@@ -247,3 +247,9 @@ uint64_t get_max_ram_size(void)
{
return max_ram_size;
}
+
+uint64_t sclp_get_stsi_mnest(void)
+{
+ assert(read_info);
+ return read_info->stsi_parm;
+}
@@ -150,7 +150,8 @@ typedef struct ReadInfo {
SCCBHeader h;
uint16_t rnmax;
uint8_t rnsize;
- uint8_t _reserved1[16 - 11]; /* 11-15 */
+ uint8_t _reserved1[15 - 11]; /* 11-14 */
+ uint8_t stsi_parm; /* 15-15 */
uint16_t entries_cpu; /* 16-17 */
uint16_t offset_cpu; /* 18-19 */
uint8_t _reserved2[24 - 20]; /* 20-23 */
@@ -341,5 +342,6 @@ int sclp_service_call(unsigned int command, void *sccb);
void sclp_memory_setup(void);
uint64_t get_ram_size(void);
uint64_t get_max_ram_size(void);
+uint64_t sclp_get_stsi_mnest(void);
#endif /* _S390X_SCLP_H_ */
@@ -29,4 +29,40 @@ struct sysinfo_3_2_2 {
uint8_t ext_names[8][256];
};
+#define CPUS_TLE_RES_BITS 0x00fffffff8000000UL
+struct topology_core {
+ uint8_t nl;
+ uint8_t reserved1[3];
+ uint8_t reserved4:5;
+ uint8_t d:1;
+ uint8_t pp:2;
+ uint8_t type;
+ uint16_t origin;
+ uint64_t mask;
+};
+
+#define CONTAINER_TLE_RES_BITS 0x00ffffffffffff00UL
+struct topology_container {
+ uint8_t nl;
+ uint8_t reserved[6];
+ uint8_t id;
+};
+
+union topology_entry {
+ uint8_t nl;
+ struct topology_core cpu;
+ struct topology_container container;
+};
+
+#define CPU_TOPOLOGY_MAX_LEVEL 6
+struct sysinfo_15_1_x {
+ uint8_t reserved0[2];
+ uint16_t length;
+ uint8_t mag[CPU_TOPOLOGY_MAX_LEVEL];
+ uint8_t reserved0a;
+ uint8_t mnest;
+ uint8_t reserved0c[4];
+ union topology_entry tle[];
+};
+
#endif /* _S390X_STSI_H_ */
@@ -17,6 +17,20 @@
#include <smp.h>
#include <sclp.h>
#include <s390x/hardware.h>
+#include <s390x/stsi.h>
+
+static uint8_t pagebuf[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+
+static int max_nested_lvl;
+static int number_of_cpus;
+static int cpus_in_masks;
+static int max_cpus;
+
+/*
+ * Topology level as defined by architecture, all levels exists with
+ * a single container unless overwritten by the QEMU -smp parameter.
+ */
+static int expected_topo_lvl[CPU_TOPOLOGY_MAX_LEVEL] = { 1, 1, 1, 1, 1, 1 };
#define PTF_REQ_HORIZONTAL 0
#define PTF_REQ_VERTICAL 1
@@ -157,11 +171,321 @@ static void test_ptf(void)
check_polarization_change();
}
+/*
+ * stsi_check_maxcpus
+ * @info: Pointer to the stsi information
+ *
+ * The product of the numbers of containers per level
+ * is the maximum number of CPU allowed by the machine.
+ */
+static void stsi_check_maxcpus(struct sysinfo_15_1_x *info)
+{
+ int n, i;
+
+ for (i = 0, n = 1; i < CPU_TOPOLOGY_MAX_LEVEL; i++)
+ n *= info->mag[i] ?: 1;
+
+ report(n == max_cpus, "Calculated max CPUs: %d", n);
+}
+
+/*
+ * stsi_check_mag
+ * @info: Pointer to the stsi information
+ *
+ * MAG field should match the architecture defined containers
+ * when MNEST as returned by SCLP matches MNEST of the SYSIB.
+ */
+static void stsi_check_mag(struct sysinfo_15_1_x *info)
+{
+ int i;
+
+ report_prefix_push("MAG");
+
+ stsi_check_maxcpus(info);
+
+ /*
+ * It is not clear how the MAG fields are calculated when mnest
+ * in the SYSIB 15.x is different from the maximum nested level
+ * in the SCLP info, so we skip here for now.
+ */
+ if (max_nested_lvl != info->mnest) {
+ report_skip("No specification on layer aggregation");
+ goto done;
+ }
+
+ /*
+ * MAG up to max_nested_lvl must match the architecture
+ * defined containers.
+ */
+ for (i = 0; i < max_nested_lvl; i++)
+ report(info->mag[CPU_TOPOLOGY_MAX_LEVEL - i - 1] == expected_topo_lvl[i],
+ "MAG %d field match %d == %d",
+ i + 1,
+ info->mag[CPU_TOPOLOGY_MAX_LEVEL - i - 1],
+ expected_topo_lvl[i]);
+
+ /* Above max_nested_lvl the MAG field must be null */
+ for (; i < CPU_TOPOLOGY_MAX_LEVEL; i++)
+ report(info->mag[CPU_TOPOLOGY_MAX_LEVEL - i - 1] == 0,
+ "MAG %d field match %d == %d", i + 1,
+ info->mag[CPU_TOPOLOGY_MAX_LEVEL - i - 1], 0);
+
+done:
+ report_prefix_pop();
+}
+
+/**
+ * check_tle:
+ * @tc: pointer to first TLE
+ *
+ * Recursively check the containers TLEs until we
+ * find a CPU TLE.
+ */
+static uint8_t *check_tle(void *tc)
+{
+ struct topology_container *container = tc;
+ struct topology_core *cpus;
+ int n;
+
+ if (container->nl) {
+ report_info("NL: %d id: %d", container->nl, container->id);
+
+ report(!(*(uint64_t *)tc & CONTAINER_TLE_RES_BITS),
+ "reserved bits %016lx",
+ *(uint64_t *)tc & CONTAINER_TLE_RES_BITS);
+
+ return check_tle(tc + sizeof(*container));
+ }
+
+ report_info("NL: %d", container->nl);
+ cpus = tc;
+
+ report(!(*(uint64_t *)tc & CPUS_TLE_RES_BITS), "reserved bits %016lx",
+ *(uint64_t *)tc & CPUS_TLE_RES_BITS);
+
+ report(cpus->type == 0x03, "type IFL");
+
+ report_info("origin: %d", cpus->origin);
+ report_info("mask: %016lx", cpus->mask);
+ report_info("dedicated: %d entitlement: %d", cpus->d, cpus->pp);
+
+ n = __builtin_popcountl(cpus->mask);
+ report(n <= expected_topo_lvl[0], "CPUs per mask: %d out of max %d",
+ n, expected_topo_lvl[0]);
+ cpus_in_masks += n;
+
+ if (!cpus->d)
+ report_skip("Not dedicated");
+ else
+ report(cpus->pp == 3 || cpus->pp == 0, "Dedicated CPUs are either vertically polarized or have high entitlement");
+
+ return tc + sizeof(*cpus);
+}
+
+/**
+ * stsi_check_tle_coherency:
+ * @info: Pointer to the stsi information
+ *
+ * We verify that we get the expected number of Topology List Entry
+ * containers for a specific level.
+ */
+static void stsi_check_tle_coherency(struct sysinfo_15_1_x *info)
+{
+ void *tc, *end;
+
+ report_prefix_push("TLE");
+ cpus_in_masks = 0;
+
+ tc = info->tle;
+ end = (void *)info + info->length;
+
+ while (tc < end)
+ tc = check_tle(tc);
+
+ report(cpus_in_masks == number_of_cpus, "CPUs in mask %d",
+ cpus_in_masks);
+
+ report_prefix_pop();
+}
+
+/**
+ * stsi_get_sysib:
+ * @info: pointer to the STSI info structure
+ * @sel2: the selector giving the topology level to check
+ *
+ * Fill the sysinfo_15_1_x info structure and check the
+ * SYSIB header.
+ *
+ * Returns instruction validity.
+ */
+static int stsi_get_sysib(struct sysinfo_15_1_x *info, int sel2)
+{
+ int ret;
+
+ report_prefix_pushf("SYSIB");
+
+ ret = stsi(pagebuf, 15, 1, sel2);
+
+ if (max_nested_lvl >= sel2) {
+ report(!ret, "Valid instruction");
+ report(sel2 == info->mnest, "Valid mnest");
+ } else {
+ report(ret, "Invalid instruction");
+ }
+
+ report_prefix_pop();
+
+ return ret;
+}
+
+/**
+ * check_sysinfo_15_1_x:
+ * @info: pointer to the STSI info structure
+ * @sel2: the selector giving the topology level to check
+ *
+ * Check if the validity of the STSI instruction and then
+ * calls specific checks on the information buffer.
+ */
+static void check_sysinfo_15_1_x(struct sysinfo_15_1_x *info, int sel2)
+{
+ int ret;
+ int cc;
+ unsigned long rc;
+
+ report_prefix_pushf("15_1_%d", sel2);
+
+ ret = stsi_get_sysib(info, sel2);
+ if (ret) {
+ report_skip("Selector 2 not supported by architecture");
+ goto end;
+ }
+
+ report_prefix_pushf("H");
+ cc = ptf(PTF_REQ_HORIZONTAL, &rc);
+ if (cc != 0 && rc != PTF_ERR_ALRDY_POLARIZED) {
+ report_fail("Unable to set horizontal polarization");
+ goto vertical;
+ }
+
+ stsi_check_mag(info);
+ stsi_check_tle_coherency(info);
+
+vertical:
+ report_prefix_pop();
+ report_prefix_pushf("V");
+
+ cc = ptf(PTF_REQ_VERTICAL, &rc);
+ if (cc != 0 && rc != PTF_ERR_ALRDY_POLARIZED) {
+ report_fail("Unable to set vertical polarization");
+ goto end;
+ }
+
+ stsi_check_mag(info);
+ stsi_check_tle_coherency(info);
+ report_prefix_pop();
+
+end:
+ report_prefix_pop();
+}
+
+/*
+ * The Maximum Nested level is given by SCLP READ_SCP_INFO if the MNEST facility
+ * is available.
+ * If the MNEST facility is not available, sclp_get_stsi_mnest returns 0 and the
+ * Maximum Nested level is 2
+ */
+#define S390_DEFAULT_MNEST 2
+static int sclp_get_mnest(void)
+{
+ return sclp_get_stsi_mnest() ?: S390_DEFAULT_MNEST;
+}
+
+static int expected_num_cpus(void)
+{
+ int i;
+ int ncpus = 1;
+
+ for (i = 0; i < CPU_TOPOLOGY_MAX_LEVEL; i++)
+ ncpus *= expected_topo_lvl[i] ?: 1;
+
+ return ncpus;
+}
+
+/**
+ * test_stsi:
+ *
+ * Retrieves the maximum nested topology level supported by the architecture
+ * and the number of CPUs.
+ * Calls the checking for the STSI instruction in sel2 reverse level order
+ * from 6 (CPU_TOPOLOGY_MAX_LEVEL) to 2 to have the most interesting level,
+ * the one triggering a topology-change-report-pending condition, level 2,
+ * at the end of the report.
+ *
+ */
+static void test_stsi(void)
+{
+ int sel2;
+
+ max_cpus = expected_num_cpus();
+ report_info("Architecture max CPUs: %d", max_cpus);
+
+ max_nested_lvl = sclp_get_mnest();
+ report_info("SCLP maximum nested level : %d", max_nested_lvl);
+
+ number_of_cpus = sclp_get_cpu_num();
+ report_info("SCLP number of CPU: %d", number_of_cpus);
+
+ /* STSI selector 2 can takes values between 2 and 6 */
+ for (sel2 = 6; sel2 >= 2; sel2--)
+ check_sysinfo_15_1_x((struct sysinfo_15_1_x *)pagebuf, sel2);
+}
+
+/**
+ * parse_topology_args:
+ * @argc: number of arguments
+ * @argv: argument array
+ *
+ * This function initialize the architecture topology levels
+ * which should be the same as the one provided by the hypervisor.
+ *
+ * We use the current names found in IBM/Z literature, Linux and QEMU:
+ * cores, sockets/packages, books, drawers and nodes to facilitate the
+ * human machine interface but store the result in a machine abstract
+ * array of architecture topology levels.
+ * Note that when QEMU uses socket as a name for the topology level 1
+ * Linux uses package or physical_package.
+ */
+static void parse_topology_args(int argc, char **argv)
+{
+ int i;
+ static const char * const levels[] = { "cores", "sockets",
+ "books", "drawers" };
+
+ for (i = 1; i < argc; i++) {
+ char *flag = argv[i];
+ int level;
+
+ if (flag[0] != '-')
+ report_abort("Argument is expected to begin with '-'");
+ flag++;
+ for (level = 0; ARRAY_SIZE(levels); level++) {
+ if (!strcmp(levels[level], flag))
+ break;
+ }
+ if (level == ARRAY_SIZE(levels))
+ report_abort("Unknown parameter %s", flag);
+
+ expected_topo_lvl[level] = atol(argv[++i]);
+ report_info("%s: %d", levels[level], expected_topo_lvl[level]);
+ }
+}
+
static struct {
const char *name;
void (*func)(void);
} tests[] = {
{ "PTF", test_ptf },
+ { "STSI", test_stsi },
{ NULL, NULL }
};
@@ -171,6 +495,8 @@ int main(int argc, char *argv[])
report_prefix_push("CPU Topology");
+ parse_topology_args(argc, argv);
+
if (!test_facility(11)) {
report_skip("Topology facility not present");
goto end;
@@ -221,3 +221,7 @@ file = ex.elf
[topology]
file = topology.elf
+
+[topology-2]
+file = topology.elf
+extra_params = -cpu max,ctop=on -smp sockets=31,cores=8,maxcpus=248 -append '-sockets 31 -cores 8'
STSI with function code 15 is used to store the CPU configuration topology. We retrieve the maximum nested level with SCLP and use the topology tree provided by sockets and cores only to stay compatible with qemu topology before topology extension with drawers and books. arguments. We check : - if the topology stored is coherent between the QEMU -smp parameters and kernel parameters. - the number of CPUs - the maximum number of CPUs - the number of containers of each levels for every STSI(15.1.x) instruction allowed by the machine. Signed-off-by: Pierre Morel <pmorel@linux.ibm.com> --- lib/s390x/sclp.c | 6 + lib/s390x/sclp.h | 4 +- lib/s390x/stsi.h | 36 +++++ s390x/topology.c | 326 ++++++++++++++++++++++++++++++++++++++++++++ s390x/unittests.cfg | 4 + 5 files changed, 375 insertions(+), 1 deletion(-)