u64 typer;
u64 cbaser_save;
u32 ctlr_save;
+ u32 mpidr;
struct list_head its_device_list;
u64 flags;
unsigned long list_nr;
};
#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 ITS_ITT_ALIGN SZ_256
return indirect;
}
+static u32 compute_common_aff(u64 val)
+{
+ u32 aff, clpiaff;
+
+ aff = FIELD_GET(GICR_TYPER_AFFINITY, val);
+ clpiaff = FIELD_GET(GICR_TYPER_COMMON_LPI_AFF, val);
+
+ return aff & ~(GENMASK(31, 0) >> (clpiaff * 8));
+}
+
+static u32 compute_its_aff(struct its_node *its)
+{
+ u64 val;
+ u32 svpet;
+
+ /*
+ * Reencode the ITS SVPET and MPIDR as a GICR_TYPER, and compute
+ * the resulting affinity. We then use that to see if this match
+ * our own affinity.
+ */
+ svpet = FIELD_GET(GITS_TYPER_SVPET, its->typer);
+ val = FIELD_PREP(GICR_TYPER_COMMON_LPI_AFF, svpet);
+ val |= FIELD_PREP(GICR_TYPER_AFFINITY, its->mpidr);
+ return compute_common_aff(val);
+}
+
+static struct its_node *find_sibling_its(struct its_node *cur_its)
+{
+ struct its_node *its;
+ u32 aff;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, cur_its->typer))
+ return NULL;
+
+ aff = compute_its_aff(cur_its);
+
+ list_for_each_entry(its, &its_nodes, entry) {
+ u64 baser;
+
+ if (!is_v4_1(its) || its == cur_its)
+ continue;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+ continue;
+
+ if (aff != compute_its_aff(its))
+ continue;
+
+ /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+ baser = its->tables[2].val;
+ if (!(baser & GITS_BASER_VALID))
+ continue;
+
+ return its;
+ }
+
+ return NULL;
+}
+
static void its_free_tables(struct its_node *its)
{
int i;
break;
case GITS_BASER_TYPE_VCPU:
+ if (is_v4_1(its)) {
+ struct its_node *sibling;
+
+ WARN_ON(i != 2);
+ if ((sibling = find_sibling_its(its))) {
+ *baser = sibling->tables[2];
+ its_write_baser(its, baser, baser->val);
+ continue;
+ }
+ }
+
indirect = its_parse_indirect_baser(its, baser,
psz, &order,
ITS_MAX_VPEID_BITS);
return 0;
}
+static u64 inherit_vpe_l1_table_from_its(void)
+{
+ struct its_node *its;
+ u64 val;
+ u32 aff;
+
+ val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+ aff = compute_common_aff(val);
+
+ list_for_each_entry(its, &its_nodes, entry) {
+ u64 baser, addr;
+
+ if (!is_v4_1(its))
+ continue;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+ continue;
+
+ if (aff != compute_its_aff(its))
+ continue;
+
+ /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+ baser = its->tables[2].val;
+ if (!(baser & GITS_BASER_VALID))
+ continue;
+
+ /* We have a winner! */
+ val = GICR_VPROPBASER_4_1_VALID;
+ if (baser & GITS_BASER_INDIRECT)
+ val |= GICR_VPROPBASER_4_1_INDIRECT;
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE,
+ FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser));
+ switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) {
+ case GIC_PAGE_SIZE_64K:
+ addr = GITS_BASER_ADDR_48_to_52(baser);
+ break;
+ default:
+ addr = baser & GENMASK_ULL(47, 12);
+ break;
+ }
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
+ val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+ FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+ val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+ FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
+
+ return val;
+ }
+
+ return 0;
+}
+
+static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
+{
+ u32 aff;
+ u64 val;
+ int cpu;
+
+ val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+ aff = compute_common_aff(val);
+
+ for_each_possible_cpu(cpu) {
+ void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+ u32 tmp;
+
+ if (!base || cpu == smp_processor_id())
+ continue;
+
+ val = gic_read_typer(base + GICR_TYPER);
+ tmp = compute_common_aff(val);
+ if (tmp != aff)
+ continue;
+
+ /*
+ * At this point, we have a victim. This particular CPU
+ * has already booted, and has an affinity that matches
+ * ours wrt CommonLPIAff. Let's use its own VPROPBASER.
+ * Make sure we don't write the Z bit in that case.
+ */
+ val = gits_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+ val &= ~GICR_VPROPBASER_4_1_Z;
+
+ *mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
+
+ return val;
+ }
+
+ return 0;
+}
+
+static int allocate_vpe_l1_table(void)
+{
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+ u64 val, gpsz, npg, pa;
+ unsigned int psz = SZ_64K;
+ unsigned int np, epp, esz;
+ struct page *page;
+
+ if (!gic_rdists->has_rvpeid)
+ return 0;
+
+ /*
+ * if VPENDBASER.Valid is set, disable any previously programmed
+ * VPE by setting PendingLast while clearing Valid. This has the
+ * effect of making sure no doorbell will be generated and we can
+ * then safely clear VPROPBASER.Valid.
+ */
+ if (gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid)
+ gits_write_vpendbaser(GICR_VPENDBASER_PendingLast,
+ vlpi_base + GICR_VPENDBASER);
+
+ /*
+ * If we can inherit the configuration from another RD, let's do
+ * so. Otherwise, we have to go through the allocation process. We
+ * assume that all RDs have the exact same requirements, as
+ * nothing will work otherwise.
+ */
+ val = inherit_vpe_l1_table_from_rd(&gic_data_rdist()->vpe_table_mask);
+ if (val & GICR_VPROPBASER_4_1_VALID)
+ goto out;
+
+ gic_data_rdist()->vpe_table_mask = kzalloc(sizeof(cpumask_t), GFP_KERNEL);
+ if (!gic_data_rdist()->vpe_table_mask)
+ return -ENOMEM;
+
+ val = inherit_vpe_l1_table_from_its();
+ if (val & GICR_VPROPBASER_4_1_VALID)
+ goto out;
+
+ /* First probe the page size */
+ val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K);
+ gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ val = gits_read_vpropbaser(vlpi_base + GICR_VPROPBASER);
+ gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+ esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val);
+
+ switch (gpsz) {
+ default:
+ gpsz = GIC_PAGE_SIZE_4K;
+ /* fall through */
+ case GIC_PAGE_SIZE_4K:
+ psz = SZ_4K;
+ break;
+ case GIC_PAGE_SIZE_16K:
+ psz = SZ_16K;
+ break;
+ case GIC_PAGE_SIZE_64K:
+ psz = SZ_64K;
+ break;
+ }
+
+ /*
+ * Start populating the register from scratch, including RO fields
+ * (which we want to print in debug cases...)
+ */
+ val = 0;
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, gpsz);
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ENTRY_SIZE, esz);
+
+ /* How many entries per GIC page? */
+ esz++;
+ epp = psz / (esz * SZ_8);
+
+ /*
+ * If we need more than just a single L1 page, flag the table
+ * as indirect and compute the number of required L1 pages.
+ */
+ if (epp < ITS_MAX_VPEID) {
+ int nl2;
+
+ val |= GICR_VPROPBASER_4_1_INDIRECT;
+
+ /* Number of L2 pages required to cover the VPEID space */
+ nl2 = DIV_ROUND_UP(ITS_MAX_VPEID, epp);
+
+ /* Number of L1 pages to point to the L2 pages */
+ npg = DIV_ROUND_UP(nl2 * SZ_8, psz);
+ } else {
+ npg = 1;
+ }
+
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg);
+
+ /* Right, that's the number of CPU pages we need for L1 */
+ np = DIV_ROUND_UP(npg * psz, PAGE_SIZE);
+
+ pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
+ np, npg, psz, epp, esz);
+ page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(np * PAGE_SIZE));
+ if (!page)
+ return -ENOMEM;
+
+ gic_data_rdist()->vpe_l1_page = page;
+ pa = virt_to_phys(page_address(page));
+ WARN_ON(!IS_ALIGNED(pa, psz));
+
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
+ val |= GICR_VPROPBASER_RaWb;
+ val |= GICR_VPROPBASER_InnerShareable;
+ val |= GICR_VPROPBASER_4_1_Z;
+ val |= GICR_VPROPBASER_4_1_VALID;
+
+out:
+ gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask);
+
+ pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n",
+ smp_processor_id(), val,
+ cpumask_pr_args(gic_data_rdist()->vpe_table_mask));
+
+ return 0;
+}
+
static int its_alloc_collections(struct its_node *its)
{
int i;
val |= GICR_CTLR_ENABLE_LPIS;
writel_relaxed(val, rbase + GICR_CTLR);
- if (gic_rdists->has_vlpis) {
+ if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
/*
WARN_ON(val & GICR_VPENDBASER_Dirty);
}
+ if (allocate_vpe_l1_table()) {
+ /*
+ * If the allocation has failed, we're in massive trouble.
+ * Disable direct injection, and pray that no VM was
+ * already running...
+ */
+ gic_rdists->has_rvpeid = false;
+ gic_rdists->has_vlpis = false;
+ }
+
/* Make sure the GIC has seen the above */
dsb(sy);
out:
} else {
pr_info("ITS@%pa: Single VMOVP capable\n", &res->start);
}
+
+ if (is_v4_1(its)) {
+ u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer);
+ its->mpidr = readl_relaxed(its_base + GITS_MPIDR);
+
+ pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n",
+ &res->start, its->mpidr, svpet);
+ }
}
its->numa_node = numa_node;
bool has_v4 = false;
int err;
+ gic_rdists = rdists;
+
its_parent = parent_domain;
of_node = to_of_node(handle);
if (of_node)
return -ENXIO;
}
- gic_rdists = rdists;
-
err = allocate_lpi_tables();
if (err)
return err;
#define GIC_V3_DIST_SIZE 0x10000
+#define GIC_PAGE_SIZE_4K 0ULL
+#define GIC_PAGE_SIZE_16K 1ULL
+#define GIC_PAGE_SIZE_64K 2ULL
+#define GIC_PAGE_SIZE_MASK 3ULL
+
/*
* Re-Distributor registers, offsets from RD_base
*/
#define GICR_TYPER_DirectLPIS (1U << 3)
#define GICR_TYPER_LAST (1U << 4)
#define GICR_TYPER_RVPEID (1U << 7)
+#define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24)
+#define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32)
#define GIC_V3_REDIST_SIZE 0x20000
#define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt)
#define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb)
+/*
+ * GICv4.1 VPROPBASER reinvention. A subtle mix between the old
+ * VPROPBASER and ITS_BASER. Just not quite any of the two.
+ */
+#define GICR_VPROPBASER_4_1_VALID (1ULL << 63)
+#define GICR_VPROPBASER_4_1_ENTRY_SIZE GENMASK_ULL(61, 59)
+#define GICR_VPROPBASER_4_1_INDIRECT (1ULL << 55)
+#define GICR_VPROPBASER_4_1_PAGE_SIZE GENMASK_ULL(54, 53)
+#define GICR_VPROPBASER_4_1_Z (1ULL << 52)
+#define GICR_VPROPBASER_4_1_ADDR GENMASK_ULL(51, 12)
+#define GICR_VPROPBASER_4_1_SIZE GENMASK_ULL(6, 0)
+
#define GICR_VPENDBASER 0x0078
#define GICR_VPENDBASER_SHAREABILITY_SHIFT (10)
#define GITS_CTLR 0x0000
#define GITS_IIDR 0x0004
#define GITS_TYPER 0x0008
+#define GITS_MPIDR 0x0018
#define GITS_CBASER 0x0080
#define GITS_CWRITER 0x0088
#define GITS_CREADR 0x0090
#define GITS_TYPER_HCC_SHIFT 24
#define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)
#define GITS_TYPER_VMOVP (1ULL << 37)
+#define GITS_TYPER_VMAPP (1ULL << 40)
+#define GITS_TYPER_SVPET GENMASK_ULL(42, 41)
#define GITS_IIDR_REV_SHIFT 12
#define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT)
#define GITS_BASER_InnerShareable \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
#define GITS_BASER_PAGE_SIZE_SHIFT (8)
-#define GITS_BASER_PAGE_SIZE_4K (0ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_16K (1ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_64K (2ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_MASK (3ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define __GITS_BASER_PSZ(sz) (GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_4K __GITS_BASER_PSZ(4K)
+#define GITS_BASER_PAGE_SIZE_16K __GITS_BASER_PSZ(16K)
+#define GITS_BASER_PAGE_SIZE_64K __GITS_BASER_PSZ(64K)
+#define GITS_BASER_PAGE_SIZE_MASK __GITS_BASER_PSZ(MASK)
#define GITS_BASER_PAGES_MAX 256
#define GITS_BASER_PAGES_SHIFT (0)
#define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1)
struct {
void __iomem *rd_base;
struct page *pend_page;
+ struct page *vpe_l1_page;
phys_addr_t phys_base;
bool lpi_enabled;
+ cpumask_t *vpe_table_mask;
} __percpu *rdist;
phys_addr_t prop_table_pa;
void *prop_table_va;
projects / users / hch / xfs.git / commitdiff