linux-kernel - [PATCH] x86/sev: take NUMA node into account when allocating memory for per-CPU variables

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date: Fri, 12 Apr 2024 11:01:30 +0800
From: Li RongQing <lirongqing@...du.com>
To: tglx@...utronix.de,
	mingo@...hat.com,
	bp@...en8.de,
	dave.hansen@...ux.intel.com,
	x86@...nel.org,
	peterz@...radead.org,
	linux-kernel@...r.kernel.org
Cc: Li RongQing <lirongqing@...du.com>
Subject: [PATCH] x86/sev: take NUMA node into account when allocating memory for per-CPU variables

per-CPU variables are dominantly accessed from their own local CPUs,
so allocate them node-local to improve performance.

Signed-off-by: Li RongQing <lirongqing@...du.com>
---
 arch/x86/kernel/sev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 7e1e63cc..dfe7c69 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -938,7 +938,7 @@ static int snp_set_vmsa(void *va, bool vmsa)
 #define INIT_LDTR_ATTRIBS	(SVM_SELECTOR_P_MASK | 2)
 #define INIT_TR_ATTRIBS		(SVM_SELECTOR_P_MASK | 3)
 
-static void *snp_alloc_vmsa_page(void)
+static void *snp_alloc_vmsa_page(int cpu)
 {
 	struct page *p;
 
@@ -950,7 +950,7 @@ static void *snp_alloc_vmsa_page(void)
 	 *
 	 * Allocate an 8k page which is also 8k-aligned.
 	 */
-	p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+	p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
 	if (!p)
 		return NULL;
 
@@ -1019,7 +1019,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	 * #VMEXIT of that vCPU would wipe out all of the settings being done
 	 * here.
 	 */
-	vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page();
+	vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(cpu);
 	if (!vmsa)
 		return -ENOMEM;
 
@@ -1341,7 +1341,7 @@ static void __init alloc_runtime_data(int cpu)
 {
 	struct sev_es_runtime_data *data;
 
-	data = memblock_alloc(sizeof(*data), PAGE_SIZE);
+	data = memblock_alloc_node(sizeof(*data), PAGE_SIZE, cpu_to_node(cpu));
 	if (!data)
 		panic("Can't allocate SEV-ES runtime data");
 
-- 
2.9.4