Merge tag 'kvm-ppc-next-4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

PPC KVM update for 4.19. This update adds no new features; it just has some minor code cleanups and bug fixes, including a fix to allow us to create KVM_MAX_VCPUS vCPUs on POWER9 in all CPU threading modes.
2026-05-02 19:15:03 -04:00 · 2018-08-02 13:57:26 +02:00
parent 6f0d349d92 b5c6f7607b
commit 3a1174cd3e
8 changed files with 125 additions and 53 deletions
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -390,4 +390,51 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu);
 #define SPLIT_HACK_MASK			0xff000000
 #define SPLIT_HACK_OFFS			0xfb000000

+/*
+ * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the
+ * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride
+ * (but not its actual threading mode, which is not available) to avoid
+ * collisions.
+ *
+ * The implementation leaves VCPU IDs from the range [0..KVM_MAX_VCPUS) (block
+ * 0) unchanged: if the guest is filling each VCORE completely then it will be
+ * using consecutive IDs and it will fill the space without any packing.
+ *
+ * For higher VCPU IDs, the packed ID is based on the VCPU ID modulo
+ * KVM_MAX_VCPUS (effectively masking off the top bits) and then an offset is
+ * added to avoid collisions.
+ *
+ * VCPU IDs in the range [KVM_MAX_VCPUS..(KVM_MAX_VCPUS*2)) (block 1) are only
+ * possible if the guest is leaving at least 1/2 of each VCORE empty, so IDs
+ * can be safely packed into the second half of each VCORE by adding an offset
+ * of (stride / 2).
+ *
+ * Similarly, if VCPU IDs in the range [(KVM_MAX_VCPUS*2)..(KVM_MAX_VCPUS*4))
+ * (blocks 2 and 3) are seen, the guest must be leaving at least 3/4 of each
+ * VCORE empty so packed IDs can be offset by (stride / 4) and (stride * 3 / 4).
+ *
+ * Finally, VCPU IDs from blocks 5..7 will only be seen if the guest is using a
+ * stride of 8 and 1 thread per core so the remaining offsets of 1, 5, 3 and 7
+ * must be free to use.
+ *
+ * (The offsets for each block are stored in block_offsets[], indexed by the
+ * block number if the stride is 8. For cases where the guest's stride is less
+ * than 8, we can re-use the block_offsets array by multiplying the block
+ * number by (MAX_SMT_THREADS / stride) to reach the correct entry.)
+ */
+static inline u32 kvmppc_pack_vcpu_id(struct kvm *kvm, u32 id)
+{
+	const int block_offsets[MAX_SMT_THREADS] = {0, 4, 2, 6, 1, 5, 3, 7};
+	int stride = kvm->arch.emul_smt_mode;
+	int block = (id / KVM_MAX_VCPUS) * (MAX_SMT_THREADS / stride);
+	u32 packed_id;
+
+	if (WARN_ONCE(block >= MAX_SMT_THREADS, "VCPU ID too large to pack"))
+		return 0;
+	packed_id = (id % KVM_MAX_VCPUS) + block_offsets[block];
+	if (WARN_ONCE(packed_id >= KVM_MAX_VCPUS, "VCPU ID packing failed"))
+		return 0;
+	return packed_id;
+}
+
 #endif /* __ASM_KVM_BOOK3S_H__ */
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -42,7 +42,14 @@
 #define KVM_USER_MEM_SLOTS	512

 #include <asm/cputhreads.h>
-#define KVM_MAX_VCPU_ID                (threads_per_subcore * KVM_MAX_VCORES)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+#include <asm/kvm_book3s_asm.h>		/* for MAX_SMT_THREADS */
+#define KVM_MAX_VCPU_ID		(MAX_SMT_THREADS * KVM_MAX_VCORES)
+
+#else
+#define KVM_MAX_VCPU_ID		KVM_MAX_VCPUS
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

 #define __KVM_HAVE_ARCH_INTC_INITIALIZED

@@ -672,7 +679,7 @@ struct kvm_vcpu_arch {
 	gva_t vaddr_accessed;
 	pgd_t *pgdir;

-	u8 io_gpr; /* GPR used as IO source/target */
+	u16 io_gpr; /* GPR used as IO source/target */
 	u8 mmio_host_swabbed;
 	u8 mmio_sign_extend;
 	/* conversion between single and double precision */
@@ -688,7 +695,6 @@ struct kvm_vcpu_arch {
 	 */
 	u8 mmio_vsx_copy_nums;
 	u8 mmio_vsx_offset;
-	u8 mmio_vsx_tx_sx_enabled;
 	u8 mmio_vmx_copy_nums;
 	u8 mmio_vmx_offset;
 	u8 mmio_copy_type;
@@ -801,14 +807,14 @@ struct kvm_vcpu_arch {
 #define KVMPPC_VCPU_BUSY_IN_HOST	2

 /* Values for vcpu->arch.io_gpr */
-#define KVM_MMIO_REG_MASK	0x001f
-#define KVM_MMIO_REG_EXT_MASK	0xffe0
+#define KVM_MMIO_REG_MASK	0x003f
+#define KVM_MMIO_REG_EXT_MASK	0xffc0
 #define KVM_MMIO_REG_GPR	0x0000
-#define KVM_MMIO_REG_FPR	0x0020
-#define KVM_MMIO_REG_QPR	0x0040
-#define KVM_MMIO_REG_FQPR	0x0060
-#define KVM_MMIO_REG_VSX	0x0080
-#define KVM_MMIO_REG_VMX	0x00c0
+#define KVM_MMIO_REG_FPR	0x0040
+#define KVM_MMIO_REG_QPR	0x0080
+#define KVM_MMIO_REG_FQPR	0x00c0
+#define KVM_MMIO_REG_VSX	0x0100
+#define KVM_MMIO_REG_VMX	0x0180

 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -161,7 +161,7 @@
 #define PSSCR_ESL		0x00200000 /* Enable State Loss */
 #define PSSCR_SD		0x00400000 /* Status Disable */
 #define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
-#define PSSCR_GUEST_VIS	0xf0000000000003ff /* Guest-visible PSSCR fields */
+#define PSSCR_GUEST_VIS	0xf0000000000003ffUL /* Guest-visible PSSCR fields */
 #define PSSCR_FAKE_SUSPEND	0x00000400 /* Fake-suspend bit (P9 DD2.2) */
 #define PSSCR_FAKE_SUSPEND_LG	10	   /* Fake-suspend bit position */

--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -180,7 +180,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 		if ((tbltmp->it_page_shift <= stt->page_shift) &&
 				(tbltmp->it_offset << tbltmp->it_page_shift ==
 				 stt->offset << stt->page_shift) &&
-				(tbltmp->it_size << tbltmp->it_page_shift ==
+				(tbltmp->it_size << tbltmp->it_page_shift >=
 				 stt->size << stt->page_shift)) {
 			/*
 			 * Reference the table to avoid races with
@@ -296,7 +296,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
 	struct kvmppc_spapr_tce_table *siter;
-	unsigned long npages, size;
+	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
 	int i;

@@ -304,7 +304,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
 		return -EINVAL;

-	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
 	if (ret)
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -128,14 +128,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 * and SPURR count and should be set according to the number of
 * online threads in the vcore being run.
 */
-#define RWMR_RPA_P8_1THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9
-#define RWMR_RPA_P8_3THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9
-#define RWMR_RPA_P8_5THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_6THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_7THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_8THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_1THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9UL
+#define RWMR_RPA_P8_3THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9UL
+#define RWMR_RPA_P8_5THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_6THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_7THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_8THREAD	0x164520C62609AECAUL

 static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = {
 	RWMR_RPA_P8_1THREAD,
@@ -1816,7 +1816,7 @@ static int threads_per_vcore(struct kvm *kvm)
 	return threads_per_subcore;
 }

-static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
+static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
 {
 	struct kvmppc_vcore *vcore;

@@ -1830,7 +1830,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
-	vcore->first_vcpuid = core * kvm->arch.smt_mode;
+	vcore->first_vcpuid = id;
 	vcore->kvm = kvm;
 	INIT_LIST_HEAD(&vcore->preempt_list);

@@ -2048,12 +2048,26 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	mutex_lock(&kvm->lock);
 	vcore = NULL;
 	err = -EINVAL;
-	core = id / kvm->arch.smt_mode;
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (id >= (KVM_MAX_VCPUS * kvm->arch.emul_smt_mode)) {
+			pr_devel("KVM: VCPU ID too high\n");
+			core = KVM_MAX_VCORES;
+		} else {
+			BUG_ON(kvm->arch.smt_mode != 1);
+			core = kvmppc_pack_vcpu_id(kvm, id);
+		}
+	} else {
+		core = id / kvm->arch.smt_mode;
+	}
 	if (core < KVM_MAX_VCORES) {
 		vcore = kvm->arch.vcores[core];
-		if (!vcore) {
+		if (vcore && cpu_has_feature(CPU_FTR_ARCH_300)) {
+			pr_devel("KVM: collision on id %u", id);
+			vcore = NULL;
+		} else if (!vcore) {
 			err = -ENOMEM;
-			vcore = kvmppc_vcore_create(kvm, core);
+			vcore = kvmppc_vcore_create(kvm,
+					id & ~(kvm->arch.smt_mode - 1));
 			kvm->arch.vcores[core] = vcore;
 			kvm->arch.online_vcores++;
 		}
@@ -4561,6 +4575,8 @@ static int kvmppc_book3s_init_hv(void)
 			pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
 			return -ENODEV;
 		}
+		/* presence of intc confirmed - node can be dropped again */
+		of_node_put(np);
 	}
 #endif

--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -317,6 +317,11 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 	return -EBUSY;
 }

+static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
+{
+	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
+}
+
 static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 			     struct kvmppc_xive_src_block *sb,
 			     struct kvmppc_xive_irq_state *state)
@@ -362,7 +367,7 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive->vp_base + state->act_server,
+					  xive_vp(xive, state->act_server),
 					  MASKED, state->number);
 		/* set old_p so we can track if an H_EOI was done */
 		state->old_p = true;
@@ -418,7 +423,7 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive->vp_base + state->act_server,
+					  xive_vp(xive, state->act_server),
 					  state->act_priority, state->number);
 		/* If an EOI is needed, do it here */
 		if (!state->old_p)
@@ -495,7 +500,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	kvmppc_xive_select_irq(state, &hw_num, NULL);

 	return xive_native_configure_irq(hw_num,
-					 xive->vp_base + server,
+					 xive_vp(xive, server),
 					 prio, state->number);
 }

@@ -883,7 +888,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	 * which is fine for a never started interrupt.
 	 */
 	xive_native_configure_irq(hw_irq,
-				  xive->vp_base + state->act_server,
+				  xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);

 	/*
@@ -959,7 +964,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,

 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
-				  xive->vp_base + state->act_server,
+				  xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);

 	/*
@@ -1084,7 +1089,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		pr_devel("Duplicate !\n");
 		return -EEXIST;
 	}
-	if (cpu >= KVM_MAX_VCPUS) {
+	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
@@ -1098,7 +1103,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = xive->vp_base + cpu;
+	xc->vp_id = xive_vp(xive, cpu);
 	xc->mfrr = 0xff;
 	xc->valid = true;

--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -106,7 +106,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	 * if mmio_vsx_tx_sx_enabled == 1, copy data between
 	 * VSR[32..63] and memory
 	 */
-	vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst);
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
@@ -242,8 +241,8 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			}

 			emulated = kvmppc_handle_vsx_load(run, vcpu,
-					KVM_MMIO_REG_VSX | (op.reg & 0x1f),
-					io_size_each, 1, op.type & SIGNEXT);
+					KVM_MMIO_REG_VSX|op.reg, io_size_each,
+					1, op.type & SIGNEXT);
 			break;
 		}
 #endif
@@ -363,7 +362,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			}

 			emulated = kvmppc_handle_vsx_store(run, vcpu,
-					op.reg & 0x1f, io_size_each, 1);
+					op.reg, io_size_each, 1);
 			break;
 		}
 #endif
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -880,10 +880,10 @@ static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;

-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsxval[offset] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		VCPU_VSX_FPR(vcpu, index, offset) = gpr;
 	}
@@ -895,11 +895,11 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
 	union kvmppc_one_reg val;
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;

-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsxval[0] = gpr;
 		val.vsxval[1] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		VCPU_VSX_FPR(vcpu, index, 0) = gpr;
 		VCPU_VSX_FPR(vcpu, index, 1) = gpr;
@@ -912,12 +912,12 @@ static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
 	union kvmppc_one_reg val;
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;

-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+	if (index >= 32) {
 		val.vsx32val[0] = gpr;
 		val.vsx32val[1] = gpr;
 		val.vsx32val[2] = gpr;
 		val.vsx32val[3] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		val.vsx32val[0] = gpr;
 		val.vsx32val[1] = gpr;
@@ -937,10 +937,10 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;

-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsx32val[offset] = gpr32;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		dword_offset = offset / 2;
 		word_offset = offset % 2;
@@ -1361,10 +1361,10 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 			break;
 		}

-		if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+		if (rs < 32) {
 			*val = VCPU_VSX_FPR(vcpu, rs, vsx_offset);
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs);
+			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
 			*val = reg.vsxval[vsx_offset];
 		}
 		break;
@@ -1378,13 +1378,13 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 			break;
 		}

-		if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+		if (rs < 32) {
 			dword_offset = vsx_offset / 2;
 			word_offset = vsx_offset % 2;
 			reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset);
 			*val = reg.vsx32val[word_offset];
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs);
+			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
 			*val = reg.vsx32val[vsx_offset];
 		}
 		break;