Message ID | 20241009234610.27039-4-yichen.wang@bytedance.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | Use Intel DSA accelerator to offload zero page checking in multifd live migration. | expand |
On Wed, Oct 09, 2024 at 04:46:01PM -0700, Yichen Wang wrote: > diff --git a/util/meson.build b/util/meson.build > index 5d8bef9891..3360f62923 100644 > --- a/util/meson.build > +++ b/util/meson.build > @@ -88,6 +88,9 @@ if have_block or have_ga > endif > if have_block > util_ss.add(files('aio-wait.c')) > + if config_host_data.get('CONFIG_DSA_OPT') > + util_ss.add(files('dsa.c')) > + endif It's not clear to me why this needs to be under have_block. Since we want to make sure this file is ignored on !x86, maybe it should be put under the "elif cpu in ['x86', 'x86_64']" section. > util_ss.add(files('buffer.c')) > util_ss.add(files('bufferiszero.c')) > util_ss.add(files('hbitmap.c')) > -- > Yichen Wang >
Yichen Wang <yichen.wang@bytedance.com> writes: > From: Hao Xiang <hao.xiang@linux.dev> > > * DSA device open and close. > * DSA group contains multiple DSA devices. > * DSA group configure/start/stop/clean. > > Signed-off-by: Hao Xiang <hao.xiang@linux.dev> > Signed-off-by: Bryan Zhang <bryan.zhang@bytedance.com> > Signed-off-by: Yichen Wang <yichen.wang@bytedance.com> > --- > include/qemu/dsa.h | 103 +++++++++++++++++ > util/dsa.c | 282 +++++++++++++++++++++++++++++++++++++++++++++ > util/meson.build | 3 + > 3 files changed, 388 insertions(+) > create mode 100644 include/qemu/dsa.h > create mode 100644 util/dsa.c > > diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h > new file mode 100644 > index 0000000000..501bb8c70d > --- /dev/null > +++ b/include/qemu/dsa.h > @@ -0,0 +1,103 @@ > +/* > + * Interface for using Intel Data Streaming Accelerator to offload certain > + * background operations. > + * > + * Copyright (C) Bytedance Ltd. > + * > + * Authors: > + * Hao Xiang <hao.xiang@bytedance.com> > + * Yichen Wang <yichen.wang@bytedance.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 QEMU_DSA_H > +#define QEMU_DSA_H > + > +#include "qemu/error-report.h" > +#include "qemu/thread.h" > +#include "qemu/queue.h" > + > +#ifdef CONFIG_DSA_OPT > + > +#pragma GCC push_options > +#pragma GCC target("enqcmd") > + > +#include <linux/idxd.h> > +#include "x86intrin.h" > + > +typedef struct { > + void *work_queue; > +} QemuDsaDevice; > + > +typedef QSIMPLEQ_HEAD(QemuDsaTaskQueue, QemuDsaBatchTask) QemuDsaTaskQueue; > + > +typedef struct { > + QemuDsaDevice *dsa_devices; > + int num_dsa_devices; > + /* The index of the next DSA device to be used. */ > + uint32_t device_allocator_index; > + bool running; > + QemuMutex task_queue_lock; > + QemuCond task_queue_cond; > + QemuDsaTaskQueue task_queue; > +} QemuDsaDeviceGroup; > + > +/** > + * @brief Initializes DSA devices. > + * > + * @param dsa_parameter A list of DSA device path from migration parameter. > + * > + * @return int Zero if successful, otherwise non zero. > + */ > +int qemu_dsa_init(const strList *dsa_parameter, Error **errp); > + > +/** > + * @brief Start logic to enable using DSA. > + */ > +void qemu_dsa_start(void); > + > +/** > + * @brief Stop the device group and the completion thread. > + */ > +void qemu_dsa_stop(void); > + > +/** > + * @brief Clean up system resources created for DSA offloading. > + */ > +void qemu_dsa_cleanup(void); > + > +/** > + * @brief Check if DSA is running. > + * > + * @return True if DSA is running, otherwise false. > + */ > +bool qemu_dsa_is_running(void); > + > +#else > + > +static inline bool qemu_dsa_is_running(void) > +{ > + return false; > +} > + > +static inline int qemu_dsa_init(const strList *dsa_parameter, Error **errp) > +{ > + if (dsa_parameter != NULL && strlen(dsa_parameter) != 0) { > + error_setg(errp, "DSA is not supported."); > + return -1; > + } > + > + return 0; > +} > + > +static inline void qemu_dsa_start(void) {} > + > +static inline void qemu_dsa_stop(void) {} > + > +static inline void qemu_dsa_cleanup(void) {} > + > +#endif > + > +#endif > diff --git a/util/dsa.c b/util/dsa.c > new file mode 100644 > index 0000000000..54d0e20c29 > --- /dev/null > +++ b/util/dsa.c > @@ -0,0 +1,282 @@ > +/* > + * Use Intel Data Streaming Accelerator to offload certain background > + * operations. > + * > + * Copyright (C) Bytedance Ltd. > + * > + * Authors: > + * Hao Xiang <hao.xiang@bytedance.com> > + * Bryan Zhang <bryan.zhang@bytedance.com> > + * Yichen Wang <yichen.wang@bytedance.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 "qapi/error.h" > +#include "qemu/queue.h" > +#include "qemu/memalign.h" > +#include "qemu/lockable.h" > +#include "qemu/cutils.h" > +#include "qemu/dsa.h" > +#include "qemu/bswap.h" > +#include "qemu/error-report.h" > +#include "qemu/rcu.h" > + > +#pragma GCC push_options > +#pragma GCC target("enqcmd") > + > +#include <linux/idxd.h> > +#include "x86intrin.h" > + > +#define DSA_WQ_PORTAL_SIZE 4096 > +#define MAX_DSA_DEVICES 16 > + > +uint32_t max_retry_count; > +static QemuDsaDeviceGroup dsa_group; > + > + > +/** > + * @brief This function opens a DSA device's work queue and > + * maps the DSA device memory into the current process. > + * > + * @param dsa_wq_path A pointer to the DSA device work queue's file path. > + * @return A pointer to the mapped memory, or MAP_FAILED on failure. > + */ > +static void * > +map_dsa_device(const char *dsa_wq_path) > +{ > + void *dsa_device; > + int fd; > + > + fd = open(dsa_wq_path, O_RDWR); > + if (fd < 0) { > + error_report("Open %s failed with errno = %d.", > + dsa_wq_path, errno); > + return MAP_FAILED; > + } > + dsa_device = mmap(NULL, DSA_WQ_PORTAL_SIZE, PROT_WRITE, > + MAP_SHARED | MAP_POPULATE, fd, 0); > + close(fd); > + if (dsa_device == MAP_FAILED) { > + error_report("mmap failed with errno = %d.", errno); > + return MAP_FAILED; > + } > + return dsa_device; > +} > + > +/** > + * @brief Initializes a DSA device structure. > + * > + * @param instance A pointer to the DSA device. > + * @param work_queue A pointer to the DSA work queue. > + */ > +static void > +dsa_device_init(QemuDsaDevice *instance, > + void *dsa_work_queue) > +{ > + instance->work_queue = dsa_work_queue; > +} > + > +/** > + * @brief Cleans up a DSA device structure. > + * > + * @param instance A pointer to the DSA device to cleanup. > + */ > +static void > +dsa_device_cleanup(QemuDsaDevice *instance) > +{ > + if (instance->work_queue != MAP_FAILED) { > + munmap(instance->work_queue, DSA_WQ_PORTAL_SIZE); > + } > +} > + > +/** > + * @brief Initializes a DSA device group. > + * > + * @param group A pointer to the DSA device group. > + * @param dsa_parameter A list of DSA device path from are separated by space > + * character migration parameter. Multiple DSA device path. > + * > + * @return Zero if successful, non-zero otherwise. > + */ > +static int > +dsa_device_group_init(QemuDsaDeviceGroup *group, > + const strList *dsa_parameter, > + Error **errp) > +{ > + if (dsa_parameter == NULL) { > + error_setg(errp, "dsa device path is not supplied."); > + return -1; > + } > + > + int ret = 0; > + const char *dsa_path[MAX_DSA_DEVICES]; > + int num_dsa_devices = 0; > + > + while (dsa_parameter) { > + dsa_path[num_dsa_devices++] = dsa_parameter->value; > + if (num_dsa_devices == MAX_DSA_DEVICES) { > + break; > + } > + dsa_parameter = dsa_parameter->next; > + } > + > + group->dsa_devices = > + g_new0(QemuDsaDevice, num_dsa_devices); > + group->num_dsa_devices = num_dsa_devices; > + group->device_allocator_index = 0; > + > + group->running = false; > + qemu_mutex_init(&group->task_queue_lock); > + qemu_cond_init(&group->task_queue_cond); > + QSIMPLEQ_INIT(&group->task_queue); > + > + void *dsa_wq = MAP_FAILED; > + for (int i = 0; i < num_dsa_devices; i++) { > + dsa_wq = map_dsa_device(dsa_path[i]); > + if (dsa_wq == MAP_FAILED) { > + error_setg(errp, "map_dsa_device failed MAP_FAILED."); > + ret = -1; > + goto exit; This will leave subsequent dsa_devices uninitialized after map_dsa_device fails for the i-th device, but the loop at dsa_device_group_cleanup() still passes all of them into dsa_device_cleanup(), so the check != MAP_FAILED there will be true. > + } > + dsa_device_init(&dsa_group.dsa_devices[i], dsa_wq); I think you mean &group->dsa_devices[i] here. > + } > + > +exit: > + return ret; > +} > + > +/** > + * @brief Starts a DSA device group. > + * > + * @param group A pointer to the DSA device group. > + */ > +static void > +dsa_device_group_start(QemuDsaDeviceGroup *group) > +{ > + group->running = true; > +} > + > +/** > + * @brief Stops a DSA device group. > + * > + * @param group A pointer to the DSA device group. > + */ > +__attribute__((unused)) > +static void > +dsa_device_group_stop(QemuDsaDeviceGroup *group) > +{ > + group->running = false; > +} > + > +/** > + * @brief Cleans up a DSA device group. > + * > + * @param group A pointer to the DSA device group. > + */ > +static void > +dsa_device_group_cleanup(QemuDsaDeviceGroup *group) > +{ > + if (!group->dsa_devices) { > + return; > + } > + for (int i = 0; i < group->num_dsa_devices; i++) { > + dsa_device_cleanup(&group->dsa_devices[i]); > + } > + g_free(group->dsa_devices); > + group->dsa_devices = NULL; > + > + qemu_mutex_destroy(&group->task_queue_lock); > + qemu_cond_destroy(&group->task_queue_cond); > +} > + > +/** > + * @brief Returns the next available DSA device in the group. > + * > + * @param group A pointer to the DSA device group. > + * > + * @return struct QemuDsaDevice* A pointer to the next available DSA device > + * in the group. > + */ > +__attribute__((unused)) > +static QemuDsaDevice * > +dsa_device_group_get_next_device(QemuDsaDeviceGroup *group) > +{ > + if (group->num_dsa_devices == 0) { > + return NULL; > + } > + uint32_t current = qatomic_fetch_inc(&group->device_allocator_index); > + current %= group->num_dsa_devices; > + return &group->dsa_devices[current]; > +} > + > +/** > + * @brief Check if DSA is running. > + * > + * @return True if DSA is running, otherwise false. > + */ > +bool qemu_dsa_is_running(void) > +{ > + return false; > +} > + > +static void > +dsa_globals_init(void) > +{ > + max_retry_count = UINT32_MAX; > +} > + > +/** > + * @brief Initializes DSA devices. > + * > + * @param dsa_parameter A list of DSA device path from migration parameter. > + * > + * @return int Zero if successful, otherwise non zero. > + */ > +int qemu_dsa_init(const strList *dsa_parameter, Error **errp) > +{ > + dsa_globals_init(); > + > + return dsa_device_group_init(&dsa_group, dsa_parameter, errp); > +} > + > +/** > + * @brief Start logic to enable using DSA. > + * > + */ > +void qemu_dsa_start(void) > +{ > + if (dsa_group.num_dsa_devices == 0) { > + return; > + } > + if (dsa_group.running) { > + return; > + } > + dsa_device_group_start(&dsa_group); > +} > + > +/** > + * @brief Stop the device group and the completion thread. > + * > + */ > +void qemu_dsa_stop(void) > +{ > + QemuDsaDeviceGroup *group = &dsa_group; > + > + if (!group->running) { > + return; > + } > +} > + > +/** > + * @brief Clean up system resources created for DSA offloading. > + * > + */ > +void qemu_dsa_cleanup(void) > +{ > + qemu_dsa_stop(); > + dsa_device_group_cleanup(&dsa_group); > +} > + > diff --git a/util/meson.build b/util/meson.build > index 5d8bef9891..3360f62923 100644 > --- a/util/meson.build > +++ b/util/meson.build > @@ -88,6 +88,9 @@ if have_block or have_ga > endif > if have_block > util_ss.add(files('aio-wait.c')) > + if config_host_data.get('CONFIG_DSA_OPT') > + util_ss.add(files('dsa.c')) > + endif > util_ss.add(files('buffer.c')) > util_ss.add(files('bufferiszero.c')) > util_ss.add(files('hbitmap.c'))
diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h new file mode 100644 index 0000000000..501bb8c70d --- /dev/null +++ b/include/qemu/dsa.h @@ -0,0 +1,103 @@ +/* + * Interface for using Intel Data Streaming Accelerator to offload certain + * background operations. + * + * Copyright (C) Bytedance Ltd. + * + * Authors: + * Hao Xiang <hao.xiang@bytedance.com> + * Yichen Wang <yichen.wang@bytedance.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 QEMU_DSA_H +#define QEMU_DSA_H + +#include "qemu/error-report.h" +#include "qemu/thread.h" +#include "qemu/queue.h" + +#ifdef CONFIG_DSA_OPT + +#pragma GCC push_options +#pragma GCC target("enqcmd") + +#include <linux/idxd.h> +#include "x86intrin.h" + +typedef struct { + void *work_queue; +} QemuDsaDevice; + +typedef QSIMPLEQ_HEAD(QemuDsaTaskQueue, QemuDsaBatchTask) QemuDsaTaskQueue; + +typedef struct { + QemuDsaDevice *dsa_devices; + int num_dsa_devices; + /* The index of the next DSA device to be used. */ + uint32_t device_allocator_index; + bool running; + QemuMutex task_queue_lock; + QemuCond task_queue_cond; + QemuDsaTaskQueue task_queue; +} QemuDsaDeviceGroup; + +/** + * @brief Initializes DSA devices. + * + * @param dsa_parameter A list of DSA device path from migration parameter. + * + * @return int Zero if successful, otherwise non zero. + */ +int qemu_dsa_init(const strList *dsa_parameter, Error **errp); + +/** + * @brief Start logic to enable using DSA. + */ +void qemu_dsa_start(void); + +/** + * @brief Stop the device group and the completion thread. + */ +void qemu_dsa_stop(void); + +/** + * @brief Clean up system resources created for DSA offloading. + */ +void qemu_dsa_cleanup(void); + +/** + * @brief Check if DSA is running. + * + * @return True if DSA is running, otherwise false. + */ +bool qemu_dsa_is_running(void); + +#else + +static inline bool qemu_dsa_is_running(void) +{ + return false; +} + +static inline int qemu_dsa_init(const strList *dsa_parameter, Error **errp) +{ + if (dsa_parameter != NULL && strlen(dsa_parameter) != 0) { + error_setg(errp, "DSA is not supported."); + return -1; + } + + return 0; +} + +static inline void qemu_dsa_start(void) {} + +static inline void qemu_dsa_stop(void) {} + +static inline void qemu_dsa_cleanup(void) {} + +#endif + +#endif diff --git a/util/dsa.c b/util/dsa.c new file mode 100644 index 0000000000..54d0e20c29 --- /dev/null +++ b/util/dsa.c @@ -0,0 +1,282 @@ +/* + * Use Intel Data Streaming Accelerator to offload certain background + * operations. + * + * Copyright (C) Bytedance Ltd. + * + * Authors: + * Hao Xiang <hao.xiang@bytedance.com> + * Bryan Zhang <bryan.zhang@bytedance.com> + * Yichen Wang <yichen.wang@bytedance.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 "qapi/error.h" +#include "qemu/queue.h" +#include "qemu/memalign.h" +#include "qemu/lockable.h" +#include "qemu/cutils.h" +#include "qemu/dsa.h" +#include "qemu/bswap.h" +#include "qemu/error-report.h" +#include "qemu/rcu.h" + +#pragma GCC push_options +#pragma GCC target("enqcmd") + +#include <linux/idxd.h> +#include "x86intrin.h" + +#define DSA_WQ_PORTAL_SIZE 4096 +#define MAX_DSA_DEVICES 16 + +uint32_t max_retry_count; +static QemuDsaDeviceGroup dsa_group; + + +/** + * @brief This function opens a DSA device's work queue and + * maps the DSA device memory into the current process. + * + * @param dsa_wq_path A pointer to the DSA device work queue's file path. + * @return A pointer to the mapped memory, or MAP_FAILED on failure. + */ +static void * +map_dsa_device(const char *dsa_wq_path) +{ + void *dsa_device; + int fd; + + fd = open(dsa_wq_path, O_RDWR); + if (fd < 0) { + error_report("Open %s failed with errno = %d.", + dsa_wq_path, errno); + return MAP_FAILED; + } + dsa_device = mmap(NULL, DSA_WQ_PORTAL_SIZE, PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + close(fd); + if (dsa_device == MAP_FAILED) { + error_report("mmap failed with errno = %d.", errno); + return MAP_FAILED; + } + return dsa_device; +} + +/** + * @brief Initializes a DSA device structure. + * + * @param instance A pointer to the DSA device. + * @param work_queue A pointer to the DSA work queue. + */ +static void +dsa_device_init(QemuDsaDevice *instance, + void *dsa_work_queue) +{ + instance->work_queue = dsa_work_queue; +} + +/** + * @brief Cleans up a DSA device structure. + * + * @param instance A pointer to the DSA device to cleanup. + */ +static void +dsa_device_cleanup(QemuDsaDevice *instance) +{ + if (instance->work_queue != MAP_FAILED) { + munmap(instance->work_queue, DSA_WQ_PORTAL_SIZE); + } +} + +/** + * @brief Initializes a DSA device group. + * + * @param group A pointer to the DSA device group. + * @param dsa_parameter A list of DSA device path from are separated by space + * character migration parameter. Multiple DSA device path. + * + * @return Zero if successful, non-zero otherwise. + */ +static int +dsa_device_group_init(QemuDsaDeviceGroup *group, + const strList *dsa_parameter, + Error **errp) +{ + if (dsa_parameter == NULL) { + error_setg(errp, "dsa device path is not supplied."); + return -1; + } + + int ret = 0; + const char *dsa_path[MAX_DSA_DEVICES]; + int num_dsa_devices = 0; + + while (dsa_parameter) { + dsa_path[num_dsa_devices++] = dsa_parameter->value; + if (num_dsa_devices == MAX_DSA_DEVICES) { + break; + } + dsa_parameter = dsa_parameter->next; + } + + group->dsa_devices = + g_new0(QemuDsaDevice, num_dsa_devices); + group->num_dsa_devices = num_dsa_devices; + group->device_allocator_index = 0; + + group->running = false; + qemu_mutex_init(&group->task_queue_lock); + qemu_cond_init(&group->task_queue_cond); + QSIMPLEQ_INIT(&group->task_queue); + + void *dsa_wq = MAP_FAILED; + for (int i = 0; i < num_dsa_devices; i++) { + dsa_wq = map_dsa_device(dsa_path[i]); + if (dsa_wq == MAP_FAILED) { + error_setg(errp, "map_dsa_device failed MAP_FAILED."); + ret = -1; + goto exit; + } + dsa_device_init(&dsa_group.dsa_devices[i], dsa_wq); + } + +exit: + return ret; +} + +/** + * @brief Starts a DSA device group. + * + * @param group A pointer to the DSA device group. + */ +static void +dsa_device_group_start(QemuDsaDeviceGroup *group) +{ + group->running = true; +} + +/** + * @brief Stops a DSA device group. + * + * @param group A pointer to the DSA device group. + */ +__attribute__((unused)) +static void +dsa_device_group_stop(QemuDsaDeviceGroup *group) +{ + group->running = false; +} + +/** + * @brief Cleans up a DSA device group. + * + * @param group A pointer to the DSA device group. + */ +static void +dsa_device_group_cleanup(QemuDsaDeviceGroup *group) +{ + if (!group->dsa_devices) { + return; + } + for (int i = 0; i < group->num_dsa_devices; i++) { + dsa_device_cleanup(&group->dsa_devices[i]); + } + g_free(group->dsa_devices); + group->dsa_devices = NULL; + + qemu_mutex_destroy(&group->task_queue_lock); + qemu_cond_destroy(&group->task_queue_cond); +} + +/** + * @brief Returns the next available DSA device in the group. + * + * @param group A pointer to the DSA device group. + * + * @return struct QemuDsaDevice* A pointer to the next available DSA device + * in the group. + */ +__attribute__((unused)) +static QemuDsaDevice * +dsa_device_group_get_next_device(QemuDsaDeviceGroup *group) +{ + if (group->num_dsa_devices == 0) { + return NULL; + } + uint32_t current = qatomic_fetch_inc(&group->device_allocator_index); + current %= group->num_dsa_devices; + return &group->dsa_devices[current]; +} + +/** + * @brief Check if DSA is running. + * + * @return True if DSA is running, otherwise false. + */ +bool qemu_dsa_is_running(void) +{ + return false; +} + +static void +dsa_globals_init(void) +{ + max_retry_count = UINT32_MAX; +} + +/** + * @brief Initializes DSA devices. + * + * @param dsa_parameter A list of DSA device path from migration parameter. + * + * @return int Zero if successful, otherwise non zero. + */ +int qemu_dsa_init(const strList *dsa_parameter, Error **errp) +{ + dsa_globals_init(); + + return dsa_device_group_init(&dsa_group, dsa_parameter, errp); +} + +/** + * @brief Start logic to enable using DSA. + * + */ +void qemu_dsa_start(void) +{ + if (dsa_group.num_dsa_devices == 0) { + return; + } + if (dsa_group.running) { + return; + } + dsa_device_group_start(&dsa_group); +} + +/** + * @brief Stop the device group and the completion thread. + * + */ +void qemu_dsa_stop(void) +{ + QemuDsaDeviceGroup *group = &dsa_group; + + if (!group->running) { + return; + } +} + +/** + * @brief Clean up system resources created for DSA offloading. + * + */ +void qemu_dsa_cleanup(void) +{ + qemu_dsa_stop(); + dsa_device_group_cleanup(&dsa_group); +} + diff --git a/util/meson.build b/util/meson.build index 5d8bef9891..3360f62923 100644 --- a/util/meson.build +++ b/util/meson.build @@ -88,6 +88,9 @@ if have_block or have_ga endif if have_block util_ss.add(files('aio-wait.c')) + if config_host_data.get('CONFIG_DSA_OPT') + util_ss.add(files('dsa.c')) + endif util_ss.add(files('buffer.c')) util_ss.add(files('bufferiszero.c')) util_ss.add(files('hbitmap.c'))