[PATCH v2] irqchip: gic-v3: Extend collection table

From: wangwudi
Date: Wed Jun 07 2023 - 05:50:39 EST


Only single level table is supported to the collection table, and only
one page is allocated.

Extend collection table to support more CPUs:
1. Recalculate the page number of collection table based on the number of
CPUs.
2. Add 2 level tables to collection table.
3. Add GITS_TYPER_CIDBITS macros.

It is noticed in an internal simulation research:
- the page_size of collection table is 4 KB
- the entry_size of collection table is 16 Byte
- with 512 CPUs

Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Marc Zyngier <maz@xxxxxxxxxx>
Signed-off-by: wangwudi <wangwudi@xxxxxxxxxxxxx>
---

ChangeLog:
v1-->v2:
1. Support 2 level table
2. Rewrite the commit log

drivers/irqchip/irq-gic-v3-its.c | 62 ++++++++++++++++++++++++++++++--------
include/linux/irqchip/arm-gic-v3.h | 3 ++
2 files changed, 53 insertions(+), 12 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 0ec2b1e1df75..573ef26ad449 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -126,6 +126,7 @@ struct its_node {
#define is_v4(its) (!!((its)->typer & GITS_TYPER_VLPIS))
#define is_v4_1(its) (!!((its)->typer & GITS_TYPER_VMAPP))
#define device_ids(its) (FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
+#define collection_ids(its) (FIELD_GET(GITS_TYPER_CIDBITS, (its)->typer) + 1)

#define ITS_ITT_ALIGN SZ_256

@@ -2626,6 +2627,10 @@ static int its_alloc_tables(struct its_node *its)
indirect = its_parse_indirect_baser(its, baser, &order,
ITS_MAX_VPEID_BITS);
break;
+ case GITS_BASER_TYPE_COLLECTION:
+ indirect = its_parse_indirect_baser(its, baser, &order,
+ order_base_2(num_possible_cpus()));
+ break;
}

err = its_setup_baser(its, baser, cache, shr, order, indirect);
@@ -3230,18 +3235,6 @@ static void its_cpu_init_collection(struct its_node *its)
its_send_invall(its, &its->collections[cpu]);
}

-static void its_cpu_init_collections(void)
-{
- struct its_node *its;
-
- raw_spin_lock(&its_lock);
-
- list_for_each_entry(its, &its_nodes, entry)
- its_cpu_init_collection(its);
-
- raw_spin_unlock(&its_lock);
-}
-
static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
{
struct its_device *its_dev = NULL, *tmp;
@@ -3316,6 +3309,51 @@ static bool its_alloc_table_entry(struct its_node *its,
return true;
}

+static bool its_alloc_collection_table(struct its_node *its, struct its_baser *baser)
+{
+ int cpu = smp_processor_id();
+ int cpu_ids = 16;
+
+ if (its->typer & GITS_TYPER_CIL)
+ cpu_ids = collection_ids(its);
+
+ if (!(ilog2(cpu) < cpu_ids)) {
+ pr_warn("ITS: CPU%d out of Collection ID range for %dbits", cpu, cpu_ids);
+ return false;
+ }
+
+ if (!its_alloc_table_entry(its, baser, cpu)) {
+ pr_warn("ITS: CPU%d failed to allocate collection l2 table", cpu);
+ return false;
+ }
+
+ return true;
+}
+
+static bool its_cpu_init_collections(void)
+{
+ struct its_node *its;
+ struct its_baser *baser;
+
+ raw_spin_lock(&its_lock);
+
+ list_for_each_entry(its, &its_nodes, entry) {
+ baser = its_get_baser(its, GITS_BASER_TYPE_COLLECTION);
+ if (!baser) {
+ raw_spin_unlock(&its_lock);
+ return false;
+ }
+
+ if (!its_alloc_collection_table(its, baser)) {
+ raw_spin_unlock(&its_lock);
+ return false;
+ }
+ its_cpu_init_collection(its);
+ }
+ raw_spin_unlock(&its_lock);
+ return true;
+}
+
static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
{
struct its_baser *baser;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 728691365464..35e83da8961f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -400,6 +400,9 @@
#define GITS_TYPER_PTA (1UL << 19)
#define GITS_TYPER_HCC_SHIFT 24
#define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)
+#define GITS_TYPER_CIDBITS_SHIFT 32
+#define GITS_TYPER_CIDBITS GENMASK_ULL(35, 32)
+#define GITS_TYPER_CIL (1ULL << 36)
#define GITS_TYPER_VMOVP (1ULL << 37)
#define GITS_TYPER_VMAPP (1ULL << 40)
#define GITS_TYPER_SVPET GENMASK_ULL(42, 41)
--
2.7.4