Since the VA space of all memseg lists is reserved in one go, it is
reserved before the memseg lists are created. The fbarray of each list
is allocated from the same VA allocator, so the first fbarray now ends
up right after the end of the memseg lists.
On Linux, the PCI bus maps device BARs in the primary process starting
at the end of the memseg lists (pci_find_max_end_va()), using it as an
address hint. This address is now taken by the fbarray, so the hint is
not honored and the kernel places the first BAR elsewhere in the mmap
area, among the shared libraries and thread stacks.
With VFIO, secondary processes map BARs at the addresses chosen by the
primary process, using MAP_FIXED, which replaces any existing mapping.
As the mmap area layout is randomized for each process (ASLR), the BAR
can overlap the secondary process' own libraries or stacks, which are
then replaced. This intermittently crashes secondary processes during
EAL init, for example dpdk-proc-info. On arm64 with 64K pages, this
was seen in about one in ten secondary process starts.
Create the memseg lists before reserving the VA space, so that, as
before that change, nothing is mapped right after the memseg lists and
the BARs can be placed there again. The VA space is still reserved in
one go.
Also destroy the memseg lists created so far if a later step fails,
since their fbarrays now exist before the VA space is reserved.
Fixes: 3368bc8600e8 ("mem: allocate all VA space in one go")
Cc: [email protected]
Signed-off-by: Aarnav JP <[email protected]>
---
lib/eal/common/eal_common_dynmem.c | 46 +++++++++++++++++++++---------
1 file changed, 33 insertions(+), 13 deletions(-)
diff --git a/lib/eal/common/eal_common_dynmem.c
b/lib/eal/common/eal_common_dynmem.c
index 868d274dc0..800f1c63c6 100644
--- a/lib/eal/common/eal_common_dynmem.c
+++ b/lib/eal/common/eal_common_dynmem.c
@@ -29,7 +29,7 @@ eal_dynmem_memseg_lists_init(void)
size_t mem_sz;
size_t va_offset;
} memtypes[RTE_MAX_MEMSEG_LISTS] = {0};
- int i, hpi_idx, msl_idx, ret = -1; /* fail unless told to succeed */
+ int i, hpi_idx, msl_idx, n_msl = 0, ret = -1; /* fail unless told to
succeed */
struct rte_memseg_list *msl;
size_t mem_va_len, mem_va_page_sz;
unsigned int n_memtypes, cur_type;
@@ -132,6 +132,31 @@ eal_dynmem_memseg_lists_init(void)
goto out;
}
+ /*
+ * Create the segment lists (and their fbarrays) before reserving the
+ * VA space, so that nothing is mapped right after the VA space. PCI
+ * BAR mapping uses the end of the VA space as its address hint.
+ */
+ msl_idx = 0;
+ for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
+ struct memtype *type = &memtypes[cur_type];
+
+ /* skip page sizes with zero memory limit */
+ if (type->n_segs == 0)
+ continue;
+
+ EAL_LOG(DEBUG, "Creating segment list: n_segs:%u socket_id:%i
hugepage_sz:%" PRIu64,
+ type->n_segs, type->socket_id, type->page_sz);
+
+ msl = &mcfg->memsegs[msl_idx];
+
+ if (eal_memseg_list_init(msl, type->page_sz, type->n_segs,
+ type->socket_id, msl_idx, true))
+ goto out;
+ msl_idx++;
+ n_msl = msl_idx;
+ }
+
mem_va_addr = eal_get_virtual_area(NULL, &mem_va_len,
mem_va_page_sz, 0, 0);
if (mem_va_addr == NULL) {
@@ -139,28 +164,17 @@ eal_dynmem_memseg_lists_init(void)
goto out;
}
- /* go through all mem types and create segment lists */
+ /* go through all mem types and assign VA space to segment lists */
msl_idx = 0;
for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
struct memtype *type = &memtypes[cur_type];
- uint64_t pagesz;
- int socket_id;
/* skip page sizes with zero memory limit */
if (type->n_segs == 0)
continue;
- pagesz = type->page_sz;
- socket_id = type->socket_id;
-
- EAL_LOG(DEBUG, "Creating segment list: n_segs:%u socket_id:%i
hugepage_sz:%" PRIu64,
- type->n_segs, socket_id, pagesz);
-
msl = &mcfg->memsegs[msl_idx];
- if (eal_memseg_list_init(msl, pagesz, type->n_segs, socket_id,
msl_idx, true))
- goto out;
-
if (eal_memseg_list_assign(msl,
RTE_PTR_ADD(mem_va_addr, type->va_offset))) {
EAL_LOG(ERR, "Cannot assign VA space for memseg list");
@@ -172,6 +186,12 @@ eal_dynmem_memseg_lists_init(void)
ret = 0;
out:
if (ret != 0) {
+ /* destroy the segment lists created so far */
+ for (i = 0; i < n_msl; i++) {
+ msl = &mcfg->memsegs[i];
+ rte_fbarray_destroy(&msl->memseg_arr);
+ memset(msl, 0, sizeof(*msl));
+ }
if (mem_va_addr != NULL)
eal_mem_free(mem_va_addr, mem_va_len);
} else {
--
2.43.0
