Merge tag 'kvm-s390-next-6.12-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

* New ucontrol selftest
* Inline assembly touchups

14 files changed, 683 insertions, 25 deletions

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index ea63a7342f5f..0c989caed19a 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -59,6 +59,7 @@ CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_S390_HYPFS_FS=y
 CONFIG_KVM=m
+CONFIG_KVM_S390_UCONTROL=y
 CONFIG_S390_UNWIND_SELFTEST=m
 CONFIG_S390_KPROBES_SANITY_TEST=m
 CONFIG_S390_MODULES_SANITY_TEST=m
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0fd96860fc45..bb7134faaebf 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -348,20 +348,29 @@ static inline int plo_test_bit(unsigned char nr)
 	return cc == 0;
 }
 
-static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
+static __always_inline void __sortl_query(u8 (*query)[32])
 {
 	asm volatile(
 		"	lghi	0,0\n"
-		"	lgr	1,%[query]\n"
+		"	la	1,%[query]\n"
 		/* Parameter registers are ignored */
-		"	.insn	rrf,%[opc] << 16,2,4,6,0\n"
+		"	.insn	rre,0xb9380000,2,4\n"
+		: [query] "=R" (*query)
 		:
-		: [query] "d" ((unsigned long)query), [opc] "i" (opcode)
-		: "cc", "memory", "0", "1");
+		: "cc", "0", "1");
 }
 
-#define INSN_SORTL 0xb938
-#define INSN_DFLTCC 0xb939
+static __always_inline void __dfltcc_query(u8 (*query)[32])
+{
+	asm volatile(
+		"	lghi	0,0\n"
+		"	la	1,%[query]\n"
+		/* Parameter registers are ignored */
+		"	.insn	rrf,0xb9390000,2,4,6,0\n"
+		: [query] "=R" (*query)
+		:
+		: "cc", "0", "1");
+}
 
 static void __init kvm_s390_cpu_feat_init(void)
 {
@@ -415,10 +424,10 @@ static void __init kvm_s390_cpu_feat_init(void)
 			      kvm_s390_available_subfunc.kdsa);
 
 	if (test_facility(150)) /* SORTL */
-		__insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl);
+		__sortl_query(&kvm_s390_available_subfunc.sortl);
 
 	if (test_facility(151)) /* DFLTCC */
-		__insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc);
+		__dfltcc_query(&kvm_s390_available_subfunc.dfltcc);
 
 	if (MACHINE_HAS_ESOP)
 		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 6d9381d60172..f2a30a58cd71 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -5,3 +5,4 @@
 !*.h
 !*.S
 !*.sh
+!config
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 0c4b254ab56b..948ec8b78af8 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -188,6 +188,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot
 TEST_GEN_PROGS_s390x += s390x/cmma_test
 TEST_GEN_PROGS_s390x += s390x/debug_test
 TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test
+TEST_GEN_PROGS_s390x += s390x/ucontrol_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += guest_print_test
diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390x/debug_print.h
new file mode 100644
index 000000000000..1bf275631cc6
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/debug_print.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Definition for kernel virtual machines on s390x
+ *
+ * Copyright IBM Corp. 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ */
+
+#ifndef SELFTEST_KVM_DEBUG_PRINT_H
+#define SELFTEST_KVM_DEBUG_PRINT_H
+
+#include "asm/ptrace.h"
+#include "kvm_util.h"
+#include "sie.h"
+
+static inline void print_hex_bytes(const char *name, u64 addr, size_t len)
+{
+	u64 pos;
+
+	pr_debug("%s (%p)\n", name, (void *)addr);
+	pr_debug("            0/0x00---------|");
+	if (len > 8)
+		pr_debug(" 8/0x08---------|");
+	if (len > 16)
+		pr_debug(" 16/0x10--------|");
+	if (len > 24)
+		pr_debug(" 24/0x18--------|");
+	for (pos = 0; pos < len; pos += 8) {
+		if ((pos % 32) == 0)
+			pr_debug("\n %3lu 0x%.3lx ", pos, pos);
+		pr_debug(" %16lx", *((u64 *)(addr + pos)));
+	}
+	pr_debug("\n");
+}
+
+static inline void print_hex(const char *name, u64 addr)
+{
+	print_hex_bytes(name, addr, 512);
+}
+
+static inline void print_psw(struct kvm_run *run, struct kvm_s390_sie_block *sie_block)
+{
+	pr_debug("flags:0x%x psw:0x%.16llx:0x%.16llx exit:%u %s\n",
+		 run->flags,
+		 run->psw_mask, run->psw_addr,
+		 run->exit_reason, exit_reason_str(run->exit_reason));
+	pr_debug("sie_block psw:0x%.16llx:0x%.16llx\n",
+		 sie_block->psw_mask, sie_block->psw_addr);
+}
+
+static inline void print_run(struct kvm_run *run, struct kvm_s390_sie_block *sie_block)
+{
+	print_hex_bytes("run", (u64)run, 0x150);
+	print_hex("sie_block", (u64)sie_block);
+	print_psw(run, sie_block);
+}
+
+static inline void print_regs(struct kvm_run *run)
+{
+	struct kvm_sync_regs *sync_regs = &run->s.regs;
+
+	print_hex_bytes("GPRS", (u64)sync_regs->gprs, 8 * NUM_GPRS);
+	print_hex_bytes("ACRS", (u64)sync_regs->acrs, 4 * NUM_ACRS);
+	print_hex_bytes("CRS", (u64)sync_regs->crs, 8 * NUM_CRS);
+}
+
+#endif /* SELFTEST_KVM_DEBUG_PRINT_H */
diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h
index 255c9b990f4c..481bd2fd6a32 100644
--- a/tools/testing/selftests/kvm/include/s390x/processor.h
+++ b/tools/testing/selftests/kvm/include/s390x/processor.h
@@ -21,6 +21,11 @@
 #define PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define PAGE_NOEXEC	0x100		/* HW no-execute bit */
 
+/* Page size definitions */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE BIT_ULL(PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
 /* Is there a portable way to do this? */
 static inline void cpu_relax(void)
 {
diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390x/sie.h
new file mode 100644
index 000000000000..160acd4a1db9
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/sie.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Definition for kernel virtual machines on s390.
+ *
+ * Adapted copy of struct definition kvm_s390_sie_block from
+ * arch/s390/include/asm/kvm_host.h for use in userspace selftest programs.
+ *
+ * Copyright IBM Corp. 2008, 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ *  Carsten Otte <cotte@de.ibm.com>
+ */
+
+#ifndef SELFTEST_KVM_SIE_H
+#define SELFTEST_KVM_SIE_H
+
+#include <linux/types.h>
+
+struct kvm_s390_sie_block {
+#define CPUSTAT_STOPPED    0x80000000
+#define CPUSTAT_WAIT       0x10000000
+#define CPUSTAT_ECALL_PEND 0x08000000
+#define CPUSTAT_STOP_INT   0x04000000
+#define CPUSTAT_IO_INT     0x02000000
+#define CPUSTAT_EXT_INT    0x01000000
+#define CPUSTAT_RUNNING    0x00800000
+#define CPUSTAT_RETAINED   0x00400000
+#define CPUSTAT_TIMING_SUB 0x00020000
+#define CPUSTAT_SIE_SUB    0x00010000
+#define CPUSTAT_RRF        0x00008000
+#define CPUSTAT_SLSV       0x00004000
+#define CPUSTAT_SLSR       0x00002000
+#define CPUSTAT_ZARCH      0x00000800
+#define CPUSTAT_MCDS       0x00000100
+#define CPUSTAT_KSS        0x00000200
+#define CPUSTAT_SM         0x00000080
+#define CPUSTAT_IBS        0x00000040
+#define CPUSTAT_GED2       0x00000010
+#define CPUSTAT_G          0x00000008
+#define CPUSTAT_GED        0x00000004
+#define CPUSTAT_J          0x00000002
+#define CPUSTAT_P          0x00000001
+	__u32 cpuflags;			/* 0x0000 */
+	__u32: 1;			/* 0x0004 */
+	__u32 prefix : 18;
+	__u32: 1;
+	__u32 ibc : 12;
+	__u8	reserved08[4];		/* 0x0008 */
+#define PROG_IN_SIE BIT(0)
+	__u32	prog0c;			/* 0x000c */
+	union {
+		__u8	reserved10[16];	/* 0x0010 */
+		struct {
+			__u64	pv_handle_cpu;
+			__u64	pv_handle_config;
+		};
+	};
+#define PROG_BLOCK_SIE	BIT(0)
+#define PROG_REQUEST	BIT(1)
+	__u32	prog20;			/* 0x0020 */
+	__u8	reserved24[4];		/* 0x0024 */
+	__u64	cputm;			/* 0x0028 */
+	__u64	ckc;			/* 0x0030 */
+	__u64	epoch;			/* 0x0038 */
+	__u32	svcc;			/* 0x0040 */
+#define LCTL_CR0	0x8000
+#define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
+#define LCTL_CR14	0x0002
+	__u16   lctl;			/* 0x0044 */
+	__s16	icpua;			/* 0x0046 */
+#define ICTL_OPEREXC	0x80000000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
+#define ICTL_TPROT	0x00000200
+	__u32	ictl;			/* 0x0048 */
+#define ECA_CEI		0x80000000
+#define ECA_IB		0x40000000
+#define ECA_SIGPI	0x10000000
+#define ECA_MVPGI	0x01000000
+#define ECA_AIV		0x00200000
+#define ECA_VX		0x00020000
+#define ECA_PROTEXCI	0x00002000
+#define ECA_APIE	0x00000008
+#define ECA_SII		0x00000001
+	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_EXTREQ	0x10
+#define ICPT_EXTINT	0x14
+#define ICPT_IOREQ	0x18
+#define ICPT_WAIT	0x1c
+#define ICPT_VALIDITY	0x20
+#define ICPT_STOP	0x28
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
+#define ICPT_KSS	0x5c
+#define ICPT_MCHKREQ	0x60
+#define ICPT_INT_ENABLE	0x64
+#define ICPT_PV_INSTR	0x68
+#define ICPT_PV_NOTIFY	0x6c
+#define ICPT_PV_PREF	0x70
+	__u8	icptcode;		/* 0x0050 */
+	__u8	icptstatus;		/* 0x0051 */
+	__u16	ihcpu;			/* 0x0052 */
+	__u8	reserved54;		/* 0x0054 */
+#define IICTL_CODE_NONE		 0x00
+#define IICTL_CODE_MCHK		 0x01
+#define IICTL_CODE_EXT		 0x02
+#define IICTL_CODE_IO		 0x03
+#define IICTL_CODE_RESTART	 0x04
+#define IICTL_CODE_SPECIFICATION 0x10
+#define IICTL_CODE_OPERAND	 0x11
+	__u8	iictl;			/* 0x0055 */
+	__u16	ipa;			/* 0x0056 */
+	__u32	ipb;			/* 0x0058 */
+	__u32	scaoh;			/* 0x005c */
+#define FPF_BPBC	0x20
+	__u8	fpf;			/* 0x0060 */
+#define ECB_GS		0x40
+#define ECB_TE		0x10
+#define ECB_SPECI	0x08
+#define ECB_SRSI	0x04
+#define ECB_HOSTPROTINT	0x02
+#define ECB_PTF		0x01
+	__u8	ecb;			/* 0x0061 */
+#define ECB2_CMMA	0x80
+#define ECB2_IEP	0x20
+#define ECB2_PFMFI	0x08
+#define ECB2_ESCA	0x04
+#define ECB2_ZPCI_LSI	0x02
+	__u8	ecb2;			/* 0x0062 */
+#define ECB3_AISI	0x20
+#define ECB3_AISII	0x10
+#define ECB3_DEA	0x08
+#define ECB3_AES	0x04
+#define ECB3_RI		0x01
+	__u8	ecb3;			/* 0x0063 */
+#define ESCA_SCAOL_MASK ~0x3fU
+	__u32	scaol;			/* 0x0064 */
+	__u8	sdf;			/* 0x0068 */
+	__u8	epdx;			/* 0x0069 */
+	__u8	cpnc;			/* 0x006a */
+	__u8	reserved6b;		/* 0x006b */
+	__u32	todpr;			/* 0x006c */
+#define GISA_FORMAT1 0x00000001
+	__u32	gd;			/* 0x0070 */
+	__u8	reserved74[12];		/* 0x0074 */
+	__u64	mso;			/* 0x0080 */
+	__u64	msl;			/* 0x0088 */
+	__u64	psw_mask;		/* 0x0090 */
+	__u64	psw_addr;		/* 0x0098 */
+	__u64	gg14;			/* 0x00a0 */
+	__u64	gg15;			/* 0x00a8 */
+	__u8	reservedb0[8];		/* 0x00b0 */
+#define HPID_KVM	0x4
+#define HPID_VSIE	0x5
+	__u8	hpid;			/* 0x00b8 */
+	__u8	reservedb9[7];		/* 0x00b9 */
+	union {
+		struct {
+			__u32	eiparams;	/* 0x00c0 */
+			__u16	extcpuaddr;	/* 0x00c4 */
+			__u16	eic;		/* 0x00c6 */
+		};
+		__u64	mcic;			/* 0x00c0 */
+	} __packed;
+	__u32	reservedc8;		/* 0x00c8 */
+	union {
+		struct {
+			__u16	pgmilc;		/* 0x00cc */
+			__u16	iprcc;		/* 0x00ce */
+		};
+		__u32	edc;			/* 0x00cc */
+	} __packed;
+	union {
+		struct {
+			__u32	dxc;		/* 0x00d0 */
+			__u16	mcn;		/* 0x00d4 */
+			__u8	perc;		/* 0x00d6 */
+			__u8	peratmid;	/* 0x00d7 */
+		};
+		__u64	faddr;			/* 0x00d0 */
+	} __packed;
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	union {
+		__u64	tecmc;		/* 0x00e8 */
+		struct {
+			__u16	subchannel_id;	/* 0x00e8 */
+			__u16	subchannel_nr;	/* 0x00ea */
+			__u32	io_int_parm;	/* 0x00ec */
+			__u32	io_int_word;	/* 0x00f0 */
+		};
+	} __packed;
+	__u8	reservedf4[8];		/* 0x00f4 */
+#define CRYCB_FORMAT_MASK	0x00000003
+#define CRYCB_FORMAT0		0x00000000
+#define CRYCB_FORMAT1		0x00000001
+#define CRYCB_FORMAT2		0x00000003
+	__u32	crycbd;			/* 0x00fc */
+	__u64	gcr[16];		/* 0x0100 */
+	union {
+		__u64	gbea;		/* 0x0180 */
+		__u64	sidad;
+	};
+	__u8    reserved188[8];		/* 0x0188 */
+	__u64   sdnxo;			/* 0x0190 */
+	__u8    reserved198[8];		/* 0x0198 */
+	__u32	fac;			/* 0x01a0 */
+	__u8	reserved1a4[20];	/* 0x01a4 */
+	__u64	cbrlo;			/* 0x01b8 */
+	__u8	reserved1c0[8];		/* 0x01c0 */
+#define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
+#define ECD_ETOKENF	0x02000000
+#define ECD_ECC		0x00200000
+	__u32	ecd;			/* 0x01c8 */
+	__u8	reserved1cc[18];	/* 0x01cc */
+	__u64	pp;			/* 0x01de */
+	__u8	reserved1e6[2];		/* 0x01e6 */
+	__u64	itdba;			/* 0x01e8 */
+	__u64   riccbd;			/* 0x01f0 */
+	__u64	gvrd;			/* 0x01f8 */
+} __packed __aligned(512);
+
+#endif /* SELFTEST_KVM_SIE_H */
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 4ad4492eea1d..20cfe970e3e3 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -14,7 +14,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
 	vm_paddr_t paddr;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	if (vm->pgd_created)
@@ -79,7 +79,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa)
 	}
 
 	/* Fill in page table entry */
-	idx = (gva >> 12) & 0x0ffu;		/* page index */
+	idx = (gva >> PAGE_SHIFT) & 0x0ffu;		/* page index */
 	if (!(entry[idx] & PAGE_INVALID))
 		fprintf(stderr,
 			"WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa);
@@ -91,7 +91,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	int ri, idx;
 	uint64_t *entry;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	entry = addr_gpa2hva(vm, vm->pgd);
@@ -103,7 +103,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 		entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN);
 	}
 
-	idx = (gva >> 12) & 0x0ffu;		/* page index */
+	idx = (gva >> PAGE_SHIFT) & 0x0ffu;		/* page index */
 
 	TEST_ASSERT(!(entry[idx] & PAGE_INVALID),
 		    "No page mapping for vm virtual address 0x%lx", gva);
@@ -168,7 +168,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	struct kvm_sregs sregs;
 	struct kvm_vcpu *vcpu;
 
-	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
+	TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
 	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
index b39033844756..e32dd59703a0 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -17,16 +17,17 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
 #define MAIN_PAGE_COUNT 512
 
 #define TEST_DATA_PAGE_COUNT 512
 #define TEST_DATA_MEMSLOT 1
-#define TEST_DATA_START_GFN 4096
+#define TEST_DATA_START_GFN PAGE_SIZE
 
 #define TEST_DATA_TWO_PAGE_COUNT 256
 #define TEST_DATA_TWO_MEMSLOT 2
-#define TEST_DATA_TWO_START_GFN 8192
+#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE)
 
 static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT];
 
@@ -66,7 +67,7 @@ static void guest_dirty_test_data(void)
 		"	lghi 5,%[page_count]\n"
 		/* r5 += r1 */
 		"2:	agfr 5,1\n"
-		/* r2 = r1 << 12 */
+		/* r2 = r1 << PAGE_SHIFT */
 		"1:	sllg 2,1,12(0)\n"
 		/* essa(r4, r2, SET_STABLE) */
 		"	.insn rrf,0xb9ab0000,4,2,1,0\n"
diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390x/config
new file mode 100644
index 000000000000..23270f2d679f
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/config
@@ -0,0 +1,2 @@
+CONFIG_KVM=y
+CONFIG_KVM_S390_UCONTROL=y
diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c
index 84313fb27529..ad8095968601 100644
--- a/tools/testing/selftests/kvm/s390x/debug_test.c
+++ b/tools/testing/selftests/kvm/s390x/debug_test.c
@@ -2,12 +2,12 @@
 /* Test KVM debugging features. */
 #include "kvm_util.h"
 #include "test_util.h"
+#include "sie.h"
 
 #include <linux/kvm.h>
 
 #define __LC_SVC_NEW_PSW 0x1c0
 #define __LC_PGM_NEW_PSW 0x1d0
-#define ICPT_INSTRUCTION 0x04
 #define IPA0_DIAG 0x8300
 #define PGM_SPECIFICATION 0x06
 
@@ -85,7 +85,7 @@ static void test_step_pgm_diag(void)
 	vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code,
 			     __LC_PGM_NEW_PSW, new_psw);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
-	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INST);
 	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG);
 	vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq);
 	vcpu_run(vcpu);
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index f2df7416be84..4374b4cd2a80 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -16,6 +16,7 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
 enum mop_target {
 	LOGICAL,
@@ -226,9 +227,6 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo,
 
 #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); })
 
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (1ULL << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE - 1))
 #define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
 #define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
 
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
index 7a742a673b7c..12d5e1cb62e3 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -9,9 +9,8 @@
 #include "kvm_util.h"
 #include "kselftest.h"
 #include "ucall_common.h"
+#include "processor.h"
 
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (1 << PAGE_SHIFT)
 #define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
 #define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
 
@@ -151,7 +150,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0)
 		 * instead.
 		 * In order to skip these tests we detect this inside the guest
 		 */
-		skip = tests[*i].addr < (void *)4096 &&
+		skip = tests[*i].addr < (void *)PAGE_SIZE &&
 		       tests[*i].expected != TRANSL_UNAVAIL &&
 		       !mapped_0;
 		if (!skip) {
diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
new file mode 100644
index 000000000000..f257beec1430
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test code for the s390x kvm ucontrol interface
+ *
+ * Copyright IBM Corp. 2024
+ *
+ * Authors:
+ *  Christoph Schlameuss <schlameuss@linux.ibm.com>
+ */
+#include "debug_print.h"
+#include "kselftest_harness.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "sie.h"
+
+#include <linux/capability.h>
+#include <linux/sizes.h>
+
+#define VM_MEM_SIZE (4 * SZ_1M)
+
+/* so directly declare capget to check caps without libcap */
+int capget(cap_user_header_t header, cap_user_data_t data);
+
+/**
+ * In order to create user controlled virtual machines on S390,
+ * check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL
+ * as privileged user (SYS_ADMIN).
+ */
+void require_ucontrol_admin(void)
+{
+	struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3];
+	struct __user_cap_header_struct hdr = {
+		.version = _LINUX_CAPABILITY_VERSION_3,
+	};
+	int rc;
+
+	rc = capget(&hdr, data);
+	TEST_ASSERT_EQ(0, rc);
+	TEST_REQUIRE((data->effective & CAP_TO_MASK(CAP_SYS_ADMIN)) > 0);
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_UCONTROL));
+}
+
+/* Test program setting some registers and looping */
+extern char test_gprs_asm[];
+asm("test_gprs_asm:\n"
+	"xgr	%r0, %r0\n"
+	"lgfi	%r1,1\n"
+	"lgfi	%r2,2\n"
+	"lgfi	%r3,3\n"
+	"lgfi	%r4,4\n"
+	"lgfi	%r5,5\n"
+	"lgfi	%r6,6\n"
+	"lgfi	%r7,7\n"
+	"0:\n"
+	"	diag	0,0,0x44\n"
+	"	ahi	%r0,1\n"
+	"	j	0b\n"
+);
+
+FIXTURE(uc_kvm)
+{
+	struct kvm_s390_sie_block *sie_block;
+	struct kvm_run *run;
+	uintptr_t base_gpa;
+	uintptr_t code_gpa;
+	uintptr_t base_hva;
+	uintptr_t code_hva;
+	int kvm_run_size;
+	void *vm_mem;
+	int vcpu_fd;
+	int kvm_fd;
+	int vm_fd;
+};
+
+/**
+ * create VM with single vcpu, map kvm_run and SIE control block for easy access
+ */
+FIXTURE_SETUP(uc_kvm)
+{
+	struct kvm_s390_vm_cpu_processor info;
+	int rc;
+
+	require_ucontrol_admin();
+
+	self->kvm_fd = open_kvm_dev_path_or_exit();
+	self->vm_fd = ioctl(self->kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL);
+	ASSERT_GE(self->vm_fd, 0);
+
+	kvm_device_attr_get(self->vm_fd, KVM_S390_VM_CPU_MODEL,
+			    KVM_S390_VM_CPU_PROCESSOR, &info);
+	TH_LOG("create VM 0x%llx", info.cpuid);
+
+	self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0);
+	ASSERT_GE(self->vcpu_fd, 0);
+
+	self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
+	ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run))
+		  TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size));
+	self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size,
+		    PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0);
+	ASSERT_NE(self->run, MAP_FAILED);
+	/**
+	 * For virtual cpus that have been created with S390 user controlled
+	 * virtual machines, the resulting vcpu fd can be memory mapped at page
+	 * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of
+	 * the virtual cpu's hardware control block.
+	 */
+	self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE,
+			  PROT_READ | PROT_WRITE, MAP_SHARED,
+			  self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT);
+	ASSERT_NE(self->sie_block, MAP_FAILED);
+
+	TH_LOG("VM created %p %p", self->run, self->sie_block);
+
+	self->base_gpa = 0;
+	self->code_gpa = self->base_gpa + (3 * SZ_1M);
+
+	self->vm_mem = aligned_alloc(SZ_1M, VM_MEM_SIZE);
+	ASSERT_NE(NULL, self->vm_mem) TH_LOG("malloc failed %u", errno);
+	self->base_hva = (uintptr_t)self->vm_mem;
+	self->code_hva = self->base_hva - self->base_gpa + self->code_gpa;
+	struct kvm_s390_ucas_mapping map = {
+		.user_addr = self->base_hva,
+		.vcpu_addr = self->base_gpa,
+		.length = VM_MEM_SIZE,
+	};
+	TH_LOG("ucas map %p %p 0x%llx",
+	       (void *)map.user_addr, (void *)map.vcpu_addr, map.length);
+	rc = ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map);
+	ASSERT_EQ(0, rc) TH_LOG("ucas map result %d not expected, %s",
+				rc, strerror(errno));
+
+	TH_LOG("page in %p", (void *)self->base_gpa);
+	rc = ioctl(self->vcpu_fd, KVM_S390_VCPU_FAULT, self->base_gpa);
+	ASSERT_EQ(0, rc) TH_LOG("vcpu fault (%p) result %d not expected, %s",
+				(void *)self->base_hva, rc, strerror(errno));
+
+	self->sie_block->cpuflags &= ~CPUSTAT_STOPPED;
+}
+
+FIXTURE_TEARDOWN(uc_kvm)
+{
+	munmap(self->sie_block, PAGE_SIZE);
+	munmap(self->run, self->kvm_run_size);
+	close(self->vcpu_fd);
+	close(self->vm_fd);
+	close(self->kvm_fd);
+	free(self->vm_mem);
+}
+
+TEST_F(uc_kvm, uc_sie_assertions)
+{
+	/* assert interception of Code 08 (Program Interruption) is set */
+	EXPECT_EQ(0, self->sie_block->ecb & ECB_SPECI);
+}
+
+TEST_F(uc_kvm, uc_attr_mem_limit)
+{
+	u64 limit;
+	struct kvm_device_attr attr = {
+		.group = KVM_S390_VM_MEM_CTRL,
+		.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
+		.addr = (unsigned long)&limit,
+	};
+	int rc;
+
+	rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr);
+	EXPECT_EQ(0, rc);
+	EXPECT_EQ(~0UL, limit);
+
+	/* assert set not supported */
+	rc = ioctl(self->vm_fd, KVM_SET_DEVICE_ATTR, &attr);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+TEST_F(uc_kvm, uc_no_dirty_log)
+{
+	struct kvm_dirty_log dlog;
+	int rc;
+
+	rc = ioctl(self->vm_fd, KVM_GET_DIRTY_LOG, &dlog);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+/**
+ * Assert HPAGE CAP cannot be enabled on UCONTROL VM
+ */
+TEST(uc_cap_hpage)
+{
+	int rc, kvm_fd, vm_fd, vcpu_fd;
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_S390_HPAGE_1M,
+	};
+
+	require_ucontrol_admin();
+
+	kvm_fd = open_kvm_dev_path_or_exit();
+	vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL);
+	ASSERT_GE(vm_fd, 0);
+
+	/* assert hpages are not supported on ucontrol vm */
+	rc = ioctl(vm_fd, KVM_CHECK_EXTENSION, KVM_CAP_S390_HPAGE_1M);
+	EXPECT_EQ(0, rc);
+
+	/* Test that KVM_CAP_S390_HPAGE_1M can't be enabled for a ucontrol vm */
+	rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* assert HPAGE CAP is rejected after vCPU creation */
+	vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
+	ASSERT_GE(vcpu_fd, 0);
+	rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EBUSY, errno);
+
+	close(vcpu_fd);
+	close(vm_fd);
+	close(kvm_fd);
+}
+
+/* verify SIEIC exit
+ * * fail on codes not expected in the test cases
+ */
+static bool uc_handle_sieic(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_s390_sie_block *sie_block = self->sie_block;
+	struct kvm_run *run = self->run;
+
+	/* check SIE interception code */
+	pr_info("sieic: 0x%.2x 0x%.4x 0x%.4x\n",
+		run->s390_sieic.icptcode,
+		run->s390_sieic.ipa,
+		run->s390_sieic.ipb);
+	switch (run->s390_sieic.icptcode) {
+	case ICPT_INST:
+		/* end execution in caller on intercepted instruction */
+		pr_info("sie instruction interception\n");
+		return false;
+	case ICPT_OPEREXC:
+		/* operation exception */
+		TEST_FAIL("sie exception on %.4x%.8x", sie_block->ipa, sie_block->ipb);
+	default:
+		TEST_FAIL("UNEXPECTED SIEIC CODE %d", run->s390_sieic.icptcode);
+	}
+	return true;
+}
+
+/* verify VM state on exit */
+static bool uc_handle_exit(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_run *run = self->run;
+
+	switch (run->exit_reason) {
+	case KVM_EXIT_S390_SIEIC:
+		return uc_handle_sieic(self);
+	default:
+		pr_info("exit_reason %2d not handled\n", run->exit_reason);
+	}
+	return true;
+}
+
+/* run the VM until interrupted */
+static int uc_run_once(FIXTURE_DATA(uc_kvm) * self)
+{
+	int rc;
+
+	rc = ioctl(self->vcpu_fd, KVM_RUN, NULL);
+	print_run(self->run, self->sie_block);
+	print_regs(self->run);
+	pr_debug("run %d / %d %s\n", rc, errno, strerror(errno));
+	return rc;
+}
+
+static void uc_assert_diag44(FIXTURE_DATA(uc_kvm) * self)
+{
+	struct kvm_s390_sie_block *sie_block = self->sie_block;
+
+	/* assert vm was interrupted by diag 0x0044 */
+	TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason);
+	TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode);
+	TEST_ASSERT_EQ(0x8300, sie_block->ipa);
+	TEST_ASSERT_EQ(0x440000, sie_block->ipb);
+}
+
+TEST_F(uc_kvm, uc_gprs)
+{
+	struct kvm_sync_regs *sync_regs = &self->run->s.regs;
+	struct kvm_run *run = self->run;
+	struct kvm_regs regs = {};
+
+	/* Set registers to values that are different from the ones that we expect below */
+	for (int i = 0; i < 8; i++)
+		sync_regs->gprs[i] = 8;
+	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
+
+	/* copy test_gprs_asm to code_hva / code_gpa */
+	TH_LOG("copy code %p to vm mapped memory %p / %p",
+	       &test_gprs_asm, (void *)self->code_hva, (void *)self->code_gpa);
+	memcpy((void *)self->code_hva, &test_gprs_asm, PAGE_SIZE);
+
+	/* DAT disabled + 64 bit mode */
+	run->psw_mask = 0x0000000180000000ULL;
+	run->psw_addr = self->code_gpa;
+
+	/* run and expect interception of diag 44 */
+	ASSERT_EQ(0, uc_run_once(self));
+	ASSERT_EQ(false, uc_handle_exit(self));
+	uc_assert_diag44(self);
+
+	/* Retrieve and check guest register values */
+	ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, &regs));
+	for (int i = 0; i < 8; i++) {
+		ASSERT_EQ(i, regs.gprs[i]);
+		ASSERT_EQ(i, sync_regs->gprs[i]);
+	}
+
+	/* run and expect interception of diag 44 again */
+	ASSERT_EQ(0, uc_run_once(self));
+	ASSERT_EQ(false, uc_handle_exit(self));
+	uc_assert_diag44(self);
+
+	/* check continued increment of register 0 value */
+	ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, &regs));
+	ASSERT_EQ(1, regs.gprs[0]);
+	ASSERT_EQ(1, sync_regs->gprs[0]);
+}
+
+TEST_HARNESS_MAIN