From: David Gibson <david@gibson.dropbear.id.au>
To: peter.maydell@linaro.org
Cc: Daniel Henrique Barboza <danielhb413@gmail.com>,
mark.cave-ayland@ilande.co.uk, qemu-devel@nongnu.org,
groug@kaod.org, hpoussin@reactos.org, clg@kaod.org,
qemu-ppc@nongnu.org, philmd@redhat.com,
David Gibson <david@gibson.dropbear.id.au>
Subject: [PULL 27/44] spapr_numa.c: parametrize FORM1 macros
Date: Thu, 30 Sep 2021 15:44:09 +1000 [thread overview]
Message-ID: <20210930054426.357344-28-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20210930054426.357344-1-david@gibson.dropbear.id.au>
From: Daniel Henrique Barboza <danielhb413@gmail.com>
The next preliminary step to introduce NUMA FORM2 affinity is to make
the existing code independent of FORM1 macros and values, i.e.
MAX_DISTANCE_REF_POINTS, NUMA_ASSOC_SIZE and VCPU_ASSOC_SIZE. This patch
accomplishes that by doing the following:
- move the NUMA related macros from spapr.h to spapr_numa.c where they
are used. spapr.h gets instead a 'NUMA_NODES_MAX_NUM' macro that is used
to refer to the maximum number of NUMA nodes, including GPU nodes, that
the machine can support;
- MAX_DISTANCE_REF_POINTS and NUMA_ASSOC_SIZE are renamed to
FORM1_DIST_REF_POINTS and FORM1_NUMA_ASSOC_SIZE. These FORM1 specific
macros are used in FORM1 init functions;
- code that uses MAX_DISTANCE_REF_POINTS now retrieves the
max_dist_ref_points value using get_max_dist_ref_points().
NUMA_ASSOC_SIZE is replaced by get_numa_assoc_size() and VCPU_ASSOC_SIZE
is replaced by get_vcpu_assoc_size(). These functions are used by the
generic device tree functions and h_home_node_associativity() and will
allow them to switch between FORM1 and FORM2 without changing their core
logic.
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20210920174947.556324-4-danielhb413@gmail.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
hw/ppc/spapr_numa.c | 74 ++++++++++++++++++++++++++++++------------
include/hw/ppc/spapr.h | 28 ++++++++--------
2 files changed, 67 insertions(+), 35 deletions(-)
diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c
index bf520d42b2..08e2d6aed8 100644
--- a/hw/ppc/spapr_numa.c
+++ b/hw/ppc/spapr_numa.c
@@ -19,6 +19,33 @@
/* Moved from hw/ppc/spapr_pci_nvlink2.c */
#define SPAPR_GPU_NUMA_ID (cpu_to_be32(1))
+/*
+ * Retrieves max_dist_ref_points of the current NUMA affinity.
+ */
+static int get_max_dist_ref_points(SpaprMachineState *spapr)
+{
+ return FORM1_DIST_REF_POINTS;
+}
+
+/*
+ * Retrieves numa_assoc_size of the current NUMA affinity.
+ */
+static int get_numa_assoc_size(SpaprMachineState *spapr)
+{
+ return FORM1_NUMA_ASSOC_SIZE;
+}
+
+/*
+ * Retrieves vcpu_assoc_size of the current NUMA affinity.
+ *
+ * vcpu_assoc_size is the size of ibm,associativity array
+ * for CPUs, which has an extra element (vcpu_id) in the end.
+ */
+static int get_vcpu_assoc_size(SpaprMachineState *spapr)
+{
+ return get_numa_assoc_size(spapr) + 1;
+}
+
static bool spapr_numa_is_symmetrical(MachineState *ms)
{
int src, dst;
@@ -96,7 +123,7 @@ static void spapr_numa_define_FORM1_domains(SpaprMachineState *spapr)
* considered a match with associativity domains of node 0.
*/
for (i = 1; i < nb_numa_nodes; i++) {
- for (j = 1; j < MAX_DISTANCE_REF_POINTS; j++) {
+ for (j = 1; j < FORM1_DIST_REF_POINTS; j++) {
spapr->numa_assoc_array[i][j] = cpu_to_be32(i);
}
}
@@ -134,7 +161,7 @@ static void spapr_numa_define_FORM1_domains(SpaprMachineState *spapr)
*
* The Linux kernel will assume that the distance between src and
* dst, in this case of no match, is 10 (local distance) doubled
- * for each NUMA it didn't match. We have MAX_DISTANCE_REF_POINTS
+ * for each NUMA it didn't match. We have FORM1_DIST_REF_POINTS
* levels (4), so this gives us 10*2*2*2*2 = 160.
*
* This logic can be seen in the Linux kernel source code, as of
@@ -169,7 +196,7 @@ static void spapr_numa_FORM1_affinity_init(SpaprMachineState *spapr,
/*
* For all associativity arrays: first position is the size,
- * position MAX_DISTANCE_REF_POINTS is always the numa_id,
+ * position FORM1_DIST_REF_POINTS is always the numa_id,
* represented by the index 'i'.
*
* This will break on sparse NUMA setups, when/if QEMU starts
@@ -177,8 +204,8 @@ static void spapr_numa_FORM1_affinity_init(SpaprMachineState *spapr,
* 'i' will be a valid node_id set by the user.
*/
for (i = 0; i < nb_numa_nodes; i++) {
- spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
- spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
+ spapr->numa_assoc_array[i][0] = cpu_to_be32(FORM1_DIST_REF_POINTS);
+ spapr->numa_assoc_array[i][FORM1_DIST_REF_POINTS] = cpu_to_be32(i);
}
/*
@@ -192,15 +219,15 @@ static void spapr_numa_FORM1_affinity_init(SpaprMachineState *spapr,
max_nodes_with_gpus = nb_numa_nodes + NVGPU_MAX_NUM;
for (i = nb_numa_nodes; i < max_nodes_with_gpus; i++) {
- spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
+ spapr->numa_assoc_array[i][0] = cpu_to_be32(FORM1_DIST_REF_POINTS);
- for (j = 1; j < MAX_DISTANCE_REF_POINTS; j++) {
+ for (j = 1; j < FORM1_DIST_REF_POINTS; j++) {
uint32_t gpu_assoc = smc->pre_5_1_assoc_refpoints ?
SPAPR_GPU_NUMA_ID : cpu_to_be32(i);
spapr->numa_assoc_array[i][j] = gpu_assoc;
}
- spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
+ spapr->numa_assoc_array[i][FORM1_DIST_REF_POINTS] = cpu_to_be32(i);
}
/*
@@ -234,13 +261,15 @@ void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
{
_FDT((fdt_setprop(fdt, offset, "ibm,associativity",
spapr->numa_assoc_array[nodeid],
- sizeof(spapr->numa_assoc_array[nodeid]))));
+ get_numa_assoc_size(spapr) * sizeof(uint32_t))));
}
static uint32_t *spapr_numa_get_vcpu_assoc(SpaprMachineState *spapr,
PowerPCCPU *cpu)
{
- uint32_t *vcpu_assoc = g_new(uint32_t, VCPU_ASSOC_SIZE);
+ int max_distance_ref_points = get_max_dist_ref_points(spapr);
+ int vcpu_assoc_size = get_vcpu_assoc_size(spapr);
+ uint32_t *vcpu_assoc = g_new(uint32_t, vcpu_assoc_size);
int index = spapr_get_vcpu_id(cpu);
/*
@@ -249,10 +278,10 @@ static uint32_t *spapr_numa_get_vcpu_assoc(SpaprMachineState *spapr,
* 0, put cpu_id last, then copy the remaining associativity
* domains.
*/
- vcpu_assoc[0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS + 1);
- vcpu_assoc[VCPU_ASSOC_SIZE - 1] = cpu_to_be32(index);
+ vcpu_assoc[0] = cpu_to_be32(max_distance_ref_points + 1);
+ vcpu_assoc[vcpu_assoc_size - 1] = cpu_to_be32(index);
memcpy(vcpu_assoc + 1, spapr->numa_assoc_array[cpu->node_id] + 1,
- (VCPU_ASSOC_SIZE - 2) * sizeof(uint32_t));
+ (vcpu_assoc_size - 2) * sizeof(uint32_t));
return vcpu_assoc;
}
@@ -261,12 +290,13 @@ int spapr_numa_fixup_cpu_dt(SpaprMachineState *spapr, void *fdt,
int offset, PowerPCCPU *cpu)
{
g_autofree uint32_t *vcpu_assoc = NULL;
+ int vcpu_assoc_size = get_vcpu_assoc_size(spapr);
vcpu_assoc = spapr_numa_get_vcpu_assoc(spapr, cpu);
/* Advertise NUMA via ibm,associativity */
return fdt_setprop(fdt, offset, "ibm,associativity", vcpu_assoc,
- VCPU_ASSOC_SIZE * sizeof(uint32_t));
+ vcpu_assoc_size * sizeof(uint32_t));
}
@@ -274,17 +304,18 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt,
int offset)
{
MachineState *machine = MACHINE(spapr);
+ int max_distance_ref_points = get_max_dist_ref_points(spapr);
int nb_numa_nodes = machine->numa_state->num_nodes;
int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
uint32_t *int_buf, *cur_index, buf_len;
int ret, i;
/* ibm,associativity-lookup-arrays */
- buf_len = (nr_nodes * MAX_DISTANCE_REF_POINTS + 2) * sizeof(uint32_t);
+ buf_len = (nr_nodes * max_distance_ref_points + 2) * sizeof(uint32_t);
cur_index = int_buf = g_malloc0(buf_len);
int_buf[0] = cpu_to_be32(nr_nodes);
/* Number of entries per associativity list */
- int_buf[1] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
+ int_buf[1] = cpu_to_be32(max_distance_ref_points);
cur_index += 2;
for (i = 0; i < nr_nodes; i++) {
/*
@@ -293,8 +324,8 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt,
*/
uint32_t *associativity = spapr->numa_assoc_array[i];
memcpy(cur_index, ++associativity,
- sizeof(uint32_t) * MAX_DISTANCE_REF_POINTS);
- cur_index += MAX_DISTANCE_REF_POINTS;
+ sizeof(uint32_t) * max_distance_ref_points);
+ cur_index += max_distance_ref_points;
}
ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf,
(cur_index - int_buf) * sizeof(uint32_t));
@@ -383,6 +414,7 @@ static target_ulong h_home_node_associativity(PowerPCCPU *cpu,
target_ulong procno = args[1];
PowerPCCPU *tcpu;
int idx, assoc_idx;
+ int vcpu_assoc_size = get_vcpu_assoc_size(spapr);
/* only support procno from H_REGISTER_VPA */
if (flags != 0x1) {
@@ -401,7 +433,7 @@ static target_ulong h_home_node_associativity(PowerPCCPU *cpu,
* 12 associativity domains for vcpus. Assert and bail if that's
* not the case.
*/
- G_STATIC_ASSERT((VCPU_ASSOC_SIZE - 1) <= 12);
+ g_assert((vcpu_assoc_size - 1) <= 12);
vcpu_assoc = spapr_numa_get_vcpu_assoc(spapr, tcpu);
/* assoc_idx starts at 1 to skip associativity size */
@@ -422,9 +454,9 @@ static target_ulong h_home_node_associativity(PowerPCCPU *cpu,
* macro. The ternary will fill the remaining registers with -1
* after we went through vcpu_assoc[].
*/
- a = assoc_idx < VCPU_ASSOC_SIZE ?
+ a = assoc_idx < vcpu_assoc_size ?
be32_to_cpu(vcpu_assoc[assoc_idx++]) : -1;
- b = assoc_idx < VCPU_ASSOC_SIZE ?
+ b = assoc_idx < vcpu_assoc_size ?
be32_to_cpu(vcpu_assoc[assoc_idx++]) : -1;
args[idx] = ASSOCIATIVITY(a, b);
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 637652ad16..814e087e98 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -100,23 +100,23 @@ typedef enum {
#define FDT_MAX_SIZE 0x200000
+/* Max number of GPUs per system */
+#define NVGPU_MAX_NUM 6
+
+/* Max number of NUMA nodes */
+#define NUMA_NODES_MAX_NUM (MAX_NODES + NVGPU_MAX_NUM)
+
/*
- * NUMA related macros. MAX_DISTANCE_REF_POINTS was taken
- * from Linux kernel arch/powerpc/mm/numa.h. It represents the
- * amount of associativity domains for non-CPU resources.
+ * NUMA FORM1 macros. FORM1_DIST_REF_POINTS was taken from
+ * MAX_DISTANCE_REF_POINTS in arch/powerpc/mm/numa.h from Linux
+ * kernel source. It represents the amount of associativity domains
+ * for non-CPU resources.
*
- * NUMA_ASSOC_SIZE is the base array size of an ibm,associativity
+ * FORM1_NUMA_ASSOC_SIZE is the base array size of an ibm,associativity
* array for any non-CPU resource.
- *
- * VCPU_ASSOC_SIZE represents the size of ibm,associativity array
- * for CPUs, which has an extra element (vcpu_id) in the end.
*/
-#define MAX_DISTANCE_REF_POINTS 4
-#define NUMA_ASSOC_SIZE (MAX_DISTANCE_REF_POINTS + 1)
-#define VCPU_ASSOC_SIZE (NUMA_ASSOC_SIZE + 1)
-
-/* Max number of these GPUsper a physical box */
-#define NVGPU_MAX_NUM 6
+#define FORM1_DIST_REF_POINTS 4
+#define FORM1_NUMA_ASSOC_SIZE (FORM1_DIST_REF_POINTS + 1)
typedef struct SpaprCapabilities SpaprCapabilities;
struct SpaprCapabilities {
@@ -249,7 +249,7 @@ struct SpaprMachineState {
unsigned gpu_numa_id;
SpaprTpmProxy *tpm_proxy;
- uint32_t numa_assoc_array[MAX_NODES + NVGPU_MAX_NUM][NUMA_ASSOC_SIZE];
+ uint32_t numa_assoc_array[NUMA_NODES_MAX_NUM][FORM1_NUMA_ASSOC_SIZE];
Error *fwnmi_migration_blocker;
};
--
2.31.1
next prev parent reply other threads:[~2021-09-30 6:14 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-30 5:43 [PULL 00/44] ppc-for-6.2 queue 20210930 David Gibson
2021-09-30 5:43 ` [PULL 01/44] host-utils: Fix overflow detection in divu128() David Gibson
2021-09-30 5:43 ` [PULL 02/44] host-utils: fix missing zero-extension in divs128 David Gibson
2021-09-30 5:43 ` [PULL 03/44] host-utils: introduce uabs64() David Gibson
2021-09-30 5:43 ` [PULL 04/44] i386/kvm: Replace abs64() with uabs64() from host-utils David Gibson
2021-09-30 5:43 ` [PULL 05/44] ppc/spapr: Add a POWER10 DD2 CPU David Gibson
2021-09-30 5:43 ` [PULL 06/44] ppc/pnv: Add a comment on the "primary-topology-index" property David Gibson
2021-09-30 5:43 ` [PULL 07/44] ppc/pnv: Remove useless variable David Gibson
2021-09-30 5:43 ` [PULL 08/44] ppc/xive: Export priority_to_ipb() helper David Gibson
2021-09-30 5:43 ` [PULL 09/44] ppc/xive: Export xive_tctx_word2() helper David Gibson
2021-09-30 5:43 ` [PULL 10/44] ppc/pnv: Rename "id" to "quad-id" in PnvQuad David Gibson
2021-09-30 5:43 ` [PULL 11/44] docs/system: ppc: Update the URL for OpenPOWER firmware images David Gibson
2021-09-30 5:43 ` [PULL 12/44] ppc/pnv: Add an assert when calculating the RAM distribution on chips David Gibson
2021-09-30 5:43 ` [PULL 13/44] target/ppc: fix setting of CR flags in bcdcfsq David Gibson
2021-09-30 5:43 ` [PULL 14/44] memory_hotplug.c: handle dev->id = NULL in acpi_memory_hotplug_write() David Gibson
2021-09-30 5:43 ` [PULL 15/44] spapr.c: handle dev->id in spapr_memory_unplug_rollback() David Gibson
2021-09-30 5:43 ` [PULL 16/44] spapr_drc.c: do not error_report() when drc->dev->id == NULL David Gibson
2021-09-30 5:43 ` [PULL 17/44] qapi/qdev.json: fix DEVICE_DELETED parameters doc David Gibson
2021-09-30 5:44 ` [PULL 18/44] qapi/qdev.json: add DEVICE_UNPLUG_GUEST_ERROR QAPI event David Gibson
2021-09-30 5:44 ` [PULL 19/44] spapr: use DEVICE_UNPLUG_GUEST_ERROR to report unplug errors David Gibson
2021-09-30 5:44 ` [PULL 20/44] memory_hotplug.c: send DEVICE_UNPLUG_GUEST_ERROR in acpi_memory_hotplug_write() David Gibson
2021-09-30 5:44 ` [PULL 21/44] target/ppc: Convert debug to trace events (exceptions) David Gibson
2021-09-30 5:44 ` [PULL 22/44] target/ppc: Replace debug messages by asserts for unknown IRQ pins David Gibson
2021-09-30 5:44 ` [PULL 23/44] target/ppc: add LPCR[HR] to DisasContext and hflags David Gibson
2021-09-30 5:44 ` [PULL 24/44] target/ppc: Check privilege level based on PSR and LPCR[HR] in tlbie[l] David Gibson
2021-09-30 5:44 ` [PULL 25/44] spapr_numa.c: split FORM1 code into helpers David Gibson
2021-09-30 5:44 ` [PULL 26/44] spapr_numa.c: scrap 'legacy_numa' concept David Gibson
2021-09-30 5:44 ` David Gibson [this message]
2021-09-30 5:44 ` [PULL 28/44] spapr_numa.c: rename numa_assoc_array to FORM1_assoc_array David Gibson
2021-09-30 5:44 ` [PULL 29/44] spapr: move FORM1 verifications to post CAS David Gibson
2021-09-30 5:44 ` [PULL 30/44] spapr_numa.c: FORM2 NUMA affinity support David Gibson
2021-09-30 5:44 ` [PULL 31/44] spapr_numa.c: handle auto NUMA node with no distance info David Gibson
2021-09-30 5:44 ` [PULL 32/44] target/ppc: Convert debug to trace events (decrementer and IRQ) David Gibson
2021-09-30 5:44 ` [PULL 33/44] target/ppc: Fix 64-bit decrementer David Gibson
2021-10-02 10:39 ` Peter Maydell
2021-10-04 6:54 ` Cédric Le Goater
2021-09-30 5:44 ` [PULL 34/44] hw/intc: openpic: Correct the reset value of IPIDR for FSL chipset David Gibson
2021-09-30 5:44 ` [PULL 35/44] hw/intc: openpic: Drop Raven related codes David Gibson
2021-09-30 5:44 ` [PULL 36/44] hw/intc: openpic: Clean up the styles David Gibson
2021-09-30 5:44 ` [PULL 37/44] spapr_numa.c: fixes in spapr_numa_FORM2_write_rtas_tables() David Gibson
2021-09-30 5:44 ` [PULL 38/44] spapr/xive: Fix kvm_xive_source_reset trace event David Gibson
2021-09-30 5:44 ` [PULL 39/44] MAINTAINERS: Remove machine specific files from ppc TCG CPUs entry David Gibson
2021-09-30 5:44 ` [PULL 40/44] MAINTAINERS: Remove David & Greg as reviewers for a number of boards David Gibson
2021-09-30 5:44 ` [PULL 41/44] MAINTAINERS: Orphan obscure ppc platforms David Gibson
2021-09-30 5:44 ` [PULL 42/44] MAINTAINERS: Remove David & Greg as reviewers/co-maintainers of powernv David Gibson
2021-09-30 5:44 ` [PULL 43/44] MAINTAINERS: Add information for OpenPIC David Gibson
2021-09-30 5:44 ` [PULL 44/44] MAINTAINERS: Demote sPAPR from "Supported" to "Maintained" David Gibson
2021-09-30 16:37 ` [PULL 00/44] ppc-for-6.2 queue 20210930 Peter Maydell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210930054426.357344-28-david@gibson.dropbear.id.au \
--to=david@gibson.dropbear.id.au \
--cc=clg@kaod.org \
--cc=danielhb413@gmail.com \
--cc=groug@kaod.org \
--cc=hpoussin@reactos.org \
--cc=mark.cave-ayland@ilande.co.uk \
--cc=peter.maydell@linaro.org \
--cc=philmd@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).