem_sz;
pr_dbg("ring->elem_sz=%zu\n", ring->elem_sz);
pr_dbg("npages=%d\n", npages);
/* TODO: Give a moment to think if we want to redo driver settings
atomic_set(&ring->ring_state->prod_tail, 0);
atomic_set(&ring->ring_state->cons_head, 0);
@ -46,14 +45,14 @@ int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev,
for (i = 0; i < npages; i++) {
if (!tbl[i]) {
pr_err("npages=%ld but tbl[%d] is NULL\n", (long)npages, i);
rdma_error_report("npages=%d but tbl[%d] is NULL", npages, i);
continue;
}
ring->pages[i] = rdma_pci_dma_map(dev, tbl[i], TARGET_PAGE_SIZE);
if (!ring->pages[i]) {
rc = -ENOMEM;
pr_dbg("Failed to map to page %d\n", i);
rdma_error_report("Failed to map to page %d in ring %s", i, name);
goto out_free;
}
memset(ring->pages[i], 0, TARGET_PAGE_SIZE);
@ -78,7 +77,7 @@ void *pvrdma_ring_next_elem_read(PvrdmaRing *ring)
e = pvrdma_idx_ring_has_data(ring->ring_state, ring->max_elems, &idx);
if (e <= 0) {
pr_dbg("No more data in ring\n");
trace_pvrdma_ring_next_elem_read_no_data(ring->name);
return NULL;
}
@ -89,11 +88,6 @@ void *pvrdma_ring_next_elem_read(PvrdmaRing *ring)
void pvrdma_ring_read_inc(PvrdmaRing *ring)
{
pvrdma_idx_ring_inc(&ring->ring_state->cons_head, ring->max_elems);
/*
pr_dbg("%s: t=%d, h=%d, m=%ld\n", ring->name,
ring->ring_state->prod_tail, ring->ring_state->cons_head,
ring->max_elems);
*/
}
void *pvrdma_ring_next_elem_write(PvrdmaRing *ring)
@ -103,13 +97,13 @@ void *pvrdma_ring_next_elem_write(PvrdmaRing *ring)
idx = pvrdma_idx_ring_has_space(ring->ring_state, ring->max_elems, &tail);
if (idx <= 0) {
pr_dbg("CQ is full\n");
rdma_error_report("CQ is full");
return NULL;
}
idx = pvrdma_idx(&ring->ring_state->prod_tail, ring->max_elems);
if (idx < 0 || tail != idx) {
pr_dbg("invalid idx\n");
rdma_error_report("Invalid idx %d", idx);
return NULL;
}
@ -120,11 +114,6 @@ void *pvrdma_ring_next_elem_write(PvrdmaRing *ring)
void pvrdma_ring_write_inc(PvrdmaRing *ring)
{
pvrdma_idx_ring_inc(&ring->ring_state->prod_tail, ring->max_elems);
/*
pr_dbg("%s: t=%d, h=%d, m=%ld\n", ring->name,
ring->ring_state->prod_tail, ring->ring_state->cons_head,
ring->max_elems);
*/
}
void pvrdma_ring_free(PvrdmaRing *ring)
@ -137,7 +126,6 @@ void pvrdma_ring_free(PvrdmaRing *ring)
return;
}
pr_dbg("ring->npages=%d\n", ring->npages);
while (ring->npages--) {
rdma_pci_dma_unmap(ring->dev, ring->pages[ring->npages],
TARGET_PAGE_SIZE);

182
hw/rdma/vmw/pvrdma_main.c
View File

@ -25,6 +25,8 @@
#include "cpu.h"
#include "trace.h"
#include "sysemu/sysemu.h"
#include "monitor/monitor.h"
#include "hw/rdma/rdma.h"
#include "../rdma_rm.h"
#include "../rdma_backend.h"
@ -55,6 +57,26 @@ static Property pvrdma_dev_properties[] = {
DEFINE_PROP_END_OF_LIST(),
};
static void pvrdma_print_statistics(Monitor *mon, RdmaProvider *obj)
{
PVRDMADev *dev = PVRDMA_DEV(obj);
PCIDevice *pdev = PCI_DEVICE(dev);
monitor_printf(mon, "%s, %x.%x\n", pdev->name, PCI_SLOT(pdev->devfn),
PCI_FUNC(pdev->devfn));
monitor_printf(mon, "\tcommands : %" PRId64 "\n",
dev->stats.commands);
monitor_printf(mon, "\tregs_reads : %" PRId64 "\n",
dev->stats.regs_reads);
monitor_printf(mon, "\tregs_writes : %" PRId64 "\n",
dev->stats.regs_writes);
monitor_printf(mon, "\tuar_writes : %" PRId64 "\n",
dev->stats.uar_writes);
monitor_printf(mon, "\tinterrupts : %" PRId64 "\n",
dev->stats.interrupts);
rdma_dump_device_counters(mon, &dev->rdma_dev_res);
}
static void free_dev_ring(PCIDevice *pci_dev, PvrdmaRing *ring,
void *ring_state)
{
@ -69,25 +91,22 @@ static int init_dev_ring(PvrdmaRing *ring, struct pvrdma_ring **ring_state,
uint64_t *dir, *tbl;
int rc = 0;
pr_dbg("Initializing device ring %s\n", name);
pr_dbg("pdir_dma=0x%llx\n", (long long unsigned int)dir_addr);
pr_dbg("num_pages=%d\n", num_pages);
dir = rdma_pci_dma_map(pci_dev, dir_addr, TARGET_PAGE_SIZE);
if (!dir) {
pr_err("Failed to map to page directory\n");
rdma_error_report("Failed to map to page directory (ring %s)", name);
rc = -ENOMEM;
goto out;
}
tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE);
if (!tbl) {
pr_err("Failed to map to page table\n");
rdma_error_report("Failed to map to page table (ring %s)", name);
rc = -ENOMEM;
goto out_free_dir;
}
*ring_state = rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
if (!*ring_state) {
pr_err("Failed to map to ring state\n");
rdma_error_report("Failed to map to ring state (ring %s)", name);
rc = -ENOMEM;
goto out_free_tbl;
}
@ -100,7 +119,6 @@ static int init_dev_ring(PvrdmaRing *ring, struct pvrdma_ring **ring_state,
sizeof(struct pvrdma_cqne),
(dma_addr_t *)&tbl[1], (dma_addr_t)num_pages - 1);
if (rc) {
pr_err("Failed to initialize ring\n");
rc = -ENOMEM;
goto out_free_ring_state;
}
@ -155,11 +173,10 @@ static int load_dsr(PVRDMADev *dev)
free_dsr(dev);
/* Map to DSR */
pr_dbg("dsr_dma=0x%llx\n", (long long unsigned int)dev->dsr_info.dma);
dev->dsr_info.dsr = rdma_pci_dma_map(pci_dev, dev->dsr_info.dma,
sizeof(struct pvrdma_device_shared_region));
if (!dev->dsr_info.dsr) {
pr_err("Failed to map to DSR\n");
rdma_error_report("Failed to map to DSR");
rc = -ENOMEM;
goto out;
}
@ -169,21 +186,19 @@ static int load_dsr(PVRDMADev *dev)
dsr = dsr_info->dsr;
/* Map to command slot */
pr_dbg("cmd_dma=0x%llx\n", (long long unsigned int)dsr->cmd_slot_dma);
dsr_info->req = rdma_pci_dma_map(pci_dev, dsr->cmd_slot_dma,
sizeof(union pvrdma_cmd_req));
if (!dsr_info->req) {
pr_err("Failed to map to command slot address\n");
rdma_error_report("Failed to map to command slot address");
rc = -ENOMEM;
goto out_free_dsr;
}
/* Map to response slot */
pr_dbg("rsp_dma=0x%llx\n", (long long unsigned int)dsr->resp_slot_dma);
dsr_info->rsp = rdma_pci_dma_map(pci_dev, dsr->resp_slot_dma,
sizeof(union pvrdma_cmd_resp));
if (!dsr_info->rsp) {
pr_err("Failed to map to response slot address\n");
rdma_error_report("Failed to map to response slot address");
rc = -ENOMEM;
goto out_free_req;
}
@ -193,7 +208,6 @@ static int load_dsr(PVRDMADev *dev)
pci_dev, dsr->cq_ring_pages.pdir_dma,
dsr->cq_ring_pages.num_pages);
if (rc) {
pr_err("Failed to map to initialize CQ ring\n");
rc = -ENOMEM;
goto out_free_rsp;
}
@ -203,7 +217,6 @@ static int load_dsr(PVRDMADev *dev)
"dev_async", pci_dev, dsr->async_ring_pages.pdir_dma,
dsr->async_ring_pages.num_pages);
if (rc) {
pr_err("Failed to map to initialize event ring\n");
rc = -ENOMEM;
goto out_free_rsp;
}
@ -230,24 +243,15 @@ static void init_dsr_dev_caps(PVRDMADev *dev)
struct pvrdma_device_shared_region *dsr;
if (dev->dsr_info.dsr == NULL) {
pr_err("Can't initialized DSR\n");
rdma_error_report("Can't initialized DSR");
return;
}
dsr = dev->dsr_info.dsr;
dsr->caps.fw_ver = PVRDMA_FW_VERSION;
pr_dbg("fw_ver=0x%" PRIx64 "\n", dsr->caps.fw_ver);
dsr->caps.mode = PVRDMA_DEVICE_MODE_ROCE;
pr_dbg("mode=%d\n", dsr->caps.mode);
dsr->caps.gid_types |= PVRDMA_GID_TYPE_FLAG_ROCE_V1;
pr_dbg("gid_types=0x%x\n", dsr->caps.gid_types);
dsr->caps.max_uar = RDMA_BAR2_UAR_SIZE;
pr_dbg("max_uar=%d\n", dsr->caps.max_uar);
dsr->caps.max_mr_size = dev->dev_attr.max_mr_size;
dsr->caps.max_qp = dev->dev_attr.max_qp;
dsr->caps.max_qp_wr = dev->dev_attr.max_qp_wr;
@ -257,23 +261,11 @@ static void init_dsr_dev_caps(PVRDMADev *dev)
dsr->caps.max_mr = dev->dev_attr.max_mr;
dsr->caps.max_pd = dev->dev_attr.max_pd;
dsr->caps.max_ah = dev->dev_attr.max_ah;
dsr->caps.gid_tbl_len = MAX_GIDS;
pr_dbg("gid_tbl_len=%d\n", dsr->caps.gid_tbl_len);
dsr->caps.sys_image_guid = 0;
pr_dbg("sys_image_guid=%" PRIx64 "\n", dsr->caps.sys_image_guid);
dsr->caps.node_guid = dev->node_guid;
pr_dbg("node_guid=%" PRIx64 "\n", be64_to_cpu(dsr->caps.node_guid));
dsr->caps.phys_port_cnt = MAX_PORTS;
pr_dbg("phys_port_cnt=%d\n", dsr->caps.phys_port_cnt);
dsr->caps.max_pkeys = MAX_PKEYS;
pr_dbg("max_pkeys=%d\n", dsr->caps.max_pkeys);
pr_dbg("Initialized\n");
}
static void uninit_msix(PCIDevice *pdev, int used_vectors)
@ -288,7 +280,7 @@ static void uninit_msix(PCIDevice *pdev, int used_vectors)
msix_uninit(pdev, &dev->msix, &dev->msix);
}
static int init_msix(PCIDevice *pdev, Error **errp)
static int init_msix(PCIDevice *pdev)
{
PVRDMADev *dev = PVRDMA_DEV(pdev);
int i;
@ -299,14 +291,14 @@ static int init_msix(PCIDevice *pdev, Error **errp)
RDMA_MSIX_PBA, 0, NULL);
if (rc < 0) {
error_setg(errp, "Failed to initialize MSI-X");
rdma_error_report("Failed to initialize MSI-X");
return rc;
}
for (i = 0; i < RDMA_MAX_INTRS; i++) {
rc = msix_vector_use(PCI_DEVICE(dev), i);
if (rc < 0) {
error_setg(errp, "Fail mark MSI-X vector %d", i);
rdma_error_report("Fail mark MSI-X vector %d", i);
uninit_msix(pdev, i);
return rc;
}
@ -319,11 +311,12 @@ static void pvrdma_fini(PCIDevice *pdev)
{
PVRDMADev *dev = PVRDMA_DEV(pdev);
pr_dbg("Closing device %s %x.%x\n", pdev->name, PCI_SLOT(pdev->devfn),
PCI_FUNC(pdev->devfn));
notifier_remove(&dev->shutdown_notifier);
pvrdma_qp_ops_fini();
rdma_backend_stop(&dev->backend_dev);
rdma_rm_fini(&dev->rdma_dev_res, &dev->backend_dev,
dev->backend_eth_device_name);
@ -335,8 +328,8 @@ static void pvrdma_fini(PCIDevice *pdev)
uninit_msix(pdev, RDMA_MAX_INTRS);
}
pr_dbg("Device %s %x.%x is down\n", pdev->name, PCI_SLOT(pdev->devfn),
PCI_FUNC(pdev->devfn));
rdma_info_report("Device %s %x.%x is down", pdev->name,
PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
}
static void pvrdma_stop(PVRDMADev *dev)
@ -353,32 +346,28 @@ static void activate_device(PVRDMADev *dev)
{
pvrdma_start(dev);
set_reg_val(dev, PVRDMA_REG_ERR, 0);
pr_dbg("Device activated\n");
}
static int unquiesce_device(PVRDMADev *dev)
{
pr_dbg("Device unquiesced\n");
return 0;
}
static void reset_device(PVRDMADev *dev)
{
pvrdma_stop(dev);
pr_dbg("Device reset complete\n");
}
static uint64_t regs_read(void *opaque, hwaddr addr, unsigned size)
static uint64_t pvrdma_regs_read(void *opaque, hwaddr addr, unsigned size)
{
PVRDMADev *dev = opaque;
uint32_t val;
/* pr_dbg("addr=0x%lx, size=%d\n", addr, size); */
dev->stats.regs_reads++;
if (get_reg_val(dev, addr, &val)) {
pr_dbg("Error trying to read REG value from address 0x%x\n",
(uint32_t)addr);
rdma_error_report("Failed to read REG value from address 0x%x",
(uint32_t)addr);
return -EINVAL;
}
@ -387,25 +376,26 @@ static uint64_t regs_read(void *opaque, hwaddr addr, unsigned size)
return val;
}
static void regs_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
static void pvrdma_regs_write(void *opaque, hwaddr addr, uint64_t val,
unsigned size)
{
PVRDMADev *dev = opaque;
/* pr_dbg("addr=0x%lx, val=0x%x, size=%d\n", addr, (uint32_t)val, size); */
dev->stats.regs_writes++;
if (set_reg_val(dev, addr, val)) {
pr_err("Fail to set REG value, addr=0x%" PRIx64 ", val=0x%" PRIx64 "\n",
addr, val);
rdma_error_report("Failed to set REG value, addr=0x%"PRIx64 ", val=0x%"PRIx64,
addr, val);
return;
}
trace_pvrdma_regs_write(addr, val);
switch (addr) {
case PVRDMA_REG_DSRLOW:
trace_pvrdma_regs_write(addr, val, "DSRLOW", "");
dev->dsr_info.dma = val;
break;
case PVRDMA_REG_DSRHIGH:
trace_pvrdma_regs_write(addr, val, "DSRHIGH", "");
dev->dsr_info.dma |= val << 32;
load_dsr(dev);
init_dsr_dev_caps(dev);
@ -413,23 +403,27 @@ static void regs_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
case PVRDMA_REG_CTL:
switch (val) {
case PVRDMA_DEVICE_CTL_ACTIVATE:
trace_pvrdma_regs_write(addr, val, "CTL", "ACTIVATE");
activate_device(dev);
break;
case PVRDMA_DEVICE_CTL_UNQUIESCE:
trace_pvrdma_regs_write(addr, val, "CTL", "UNQUIESCE");
unquiesce_device(dev);
break;
case PVRDMA_DEVICE_CTL_RESET:
trace_pvrdma_regs_write(addr, val, "CTL", "URESET");
reset_device(dev);
break;
}
break;
case PVRDMA_REG_IMR:
pr_dbg("Interrupt mask=0x%" PRIx64 "\n", val);
trace_pvrdma_regs_write(addr, val, "INTR_MASK", "");
dev->interrupt_mask = val;
break;
case PVRDMA_REG_REQUEST:
if (val == 0) {
execute_command(dev);
trace_pvrdma_regs_write(addr, val, "REQUEST", "");
pvrdma_exec_cmd(dev);
}
break;
default:
@ -438,8 +432,8 @@ static void regs_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
}
static const MemoryRegionOps regs_ops = {
.read = regs_read,
.write = regs_write,
.read = pvrdma_regs_read,
.write = pvrdma_regs_write,
.endianness = DEVICE_LITTLE_ENDIAN,
.impl = {
.min_access_size = sizeof(uint32_t),
@ -447,54 +441,60 @@ static const MemoryRegionOps regs_ops = {
},
};
static uint64_t uar_read(void *opaque, hwaddr addr, unsigned size)
static uint64_t pvrdma_uar_read(void *opaque, hwaddr addr, unsigned size)
{
return 0xffffffff;
}
static void uar_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
static void pvrdma_uar_write(void *opaque, hwaddr addr, uint64_t val,
unsigned size)
{
PVRDMADev *dev = opaque;
/* pr_dbg("addr=0x%lx, val=0x%x, size=%d\n", addr, (uint32_t)val, size); */
dev->stats.uar_writes++;
switch (addr & 0xFFF) { /* Mask with 0xFFF as each UC gets page */
case PVRDMA_UAR_QP_OFFSET:
pr_dbg("UAR QP command, addr=0x%" PRIx64 ", val=0x%" PRIx64 "\n",
(uint64_t)addr, val);
if (val & PVRDMA_UAR_QP_SEND) {
trace_pvrdma_uar_write(addr, val, "QP", "SEND",
val & PVRDMA_UAR_HANDLE_MASK, 0);
pvrdma_qp_send(dev, val & PVRDMA_UAR_HANDLE_MASK);
}
if (val & PVRDMA_UAR_QP_RECV) {
trace_pvrdma_uar_write(addr, val, "QP", "RECV",
val & PVRDMA_UAR_HANDLE_MASK, 0);
pvrdma_qp_recv(dev, val & PVRDMA_UAR_HANDLE_MASK);
}
break;
case PVRDMA_UAR_CQ_OFFSET:
/* pr_dbg("UAR CQ cmd, addr=0x%x, val=0x%lx\n", (uint32_t)addr, val); */
if (val & PVRDMA_UAR_CQ_ARM) {
trace_pvrdma_uar_write(addr, val, "CQ", "ARM",
val & PVRDMA_UAR_HANDLE_MASK,
!!(val & PVRDMA_UAR_CQ_ARM_SOL));
rdma_rm_req_notify_cq(&dev->rdma_dev_res,
val & PVRDMA_UAR_HANDLE_MASK,
!!(val & PVRDMA_UAR_CQ_ARM_SOL));
}
if (val & PVRDMA_UAR_CQ_ARM_SOL) {
pr_dbg("UAR_CQ_ARM_SOL (%" PRIx64 ")\n",
val & PVRDMA_UAR_HANDLE_MASK);
trace_pvrdma_uar_write(addr, val, "CQ", "ARMSOL - not supported", 0,
0);
}
if (val & PVRDMA_UAR_CQ_POLL) {
pr_dbg("UAR_CQ_POLL (%" PRIx64 ")\n", val & PVRDMA_UAR_HANDLE_MASK);
trace_pvrdma_uar_write(addr, val, "CQ", "POLL",
val & PVRDMA_UAR_HANDLE_MASK, 0);
pvrdma_cq_poll(&dev->rdma_dev_res, val & PVRDMA_UAR_HANDLE_MASK);
}
break;
default:
pr_err("Unsupported command, addr=0x%" PRIx64 ", val=0x%" PRIx64 "\n",
addr, val);
rdma_error_report("Unsupported command, addr=0x%"PRIx64", val=0x%"PRIx64,
addr, val);
break;
}
}
static const MemoryRegionOps uar_ops = {
.read = uar_read,
.write = uar_write,
.read = pvrdma_uar_read,
.write = pvrdma_uar_write,
.endianness = DEVICE_LITTLE_ENDIAN,
.impl = {
.min_access_size = sizeof(uint32_t),
@ -551,11 +551,9 @@ static void init_dev_caps(PVRDMADev *dev)
(wr_sz + sizeof(struct pvrdma_sge) *
dev->dev_attr.max_sge) - TARGET_PAGE_SIZE;
/* First page is ring state ^^^^ */
pr_dbg("max_qp_wr=%d\n", dev->dev_attr.max_qp_wr);
dev->dev_attr.max_cqe = pg_tbl_bytes / sizeof(struct pvrdma_cqe) -
TARGET_PAGE_SIZE; /* First page is ring state */
pr_dbg("max_cqe=%d\n", dev->dev_attr.max_cqe);
}
static int pvrdma_check_ram_shared(Object *obj, void *opaque)
@ -585,10 +583,8 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp)
bool ram_shared = false;
PCIDevice *func0;
init_pr_dbg();
pr_dbg("Initializing device %s %x.%x\n", pdev->name,
PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
rdma_info_report("Initializing device %s %x.%x", pdev->name,
PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
if (TARGET_PAGE_SIZE != getpagesize()) {
error_setg(errp, "Target page size must be the same as host page size");
@ -597,9 +593,7 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp)
func0 = pci_get_function_0(pdev);
/* Break if not vmxnet3 device in slot 0 */
if (strcmp(object_get_typename(&func0->qdev.parent_obj), TYPE_VMXNET3)) {
pr_dbg("func0 type is %s\n",
object_get_typename(&func0->qdev.parent_obj));
if (strcmp(object_get_typename(OBJECT(func0)), TYPE_VMXNET3)) {
error_setg(errp, "Device on %x.0 must be %s", PCI_SLOT(pdev->devfn),
TYPE_VMXNET3);
return;
@ -626,21 +620,21 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp)
init_regs(pdev);
rc = init_msix(pdev, errp);
rc = init_msix(pdev);
if (rc) {
goto out;
}
rc = rdma_backend_init(&dev->backend_dev, pdev, &dev->rdma_dev_res,
dev->backend_device_name, dev->backend_port_num,
&dev->dev_attr, &dev->mad_chr, errp);
&dev->dev_attr, &dev->mad_chr);
if (rc) {
goto out;
}
init_dev_caps(dev);
rc = rdma_rm_init(&dev->rdma_dev_res, &dev->dev_attr, errp);
rc = rdma_rm_init(&dev->rdma_dev_res, &dev->dev_attr);
if (rc) {
goto out;
}
@ -650,28 +644,25 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp)
goto out;
}
memset(&dev->stats, 0, sizeof(dev->stats));
dev->shutdown_notifier.notify = pvrdma_shutdown_notifier;
qemu_register_shutdown_notifier(&dev->shutdown_notifier);
out:
if (rc) {
pvrdma_fini(pdev);
error_append_hint(errp, "Device fail to load\n");
error_append_hint(errp, "Device failed to load\n");
}
}
static void pvrdma_exit(PCIDevice *pdev)
{
pvrdma_fini(pdev);
}
static void pvrdma_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
RdmaProviderClass *ir = INTERFACE_RDMA_PROVIDER_CLASS(klass);
k->realize = pvrdma_realize;
k->exit = pvrdma_exit;
k->vendor_id = PCI_VENDOR_ID_VMWARE;
k->device_id = PCI_DEVICE_ID_VMWARE_PVRDMA;
k->revision = 0x00;
@ -680,6 +671,8 @@ static void pvrdma_class_init(ObjectClass *klass, void *data)
dc->desc = "RDMA Device";
dc->props = pvrdma_dev_properties;
set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
ir->print_statistics = pvrdma_print_statistics;
}
static const TypeInfo pvrdma_info = {
@ -689,6 +682,7 @@ static const TypeInfo pvrdma_info = {
.class_init = pvrdma_class_init,
.interfaces = (InterfaceInfo[]) {
{ INTERFACE_CONVENTIONAL_PCI_DEVICE },
{ INTERFACE_RDMA_PROVIDER },
{ }
}
};

54
hw/rdma/vmw/pvrdma_qp_ops.c
View File

@ -19,6 +19,8 @@
#include "../rdma_rm.h"
#include "../rdma_backend.h"
#include "trace.h"
#include "pvrdma.h"
#include "standard-headers/rdma/vmw_pvrdma-abi.h"
#include "pvrdma_qp_ops.h"
@ -55,18 +57,14 @@ static int pvrdma_post_cqe(PVRDMADev *dev, uint32_t cq_handle,
RdmaRmCQ *cq = rdma_rm_get_cq(&dev->rdma_dev_res, cq_handle);
if (unlikely(!cq)) {
pr_dbg("Invalid cqn %d\n", cq_handle);
return -EINVAL;
}
ring = (PvrdmaRing *)cq->opaque;
pr_dbg("ring=%p\n", ring);
/* Step #1: Put CQE on CQ ring */
pr_dbg("Writing CQE\n");
cqe1 = pvrdma_ring_next_elem_write(ring);
if (unlikely(!cqe1)) {
pr_dbg("No CQEs in ring\n");
return -EINVAL;
}
@ -80,19 +78,13 @@ static int pvrdma_post_cqe(PVRDMADev *dev, uint32_t cq_handle,
cqe1->wc_flags = wc->wc_flags;
cqe1->vendor_err = wc->vendor_err;
pr_dbg("wr_id=%" PRIx64 "\n", cqe1->wr_id);
pr_dbg("qp=0x%lx\n", cqe1->qp);
pr_dbg("opcode=%d\n", cqe1->opcode);
pr_dbg("status=%d\n", cqe1->status);
pr_dbg("byte_len=%d\n", cqe1->byte_len);
pr_dbg("src_qp=%d\n", cqe1->src_qp);
pr_dbg("wc_flags=%d\n", cqe1->wc_flags);
pr_dbg("vendor_err=%d\n", cqe1->vendor_err);
trace_pvrdma_post_cqe(cq_handle, cq->notify, cqe1->wr_id, cqe1->qp,
cqe1->opcode, cqe1->status, cqe1->byte_len,
cqe1->src_qp, cqe1->wc_flags, cqe1->vendor_err);
pvrdma_ring_write_inc(ring);
/* Step #2: Put CQ number on dsr completion ring */
pr_dbg("Writing CQNE\n");
cqne = pvrdma_ring_next_elem_write(&dev->dsr_info.cq);
if (unlikely(!cqne)) {
return -EINVAL;
@ -101,7 +93,6 @@ static int pvrdma_post_cqe(PVRDMADev *dev, uint32_t cq_handle,
cqne->info = cq_handle;
pvrdma_ring_write_inc(&dev->dsr_info.cq);
pr_dbg("cq->notify=%d\n", cq->notify);
if (cq->notify != CNT_CLEAR) {
if (cq->notify == CNT_ARM) {
cq->notify = CNT_CLEAR;
@ -123,7 +114,7 @@ static void pvrdma_qp_ops_comp_handler(void *ctx, struct ibv_wc *wc)
static void complete_with_error(uint32_t vendor_err, void *ctx)
{
struct ibv_wc wc = {0};
struct ibv_wc wc = {};
wc.status = IBV_WC_GENERAL_ERR;
wc.vendor_err = vendor_err;
@ -151,23 +142,17 @@ void pvrdma_qp_send(PVRDMADev *dev, uint32_t qp_handle)
int sgid_idx;
union ibv_gid *sgid;
pr_dbg("qp_handle=0x%x\n", qp_handle);
qp = rdma_rm_get_qp(&dev->rdma_dev_res, qp_handle);
if (unlikely(!qp)) {
pr_dbg("Invalid qpn\n");
return;
}
ring = (PvrdmaRing *)qp->opaque;
pr_dbg("sring=%p\n", ring);
wqe = (struct PvrdmaSqWqe *)pvrdma_ring_next_elem_read(ring);
while (wqe) {
CompHandlerCtx *comp_ctx;
pr_dbg("wr_id=%" PRIx64 "\n", wqe->hdr.wr_id);
/* Prepare CQE */
comp_ctx = g_malloc(sizeof(CompHandlerCtx));
comp_ctx->dev = dev;
@ -178,26 +163,25 @@ void pvrdma_qp_send(PVRDMADev *dev, uint32_t qp_handle)
sgid = rdma_rm_get_gid(&dev->rdma_dev_res, wqe->hdr.wr.ud.av.gid_index);
if (!sgid) {
pr_dbg("Fail to get gid for idx %d\n", wqe->hdr.wr.ud.av.gid_index);
rdma_error_report("Failed to get gid for idx %d",
wqe->hdr.wr.ud.av.gid_index);
complete_with_error(VENDOR_ERR_INV_GID_IDX, comp_ctx);
continue;
}
pr_dbg("sgid_id=%d, sgid=0x%llx\n", wqe->hdr.wr.ud.av.gid_index,
sgid->global.interface_id);
sgid_idx = rdma_rm_get_backend_gid_index(&dev->rdma_dev_res,
&dev->backend_dev,
wqe->hdr.wr.ud.av.gid_index);
if (sgid_idx <= 0) {
pr_dbg("Fail to get bk sgid_idx for sgid_idx %d\n",
wqe->hdr.wr.ud.av.gid_index);
rdma_error_report("Failed to get bk sgid_idx for sgid_idx %d",
wqe->hdr.wr.ud.av.gid_index);
complete_with_error(VENDOR_ERR_INV_GID_IDX, comp_ctx);
continue;
}
if (wqe->hdr.num_sge > dev->dev_attr.max_sge) {
pr_dbg("Invalid num_sge=%d (max %d)\n", wqe->hdr.num_sge,
dev->dev_attr.max_sge);
rdma_error_report("Invalid num_sge=%d (max %d)", wqe->hdr.num_sge,
dev->dev_attr.max_sge);
complete_with_error(VENDOR_ERR_INV_NUM_SGE, comp_ctx);
continue;
}
@ -221,23 +205,17 @@ void pvrdma_qp_recv(PVRDMADev *dev, uint32_t qp_handle)
PvrdmaRqWqe *wqe;
PvrdmaRing *ring;
pr_dbg("qp_handle=0x%x\n", qp_handle);
qp = rdma_rm_get_qp(&dev->rdma_dev_res, qp_handle);
if (unlikely(!qp)) {
pr_dbg("Invalid qpn\n");
return;
}
ring = &((PvrdmaRing *)qp->opaque)[1];
pr_dbg("rring=%p\n", ring);
wqe = (struct PvrdmaRqWqe *)pvrdma_ring_next_elem_read(ring);
while (wqe) {
CompHandlerCtx *comp_ctx;
pr_dbg("wr_id=%" PRIx64 "\n", wqe->hdr.wr_id);
/* Prepare CQE */
comp_ctx = g_malloc(sizeof(CompHandlerCtx));
comp_ctx->dev = dev;
@ -247,14 +225,13 @@ void pvrdma_qp_recv(PVRDMADev *dev, uint32_t qp_handle)
comp_ctx->cqe.opcode = IBV_WC_RECV;
if (wqe->hdr.num_sge > dev->dev_attr.max_sge) {
pr_dbg("Invalid num_sge=%d (max %d)\n", wqe->hdr.num_sge,
dev->dev_attr.max_sge);
rdma_error_report("Invalid num_sge=%d (max %d)", wqe->hdr.num_sge,
dev->dev_attr.max_sge);
complete_with_error(VENDOR_ERR_INV_NUM_SGE, comp_ctx);
continue;
}
rdma_backend_post_recv(&dev->backend_dev, &dev->rdma_dev_res,
&qp->backend_qp, qp->qp_type,
rdma_backend_post_recv(&dev->backend_dev, &qp->backend_qp, qp->qp_type,
(struct ibv_sge *)&wqe->sge[0], wqe->hdr.num_sge,
comp_ctx);
@ -270,7 +247,6 @@ void pvrdma_cq_poll(RdmaDeviceResources *dev_res, uint32_t cq_handle)
cq = rdma_rm_get_cq(dev_res, cq_handle);
if (!cq) {
pr_dbg("Invalid CQ# %d\n", cq_handle);
return;
}

18
hw/rdma/vmw/trace-events
View File

@ -1,5 +1,17 @@
# See docs/tracing.txt for syntax documentation.
# See docs/devel/tracing.txt for syntax documentation.
# hw/rdma/vmw/pvrdma_main.c
pvrdma_regs_read(uint64_t addr, uint64_t val) "regs[0x%"PRIx64"] = 0x%"PRIx64
pvrdma_regs_write(uint64_t addr, uint64_t val) "regs[0x%"PRIx64"] = 0x%"PRIx64
pvrdma_regs_read(uint64_t addr, uint64_t val) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64
pvrdma_regs_write(uint64_t addr, uint64_t val, const char *reg_name, const char *val_name) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64" (%s %s)"
pvrdma_uar_write(uint64_t addr, uint64_t val, const char *reg_name, const char *val_name, int val1, int val2) "uar[0x%"PRIx64"]=0x%"PRIx64" (cls=%s, op=%s, obj=%d, val=%d)"
# hw/rdma/vmw/pvrdma_cmd.c
pvrdma_map_to_pdir_host_virt(void *vfirst, void *vremaped) "mremap %p -> %p"
pvrdma_map_to_pdir_next_page(int page_idx, void *vnext, void *vremaped) "mremap [%d] %p -> %p"
pvrdma_exec_cmd(int cmd, int err) "cmd=%d, err=%d"
# hw/rdma/vmw/pvrdma_dev_ring.c
pvrdma_ring_next_elem_read_no_data(char *ring_name) "pvrdma_ring %s is empty"
# hw/rdma/vmw/pvrdma_qp_ops.c
pvrdma_post_cqe(uint32_t cq_handle, int notify, uint64_t wr_id, uint64_t qpn, uint32_t op_code, uint32_t status, uint32_t byte_len, uint32_t src_qp, uint32_t wc_flags, uint32_t vendor_err) "cq_handle=%d, notify=%d, wr_id=0x%"PRIx64", qpn=0x%"PRIx64", opcode=%d, status=%d, byte_len=%d, src_qp=%d, wc_flags=%d, vendor_err=%d"

40
include/hw/rdma/rdma.h Normal file
View File

@ -0,0 +1,40 @@
/*
* RDMA device interface
*
* Copyright (C) 2019 Oracle
* Copyright (C) 2019 Red Hat Inc
*
* Authors:
* Yuval Shaia <yuval.shaia@oracle.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#ifndef RDMA_H
#define RDMA_H
#include "qom/object.h"
#define INTERFACE_RDMA_PROVIDER "rdma"
#define INTERFACE_RDMA_PROVIDER_CLASS(klass) \
OBJECT_CLASS_CHECK(RdmaProviderClass, (klass), \
INTERFACE_RDMA_PROVIDER)
#define RDMA_PROVIDER_GET_CLASS(obj) \
OBJECT_GET_CLASS(RdmaProviderClass, (obj), \
INTERFACE_RDMA_PROVIDER)
#define RDMA_PROVIDER(obj) \
INTERFACE_CHECK(RdmaProvider, (obj), \
INTERFACE_RDMA_PROVIDER)
typedef struct RdmaProvider RdmaProvider;
typedef struct RdmaProviderClass {
InterfaceClass parent;
void (*print_statistics)(Monitor *mon, RdmaProvider *obj);
} RdmaProviderClass;
#endif