powerpc: Update to new option-vector-5 format for CAS

On POWER9 the ibm,client-architecture-support (CAS) negotiation process
has been updated to change how the host to guest negotiation is done for
the new hash/radix mmu as well as the nest mmu, process tables and guest
translation shootdown (GTSE).

This is documented in the unreleased PAPR ACR "CAS option vector
additions for P9".

The host tells the guest which options it supports in
ibm,arch-vec-5-platform-support. The guest then chooses a subset of these
to request in the CAS call and these are agreed to in the
ibm,architecture-vec-5 property of the chosen node.

Thus we read ibm,arch-vec-5-platform-support and make our selection before
calling CAS. We then parse the ibm,architecture-vec-5 property of the
chosen node to check whether we should run as hash or radix.

ibm,arch-vec-5-platform-support format:

index value pairs: <index, val> ... <index, val>

index: Option vector 5 byte number
val:   Some representation of supported values

Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Don't print about unknown options, be consistent with OV5_FEAT]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 150 insertions, 14 deletions

diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634e8322..35c00d7a0cf8 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_ENCR         0x1120  /* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS      0x1501  /* 1,2,or 4 Sub-Processors supported */
 #define OV5_XIVE_EXPLOIT        0x1701  /* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300       0x1880  /* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300        0x1840  /* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX      0x1820  /* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL        0x1810  /* hcall selects SLB or proc table */
-#define OV5_MMU_SLB             0x1800  /* always use SLB */
-#define OV5_MMU_GTSE            0x1808  /* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT         0x18C0  /* MMU Mode Support Mask */
+#define OV5_MMU_HASH            0x1800  /* Hash MMU Only */
+#define OV5_MMU_RADIX           0x1840  /* Radix MMU Only */
+#define OV5_MMU_EITHER          0x1880  /* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC         0x18C0  /* Hash or Radix Can Switch Later */
+#define OV5_NMMU                0x1820  /* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL        0x1980  /* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE           0x1940  /* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE          0x1A40  /* Guest Translation Shoot Down Avail */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX               0x02    /* Linux is our OS */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index bf3966d12565..1c1b44ec7642 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+        bool hash_mmu;
+        bool radix_mmu;
+        bool radix_gtse;
+};
+
 /* Platforms codes are now obsolete in the kernel. Now only used within this
  * file and ultimately gone too. Feel free to change them if you need, they
  * are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
                 prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
 #endif
         }
+
+        opt = strstr(prom_cmd_line, "disable_radix");
+        if (opt) {
+                prom_debug("Radix disabled from cmdline\n");
+                prom_radix_disable = true;
+        }
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
         u8 byte22;
         u8 intarch;
         u8 mmu;
+        u8 hash_ext;
+        u8 radix_ext;
 } __packed;
 
 struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
                 .reserved3 = 0,
                 .subprocessors = 1,
                 .intarch = 0,
-                .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
-                        OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+                .mmu = 0,
+                .hash_ext = 0,
+                .radix_ext = 0,
         },
 
         /* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
 
 }
 
+static void __init prom_parse_mmu_model(u8 val,
+                                        struct platform_support *support)
+{
+        switch (val) {
+        case OV5_FEAT(OV5_MMU_DYNAMIC):
+        case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+                prom_debug("MMU - either supported\n");
+                support->radix_mmu = !prom_radix_disable;
+                support->hash_mmu = true;
+                break;
+        case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+                prom_debug("MMU - radix only\n");
+                if (prom_radix_disable) {
+                        /*
+                         * If we __have__ to do radix, we're better off ignoring
+                         * the command line rather than not booting.
+                         */
+                        prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+                }
+                support->radix_mmu = true;
+                break;
+        case OV5_FEAT(OV5_MMU_HASH):
+                prom_debug("MMU - hash only\n");
+                support->hash_mmu = true;
+                break;
+        default:
+                prom_debug("Unknown mmu support option: 0x%x\n", val);
+                break;
+        }
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+                                               struct platform_support *support)
+{
+        switch (index) {
+        case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+                prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+                break;
+        case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+                if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+                        prom_debug("Radix - GTSE supported\n");
+                        support->radix_gtse = true;
+                }
+                break;
+        }
+}
+
+static void __init prom_check_platform_support(void)
+{
+        struct platform_support supported = {
+                .hash_mmu = false,
+                .radix_mmu = false,
+                .radix_gtse = false
+        };
+        int prop_len = prom_getproplen(prom.chosen,
+                                       "ibm,arch-vec-5-platform-support");
+        if (prop_len > 1) {
+                int i;
+                u8 vec[prop_len];
+                prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+                           prop_len);
+                prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+                             &vec, sizeof(vec));
+                for (i = 0; i < prop_len; i += 2) {
+                        prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+                                                                  , vec[i]
+                                                                  , vec[i + 1]);
+                        prom_parse_platform_support(vec[i], vec[i + 1],
+                                                    &supported);
+                }
+        }
+
+        if (supported.radix_mmu && supported.radix_gtse) {
+                /* Radix preferred - but we require GTSE for now */
+                prom_debug("Asking for radix with GTSE\n");
+                ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+                ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+        } else if (supported.hash_mmu) {
+                /* Default to hash mmu (if we can) */
+                prom_debug("Asking for hash\n");
+                ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+        } else {
+                /* We're probably on a legacy hypervisor */
+                prom_debug("Assuming legacy hash support\n");
+        }
+}
 
 static void __init prom_send_capabilities(void)
 {
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
         prom_arg_t ret;
         u32 cores;
 
+        /* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+        prom_check_platform_support();
+
         root = call_prom("open", 1, 1, ADDR("/"));
         if (root != 0) {
                 /* We need to tell the FW about the number of cores we support.
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76aa0d6..9be992083d2a 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -356,18 +356,42 @@ static void early_check_vec5(void)
         unsigned long root, chosen;
         int size;
         const u8 *vec5;
+        u8 mmu_supported;
 
         root = of_get_flat_dt_root();
         chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
-        if (chosen == -FDT_ERR_NOTFOUND)
+        if (chosen == -FDT_ERR_NOTFOUND) {
+                cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
                 return;
+        }
         vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
-        if (!vec5)
+        if (!vec5) {
+                cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
                 return;
-        if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
-            !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
-                /* Hypervisor doesn't support radix */
+        }
+        if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
                 cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+                return;
+        }
+
+        /* Check for supported configuration */
+        mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+                        OV5_FEAT(OV5_MMU_SUPPORT);
+        if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+                /* Hypervisor only supports radix - check enabled && GTSE */
+                if (!early_radix_enabled()) {
+                        pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+                }
+                if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+                                                OV5_FEAT(OV5_RADIX_GTSE))) {
+                        pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+                }
+                /* Do radix anyway - the hypervisor said we had to */
+                cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+        } else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+                /* Hypervisor only supports hash - disable radix */
+                cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+        }
 }
 
 void __init mmu_early_init_devtree(void)
@@ -383,7 +407,7 @@ void __init mmu_early_init_devtree(void)
          * even though the ibm,architecture-vec-5 property created by
          * skiboot doesn't have the necessary bits set.
          */
-        if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+        if (!(mfmsr() & MSR_HV))
                 early_check_vec5();
 
         if (early_radix_enabled())