KVM: PPC: Book3S HV: Add Power11 capability support for Nested PAPR guests

The Power11 architected and raw mode support in Linux was merged in commit
c2ed087ed35c ("powerpc: Add Power11 architected and raw mode"), and the
corresponding support in QEMU is pending in [1], which is currently in
its V6.

Currently, booting a KVM guest inside a pseries LPAR (Logical Partition)
on a kernel without P11 support results the guest boot in a Power10
compatibility mode (i.e., with logical PVR of Power10). However, booting
a KVM guest on a kernel with P11 support causes the following boot crash.

On a Power11 LPAR, the Power Hypervisor (L0) returns a support for both
Power10 and Power11 capabilities through H_GUEST_GET_CAPABILITIES hcall.
However, KVM currently supports only Power10 capabilities, resulting in
only Power10 capabilities being set as "nested capabilities" via an
H_GUEST_SET_CAPABILITIES hcall.

In the guest entry path, gs_msg_ops_kvmhv_nestedv2_config_fill_info() is
called by kvmhv_nestedv2_flush_vcpu() to fill the GSB (Guest State
Buffer) elements. The arch_compat is set to the logical PVR of Power11,
followed by an H_GUEST_SET_STATE hcall. This hcall returns
H_INVALID_ELEMENT_VALUE as a return code when setting a Power11 logical
PVR, as only Power10 capabilities were communicated as supported between
PHYP and KVM, utimately resulting in the KVM guest boot crash.

  KVM: unknown exit, hardware reason ffffffffffffffea
  NIP 000000007daf97e0   LR 000000007daf1aec CTR 000000007daf1ab4 XER 0000000020040000 CPU#0
  MSR 8000000000103000 HID0 0000000000000000  HF 6c002000 iidx 3 didx 3
  TB 00000000 00000000 DECR 0
  GPR00 8000000000003000 000000007e580e20 000000007db26700 0000000000000000
  GPR04 00000000041a0c80 000000007df7f000 0000000000200000 000000007df7f000
  GPR08 000000007db6d5d8 000000007e65fa90 000000007db6d5d0 0000000000003000
  GPR12 8000000000000001 0000000000000000 0000000000000000 0000000000000000
  GPR16 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20 0000000000000000 0000000000000000 0000000000000000 000000007db21a30
  GPR24 000000007db65000 0000000000000000 0000000000000000 0000000000000003
  GPR28 000000007db6d5e0 000000007db22220 000000007daf27ac 000000007db75000
  CR 20000404  [ E  -  -  -  -  G  -  G  ]     RES 000@ffffffffffffffff
   SRR0 000000007daf97e0  SRR1 8000000000102000    PVR 0000000000820200 VRSAVE 0000000000000000
  SPRG0 0000000000000000 SPRG1 000000000000ff20  SPRG2 0000000000000000  SPRG3 0000000000000000
  SPRG4 0000000000000000 SPRG5 0000000000000000  SPRG6 0000000000000000  SPRG7 0000000000000000
   CFAR 0000000000000000
   LPCR 0000000000020400
   PTCR 0000000000000000   DAR 0000000000000000  DSISR 0000000000000000

Fix this by adding the Power11 capability support and the required
plumbing in place.

Note:
  * Booting a Power11 KVM nested PAPR guest requires [1] in QEMU.

[1] https://lore.kernel.org/all/20240731055022.696051-1-adityag@linux.ibm.com/

Signed-off-by: Amit Machhiwal <amachhiw@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241028101622.741573-1-amachhiw@linux.ibm.com

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 201218f..29a529d 100644 (file)
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -193,6 +193,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_ARCH_31                        LONG_ASM_CONST(0x0004000000000000)
 #define CPU_FTR_DAWR1                  LONG_ASM_CONST(0x0008000000000000)
 #define CPU_FTR_DEXCR_NPHIE            LONG_ASM_CONST(0x0010000000000000)
+#define CPU_FTR_P11_PVR                        LONG_ASM_CONST(0x0020000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -454,7 +455,7 @@ static inline void cpu_feature_keys_init(void) { }
            CPU_FTR_DAWR | CPU_FTR_DAWR1 | \
            CPU_FTR_DEXCR_NPHIE)
 
-#define CPU_FTRS_POWER11       CPU_FTRS_POWER10
+#define CPU_FTRS_POWER11       (CPU_FTRS_POWER10 | CPU_FTR_P11_PVR)
 
 #define CPU_FTRS_CELL  (CPU_FTR_LWSYNC | \
            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
@@ -475,7 +476,7 @@ static inline void cpu_feature_keys_init(void) { }
            (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
             CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \
             CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
-            CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+            CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
 #else
 #define CPU_FTRS_POSSIBLE      \
            (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
@@ -483,7 +484,7 @@ static inline void cpu_feature_keys_init(void) { }
             CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \
             CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \
             CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
-            CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+            CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
@@ -547,7 +548,7 @@ enum {
            (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & \
             CPU_FTRS_POWER7 & CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & \
             CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
-            CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+            CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
 #else
 #define CPU_FTRS_ALWAYS                \
            (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
@@ -555,7 +556,7 @@ enum {
             CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
             ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & CPU_FTRS_POSSIBLE & \
             CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
-            CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+            CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 7a84956..65d1f29 100644 (file)
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -495,6 +495,7 @@
 #define H_GUEST_CAP_COPY_MEM   (1UL<<(63-0))
 #define H_GUEST_CAP_POWER9     (1UL<<(63-1))
 #define H_GUEST_CAP_POWER10    (1UL<<(63-2))
+#define H_GUEST_CAP_POWER11    (1UL<<(63-3))
 #define H_GUEST_CAP_BITMAP2    (1UL<<(63-63))
 
 #ifndef __ASSEMBLY__

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ba0492f..3cdd6d6 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -400,7 +400,10 @@ static inline unsigned long map_pcr_to_cap(unsigned long pcr)
                cap = H_GUEST_CAP_POWER9;
                break;
        case PCR_ARCH_31:
-               cap = H_GUEST_CAP_POWER10;
+               if (cpu_has_feature(CPU_FTR_P11_PVR))
+                       cap = H_GUEST_CAP_POWER11;
+               else
+                       cap = H_GUEST_CAP_POWER10;
                break;
        default:
                break;
@@ -415,7 +418,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
        struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
        /* We can (emulate) our own architecture version and anything older */
-       if (cpu_has_feature(CPU_FTR_ARCH_31))
+       if (cpu_has_feature(CPU_FTR_P11_PVR) || cpu_has_feature(CPU_FTR_ARCH_31))
                host_pcr_bit = PCR_ARCH_31;
        else if (cpu_has_feature(CPU_FTR_ARCH_300))
                host_pcr_bit = PCR_ARCH_300;

diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 05f5220..db54b25 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -445,6 +445,8 @@ long kvmhv_nested_init(void)
        if (rc == H_SUCCESS) {
                unsigned long capabilities = 0;
 
+               if (cpu_has_feature(CPU_FTR_P11_PVR))
+                       capabilities |= H_GUEST_CAP_POWER11;
                if (cpu_has_feature(CPU_FTR_ARCH_31))
                        capabilities |= H_GUEST_CAP_POWER10;
                if (cpu_has_feature(CPU_FTR_ARCH_300))

diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index eeecea8..e5c7ce1 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -370,7 +370,9 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
                         * default to L1's PVR.
                         */
                        if (!vcpu->arch.vcore->arch_compat) {
-                               if (cpu_has_feature(CPU_FTR_ARCH_31))
+                               if (cpu_has_feature(CPU_FTR_P11_PVR))
+                                       arch_compat = PVR_ARCH_31_P11;
+                               else if (cpu_has_feature(CPU_FTR_ARCH_31))
                                        arch_compat = PVR_ARCH_31;
                                else if (cpu_has_feature(CPU_FTR_ARCH_300))
                                        arch_compat = PVR_ARCH_300;