#include "eal_memalloc.h"
#include "eal_private.h"
#include "eal_internal_cfg.h"
+#include "malloc_heap.h"
/*
* Try to mmap *size bytes in /dev/zero. If it is successful, return the
static void *next_baseaddr;
static uint64_t system_page_sz;
+#ifdef RTE_ARCH_64
+/*
+ * Linux kernel uses a really high address as starting address for serving
+ * mmaps calls. If there exists addressing limitations and IOVA mode is VA,
+ * this starting address is likely too high for those devices. However, it
+ * is possible to use a lower address in the process virtual address space
+ * as with 64 bits there is a lot of available space.
+ *
+ * Current known limitations are 39 or 40 bits. Setting the starting address
+ * at 4GB implies there are 508GB or 1020GB for mapping the available
+ * hugepages. This is likely enough for most systems, although a device with
+ * addressing limitations should call rte_mem_check_dma_mask for ensuring all
+ * memory is within supported range.
+ */
+static uint64_t baseaddr = 0x100000000;
+#endif
+
+#define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
void *
eal_get_virtual_area(void *requested_addr, size_t *size,
size_t page_sz, int flags, int mmap_flags)
bool addr_is_hint, allow_shrink, unmap, no_align;
uint64_t map_sz;
void *mapped_addr, *aligned_addr;
+ uint8_t try = 0;
if (system_page_sz == 0)
system_page_sz = sysconf(_SC_PAGESIZE);
rte_eal_process_type() == RTE_PROC_PRIMARY)
next_baseaddr = (void *) internal_config.base_virtaddr;
+#ifdef RTE_ARCH_64
+ if (next_baseaddr == NULL && internal_config.base_virtaddr == 0 &&
+ rte_eal_process_type() == RTE_PROC_PRIMARY)
+ next_baseaddr = (void *) baseaddr;
+#endif
if (requested_addr == NULL && next_baseaddr != NULL) {
requested_addr = next_baseaddr;
requested_addr = RTE_PTR_ALIGN(requested_addr, page_sz);
mmap_flags, -1, 0);
if (mapped_addr == MAP_FAILED && allow_shrink)
*size -= page_sz;
- } while (allow_shrink && mapped_addr == MAP_FAILED && *size > 0);
+
+ if (mapped_addr != MAP_FAILED && addr_is_hint &&
+ mapped_addr != requested_addr) {
+ try++;
+ next_baseaddr = RTE_PTR_ADD(next_baseaddr, page_sz);
+ if (try <= MAX_MMAP_WITH_DEFINED_ADDR_TRIES) {
+ /* hint was not used. Try with another offset */
+ munmap(mapped_addr, map_sz);
+ mapped_addr = MAP_FAILED;
+ requested_addr = next_baseaddr;
+ }
+ }
+ } while ((allow_shrink || addr_is_hint) &&
+ mapped_addr == MAP_FAILED && *size > 0);
/* align resulting address - if map failed, we will ignore the value
* anyway, so no need to add additional checks.
return msl;
}
-__rte_experimental struct rte_memseg_list *
+struct rte_memseg_list *
rte_mem_virt2memseg_list(const void *addr)
{
return virt2memseg_list(addr);
return 0;
}
-__rte_experimental void *
+void *
rte_mem_iova2virt(rte_iova_t iova)
{
struct virtiova vi;
return vi.virt;
}
-__rte_experimental struct rte_memseg *
+struct rte_memseg *
rte_mem_virt2memseg(const void *addr, const struct rte_memseg_list *msl)
{
return virt2memseg(addr, msl != NULL ? msl :
* Defining here because declared in rte_memory.h, but the actual implementation
* is in eal_common_memalloc.c, like all other memalloc internals.
*/
-int __rte_experimental
+int
rte_mem_event_callback_register(const char *name, rte_mem_event_callback_t clb,
void *arg)
{
return eal_memalloc_mem_event_callback_register(name, clb, arg);
}
-int __rte_experimental
+int
rte_mem_event_callback_unregister(const char *name, void *arg)
{
/* FreeBSD boots with legacy mem enabled by default */
return eal_memalloc_mem_event_callback_unregister(name, arg);
}
-int __rte_experimental
+int
rte_mem_alloc_validator_register(const char *name,
rte_mem_alloc_validator_t clb, int socket_id, size_t limit)
{
limit);
}
-int __rte_experimental
+int
rte_mem_alloc_validator_unregister(const char *name, int socket_id)
{
/* FreeBSD boots with legacy mem enabled by default */
return 1;
}
-#if defined(RTE_ARCH_64)
#define MAX_DMA_MASK_BITS 63
-#else
-#define MAX_DMA_MASK_BITS 31
-#endif
/* check memseg iovas are within the required range based on dma mask */
-int __rte_experimental
-rte_eal_check_dma_mask(uint8_t maskbits)
+static int
+check_dma_mask(uint8_t maskbits, bool thread_unsafe)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
uint64_t mask;
+ int ret;
- /* sanity check */
+ /* Sanity check. We only check width can be managed with 64 bits
+ * variables. Indeed any higher value is likely wrong. */
if (maskbits > MAX_DMA_MASK_BITS) {
RTE_LOG(ERR, EAL, "wrong dma mask size %u (Max: %u)\n",
maskbits, MAX_DMA_MASK_BITS);
/* create dma mask */
mask = ~((1ULL << maskbits) - 1);
- if (rte_memseg_walk(check_iova, &mask))
+ if (thread_unsafe)
+ ret = rte_memseg_walk_thread_unsafe(check_iova, &mask);
+ else
+ ret = rte_memseg_walk(check_iova, &mask);
+
+ if (ret)
/*
* Dma mask precludes hugepage usage.
* This device can not be used and we do not need to keep
return 0;
}
+int
+rte_mem_check_dma_mask(uint8_t maskbits)
+{
+ return check_dma_mask(maskbits, false);
+}
+
+int
+rte_mem_check_dma_mask_thread_unsafe(uint8_t maskbits)
+{
+ return check_dma_mask(maskbits, true);
+}
+
+/*
+ * Set dma mask to use when memory initialization is done.
+ *
+ * This function should ONLY be used by code executed before the memory
+ * initialization. PMDs should use rte_mem_check_dma_mask if addressing
+ * limitations by the device.
+ */
+void
+rte_mem_set_dma_mask(uint8_t maskbits)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+
+ mcfg->dma_maskbits = mcfg->dma_maskbits == 0 ? maskbits :
+ RTE_MIN(mcfg->dma_maskbits, maskbits);
+}
+
/* return the number of memory channels */
unsigned rte_memory_get_nchannel(void)
{
return mlock((void *)aligned, page_size);
}
-int __rte_experimental
+int
rte_memseg_contig_walk_thread_unsafe(rte_memseg_contig_walk_t func, void *arg)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
return 0;
}
-int __rte_experimental
+int
rte_memseg_contig_walk(rte_memseg_contig_walk_t func, void *arg)
{
- struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
int ret = 0;
/* do not allow allocations/frees/init while we iterate */
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
ret = rte_memseg_contig_walk_thread_unsafe(func, arg);
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return ret;
}
-int __rte_experimental
+int
rte_memseg_walk_thread_unsafe(rte_memseg_walk_t func, void *arg)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
return 0;
}
-int __rte_experimental
+int
rte_memseg_walk(rte_memseg_walk_t func, void *arg)
{
- struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
int ret = 0;
/* do not allow allocations/frees/init while we iterate */
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
ret = rte_memseg_walk_thread_unsafe(func, arg);
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return ret;
}
-int __rte_experimental
+int
rte_memseg_list_walk_thread_unsafe(rte_memseg_list_walk_t func, void *arg)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
return 0;
}
-int __rte_experimental
+int
rte_memseg_list_walk(rte_memseg_list_walk_t func, void *arg)
{
- struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
int ret = 0;
/* do not allow allocations/frees/init while we iterate */
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
ret = rte_memseg_list_walk_thread_unsafe(func, arg);
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return ret;
}
-int __rte_experimental
+int
rte_memseg_get_fd_thread_unsafe(const struct rte_memseg *ms)
{
struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
return -1;
}
+ /* segment fd API is not supported for external segments */
+ if (msl->external) {
+ rte_errno = ENOTSUP;
+ return -1;
+ }
+
ret = eal_memalloc_get_seg_fd(msl_idx, seg_idx);
if (ret < 0) {
rte_errno = -ret;
return ret;
}
-int __rte_experimental
+int
rte_memseg_get_fd(const struct rte_memseg *ms)
{
- struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
int ret;
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
ret = rte_memseg_get_fd_thread_unsafe(ms);
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return ret;
}
-int __rte_experimental
+int
rte_memseg_get_fd_offset_thread_unsafe(const struct rte_memseg *ms,
size_t *offset)
{
return -1;
}
+ /* segment fd API is not supported for external segments */
+ if (msl->external) {
+ rte_errno = ENOTSUP;
+ return -1;
+ }
+
ret = eal_memalloc_get_seg_fd_offset(msl_idx, seg_idx, offset);
if (ret < 0) {
rte_errno = -ret;
return ret;
}
-int __rte_experimental
+int
rte_memseg_get_fd_offset(const struct rte_memseg *ms, size_t *offset)
{
- struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
int ret;
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
ret = rte_memseg_get_fd_offset_thread_unsafe(ms, offset);
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return ret;
}
+int
+rte_extmem_register(void *va_addr, size_t len, rte_iova_t iova_addrs[],
+ unsigned int n_pages, size_t page_sz)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ unsigned int socket_id, n;
+ int ret = 0;
+
+ if (va_addr == NULL || page_sz == 0 || len == 0 ||
+ !rte_is_power_of_2(page_sz) ||
+ RTE_ALIGN(len, page_sz) != len ||
+ ((len / page_sz) != n_pages && iova_addrs != NULL) ||
+ !rte_is_aligned(va_addr, page_sz)) {
+ rte_errno = EINVAL;
+ return -1;
+ }
+ rte_mcfg_mem_write_lock();
+
+ /* make sure the segment doesn't already exist */
+ if (malloc_heap_find_external_seg(va_addr, len) != NULL) {
+ rte_errno = EEXIST;
+ ret = -1;
+ goto unlock;
+ }
+
+ /* get next available socket ID */
+ socket_id = mcfg->next_socket_id;
+ if (socket_id > INT32_MAX) {
+ RTE_LOG(ERR, EAL, "Cannot assign new socket ID's\n");
+ rte_errno = ENOSPC;
+ ret = -1;
+ goto unlock;
+ }
+
+ /* we can create a new memseg */
+ n = len / page_sz;
+ if (malloc_heap_create_external_seg(va_addr, iova_addrs, n,
+ page_sz, "extmem", socket_id) == NULL) {
+ ret = -1;
+ goto unlock;
+ }
+
+ /* memseg list successfully created - increment next socket ID */
+ mcfg->next_socket_id++;
+unlock:
+ rte_mcfg_mem_write_unlock();
+ return ret;
+}
+
+int
+rte_extmem_unregister(void *va_addr, size_t len)
+{
+ struct rte_memseg_list *msl;
+ int ret = 0;
+
+ if (va_addr == NULL || len == 0) {
+ rte_errno = EINVAL;
+ return -1;
+ }
+ rte_mcfg_mem_write_lock();
+
+ /* find our segment */
+ msl = malloc_heap_find_external_seg(va_addr, len);
+ if (msl == NULL) {
+ rte_errno = ENOENT;
+ ret = -1;
+ goto unlock;
+ }
+
+ ret = malloc_heap_destroy_external_seg(msl);
+unlock:
+ rte_mcfg_mem_write_unlock();
+ return ret;
+}
+
+static int
+sync_memory(void *va_addr, size_t len, bool attach)
+{
+ struct rte_memseg_list *msl;
+ int ret = 0;
+
+ if (va_addr == NULL || len == 0) {
+ rte_errno = EINVAL;
+ return -1;
+ }
+ rte_mcfg_mem_write_lock();
+
+ /* find our segment */
+ msl = malloc_heap_find_external_seg(va_addr, len);
+ if (msl == NULL) {
+ rte_errno = ENOENT;
+ ret = -1;
+ goto unlock;
+ }
+ if (attach)
+ ret = rte_fbarray_attach(&msl->memseg_arr);
+ else
+ ret = rte_fbarray_detach(&msl->memseg_arr);
+
+unlock:
+ rte_mcfg_mem_write_unlock();
+ return ret;
+}
+
+int
+rte_extmem_attach(void *va_addr, size_t len)
+{
+ return sync_memory(va_addr, len, true);
+}
+
+int
+rte_extmem_detach(void *va_addr, size_t len)
+{
+ return sync_memory(va_addr, len, false);
+}
+
/* init memory subsystem */
int
rte_eal_memory_init(void)
return -1;
/* lock mem hotplug here, to prevent races while we init */
- rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_lock();
if (rte_eal_memseg_init() < 0)
goto fail;
return 0;
fail:
- rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ rte_mcfg_mem_read_unlock();
return -1;
}