Skip to contentSkip to conversation

KVM: selftests: Allow specify physical cpu list in demand paging test

PATCH In review Sean Christopherson 2 participants 3 messages Jun 7, 2023

Subsystems (2)
lore
Share & tools
lore

Sean Christopherson

author reviewer
#0 lore raw

PATCH v3 1/1 KVM: selftests: Allow specify physical cpu list in demand paging test

From: Peter Xu <[email protected]>

Mimic the dirty log test and allow the user to pin demand paging test tasks to physical CPUs.

Put the help message into a general helper as suggested by Sean.

[sean: rebase, tweak arg ordering, add "print" to helper, print program name]
---
 .../testing/selftests/kvm/demand_paging_test.c  | 15 +++++++++++++--
 .../testing/selftests/kvm/dirty_log_perf_test.c | 12 +-----------
 .../selftests/kvm/include/kvm_util_base.h       |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c      | 17 +++++++++++++++++
 4 files changed, 32 insertions(+), 13 deletions(-)
tools/testing/selftests/kvm/demand_paging_test.c +13 -2
index 9c18686b4f63..09c116a82a84 100644
@@ -208,10 +208,11 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-s type] [-v vcpus] [-o]\n", name);
+	       "          [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
 	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\n");
+	kvm_print_vcpu_pinning_help();
 	printf(" -d: add a delay in usec to the User Fault\n"
 	       "     FD handler to simulate demand paging\n"
 	       "     overheads. Ignored without -u.\n");
@@ -229,6 +230,7 @@ static void help(char *name)
 int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	const char *cpulist = NULL;
 	struct test_params p = {
 		.src_type = DEFAULT_VM_MEM_SRC,
 		.partition_vcpu_memory_access = true,
@@ -237,7 +239,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -264,6 +266,9 @@ int main(int argc, char *argv[])
 			TEST_ASSERT(nr_vcpus <= max_vcpus,
 				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
+		case 'c':
+			cpulist = optarg;
+			break;
 		case 'o':
 			p.partition_vcpu_memory_access = false;
 			break;
@@ -279,6 +284,12 @@ int main(int argc, char *argv[])
 		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s");
 	}
 
+	if (cpulist) {
+		kvm_parse_vcpu_pinning(cpulist, memstress_args.vcpu_to_pcpu,
+				       nr_vcpus);
+		memstress_args.pin_vcpus = true;
+	}
+
 	for_each_guest_mode(run_test, &p);
 
 	return 0;
tools/testing/selftests/kvm/dirty_log_perf_test.c +1 -11
index 416719e20518..d374dbcf9a53 100644
@@ -332,17 +332,7 @@ static void help(char *name)
 	       "     so -w X means each page has an X%% chance of writing\n"
 	       "     and a (100-X)%% chance of reading.\n"
 	       "     (default: 100 i.e. all pages are written to.)\n");
-	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
-	       "     values (target pCPU), one for each vCPU, plus an optional\n"
-	       "     entry for the main application task (specified via entry\n"
-	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
-	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
-	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
-	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
-	       "         ./dirty_log_perf_test -v 3 -c 22,23,24,50\n\n"
-	       "     To leave the application task unpinned, drop the final entry:\n\n"
-	       "         ./dirty_log_perf_test -v 3 -c 22,23,24\n\n"
-	       "     (default: no pinning)\n");
+	kvm_print_vcpu_pinning_help();
 	puts("");
 	exit(0);
 }
tools/testing/selftests/kvm/include/kvm_util_base.h +1 -0
index a089c356f354..07732a157ccd 100644
@@ -733,6 +733,7 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
 
 void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
+void kvm_print_vcpu_pinning_help(void);
 void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 			    int nr_vcpus);
 
tools/testing/selftests/kvm/lib/kvm_util.c +17 -0
index 298c4372fb1a..9741a7ff6380 100644
@@ -494,6 +494,23 @@ static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
 	return pcpu;
 }
 
+void kvm_print_vcpu_pinning_help(void)
+{
+	const char *name = program_invocation_name;
+
+	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
+	       "     values (target pCPU), one for each vCPU, plus an optional\n"
+	       "     entry for the main application task (specified via entry\n"
+	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
+	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
+	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
+	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
+	       "         %s -v 3 -c 22,23,24,50\n\n"
+	       "     To leave the application task unpinned, drop the final entry:\n\n"
+	       "         %s -v 3 -c 22,23,24\n\n"
+	       "     (default: no pinning)\n", name, name);
+}
+
 void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 			    int nr_vcpus)
 {

base-commit: dfa78a20cc879205b2c6239300dac09907ad3da1

Signature · 1 line
2.41.0.162.gfafddb0af9-goog
author reviewer
#1 lore raw
Quoted 6 lines · Sean Christopherson

Mimic the dirty log test and allow the user to pin demand paging test tasks to physical CPUs.

Put the help message into a general helper as suggested by Sean.

Somewhat speculatively applied to kvm-x86 selftests, as I'm OOO later this week and want to get this into linux-next before I go offline. Holler if you don't like the end result.

Thanks!

[1/1] KVM: selftests: Allow specify physical cpu list in demand paging test

      https://github.com/kvm-x86/linux/commit/d4ec586c60ab

--
https://github.com/kvm-x86/linux/tree/next
https://github.com/kvm-x86/linux/tree/fixes

#2 lore raw
In reply to Sean Christopherson
Quoted 11 lines · Sean Christopherson

From: Peter Xu <[email protected]>

Mimic the dirty log test and allow the user to pin demand paging test tasks to physical CPUs.

Put the help message into a general helper as suggested by Sean.

[sean: rebase, tweak arg ordering, add "print" to helper, print program name]

Thanks, Sean!

Signature · 1 line
Peter Xu