eal/windows: implement basic memory management

Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode. Multi-process mode is not
implemented and is forcefully disabled at startup. Assign myself as a
maintainer for Windows file and memory management implementation.

Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
This commit is contained in:
Dmitry Kozlyuk 2020-06-15 03:43:54 +03:00 committed by Thomas Monjalon
parent c08bd191b1
commit 2a5d547a4a
18 changed files with 1768 additions and 4 deletions

View File

@ -337,6 +337,7 @@ F: doc/guides/windows_gsg/
Windows memory allocation
M: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
F: lib/librte_eal/windows/eal_hugepages.c
F: lib/librte_eal/windows/eal_mem*
Core Libraries

View File

@ -261,15 +261,21 @@ if is_freebsd
endif
if is_windows
# Minimum supported API is Windows 7.
add_project_arguments('-D_WIN32_WINNT=0x0601', language: 'c')
# VirtualAlloc2() is available since Windows 10 / Server 2016.
add_project_arguments('-D_WIN32_WINNT=0x0A00', language: 'c')
# Use MinGW-w64 stdio, because DPDK assumes ANSI-compliant formatting.
if cc.get_id() == 'gcc'
add_project_arguments('-D__USE_MINGW_ANSI_STDIO', language: 'c')
endif
add_project_link_arguments('-ladvapi32', language: 'c')
# Contrary to docs, VirtualAlloc2() is exported by mincore.lib
# in Windows SDK, while MinGW exports it by advapi32.a.
if is_ms_linker
add_project_link_arguments('-lmincore', language: 'c')
endif
add_project_link_arguments('-ladvapi32', '-lsetupapi', language: 'c')
endif
if get_option('b_lto')

View File

@ -27,6 +27,54 @@ See `Large-Page Support`_ in MSDN for details.
.. _Large-Page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
Load virt2phys Driver
---------------------
Access to physical addresses is provided by a kernel-mode driver, virt2phys.
It is mandatory at least for using hardware PMDs, but may also be required
for mempools.
Refer to documentation in ``dpdk-kmods`` repository for details on system
setup, driver build and installation. This driver is not signed, so signature
checking must be disabled to load it.
.. warning::
Disabling driver signature enforcement weakens OS security.
It is discouraged in production environments.
Compiled package consists of ``virt2phys.inf``, ``virt2phys.cat``,
and ``virt2phys.sys``. It can be installed as follows
from Elevated Command Prompt:
.. code-block:: console
pnputil /add-driver Z:\path\to\virt2phys.inf /install
On Windows Server additional steps are required:
1. From Device Manager, Action menu, select "Add legacy hardware".
2. It will launch the "Add Hardware Wizard". Click "Next".
3. Select second option "Install the hardware that I manually select
from a list (Advanced)".
4. On the next screen, "Kernel bypass" will be shown as a device class.
5. Select it, and click "Next".
6. The previously installed drivers will now be installed for the
"Virtual to physical address translator" device.
When loaded successfully, the driver is shown in *Device Manager* as *Virtual
to physical address translator* device under *Kernel bypass* category.
Installed driver persists across reboots.
If DPDK is unable to communicate with the driver, a warning is printed
on initialization (debug-level logs provide more details):
.. code-block:: text
EAL: Cannot open virt2phys driver interface
Run the ``helloworld`` Example
------------------------------

View File

@ -8,13 +8,24 @@ if is_windows
'eal_common_bus.c',
'eal_common_class.c',
'eal_common_devargs.c',
'eal_common_dynmem.c',
'eal_common_errno.c',
'eal_common_fbarray.c',
'eal_common_launch.c',
'eal_common_lcore.c',
'eal_common_log.c',
'eal_common_mcfg.c',
'eal_common_memalloc.c',
'eal_common_memory.c',
'eal_common_memzone.c',
'eal_common_options.c',
'eal_common_string_fns.c',
'eal_common_tailqs.c',
'eal_common_thread.c',
'eal_common_trace_points.c',
'malloc_elem.c',
'malloc_heap.c',
'rte_malloc.c',
)
subdir_done()
endif

View File

@ -20,6 +20,7 @@
#include <rte_lcore.h>
#include <rte_common.h>
#include <rte_spinlock.h>
#include <rte_eal_trace.h>
#include <rte_malloc.h>

View File

@ -1,8 +1,128 @@
EXPORTS
__rte_panic
rte_calloc
rte_calloc_socket
rte_eal_get_configuration
rte_eal_has_hugepages
rte_eal_init
rte_eal_iova_mode
rte_eal_mp_remote_launch
rte_eal_mp_wait_lcore
rte_eal_process_type
rte_eal_remote_launch
rte_log
rte_eal_tailq_lookup
rte_eal_tailq_register
rte_eal_using_phys_addrs
rte_free
rte_malloc
rte_malloc_dump_stats
rte_malloc_get_socket_stats
rte_malloc_set_limit
rte_malloc_socket
rte_malloc_validate
rte_malloc_virt2iova
rte_mcfg_mem_read_lock
rte_mcfg_mem_read_unlock
rte_mcfg_mem_write_lock
rte_mcfg_mem_write_unlock
rte_mcfg_mempool_read_lock
rte_mcfg_mempool_read_unlock
rte_mcfg_mempool_write_lock
rte_mcfg_mempool_write_unlock
rte_mcfg_tailq_read_lock
rte_mcfg_tailq_read_unlock
rte_mcfg_tailq_write_lock
rte_mcfg_tailq_write_unlock
rte_mem_lock_page
rte_mem_virt2iova
rte_mem_virt2phy
rte_memory_get_nchannel
rte_memory_get_nrank
rte_memzone_dump
rte_memzone_free
rte_memzone_lookup
rte_memzone_reserve
rte_memzone_reserve_aligned
rte_memzone_reserve_bounded
rte_memzone_walk
rte_vlog
rte_realloc
rte_zmalloc
rte_zmalloc_socket
rte_mp_action_register
rte_mp_action_unregister
rte_mp_reply
rte_mp_sendmsg
rte_fbarray_attach
rte_fbarray_destroy
rte_fbarray_detach
rte_fbarray_dump_metadata
rte_fbarray_find_contig_free
rte_fbarray_find_contig_used
rte_fbarray_find_idx
rte_fbarray_find_next_free
rte_fbarray_find_next_n_free
rte_fbarray_find_next_n_used
rte_fbarray_find_next_used
rte_fbarray_get
rte_fbarray_init
rte_fbarray_is_used
rte_fbarray_set_free
rte_fbarray_set_used
rte_malloc_dump_heaps
rte_mem_alloc_validator_register
rte_mem_alloc_validator_unregister
rte_mem_check_dma_mask
rte_mem_event_callback_register
rte_mem_event_callback_unregister
rte_mem_iova2virt
rte_mem_virt2memseg
rte_mem_virt2memseg_list
rte_memseg_contig_walk
rte_memseg_list_walk
rte_memseg_walk
rte_mp_request_async
rte_mp_request_sync
rte_fbarray_find_prev_free
rte_fbarray_find_prev_n_free
rte_fbarray_find_prev_n_used
rte_fbarray_find_prev_used
rte_fbarray_find_rev_contig_free
rte_fbarray_find_rev_contig_used
rte_memseg_contig_walk_thread_unsafe
rte_memseg_list_walk_thread_unsafe
rte_memseg_walk_thread_unsafe
rte_malloc_heap_create
rte_malloc_heap_destroy
rte_malloc_heap_get_socket
rte_malloc_heap_memory_add
rte_malloc_heap_memory_attach
rte_malloc_heap_memory_detach
rte_malloc_heap_memory_remove
rte_malloc_heap_socket_is_external
rte_mem_check_dma_mask_thread_unsafe
rte_mem_set_dma_mask
rte_memseg_get_fd
rte_memseg_get_fd_offset
rte_memseg_get_fd_offset_thread_unsafe
rte_memseg_get_fd_thread_unsafe
rte_extmem_attach
rte_extmem_detach
rte_extmem_register
rte_extmem_unregister
rte_fbarray_find_biggest_free
rte_fbarray_find_biggest_used
rte_fbarray_find_rev_biggest_free
rte_fbarray_find_rev_biggest_used
rte_mem_lock
rte_mem_map
rte_mem_page_size
rte_mem_unmap

View File

@ -94,6 +94,24 @@ eal_proc_type_detect(void)
return ptype;
}
enum rte_proc_type_t
rte_eal_process_type(void)
{
return rte_config.process_type;
}
int
rte_eal_has_hugepages(void)
{
return !internal_config.no_hugetlbfs;
}
enum rte_iova_mode
rte_eal_iova_mode(void)
{
return rte_config.iova_mode;
}
/* display usage */
static void
eal_usage(const char *prgname)
@ -256,7 +274,7 @@ __rte_trace_point_register(rte_trace_point_t *trace, const char *name,
return -ENOTSUP;
}
/* Launch threads, called at application init(). */
/* Launch threads, called at application init(). */
int
rte_eal_init(int argc, char **argv)
{
@ -282,6 +300,13 @@ rte_eal_init(int argc, char **argv)
if (fctret < 0)
exit(1);
/* Prevent creation of shared memory files. */
if (internal_config.in_memory == 0) {
RTE_LOG(WARNING, EAL, "Multi-process support is requested, "
"but not available.\n");
internal_config.in_memory = 1;
}
if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
rte_eal_init_alert("Cannot get hugepage information");
rte_errno = EACCES;
@ -293,6 +318,42 @@ rte_eal_init(int argc, char **argv)
internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
}
if (eal_mem_win32api_init() < 0) {
rte_eal_init_alert("Cannot access Win32 memory management");
rte_errno = ENOTSUP;
return -1;
}
if (eal_mem_virt2iova_init() < 0) {
/* Non-fatal error if physical addresses are not required. */
RTE_LOG(WARNING, EAL, "Cannot access virt2phys driver, "
"PA will not be available\n");
}
if (rte_eal_memzone_init() < 0) {
rte_eal_init_alert("Cannot init memzone");
rte_errno = ENODEV;
return -1;
}
if (rte_eal_memory_init() < 0) {
rte_eal_init_alert("Cannot init memory");
rte_errno = ENOMEM;
return -1;
}
if (rte_eal_malloc_heap_init() < 0) {
rte_eal_init_alert("Cannot init malloc heap");
rte_errno = ENODEV;
return -1;
}
if (rte_eal_tailqs_init() < 0) {
rte_eal_init_alert("Cannot init tail queues for objects");
rte_errno = EFAULT;
return -1;
}
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {

View File

@ -0,0 +1,125 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2020 Dmitry Kozlyuk
*/
#include <fcntl.h>
#include <io.h>
#include <share.h>
#include <sys/stat.h>
#include "eal_private.h"
#include "eal_windows.h"
int
eal_file_open(const char *path, int flags)
{
static const int MODE_MASK = EAL_OPEN_READONLY | EAL_OPEN_READWRITE;
int fd, ret, sys_flags;
switch (flags & MODE_MASK) {
case EAL_OPEN_READONLY:
sys_flags = _O_RDONLY;
break;
case EAL_OPEN_READWRITE:
sys_flags = _O_RDWR;
break;
default:
rte_errno = ENOTSUP;
return -1;
}
if (flags & EAL_OPEN_CREATE)
sys_flags |= _O_CREAT;
ret = _sopen_s(&fd, path, sys_flags, _SH_DENYNO, _S_IWRITE);
if (ret < 0) {
rte_errno = errno;
return -1;
}
return fd;
}
int
eal_file_truncate(int fd, ssize_t size)
{
HANDLE handle;
DWORD ret;
LONG low = (LONG)((size_t)size);
LONG high = (LONG)((size_t)size >> 32);
handle = (HANDLE)_get_osfhandle(fd);
if (handle == INVALID_HANDLE_VALUE) {
rte_errno = EBADF;
return -1;
}
ret = SetFilePointer(handle, low, &high, FILE_BEGIN);
if (ret == INVALID_SET_FILE_POINTER) {
RTE_LOG_WIN32_ERR("SetFilePointer()");
rte_errno = EINVAL;
return -1;
}
return 0;
}
static int
lock_file(HANDLE handle, enum eal_flock_op op, enum eal_flock_mode mode)
{
DWORD sys_flags = 0;
OVERLAPPED overlapped;
if (op == EAL_FLOCK_EXCLUSIVE)
sys_flags |= LOCKFILE_EXCLUSIVE_LOCK;
if (mode == EAL_FLOCK_RETURN)
sys_flags |= LOCKFILE_FAIL_IMMEDIATELY;
memset(&overlapped, 0, sizeof(overlapped));
if (!LockFileEx(handle, sys_flags, 0, 0, 0, &overlapped)) {
if ((sys_flags & LOCKFILE_FAIL_IMMEDIATELY) &&
(GetLastError() == ERROR_IO_PENDING)) {
rte_errno = EWOULDBLOCK;
} else {
RTE_LOG_WIN32_ERR("LockFileEx()");
rte_errno = EINVAL;
}
return -1;
}
return 0;
}
static int
unlock_file(HANDLE handle)
{
if (!UnlockFileEx(handle, 0, 0, 0, NULL)) {
RTE_LOG_WIN32_ERR("UnlockFileEx()");
rte_errno = EINVAL;
return -1;
}
return 0;
}
int
eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
{
HANDLE handle = (HANDLE)_get_osfhandle(fd);
if (handle == INVALID_HANDLE_VALUE) {
rte_errno = EBADF;
return -1;
}
switch (op) {
case EAL_FLOCK_EXCLUSIVE:
case EAL_FLOCK_SHARED:
return lock_file(handle, op, mode);
case EAL_FLOCK_UNLOCK:
return unlock_file(handle);
default:
rte_errno = EINVAL;
return -1;
}
}

View File

@ -0,0 +1,441 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright (c) 2020 Dmitry Kozlyuk
*/
#include <rte_errno.h>
#include <rte_os.h>
#include "eal_internal_cfg.h"
#include "eal_memalloc.h"
#include "eal_memcfg.h"
#include "eal_private.h"
#include "eal_windows.h"
int
eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
{
/* Hugepages have no associated files in Windows. */
RTE_SET_USED(list_idx);
RTE_SET_USED(seg_idx);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
eal_memalloc_get_seg_fd_offset(int list_idx, int seg_idx, size_t *offset)
{
/* Hugepages have no associated files in Windows. */
RTE_SET_USED(list_idx);
RTE_SET_USED(seg_idx);
RTE_SET_USED(offset);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
static int
alloc_seg(struct rte_memseg *ms, void *requested_addr, int socket_id,
struct hugepage_info *hi)
{
HANDLE current_process;
unsigned int numa_node;
size_t alloc_sz;
void *addr;
rte_iova_t iova = RTE_BAD_IOVA;
PSAPI_WORKING_SET_EX_INFORMATION info;
PSAPI_WORKING_SET_EX_BLOCK *page;
if (ms->len > 0) {
/* If a segment is already allocated as needed, return it. */
if ((ms->addr == requested_addr) &&
(ms->socket_id == socket_id) &&
(ms->hugepage_sz == hi->hugepage_sz)) {
return 0;
}
/* Bugcheck, should not happen. */
RTE_LOG(DEBUG, EAL, "Attempted to reallocate segment %p "
"(size %zu) on socket %d", ms->addr,
ms->len, ms->socket_id);
return -1;
}
current_process = GetCurrentProcess();
numa_node = eal_socket_numa_node(socket_id);
alloc_sz = hi->hugepage_sz;
if (requested_addr == NULL) {
/* Request a new chunk of memory from OS. */
addr = eal_mem_alloc_socket(alloc_sz, socket_id);
if (addr == NULL) {
RTE_LOG(DEBUG, EAL, "Cannot allocate %zu bytes "
"on socket %d\n", alloc_sz, socket_id);
return -1;
}
} else {
/* Requested address is already reserved, commit memory. */
addr = eal_mem_commit(requested_addr, alloc_sz, socket_id);
/* During commitment, memory is temporary freed and might
* be allocated by different non-EAL thread. This is a fatal
* error, because it breaks MSL assumptions.
*/
if ((addr != NULL) && (addr != requested_addr)) {
RTE_LOG(CRIT, EAL, "Address %p occupied by an alien "
" allocation - MSL is not VA-contiguous!\n",
requested_addr);
return -1;
}
if (addr == NULL) {
RTE_LOG(DEBUG, EAL, "Cannot commit reserved memory %p "
"(size %zu) on socket %d\n",
requested_addr, alloc_sz, socket_id);
return -1;
}
}
/* Force OS to allocate a physical page and select a NUMA node.
* Hugepages are not pageable in Windows, so there's no race
* for physical address.
*/
*(volatile int *)addr = *(volatile int *)addr;
/* Only try to obtain IOVA if it's available, so that applications
* that do not need IOVA can use this allocator.
*/
if (rte_eal_using_phys_addrs()) {
iova = rte_mem_virt2iova(addr);
if (iova == RTE_BAD_IOVA) {
RTE_LOG(DEBUG, EAL,
"Cannot get IOVA of allocated segment\n");
goto error;
}
}
/* Only "Ex" function can handle hugepages. */
info.VirtualAddress = addr;
if (!QueryWorkingSetEx(current_process, &info, sizeof(info))) {
RTE_LOG_WIN32_ERR("QueryWorkingSetEx(%p)", addr);
goto error;
}
page = &info.VirtualAttributes;
if (!page->Valid || !page->LargePage) {
RTE_LOG(DEBUG, EAL, "Got regular page instead of a hugepage\n");
goto error;
}
if (page->Node != numa_node) {
RTE_LOG(DEBUG, EAL,
"NUMA node hint %u (socket %d) not respected, got %u\n",
numa_node, socket_id, page->Node);
goto error;
}
ms->addr = addr;
ms->hugepage_sz = hi->hugepage_sz;
ms->len = alloc_sz;
ms->nchannel = rte_memory_get_nchannel();
ms->nrank = rte_memory_get_nrank();
ms->iova = iova;
ms->socket_id = socket_id;
return 0;
error:
/* Only jump here when `addr` and `alloc_sz` are valid. */
if (eal_mem_decommit(addr, alloc_sz) && (rte_errno == EADDRNOTAVAIL)) {
/* During decommitment, memory is temporarily returned
* to the system and the address may become unavailable.
*/
RTE_LOG(CRIT, EAL, "Address %p occupied by an alien "
" allocation - MSL is not VA-contiguous!\n", addr);
}
return -1;
}
static int
free_seg(struct rte_memseg *ms)
{
if (eal_mem_decommit(ms->addr, ms->len)) {
if (rte_errno == EADDRNOTAVAIL) {
/* See alloc_seg() for explanation. */
RTE_LOG(CRIT, EAL, "Address %p occupied by an alien "
" allocation - MSL is not VA-contiguous!\n",
ms->addr);
}
return -1;
}
/* Must clear the segment, because alloc_seg() inspects it. */
memset(ms, 0, sizeof(*ms));
return 0;
}
struct alloc_walk_param {
struct hugepage_info *hi;
struct rte_memseg **ms;
size_t page_sz;
unsigned int segs_allocated;
unsigned int n_segs;
int socket;
bool exact;
};
static int
alloc_seg_walk(const struct rte_memseg_list *msl, void *arg)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
struct alloc_walk_param *wa = arg;
struct rte_memseg_list *cur_msl;
size_t page_sz;
int cur_idx, start_idx, j;
unsigned int msl_idx, need, i;
if (msl->page_sz != wa->page_sz)
return 0;
if (msl->socket_id != wa->socket)
return 0;
page_sz = (size_t)msl->page_sz;
msl_idx = msl - mcfg->memsegs;
cur_msl = &mcfg->memsegs[msl_idx];
need = wa->n_segs;
/* try finding space in memseg list */
if (wa->exact) {
/* if we require exact number of pages in a list, find them */
cur_idx = rte_fbarray_find_next_n_free(
&cur_msl->memseg_arr, 0, need);
if (cur_idx < 0)
return 0;
start_idx = cur_idx;
} else {
int cur_len;
/* we don't require exact number of pages, so we're going to go
* for best-effort allocation. that means finding the biggest
* unused block, and going with that.
*/
cur_idx = rte_fbarray_find_biggest_free(
&cur_msl->memseg_arr, 0);
if (cur_idx < 0)
return 0;
start_idx = cur_idx;
/* adjust the size to possibly be smaller than original
* request, but do not allow it to be bigger.
*/
cur_len = rte_fbarray_find_contig_free(
&cur_msl->memseg_arr, cur_idx);
need = RTE_MIN(need, (unsigned int)cur_len);
}
for (i = 0; i < need; i++, cur_idx++) {
struct rte_memseg *cur;
void *map_addr;
cur = rte_fbarray_get(&cur_msl->memseg_arr, cur_idx);
map_addr = RTE_PTR_ADD(cur_msl->base_va, cur_idx * page_sz);
if (alloc_seg(cur, map_addr, wa->socket, wa->hi)) {
RTE_LOG(DEBUG, EAL, "attempted to allocate %i segments, "
"but only %i were allocated\n", need, i);
/* if exact number wasn't requested, stop */
if (!wa->exact)
goto out;
/* clean up */
for (j = start_idx; j < cur_idx; j++) {
struct rte_memseg *tmp;
struct rte_fbarray *arr = &cur_msl->memseg_arr;
tmp = rte_fbarray_get(arr, j);
rte_fbarray_set_free(arr, j);
if (free_seg(tmp))
RTE_LOG(DEBUG, EAL, "Cannot free page\n");
}
/* clear the list */
if (wa->ms)
memset(wa->ms, 0, sizeof(*wa->ms) * wa->n_segs);
return -1;
}
if (wa->ms)
wa->ms[i] = cur;
rte_fbarray_set_used(&cur_msl->memseg_arr, cur_idx);
}
out:
wa->segs_allocated = i;
if (i > 0)
cur_msl->version++;
/* if we didn't allocate any segments, move on to the next list */
return i > 0;
}
struct free_walk_param {
struct hugepage_info *hi;
struct rte_memseg *ms;
};
static int
free_seg_walk(const struct rte_memseg_list *msl, void *arg)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
struct rte_memseg_list *found_msl;
struct free_walk_param *wa = arg;
uintptr_t start_addr, end_addr;
int msl_idx, seg_idx, ret;
start_addr = (uintptr_t) msl->base_va;
end_addr = start_addr + msl->len;
if ((uintptr_t)wa->ms->addr < start_addr ||
(uintptr_t)wa->ms->addr >= end_addr)
return 0;
msl_idx = msl - mcfg->memsegs;
seg_idx = RTE_PTR_DIFF(wa->ms->addr, start_addr) / msl->page_sz;
/* msl is const */
found_msl = &mcfg->memsegs[msl_idx];
found_msl->version++;
rte_fbarray_set_free(&found_msl->memseg_arr, seg_idx);
ret = free_seg(wa->ms);
return (ret < 0) ? (-1) : 1;
}
int
eal_memalloc_alloc_seg_bulk(struct rte_memseg **ms, int n_segs,
size_t page_sz, int socket, bool exact)
{
unsigned int i;
int ret = -1;
struct alloc_walk_param wa;
struct hugepage_info *hi = NULL;
if (internal_config.legacy_mem) {
RTE_LOG(ERR, EAL, "dynamic allocation not supported in legacy mode\n");
return -ENOTSUP;
}
for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
struct hugepage_info *hpi = &internal_config.hugepage_info[i];
if (page_sz == hpi->hugepage_sz) {
hi = hpi;
break;
}
}
if (!hi) {
RTE_LOG(ERR, EAL, "cannot find relevant hugepage_info entry\n");
return -1;
}
memset(&wa, 0, sizeof(wa));
wa.exact = exact;
wa.hi = hi;
wa.ms = ms;
wa.n_segs = n_segs;
wa.page_sz = page_sz;
wa.socket = socket;
wa.segs_allocated = 0;
/* memalloc is locked, so it's safe to use thread-unsafe version */
ret = rte_memseg_list_walk_thread_unsafe(alloc_seg_walk, &wa);
if (ret == 0) {
RTE_LOG(ERR, EAL, "cannot find suitable memseg_list\n");
ret = -1;
} else if (ret > 0) {
ret = (int)wa.segs_allocated;
}
return ret;
}
struct rte_memseg *
eal_memalloc_alloc_seg(size_t page_sz, int socket)
{
struct rte_memseg *ms = NULL;
eal_memalloc_alloc_seg_bulk(&ms, 1, page_sz, socket, true);
return ms;
}
int
eal_memalloc_free_seg_bulk(struct rte_memseg **ms, int n_segs)
{
int seg, ret = 0;
/* dynamic free not supported in legacy mode */
if (internal_config.legacy_mem)
return -1;
for (seg = 0; seg < n_segs; seg++) {
struct rte_memseg *cur = ms[seg];
struct hugepage_info *hi = NULL;
struct free_walk_param wa;
size_t i;
int walk_res;
/* if this page is marked as unfreeable, fail */
if (cur->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
RTE_LOG(DEBUG, EAL, "Page is not allowed to be freed\n");
ret = -1;
continue;
}
memset(&wa, 0, sizeof(wa));
for (i = 0; i < RTE_DIM(internal_config.hugepage_info); i++) {
hi = &internal_config.hugepage_info[i];
if (cur->hugepage_sz == hi->hugepage_sz)
break;
}
if (i == RTE_DIM(internal_config.hugepage_info)) {
RTE_LOG(ERR, EAL, "Can't find relevant hugepage_info entry\n");
ret = -1;
continue;
}
wa.ms = cur;
wa.hi = hi;
/* memalloc is locked, so it's safe to use thread-unsafe version
*/
walk_res = rte_memseg_list_walk_thread_unsafe(free_seg_walk,
&wa);
if (walk_res == 1)
continue;
if (walk_res == 0)
RTE_LOG(ERR, EAL, "Couldn't find memseg list\n");
ret = -1;
}
return ret;
}
int
eal_memalloc_free_seg(struct rte_memseg *ms)
{
return eal_memalloc_free_seg_bulk(&ms, 1);
}
int
eal_memalloc_sync_with_primary(void)
{
/* No multi-process support. */
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
eal_memalloc_init(void)
{
/* No action required. */
return 0;
}

View File

@ -0,0 +1,710 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright (c) 2020 Dmitry Kozlyuk
*/
#include <inttypes.h>
#include <io.h>
#include <rte_eal_paging.h>
#include <rte_errno.h>
#include "eal_internal_cfg.h"
#include "eal_memalloc.h"
#include "eal_memcfg.h"
#include "eal_options.h"
#include "eal_private.h"
#include "eal_windows.h"
#include <rte_virt2phys.h>
/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
* Provide a copy of definitions and code to load it dynamically.
* Note: definitions are copied verbatim from Microsoft documentation
* and don't follow DPDK code style.
*
* MEM_RESERVE_PLACEHOLDER being defined means VirtualAlloc2() is present too.
*/
#ifndef MEM_PRESERVE_PLACEHOLDER
/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ne-winnt-mem_extended_parameter_type */
typedef enum MEM_EXTENDED_PARAMETER_TYPE {
MemExtendedParameterInvalidType,
MemExtendedParameterAddressRequirements,
MemExtendedParameterNumaNode,
MemExtendedParameterPartitionHandle,
MemExtendedParameterUserPhysicalHandle,
MemExtendedParameterAttributeFlags,
MemExtendedParameterMax
} *PMEM_EXTENDED_PARAMETER_TYPE;
#define MEM_EXTENDED_PARAMETER_TYPE_BITS 4
/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ns-winnt-mem_extended_parameter */
typedef struct MEM_EXTENDED_PARAMETER {
struct {
DWORD64 Type : MEM_EXTENDED_PARAMETER_TYPE_BITS;
DWORD64 Reserved : 64 - MEM_EXTENDED_PARAMETER_TYPE_BITS;
} DUMMYSTRUCTNAME;
union {
DWORD64 ULong64;
PVOID Pointer;
SIZE_T Size;
HANDLE Handle;
DWORD ULong;
} DUMMYUNIONNAME;
} MEM_EXTENDED_PARAMETER, *PMEM_EXTENDED_PARAMETER;
/* https://docs.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualalloc2 */
typedef PVOID (*VirtualAlloc2_type)(
HANDLE Process,
PVOID BaseAddress,
SIZE_T Size,
ULONG AllocationType,
ULONG PageProtection,
MEM_EXTENDED_PARAMETER *ExtendedParameters,
ULONG ParameterCount
);
/* VirtualAlloc2() flags. */
#define MEM_COALESCE_PLACEHOLDERS 0x00000001
#define MEM_PRESERVE_PLACEHOLDER 0x00000002
#define MEM_REPLACE_PLACEHOLDER 0x00004000
#define MEM_RESERVE_PLACEHOLDER 0x00040000
/* Named exactly as the function, so that user code does not depend
* on it being found at compile time or dynamically.
*/
static VirtualAlloc2_type VirtualAlloc2;
int
eal_mem_win32api_init(void)
{
/* Contrary to the docs, VirtualAlloc2() is not in kernel32.dll,
* see https://github.com/MicrosoftDocs/feedback/issues/1129.
*/
static const char library_name[] = "kernelbase.dll";
static const char function[] = "VirtualAlloc2";
HMODULE library = NULL;
int ret = 0;
/* Already done. */
if (VirtualAlloc2 != NULL)
return 0;
library = LoadLibraryA(library_name);
if (library == NULL) {
RTE_LOG_WIN32_ERR("LoadLibraryA(\"%s\")", library_name);
return -1;
}
VirtualAlloc2 = (VirtualAlloc2_type)(
(void *)GetProcAddress(library, function));
if (VirtualAlloc2 == NULL) {
RTE_LOG_WIN32_ERR("GetProcAddress(\"%s\", \"%s\")\n",
library_name, function);
/* Contrary to the docs, Server 2016 is not supported. */
RTE_LOG(ERR, EAL, "Windows 10 or Windows Server 2019 "
" is required for memory management\n");
ret = -1;
}
FreeLibrary(library);
return ret;
}
#else
/* Stub in case VirtualAlloc2() is provided by the compiler. */
int
eal_mem_win32api_init(void)
{
return 0;
}
#endif /* defined(MEM_RESERVE_PLACEHOLDER) */
static HANDLE virt2phys_device = INVALID_HANDLE_VALUE;
int
eal_mem_virt2iova_init(void)
{
HDEVINFO list = INVALID_HANDLE_VALUE;
SP_DEVICE_INTERFACE_DATA ifdata;
SP_DEVICE_INTERFACE_DETAIL_DATA *detail = NULL;
DWORD detail_size;
int ret = -1;
list = SetupDiGetClassDevs(
&GUID_DEVINTERFACE_VIRT2PHYS, NULL, NULL,
DIGCF_DEVICEINTERFACE | DIGCF_PRESENT);
if (list == INVALID_HANDLE_VALUE) {
RTE_LOG_WIN32_ERR("SetupDiGetClassDevs()");
goto exit;
}
ifdata.cbSize = sizeof(ifdata);
if (!SetupDiEnumDeviceInterfaces(
list, NULL, &GUID_DEVINTERFACE_VIRT2PHYS, 0, &ifdata)) {
RTE_LOG_WIN32_ERR("SetupDiEnumDeviceInterfaces()");
goto exit;
}
if (!SetupDiGetDeviceInterfaceDetail(
list, &ifdata, NULL, 0, &detail_size, NULL)) {
if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
RTE_LOG_WIN32_ERR(
"SetupDiGetDeviceInterfaceDetail(probe)");
goto exit;
}
}
detail = malloc(detail_size);
if (detail == NULL) {
RTE_LOG(ERR, EAL, "Cannot allocate virt2phys "
"device interface detail data\n");
goto exit;
}
detail->cbSize = sizeof(*detail);
if (!SetupDiGetDeviceInterfaceDetail(
list, &ifdata, detail, detail_size, NULL, NULL)) {
RTE_LOG_WIN32_ERR("SetupDiGetDeviceInterfaceDetail(read)");
goto exit;
}
RTE_LOG(DEBUG, EAL, "Found virt2phys device: %s\n", detail->DevicePath);
virt2phys_device = CreateFile(
detail->DevicePath, 0, 0, NULL, OPEN_EXISTING, 0, NULL);
if (virt2phys_device == INVALID_HANDLE_VALUE) {
RTE_LOG_WIN32_ERR("CreateFile()");
goto exit;
}
/* Indicate success. */
ret = 0;
exit:
if (detail != NULL)
free(detail);
if (list != INVALID_HANDLE_VALUE)
SetupDiDestroyDeviceInfoList(list);
return ret;
}
phys_addr_t
rte_mem_virt2phy(const void *virt)
{
LARGE_INTEGER phys;
DWORD bytes_returned;
if (virt2phys_device == INVALID_HANDLE_VALUE)
return RTE_BAD_PHYS_ADDR;
if (!DeviceIoControl(
virt2phys_device, IOCTL_VIRT2PHYS_TRANSLATE,
&virt, sizeof(virt), &phys, sizeof(phys),
&bytes_returned, NULL)) {
RTE_LOG_WIN32_ERR("DeviceIoControl(IOCTL_VIRT2PHYS_TRANSLATE)");
return RTE_BAD_PHYS_ADDR;
}
return phys.QuadPart;
}
/* Windows currently only supports IOVA as PA. */
rte_iova_t
rte_mem_virt2iova(const void *virt)
{
phys_addr_t phys;
if (virt2phys_device == INVALID_HANDLE_VALUE)
return RTE_BAD_IOVA;
phys = rte_mem_virt2phy(virt);
if (phys == RTE_BAD_PHYS_ADDR)
return RTE_BAD_IOVA;
return (rte_iova_t)phys;
}
/* Always using physical addresses under Windows if they can be obtained. */
int
rte_eal_using_phys_addrs(void)
{
return virt2phys_device != INVALID_HANDLE_VALUE;
}
/* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
static void
set_errno_from_win32_alloc_error(DWORD code)
{
switch (code) {
case ERROR_SUCCESS:
rte_errno = 0;
break;
case ERROR_INVALID_ADDRESS:
/* A valid requested address is not available. */
case ERROR_COMMITMENT_LIMIT:
/* May occur when committing regular memory. */
case ERROR_NO_SYSTEM_RESOURCES:
/* Occurs when the system runs out of hugepages. */
rte_errno = ENOMEM;
break;
case ERROR_INVALID_PARAMETER:
default:
rte_errno = EINVAL;
break;
}
}
void *
eal_mem_reserve(void *requested_addr, size_t size, int flags)
{
HANDLE process;
void *virt;
/* Windows requires hugepages to be committed. */
if (flags & EAL_RESERVE_HUGEPAGES) {
rte_errno = ENOTSUP;
return NULL;
}
process = GetCurrentProcess();
virt = VirtualAlloc2(process, requested_addr, size,
MEM_RESERVE | MEM_RESERVE_PLACEHOLDER, PAGE_NOACCESS,
NULL, 0);
if (virt == NULL) {
DWORD err = GetLastError();
RTE_LOG_WIN32_ERR("VirtualAlloc2()");
set_errno_from_win32_alloc_error(err);
return NULL;
}
if ((flags & EAL_RESERVE_FORCE_ADDRESS) && (virt != requested_addr)) {
if (!VirtualFreeEx(process, virt, 0, MEM_RELEASE))
RTE_LOG_WIN32_ERR("VirtualFreeEx()");
rte_errno = ENOMEM;
return NULL;
}
return virt;
}
void *
eal_mem_alloc_socket(size_t size, int socket_id)
{
DWORD flags = MEM_RESERVE | MEM_COMMIT;
void *addr;
flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
addr = VirtualAllocExNuma(GetCurrentProcess(), NULL, size, flags,
PAGE_READWRITE, eal_socket_numa_node(socket_id));
if (addr == NULL)
rte_errno = ENOMEM;
return addr;
}
void *
eal_mem_commit(void *requested_addr, size_t size, int socket_id)
{
HANDLE process;
MEM_EXTENDED_PARAMETER param;
DWORD param_count = 0;
DWORD flags;
void *addr;
process = GetCurrentProcess();
if (requested_addr != NULL) {
MEMORY_BASIC_INFORMATION info;
if (VirtualQueryEx(process, requested_addr, &info,
sizeof(info)) != sizeof(info)) {
RTE_LOG_WIN32_ERR("VirtualQuery(%p)", requested_addr);
return NULL;
}
/* Split reserved region if only a part is committed. */
flags = MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER;
if ((info.RegionSize > size) && !VirtualFreeEx(
process, requested_addr, size, flags)) {
RTE_LOG_WIN32_ERR(
"VirtualFreeEx(%p, %zu, preserve placeholder)",
requested_addr, size);
return NULL;
}
/* Temporarily release the region to be committed.
*
* There is an inherent race for this memory range
* if another thread allocates memory via OS API.
* However, VirtualAlloc2(MEM_REPLACE_PLACEHOLDER)
* doesn't work with MEM_LARGE_PAGES on Windows Server.
*/
if (!VirtualFreeEx(process, requested_addr, 0, MEM_RELEASE)) {
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, 0, release)",
requested_addr);
return NULL;
}
}
if (socket_id != SOCKET_ID_ANY) {
param_count = 1;
memset(&param, 0, sizeof(param));
param.Type = MemExtendedParameterNumaNode;
param.ULong = eal_socket_numa_node(socket_id);
}
flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
addr = VirtualAlloc2(process, requested_addr, size,
flags, PAGE_READWRITE, &param, param_count);
if (addr == NULL) {
/* Logging may overwrite GetLastError() result. */
DWORD err = GetLastError();
RTE_LOG_WIN32_ERR("VirtualAlloc2(%p, %zu, commit large pages)",
requested_addr, size);
set_errno_from_win32_alloc_error(err);
return NULL;
}
if ((requested_addr != NULL) && (addr != requested_addr)) {
/* We lost the race for the requested_addr. */
if (!VirtualFreeEx(process, addr, 0, MEM_RELEASE))
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, release)", addr);
rte_errno = EADDRNOTAVAIL;
return NULL;
}
return addr;
}
int
eal_mem_decommit(void *addr, size_t size)
{
HANDLE process;
void *stub;
DWORD flags;
process = GetCurrentProcess();
/* Hugepages cannot be decommited on Windows,
* so free them and replace the block with a placeholder.
* There is a race for VA in this block until VirtualAlloc2 call.
*/
if (!VirtualFreeEx(process, addr, 0, MEM_RELEASE)) {
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, 0, release)", addr);
return -1;
}
flags = MEM_RESERVE | MEM_RESERVE_PLACEHOLDER;
stub = VirtualAlloc2(
process, addr, size, flags, PAGE_NOACCESS, NULL, 0);
if (stub == NULL) {
/* We lost the race for the VA. */
if (!VirtualFreeEx(process, stub, 0, MEM_RELEASE))
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, release)", stub);
rte_errno = EADDRNOTAVAIL;
return -1;
}
/* No need to join reserved regions adjacent to the freed one:
* eal_mem_commit() will just pick up the page-size placeholder
* created here.
*/
return 0;
}
/**
* Free a reserved memory region in full or in part.
*
* @param addr
* Starting address of the area to free.
* @param size
* Number of bytes to free. Must be a multiple of page size.
* @param reserved
* Fail if the region is not in reserved state.
* @return
* * 0 on successful deallocation;
* * 1 if region must be in reserved state but it is not;
* * (-1) on system API failures.
*/
static int
mem_free(void *addr, size_t size, bool reserved)
{
MEMORY_BASIC_INFORMATION info;
HANDLE process;
process = GetCurrentProcess();
if (VirtualQueryEx(
process, addr, &info, sizeof(info)) != sizeof(info)) {
RTE_LOG_WIN32_ERR("VirtualQueryEx(%p)", addr);
return -1;
}
if (reserved && (info.State != MEM_RESERVE))
return 1;
/* Free complete region. */
if ((addr == info.AllocationBase) && (size == info.RegionSize)) {
if (!VirtualFreeEx(process, addr, 0, MEM_RELEASE)) {
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, 0, release)",
addr);
}
return 0;
}
/* Split the part to be freed and the remaining reservation. */
if (!VirtualFreeEx(process, addr, size,
MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
RTE_LOG_WIN32_ERR(
"VirtualFreeEx(%p, %zu, preserve placeholder)",
addr, size);
return -1;
}
/* Actually free reservation part. */
if (!VirtualFreeEx(process, addr, 0, MEM_RELEASE)) {
RTE_LOG_WIN32_ERR("VirtualFreeEx(%p, 0, release)", addr);
return -1;
}
return 0;
}
void
eal_mem_free(void *virt, size_t size)
{
mem_free(virt, size, false);
}
int
eal_mem_set_dump(void *virt, size_t size, bool dump)
{
RTE_SET_USED(virt);
RTE_SET_USED(size);
RTE_SET_USED(dump);
/* Windows does not dump reserved memory by default.
*
* There is <werapi.h> to include or exclude regions from the dump,
* but this is not currently required by EAL.
*/
rte_errno = ENOTSUP;
return -1;
}
void *
rte_mem_map(void *requested_addr, size_t size, int prot, int flags,
int fd, size_t offset)
{
HANDLE file_handle = INVALID_HANDLE_VALUE;
HANDLE mapping_handle = INVALID_HANDLE_VALUE;
DWORD sys_prot = 0;
DWORD sys_access = 0;
DWORD size_high = (DWORD)(size >> 32);
DWORD size_low = (DWORD)size;
DWORD offset_high = (DWORD)(offset >> 32);
DWORD offset_low = (DWORD)offset;
LPVOID virt = NULL;
if (prot & RTE_PROT_EXECUTE) {
if (prot & RTE_PROT_READ) {
sys_prot = PAGE_EXECUTE_READ;
sys_access = FILE_MAP_READ | FILE_MAP_EXECUTE;
}
if (prot & RTE_PROT_WRITE) {
sys_prot = PAGE_EXECUTE_READWRITE;
sys_access = FILE_MAP_WRITE | FILE_MAP_EXECUTE;
}
} else {
if (prot & RTE_PROT_READ) {
sys_prot = PAGE_READONLY;
sys_access = FILE_MAP_READ;
}
if (prot & RTE_PROT_WRITE) {
sys_prot = PAGE_READWRITE;
sys_access = FILE_MAP_WRITE;
}
}
if (flags & RTE_MAP_PRIVATE)
sys_access |= FILE_MAP_COPY;
if ((flags & RTE_MAP_ANONYMOUS) == 0)
file_handle = (HANDLE)_get_osfhandle(fd);
mapping_handle = CreateFileMapping(
file_handle, NULL, sys_prot, size_high, size_low, NULL);
if (mapping_handle == INVALID_HANDLE_VALUE) {
RTE_LOG_WIN32_ERR("CreateFileMapping()");
return NULL;
}
/* There is a race for the requested_addr between mem_free()
* and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
* region with a mapping in a single operation, but it does not support
* private mappings.
*/
if (requested_addr != NULL) {
int ret = mem_free(requested_addr, size, true);
if (ret) {
if (ret > 0) {
RTE_LOG(ERR, EAL, "Cannot map memory "
"to a region not reserved\n");
rte_errno = EADDRNOTAVAIL;
}
return NULL;
}
}
virt = MapViewOfFileEx(mapping_handle, sys_access,
offset_high, offset_low, size, requested_addr);
if (!virt) {
RTE_LOG_WIN32_ERR("MapViewOfFileEx()");
return NULL;
}
if ((flags & RTE_MAP_FORCE_ADDRESS) && (virt != requested_addr)) {
if (!UnmapViewOfFile(virt))
RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
virt = NULL;
}
if (!CloseHandle(mapping_handle))
RTE_LOG_WIN32_ERR("CloseHandle()");
return virt;
}
int
rte_mem_unmap(void *virt, size_t size)
{
RTE_SET_USED(size);
if (!UnmapViewOfFile(virt)) {
RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
rte_errno = EINVAL;
return -1;
}
return 0;
}
uint64_t
eal_get_baseaddr(void)
{
/* Windows strategy for memory allocation is undocumented.
* Returning 0 here effectively disables address guessing
* unless user provides an address hint.
*/
return 0;
}
size_t
rte_mem_page_size(void)
{
static SYSTEM_INFO info;
if (info.dwPageSize == 0)
GetSystemInfo(&info);
return info.dwPageSize;
}
int
rte_mem_lock(const void *virt, size_t size)
{
/* VirtualLock() takes `void*`, work around compiler warning. */
void *addr = (void *)((uintptr_t)virt);
if (!VirtualLock(addr, size)) {
RTE_LOG_WIN32_ERR("VirtualLock(%p %#zx)", virt, size);
return -1;
}
return 0;
}
int
rte_eal_memseg_init(void)
{
if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
return eal_dynmem_memseg_lists_init();
}
static int
eal_nohuge_init(void)
{
struct rte_mem_config *mcfg;
struct rte_memseg_list *msl;
int n_segs;
uint64_t mem_sz, page_sz;
void *addr;
mcfg = rte_eal_get_configuration()->mem_config;
/* nohuge mode is legacy mode */
internal_config.legacy_mem = 1;
msl = &mcfg->memsegs[0];
mem_sz = internal_config.memory;
page_sz = RTE_PGSIZE_4K;
n_segs = mem_sz / page_sz;
if (eal_memseg_list_init_named(
msl, "nohugemem", page_sz, n_segs, 0, true)) {
return -1;
}
addr = VirtualAlloc(
NULL, mem_sz, MEM_RESERVE | MEM_COMMIT, PAGE_READWRITE);
if (addr == NULL) {
RTE_LOG_WIN32_ERR("VirtualAlloc(size=%#zx)", mem_sz);
RTE_LOG(ERR, EAL, "Cannot allocate memory\n");
return -1;
}
msl->base_va = addr;
msl->len = mem_sz;
eal_memseg_list_populate(msl, addr, n_segs);
if (mcfg->dma_maskbits &&
rte_mem_check_dma_mask_thread_unsafe(mcfg->dma_maskbits)) {
RTE_LOG(ERR, EAL,
"%s(): couldn't allocate memory due to IOVA "
"exceeding limits of current DMA mask.\n", __func__);
return -1;
}
return 0;
}
int
rte_eal_hugepage_init(void)
{
return internal_config.no_hugetlbfs ?
eal_nohuge_init() : eal_dynmem_hugepage_init();
}
int
rte_eal_hugepage_attach(void)
{
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}

View File

@ -0,0 +1,103 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright (c) 2020 Dmitry Kozlyuk
*/
/**
* @file Multiprocess support stubs
*
* Stubs must log an error until implemented. If success is required
* for non-multiprocess operation, stub must log a warning and a comment
* must document what requires success emulation.
*/
#include <rte_eal.h>
#include <rte_errno.h>
#include "eal_private.h"
#include "eal_windows.h"
#include "malloc_mp.h"
void
rte_mp_channel_cleanup(void)
{
EAL_LOG_NOT_IMPLEMENTED();
}
int
rte_mp_action_register(const char *name, rte_mp_t action)
{
RTE_SET_USED(name);
RTE_SET_USED(action);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
void
rte_mp_action_unregister(const char *name)
{
RTE_SET_USED(name);
EAL_LOG_NOT_IMPLEMENTED();
}
int
rte_mp_sendmsg(struct rte_mp_msg *msg)
{
RTE_SET_USED(msg);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
const struct timespec *ts)
{
RTE_SET_USED(req);
RTE_SET_USED(reply);
RTE_SET_USED(ts);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
rte_mp_async_reply_t clb)
{
RTE_SET_USED(req);
RTE_SET_USED(ts);
RTE_SET_USED(clb);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
{
RTE_SET_USED(msg);
RTE_SET_USED(peer);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
register_mp_requests(void)
{
/* Non-stub function succeeds if multi-process is not supported. */
EAL_LOG_STUB();
return 0;
}
int
request_to_primary(struct malloc_mp_req *req)
{
RTE_SET_USED(req);
EAL_LOG_NOT_IMPLEMENTED();
return -1;
}
int
request_sync(void)
{
/* Common memory allocator depends on this function success. */
EAL_LOG_STUB();
return 0;
}

View File

@ -12,6 +12,21 @@
#include <rte_errno.h>
#include <rte_windows.h>
/**
* Log current function as not implemented and set rte_errno.
*/
#define EAL_LOG_NOT_IMPLEMENTED() \
do { \
RTE_LOG(DEBUG, EAL, "%s() is not implemented\n", __func__); \
rte_errno = ENOTSUP; \
} while (0)
/**
* Log current function as a stub.
*/
#define EAL_LOG_STUB() \
RTE_LOG(DEBUG, EAL, "Windows: %s() is a stub\n", __func__)
/**
* Create a map of processors and cores on the system.
*
@ -40,4 +55,63 @@ int eal_thread_create(pthread_t *thread);
*/
unsigned int eal_socket_numa_node(unsigned int socket_id);
/**
* Open virt2phys driver interface device.
*
* @return 0 on success, (-1) on failure.
*/
int eal_mem_virt2iova_init(void);
/**
* Locate Win32 memory management routines in system libraries.
*
* @return 0 on success, (-1) on failure.
*/
int eal_mem_win32api_init(void);
/**
* Allocate new memory in hugepages on the specified NUMA node.
*
* @param size
* Number of bytes to allocate. Must be a multiple of huge page size.
* @param socket_id
* Socket ID.
* @return
* Address of the memory allocated on success or NULL on failure.
*/
void *eal_mem_alloc_socket(size_t size, int socket_id);
/**
* Commit memory previously reserved with eal_mem_reserve()
* or decommitted from hugepages by eal_mem_decommit().
*
* @param requested_addr
* Address within a reserved region. Must not be NULL.
* @param size
* Number of bytes to commit. Must be a multiple of page size.
* @param socket_id
* Socket ID to allocate on. Can be SOCKET_ID_ANY.
* @return
* On success, address of the committed memory, that is, requested_addr.
* On failure, NULL and rte_errno is set.
*/
void *eal_mem_commit(void *requested_addr, size_t size, int socket_id);
/**
* Put allocated or committed memory back into reserved state.
*
* @param addr
* Address of the region to decommit.
* @param size
* Number of bytes to decommit, must be the size of a page
* (hugepage or regular one).
*
* The *addr* and *size* must match location and size
* of a previously allocated or committed region.
*
* @return
* 0 on success, (-1) on failure.
*/
int eal_mem_decommit(void *addr, size_t size);
#endif /* _EAL_WINDOWS_H_ */

View File

@ -5,5 +5,6 @@ includes += include_directories('.')
headers += files(
'rte_os.h',
'rte_virt2phys.h',
'rte_windows.h',
)

View File

@ -14,6 +14,7 @@
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#ifdef __cplusplus
extern "C" {
@ -36,6 +37,9 @@ extern "C" {
#define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
#define close _close
#define unlink _unlink
/* cpu_set macros implementation */
#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
@ -46,6 +50,7 @@ extern "C" {
typedef long long ssize_t;
#ifndef RTE_TOOLCHAIN_GCC
static inline int
asprintf(char **buffer, const char *format, ...)
{
@ -72,6 +77,18 @@ asprintf(char **buffer, const char *format, ...)
}
return ret;
}
static inline const char *
eal_strerror(int code)
{
static char buffer[128];
strerror_s(buffer, sizeof(buffer), code);
return buffer;
}
#define strerror eal_strerror
#endif /* RTE_TOOLCHAIN_GCC */
#ifdef __cplusplus

View File

@ -0,0 +1,34 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright (c) 2020 Dmitry Kozlyuk
*/
/**
* @file virt2phys driver interface
*/
/**
* Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
*/
DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
0x539c2135, 0x793a, 0x4926,
0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
/**
* Driver device type for IO control codes.
*/
#define VIRT2PHYS_DEVTYPE 0x8000
/**
* Translate a valid non-paged virtual address to a physical address.
*
* Note: A physical address zero (0) is reported if input address
* is paged out or not mapped. However, if input is a valid mapping
* of I/O port 0x0000, output is also zero. There is no way
* to distinguish between these cases by return value only.
*
* Input: a non-paged virtual address (PVOID).
*
* Output: the corresponding physical address (LARGE_INTEGER).
*/
#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)

View File

@ -23,6 +23,8 @@
#include <basetsd.h>
#include <psapi.h>
#include <setupapi.h>
#include <winioctl.h>
/* Have GUIDs defined. */
#ifndef INITGUID

View File

@ -9,4 +9,7 @@
* as Microsoft libc does not contain unistd.h. This may be removed
* in future releases.
*/
#include <io.h>
#endif /* _UNISTD_H_ */

View File

@ -6,10 +6,16 @@ subdir('include')
sources += files(
'eal.c',
'eal_debug.c',
'eal_file.c',
'eal_hugepages.c',
'eal_lcore.c',
'eal_log.c',
'eal_memalloc.c',
'eal_memory.c',
'eal_mp.c',
'eal_thread.c',
'fnmatch.c',
'getopt.c',
)
dpdk_conf.set10('RTE_EAL_NUMA_AWARE_HUGEPAGES', true)