When current node doesn't have a EPC section configured by firmware and
all other EPC sections memory are used up, CPU can stuck inside the
while loop in __sgx_alloc_epc_page() forever and soft lockup will happen.
Note how nid_of_current will never equal to nid in that while loop because
nid_of_current is not set in sgx_numa_mask.
Also worth mentioning is that it's perfectly fine for firmware to not
seup an EPC section on a node. Setting an EPC section on each node can
be good for performance but that's not a requirement functionality wise.
Fixes: 901ddbb9ecf5 ("x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page()")
Reported-by: Zhimin Luo <zhimin.luo@xxxxxxxxx>
Tested-by: Zhimin Luo <zhimin.luo@xxxxxxxxx>
Signed-off-by: Aaron Lu <aaron.lu@xxxxxxxxx>
---
This issue is found by Zhimin when doing internal testing and no
external bug report has been sent out so there is no Closes: tag.
arch/x86/kernel/cpu/sgx/main.c | 27 ++++++++++++++-------------
1 file changed, 14 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 1a000acd933a..694fcf7a5e3a 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -475,24 +475,25 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void)
{
struct sgx_epc_page *page;
int nid_of_current = numa_node_id();
- int nid = nid_of_current;
+ int nid_start, nid;
- if (node_isset(nid_of_current, sgx_numa_mask)) {
- page = __sgx_alloc_epc_page_from_node(nid_of_current);
- if (page)
- return page;
- }
-
- /* Fall back to the non-local NUMA nodes: */
- while (true) {
- nid = next_node_in(nid, sgx_numa_mask);
- if (nid == nid_of_current)
- break;
+ /*
+ * Try local node first. If it doesn't have an EPC section,
+ * fall back to the non-local NUMA nodes.
+ */
+ if (node_isset(nid_of_current, sgx_numa_mask))
+ nid_start = nid_of_current;
+ else
+ nid_start = next_node_in(nid_of_current, sgx_numa_mask);
+ nid = nid_start;
+ do {
page = __sgx_alloc_epc_page_from_node(nid);
if (page)
return page;
- }
+
+ nid = next_node_in(nid, sgx_numa_mask);
+ } while (nid != nid_start);
return ERR_PTR(-ENOMEM);
}
base-commit: a85536e1bce722cb184abbac98068217874bdd6e
--
2.45.2
