From 0bab189c96c780341a954186276f9b58ea3244b9 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 30 Jan 2020 14:34:17 +0100 Subject: [PATCH 1/7] target/s390x/translate: Fix RNSBG instruction RNSBG is handled via the op_rosbg() helper function. But RNSBG has the opcode 0xEC54, i.e. 0x54 as second byte, while op_rosbg() currently checks for 0x55. This seems to be a typo, fix it to use 0x54 instead, so that op_rosbg() does not abort() anymore if a program uses RNSBG. I've checked with a simple test function that I now get the same results with KVM and with TCG: static void test_rnsbg(void) { uint64_t r1, r2; r2 = 0xffff000000000000UL; r1 = 0x123456789bdfaaaaUL; asm volatile (" rnsbg %0,%1,12,61,16 " : "+r"(r1) : "r"(r2)); printf("r1 afterwards: 0x%lx\n", r1); } Buglink: https://bugs.launchpad.net/qemu/+bug/1860920 Signed-off-by: Thomas Huth Message-Id: <20200130133417.10531-1-thuth@redhat.com> Fixes: d6c6372e186e ("target-s390: Implement R[NOX]SBG") Reviewed-by: David Hildenbrand Signed-off-by: Cornelia Huck --- target/s390x/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/s390x/translate.c b/target/s390x/translate.c index 0bd2073718..4f6f1e31cd 100644 --- a/target/s390x/translate.c +++ b/target/s390x/translate.c @@ -3874,7 +3874,7 @@ static DisasJumpType op_rosbg(DisasContext *s, DisasOps *o) /* Operate. */ switch (s->fields.op2) { - case 0x55: /* AND */ + case 0x54: /* AND */ tcg_gen_ori_i64(o->in2, o->in2, ~mask); tcg_gen_and_i64(o->out, o->out, o->in2); break; From ddda37483dd17c9936fdde9ebf8f6ca2692b3842 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 18 Feb 2020 15:44:59 +0100 Subject: [PATCH 2/7] linux-headers: update Update to commit b1da3acc781c ("Merge tag 'ecryptfs-5.6-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs") Signed-off-by: Cornelia Huck --- include/standard-headers/drm/drm_fourcc.h | 24 +++++++++++++++++++++++ include/standard-headers/linux/ethtool.h | 11 +++++++++++ include/standard-headers/linux/input.h | 1 + include/standard-headers/linux/pci_regs.h | 1 + linux-headers/asm-arm/unistd-common.h | 2 ++ linux-headers/asm-arm64/kvm.h | 12 ++++++++++-- linux-headers/asm-arm64/unistd.h | 1 + linux-headers/asm-generic/mman-common.h | 2 ++ linux-headers/asm-generic/unistd.h | 7 ++++++- linux-headers/asm-mips/unistd_n32.h | 2 ++ linux-headers/asm-mips/unistd_n64.h | 2 ++ linux-headers/asm-mips/unistd_o32.h | 2 ++ linux-headers/asm-powerpc/unistd_32.h | 2 ++ linux-headers/asm-powerpc/unistd_64.h | 2 ++ linux-headers/asm-s390/unistd_32.h | 2 ++ linux-headers/asm-s390/unistd_64.h | 2 ++ linux-headers/asm-x86/unistd_32.h | 2 ++ linux-headers/asm-x86/unistd_64.h | 2 ++ linux-headers/asm-x86/unistd_x32.h | 2 ++ linux-headers/linux/kvm.h | 5 +++++ 20 files changed, 83 insertions(+), 3 deletions(-) diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index 46d279f515..66e838074c 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -409,6 +409,30 @@ extern "C" { #define I915_FORMAT_MOD_Y_TILED_CCS fourcc_mod_code(INTEL, 4) #define I915_FORMAT_MOD_Yf_TILED_CCS fourcc_mod_code(INTEL, 5) +/* + * Intel color control surfaces (CCS) for Gen-12 render compression. + * + * The main surface is Y-tiled and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * Y-tile widths. + */ +#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS fourcc_mod_code(INTEL, 6) + +/* + * Intel color control surfaces (CCS) for Gen-12 media compression + * + * The main surface is Y-tiled and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * Y-tile widths. For semi-planar formats like NV12, CCS planes follow the + * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces, + * planes 2 and 3 for the respective CCS. + */ +#define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 6e8a10ee10..8adf3b018b 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -593,6 +593,9 @@ struct ethtool_pauseparam { * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS * @ETH_SS_PHY_TUNABLES: PHY tunable names + * @ETH_SS_LINK_MODES: link mode names + * @ETH_SS_MSG_CLASSES: debug message class names + * @ETH_SS_WOL_MODES: wake-on-lan modes */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -604,6 +607,12 @@ enum ethtool_stringset { ETH_SS_TUNABLES, ETH_SS_PHY_STATS, ETH_SS_PHY_TUNABLES, + ETH_SS_LINK_MODES, + ETH_SS_MSG_CLASSES, + ETH_SS_WOL_MODES, + + /* add new constants above here */ + ETH_SS_COUNT }; /** @@ -1688,6 +1697,8 @@ static inline int ethtool_validate_duplex(uint8_t duplex) #define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ #define WAKE_FILTER (1 << 7) +#define WOL_MODE_COUNT 8 + /* L2-L4 network traffic flow types */ #define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ #define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index d8914f25a5..f89c986190 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -31,6 +31,7 @@ struct input_event { unsigned long __sec; #if defined(__sparc__) && defined(__arch64__) unsigned int __usec; + unsigned int __pad; #else unsigned long __usec; #endif diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index acb7d2bdb4..5437690483 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -676,6 +676,7 @@ #define PCI_EXP_LNKCTL2_TLS_32_0GT 0x0005 /* Supported Speed 32GT/s */ #define PCI_EXP_LNKCTL2_ENTER_COMP 0x0010 /* Enter Compliance */ #define PCI_EXP_LNKCTL2_TX_MARGIN 0x0380 /* Transmit Margin */ +#define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ #define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ diff --git a/linux-headers/asm-arm/unistd-common.h b/linux-headers/asm-arm/unistd-common.h index eb5d361b11..23de64e44c 100644 --- a/linux-headers/asm-arm/unistd-common.h +++ b/linux-headers/asm-arm/unistd-common.h @@ -390,5 +390,7 @@ #define __NR_fspick (__NR_SYSCALL_BASE + 433) #define __NR_pidfd_open (__NR_SYSCALL_BASE + 434) #define __NR_clone3 (__NR_SYSCALL_BASE + 435) +#define __NR_openat2 (__NR_SYSCALL_BASE + 437) +#define __NR_pidfd_getfd (__NR_SYSCALL_BASE + 438) #endif /* _ASM_ARM_UNISTD_COMMON_H */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index 920af01c8b..9e34f0f875 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -220,10 +220,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2) #define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1) -/* EL0 Virtual Timer Registers */ +/* + * EL0 Virtual Timer Registers + * + * WARNING: + * KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined + * with the appropriate register encodings. Their values have been + * accidentally swapped. As this is set API, the definitions here + * must be used, rather than ones derived from the encodings. + */ #define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1) -#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) /* KVM-as-firmware specific pseudo-registers */ #define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/linux-headers/asm-arm64/unistd.h b/linux-headers/asm-arm64/unistd.h index 4703d21866..f83a70e07d 100644 --- a/linux-headers/asm-arm64/unistd.h +++ b/linux-headers/asm-arm64/unistd.h @@ -19,5 +19,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYS_CLONE3 #include diff --git a/linux-headers/asm-generic/mman-common.h b/linux-headers/asm-generic/mman-common.h index c160a5354e..f94f65d429 100644 --- a/linux-headers/asm-generic/mman-common.h +++ b/linux-headers/asm-generic/mman-common.h @@ -11,6 +11,8 @@ #define PROT_WRITE 0x2 /* page can be written */ #define PROT_EXEC 0x4 /* page can be executed */ #define PROT_SEM 0x8 /* page may be used for atomic ops */ +/* 0x10 reserved for arch-specific use */ +/* 0x20 reserved for arch-specific use */ #define PROT_NONE 0x0 /* page can not be accessed */ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index 1fc8faa6e9..3a3201e461 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open) __SYSCALL(__NR_clone3, sys_clone3) #endif +#define __NR_openat2 437 +__SYSCALL(__NR_openat2, sys_openat2) +#define __NR_pidfd_getfd 438 +__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) + #undef __NR_syscalls -#define __NR_syscalls 436 +#define __NR_syscalls 439 /* * 32 bit systems traditionally used different diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h index 659d5c9ade..aec9f6081a 100644 --- a/linux-headers/asm-mips/unistd_n32.h +++ b/linux-headers/asm-mips/unistd_n32.h @@ -365,6 +365,8 @@ #define __NR_fspick (__NR_Linux + 433) #define __NR_pidfd_open (__NR_Linux + 434) #define __NR_clone3 (__NR_Linux + 435) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) #endif /* _ASM_MIPS_UNISTD_N32_H */ diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h index 4b6310a05c..1c75d83df5 100644 --- a/linux-headers/asm-mips/unistd_n64.h +++ b/linux-headers/asm-mips/unistd_n64.h @@ -341,6 +341,8 @@ #define __NR_fspick (__NR_Linux + 433) #define __NR_pidfd_open (__NR_Linux + 434) #define __NR_clone3 (__NR_Linux + 435) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) #endif /* _ASM_MIPS_UNISTD_N64_H */ diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h index 4ce7b4e288..660716e240 100644 --- a/linux-headers/asm-mips/unistd_o32.h +++ b/linux-headers/asm-mips/unistd_o32.h @@ -411,6 +411,8 @@ #define __NR_fspick (__NR_Linux + 433) #define __NR_pidfd_open (__NR_Linux + 434) #define __NR_clone3 (__NR_Linux + 435) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) #endif /* _ASM_MIPS_UNISTD_O32_H */ diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h index 5584cc1b4f..4ba8e32f73 100644 --- a/linux-headers/asm-powerpc/unistd_32.h +++ b/linux-headers/asm-powerpc/unistd_32.h @@ -418,6 +418,8 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_POWERPC_UNISTD_32_H */ diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h index 251bcff77e..ac20bb4f95 100644 --- a/linux-headers/asm-powerpc/unistd_64.h +++ b/linux-headers/asm-powerpc/unistd_64.h @@ -390,6 +390,8 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_POWERPC_UNISTD_64_H */ diff --git a/linux-headers/asm-s390/unistd_32.h b/linux-headers/asm-s390/unistd_32.h index 7cce3ee296..e4a6b654f1 100644 --- a/linux-headers/asm-s390/unistd_32.h +++ b/linux-headers/asm-s390/unistd_32.h @@ -408,5 +408,7 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_S390_UNISTD_32_H */ diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h index 2371ff1e7a..472f732956 100644 --- a/linux-headers/asm-s390/unistd_64.h +++ b/linux-headers/asm-s390/unistd_64.h @@ -356,5 +356,7 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_S390_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h index e8ebec1cdc..f6e06fcfbd 100644 --- a/linux-headers/asm-x86/unistd_32.h +++ b/linux-headers/asm-x86/unistd_32.h @@ -426,5 +426,7 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_X86_UNISTD_32_H */ diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index a2f863d549..924f826d2d 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -348,5 +348,7 @@ #define __NR_fspick 433 #define __NR_pidfd_open 434 #define __NR_clone3 435 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 #endif /* _ASM_X86_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 4cdc67d848..010307757b 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -301,6 +301,8 @@ #define __NR_fspick (__X32_SYSCALL_BIT + 433) #define __NR_pidfd_open (__X32_SYSCALL_BIT + 434) #define __NR_clone3 (__X32_SYSCALL_BIT + 435) +#define __NR_openat2 (__X32_SYSCALL_BIT + 437) +#define __NR_pidfd_getfd (__X32_SYSCALL_BIT + 438) #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) #define __NR_ioctl (__X32_SYSCALL_BIT + 514) diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 9d647fad76..265099100e 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 +#define KVM_CAP_S390_VCPU_RESETS 179 #ifdef KVM_CAP_IRQ_ROUTING @@ -1473,6 +1474,10 @@ struct kvm_enc_region { /* Available with KVM_CAP_ARM_SVE */ #define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) +/* Available with KVM_CAP_S390_VCPU_RESETS */ +#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) +#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ From b91a03946e0f65ddd22927dd80ca1276bf89c5af Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 14 Feb 2020 10:16:21 -0500 Subject: [PATCH 3/7] s390x: Add missing vcpu reset functions Up to now we only had an ioctl to reset vcpu data QEMU couldn't reach for the initial reset, which was also called for the clear reset. To be architecture compliant, we also need to clear local interrupts on a normal reset. Because of this and the upcoming protvirt support we need to add ioctls for the missing clear and normal resets. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Acked-by: David Hildenbrand Message-Id: <20200214151636.8764-3-frankja@linux.ibm.com> Signed-off-by: Cornelia Huck --- target/s390x/cpu.c | 14 ++++++++++++-- target/s390x/kvm-stub.c | 10 +++++++++- target/s390x/kvm.c | 42 ++++++++++++++++++++++++++++++++-------- target/s390x/kvm_s390x.h | 4 +++- 4 files changed, 58 insertions(+), 12 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index cf84d307c6..8da1905485 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -144,8 +144,18 @@ static void s390_cpu_reset(CPUState *s, cpu_reset_type type) } /* Reset state inside the kernel that we cannot access yet from QEMU. */ - if (kvm_enabled() && type != S390_CPU_RESET_NORMAL) { - kvm_s390_reset_vcpu(cpu); + if (kvm_enabled()) { + switch (type) { + case S390_CPU_RESET_CLEAR: + kvm_s390_reset_vcpu_clear(cpu); + break; + case S390_CPU_RESET_INITIAL: + kvm_s390_reset_vcpu_initial(cpu); + break; + case S390_CPU_RESET_NORMAL: + kvm_s390_reset_vcpu_normal(cpu); + break; + } } } diff --git a/target/s390x/kvm-stub.c b/target/s390x/kvm-stub.c index 5152e2bdf1..c4cd497f85 100644 --- a/target/s390x/kvm-stub.c +++ b/target/s390x/kvm-stub.c @@ -83,7 +83,15 @@ void kvm_s390_cmma_reset(void) { } -void kvm_s390_reset_vcpu(S390CPU *cpu) +void kvm_s390_reset_vcpu_initial(S390CPU *cpu) +{ +} + +void kvm_s390_reset_vcpu_clear(S390CPU *cpu) +{ +} + +void kvm_s390_reset_vcpu_normal(S390CPU *cpu) { } diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c index 30112e529c..1d6fd6a27b 100644 --- a/target/s390x/kvm.c +++ b/target/s390x/kvm.c @@ -151,6 +151,7 @@ static int cap_s390_irq; static int cap_ri; static int cap_gs; static int cap_hpage_1m; +static int cap_vcpu_resets; static int active_cmma; @@ -342,6 +343,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF); cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP); cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ); + cap_vcpu_resets = kvm_check_extension(s, KVM_CAP_S390_VCPU_RESETS); if (!kvm_check_extension(s, KVM_CAP_S390_GMAP) || !kvm_check_extension(s, KVM_CAP_S390_COW)) { @@ -406,17 +408,41 @@ int kvm_arch_destroy_vcpu(CPUState *cs) return 0; } -void kvm_s390_reset_vcpu(S390CPU *cpu) +static void kvm_s390_reset_vcpu(S390CPU *cpu, unsigned long type) { CPUState *cs = CPU(cpu); - /* The initial reset call is needed here to reset in-kernel - * vcpu data that we can't access directly from QEMU - * (i.e. with older kernels which don't support sync_regs/ONE_REG). - * Before this ioctl cpu_synchronize_state() is called in common kvm - * code (kvm-all) */ - if (kvm_vcpu_ioctl(cs, KVM_S390_INITIAL_RESET, NULL)) { - error_report("Initial CPU reset failed on CPU %i", cs->cpu_index); + /* + * The reset call is needed here to reset in-kernel vcpu data that + * we can't access directly from QEMU (i.e. with older kernels + * which don't support sync_regs/ONE_REG). Before this ioctl + * cpu_synchronize_state() is called in common kvm code + * (kvm-all). + */ + if (kvm_vcpu_ioctl(cs, type)) { + error_report("CPU reset failed on CPU %i type %lx", + cs->cpu_index, type); + } +} + +void kvm_s390_reset_vcpu_initial(S390CPU *cpu) +{ + kvm_s390_reset_vcpu(cpu, KVM_S390_INITIAL_RESET); +} + +void kvm_s390_reset_vcpu_clear(S390CPU *cpu) +{ + if (cap_vcpu_resets) { + kvm_s390_reset_vcpu(cpu, KVM_S390_CLEAR_RESET); + } else { + kvm_s390_reset_vcpu(cpu, KVM_S390_INITIAL_RESET); + } +} + +void kvm_s390_reset_vcpu_normal(S390CPU *cpu) +{ + if (cap_vcpu_resets) { + kvm_s390_reset_vcpu(cpu, KVM_S390_NORMAL_RESET); } } diff --git a/target/s390x/kvm_s390x.h b/target/s390x/kvm_s390x.h index caf985955b..0b21789796 100644 --- a/target/s390x/kvm_s390x.h +++ b/target/s390x/kvm_s390x.h @@ -34,7 +34,9 @@ int kvm_s390_assign_subch_ioeventfd(EventNotifier *notifier, uint32_t sch, int vq, bool assign); int kvm_s390_cmma_active(void); void kvm_s390_cmma_reset(void); -void kvm_s390_reset_vcpu(S390CPU *cpu); +void kvm_s390_reset_vcpu_clear(S390CPU *cpu); +void kvm_s390_reset_vcpu_normal(S390CPU *cpu); +void kvm_s390_reset_vcpu_initial(S390CPU *cpu); int kvm_s390_set_mem_limit(uint64_t new_limit, uint64_t *hw_limit); void kvm_s390_set_max_pagesize(uint64_t pagesize, Error **errp); void kvm_s390_crypto_reset(void); From 8b51c0961cc13e55b26bb6665ec3a341abdc7658 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 20 Feb 2020 14:16:22 +0100 Subject: [PATCH 4/7] s390/sclp: improve special wait psw logic There is a special quiesce PSW that we check for "shutdown". Otherwise disabled wait is detected as "crashed". Architecturally we must only check PSW bits 116-127. Fix this. Cc: qemu-stable@nongnu.org Signed-off-by: Christian Borntraeger Message-Id: <1582204582-22995-1-git-send-email-borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand Acked-by: Janosch Frank Signed-off-by: Cornelia Huck --- target/s390x/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/s390x/helper.c b/target/s390x/helper.c index b810ad431e..ed72684911 100644 --- a/target/s390x/helper.c +++ b/target/s390x/helper.c @@ -89,7 +89,7 @@ hwaddr s390_cpu_get_phys_addr_debug(CPUState *cs, vaddr vaddr) static inline bool is_special_wait_psw(uint64_t psw_addr) { /* signal quiesce */ - return psw_addr == 0xfffUL; + return (psw_addr & 0xfffUL) == 0xfffUL; } void s390_handle_wait(S390CPU *cpu) From cc3d15a5ea960a65edbd1d6a3fb57e127f7a8080 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 28 Jan 2020 13:24:14 +0100 Subject: [PATCH 5/7] docs: rstfy s390 dasd ipl documentation While at it, also fix the numbering in 'What QEMU does'. Reviewed-by: Thomas Huth Message-Id: <20200213162942.14177-2-cohuck@redhat.com> Signed-off-by: Cornelia Huck --- MAINTAINERS | 2 +- docs/devel/index.rst | 1 + .../{s390-dasd-ipl.txt => s390-dasd-ipl.rst} | 117 +++++++++--------- 3 files changed, 63 insertions(+), 57 deletions(-) rename docs/devel/{s390-dasd-ipl.txt => s390-dasd-ipl.rst} (51%) diff --git a/MAINTAINERS b/MAINTAINERS index 36d94c17a6..c591ea6a60 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1259,7 +1259,7 @@ S: Supported F: hw/s390x/ipl.* F: pc-bios/s390-ccw/ F: pc-bios/s390-ccw.img -F: docs/devel/s390-dasd-ipl.txt +F: docs/devel/s390-dasd-ipl.rst T: git https://github.com/borntraeger/qemu.git s390-next L: qemu-s390x@nongnu.org diff --git a/docs/devel/index.rst b/docs/devel/index.rst index 4dc2ca8d71..b734ba4655 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -25,3 +25,4 @@ Contents: tcg-plugins bitops reset + s390-dasd-ipl diff --git a/docs/devel/s390-dasd-ipl.txt b/docs/devel/s390-dasd-ipl.rst similarity index 51% rename from docs/devel/s390-dasd-ipl.txt rename to docs/devel/s390-dasd-ipl.rst index 9107e048e4..2529eb5f54 100644 --- a/docs/devel/s390-dasd-ipl.txt +++ b/docs/devel/s390-dasd-ipl.rst @@ -1,49 +1,55 @@ -***************************** -***** s390 hardware IPL ***** -***************************** +Booting from real channel-attached devices on s390x +=================================================== + +s390 hardware IPL +----------------- The s390 hardware IPL process consists of the following steps. -1. A READ IPL ccw is constructed in memory location 0x0. - This ccw, by definition, reads the IPL1 record which is located on the disk - at cylinder 0 track 0 record 1. Note that the chain flag is on in this ccw - so when it is complete another ccw will be fetched and executed from memory - location 0x08. +1. A READ IPL ccw is constructed in memory location ``0x0``. + This ccw, by definition, reads the IPL1 record which is located on the disk + at cylinder 0 track 0 record 1. Note that the chain flag is on in this ccw + so when it is complete another ccw will be fetched and executed from memory + location ``0x08``. -2. Execute the Read IPL ccw at 0x00, thereby reading IPL1 data into 0x00. - IPL1 data is 24 bytes in length and consists of the following pieces of - information: [psw][read ccw][tic ccw]. When the machine executes the Read - IPL ccw it read the 24-bytes of IPL1 to be read into memory starting at - location 0x0. Then the ccw program at 0x08 which consists of a read - ccw and a tic ccw is automatically executed because of the chain flag from - the original READ IPL ccw. The read ccw will read the IPL2 data into memory - and the TIC (Transfer In Channel) will transfer control to the channel - program contained in the IPL2 data. The TIC channel command is the - equivalent of a branch/jump/goto instruction for channel programs. - NOTE: The ccws in IPL1 are defined by the architecture to be format 0. +2. Execute the Read IPL ccw at ``0x00``, thereby reading IPL1 data into ``0x00``. + IPL1 data is 24 bytes in length and consists of the following pieces of + information: ``[psw][read ccw][tic ccw]``. When the machine executes the Read + IPL ccw it read the 24-bytes of IPL1 to be read into memory starting at + location ``0x0``. Then the ccw program at ``0x08`` which consists of a read + ccw and a tic ccw is automatically executed because of the chain flag from + the original READ IPL ccw. The read ccw will read the IPL2 data into memory + and the TIC (Transfer In Channel) will transfer control to the channel + program contained in the IPL2 data. The TIC channel command is the + equivalent of a branch/jump/goto instruction for channel programs. + + NOTE: The ccws in IPL1 are defined by the architecture to be format 0. 3. Execute IPL2. - The TIC ccw instruction at the end of the IPL1 channel program will begin - the execution of the IPL2 channel program. IPL2 is stage-2 of the boot - process and will contain a larger channel program than IPL1. The point of - IPL2 is to find and load either the operating system or a small program that - loads the operating system from disk. At the end of this step all or some of - the real operating system is loaded into memory and we are ready to hand - control over to the guest operating system. At this point the guest - operating system is entirely responsible for loading any more data it might - need to function. NOTE: The IPL2 channel program might read data into memory - location 0 thereby overwriting the IPL1 psw and channel program. This is ok - as long as the data placed in location 0 contains a psw whose instruction - address points to the guest operating system code to execute at the end of - the IPL/boot process. - NOTE: The ccws in IPL2 are defined by the architecture to be format 0. + The TIC ccw instruction at the end of the IPL1 channel program will begin + the execution of the IPL2 channel program. IPL2 is stage-2 of the boot + process and will contain a larger channel program than IPL1. The point of + IPL2 is to find and load either the operating system or a small program that + loads the operating system from disk. At the end of this step all or some of + the real operating system is loaded into memory and we are ready to hand + control over to the guest operating system. At this point the guest + operating system is entirely responsible for loading any more data it might + need to function. + + NOTE: The IPL2 channel program might read data into memory + location ``0x0`` thereby overwriting the IPL1 psw and channel program. This is ok + as long as the data placed in location ``0x0`` contains a psw whose instruction + address points to the guest operating system code to execute at the end of + the IPL/boot process. + + NOTE: The ccws in IPL2 are defined by the architecture to be format 0. 4. Start executing the guest operating system. - The psw that was loaded into memory location 0 as part of the ipl process - should contain the needed flags for the operating system we have loaded. The - psw's instruction address will point to the location in memory where we want - to start executing the operating system. This psw is loaded (via LPSW - instruction) causing control to be passed to the operating system code. + The psw that was loaded into memory location ``0x0`` as part of the ipl process + should contain the needed flags for the operating system we have loaded. The + psw's instruction address will point to the location in memory where we want + to start executing the operating system. This psw is loaded (via LPSW + instruction) causing control to be passed to the operating system code. In a non-virtualized environment this process, handled entirely by the hardware, is kicked off by the user initiating a "Load" procedure from the hardware @@ -54,18 +60,17 @@ written immediately after the special "Read IPL" ccw, the IPL1 channel program will be executed immediately (the special read ccw has the chaining bit turned on). The TIC at the end of the IPL1 channel program will cause the IPL2 channel program to be executed automatically. After this sequence completes the "Load" -procedure then loads the psw from 0x0. +procedure then loads the psw from ``0x0``. -********************************************************** -***** How this all pertains to QEMU (and the kernel) ***** -********************************************************** +How this all pertains to QEMU (and the kernel) +---------------------------------------------- In theory we should merely have to do the following to IPL/boot a guest operating system from a DASD device: -1. Place a "Read IPL" ccw into memory location 0x0 with chaining bit on. -2. Execute channel program at 0x0. -3. LPSW 0x0. +1. Place a "Read IPL" ccw into memory location ``0x0`` with chaining bit on. +2. Execute channel program at ``0x0``. +3. LPSW ``0x0``. However, our emulation of the machine's channel program logic within the kernel is missing one key feature that is required for this process to work: @@ -89,32 +94,31 @@ Lastly, in some cases (the zipl bootloader for example) the IPL2 program also transfers control to another channel program segment immediately after reading it from the disk. So we need to be able to handle this case. -************************** -***** What QEMU does ***** -************************** +What QEMU does +-------------- Since we are forced to live with prefetch we cannot use the very simple IPL procedure we defined in the preceding section. So we compensate by doing the following. -1. Place "Read IPL" ccw into memory location 0x0, but turn off chaining bit. -2. Execute "Read IPL" at 0x0. +1. Place "Read IPL" ccw into memory location ``0x0``, but turn off chaining bit. +2. Execute "Read IPL" at ``0x0``. - So now IPL1's psw is at 0x0 and IPL1's channel program is at 0x08. + So now IPL1's psw is at ``0x0`` and IPL1's channel program is at ``0x08``. -4. Write a custom channel program that will seek to the IPL2 record and then +3. Write a custom channel program that will seek to the IPL2 record and then execute the READ and TIC ccws from IPL1. Normally the seek is not required because after reading the IPL1 record the disk is automatically positioned to read the very next record which will be IPL2. But since we are not reading both IPL1 and IPL2 as part of the same channel program we must manually set the position. -5. Grab the target address of the TIC instruction from the IPL1 channel program. +4. Grab the target address of the TIC instruction from the IPL1 channel program. This address is where the IPL2 channel program starts. Now IPL2 is loaded into memory somewhere, and we know the address. -6. Execute the IPL2 channel program at the address obtained in step #5. +5. Execute the IPL2 channel program at the address obtained in step #4. Because this channel program can be dynamic, we must use a special algorithm that detects a READ immediately followed by a TIC and breaks the ccw chain @@ -126,8 +130,9 @@ following. channel program from executing properly. Now the operating system code is loaded somewhere in guest memory and the psw - in memory location 0x0 will point to entry code for the guest operating + in memory location ``0x0`` will point to entry code for the guest operating system. -7. LPSW 0x0. +6. LPSW ``0x0`` + LPSW transfers control to the guest operating system and we're done. From 8f4335242a2ed7862363ff3bf08d0dfc3c3098e7 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 28 Jan 2020 18:37:27 +0100 Subject: [PATCH 6/7] docs: rstfy vfio-ap documentation Move to system/, as this is mostly about configuring vfio-ap. Message-Id: <20200213162942.14177-3-cohuck@redhat.com> Reviewed-by: Pierre Morel Signed-off-by: Cornelia Huck --- MAINTAINERS | 2 +- docs/system/index.rst | 1 + docs/{vfio-ap.txt => system/vfio-ap.rst} | 774 ++++++++++++----------- 3 files changed, 409 insertions(+), 368 deletions(-) rename docs/{vfio-ap.txt => system/vfio-ap.rst} (55%) diff --git a/MAINTAINERS b/MAINTAINERS index c591ea6a60..65c54874d8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1570,7 +1570,7 @@ F: hw/s390x/ap-bridge.c F: include/hw/s390x/ap-device.h F: include/hw/s390x/ap-bridge.h F: hw/vfio/ap.c -F: docs/vfio-ap.txt +F: docs/system/vfio-ap.rst L: qemu-s390x@nongnu.org vhost diff --git a/docs/system/index.rst b/docs/system/index.rst index f66e6ea585..1a4b2c82ac 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -15,3 +15,4 @@ Contents: :maxdepth: 2 qemu-block-drivers + vfio-ap diff --git a/docs/vfio-ap.txt b/docs/system/vfio-ap.rst similarity index 55% rename from docs/vfio-ap.txt rename to docs/system/vfio-ap.rst index b1eb2deeaf..3cd84179a2 100644 --- a/docs/vfio-ap.txt +++ b/docs/system/vfio-ap.rst @@ -1,17 +1,11 @@ Adjunct Processor (AP) Device ============================= -Contents: -========= -* Introduction -* AP Architectural Overview -* Start Interpretive Execution (SIE) Instruction -* AP Matrix Configuration on Linux Host -* Starting a Linux Guest Configured with an AP Matrix -* Example: Configure AP Matrices for Three Linux Guests +.. contents:: + +Introduction +------------ -Introduction: -============ The IBM Adjunct Processor (AP) Cryptographic Facility is comprised of three AP instructions and from 1 to 256 PCIe cryptographic adapter cards. These AP devices provide cryptographic functions to all CPUs assigned to a @@ -21,8 +15,9 @@ On s390x, AP adapter cards are exposed via the AP bus. This document describes how those cards may be made available to KVM guests using the VFIO mediated device framework. -AP Architectural Overview: -========================= +AP Architectural Overview +------------------------- + In order understand the terminology used in the rest of this document, let's start with some definitions: @@ -75,7 +70,8 @@ start with some definitions: must be one of the control domains. Start Interpretive Execution (SIE) Instruction -============================================== +---------------------------------------------- + A KVM guest is started by executing the Start Interpretive Execution (SIE) instruction. The SIE state description is a control block that contains the state information for a KVM guest and is supplied as input to the SIE @@ -114,246 +110,278 @@ The APQNs can provide secure key functionality - i.e., a private key is stored on the adapter card for each of its domains - so each APQN must be assigned to at most one guest or the linux host. - Example 1: Valid configuration: - ------------------------------ - Guest1: adapters 1,2 domains 5,6 - Guest2: adapter 1,2 domain 7 +Example 1: Valid configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - This is valid because both guests have a unique set of APQNs: Guest1 has - APQNs (1,5), (1,6), (2,5) and (2,6); Guest2 has APQNs (1,7) and (2,7). ++----------+--------+--------+ +| | Guest1 | Guest2 | ++==========+========+========+ +| adapters | 1, 2 | 1, 2 | ++----------+--------+--------+ +| domains | 5, 6 | 7 | ++----------+--------+--------+ - Example 2: Valid configuration: - ------------------------------ - Guest1: adapters 1,2 domains 5,6 - Guest2: adapters 3,4 domains 5,6 +This is valid because both guests have a unique set of APQNs: - This is also valid because both guests have a unique set of APQNs: - Guest1 has APQNs (1,5), (1,6), (2,5), (2,6); - Guest2 has APQNs (3,5), (3,6), (4,5), (4,6) +* Guest1 has APQNs (1,5), (1,6), (2,5) and (2,6); +* Guest2 has APQNs (1,7) and (2,7). - Example 3: Invalid configuration: - -------------------------------- - Guest1: adapters 1,2 domains 5,6 - Guest2: adapter 1 domains 6,7 +Example 2: Valid configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - This is an invalid configuration because both guests have access to - APQN (1,6). ++----------+--------+--------+ +| | Guest1 | Guest2 | ++==========+========+========+ +| adapters | 1, 2 | 3, 4 | ++----------+--------+--------+ +| domains | 5, 6 | 5, 6 | ++----------+--------+--------+ + +This is also valid because both guests have a unique set of APQNs: + +* Guest1 has APQNs (1,5), (1,6), (2,5), (2,6); +* Guest2 has APQNs (3,5), (3,6), (4,5), (4,6) + +Example 3: Invalid configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + ++----------+--------+--------+ +| | Guest1 | Guest2 | ++==========+========+========+ +| adapters | 1, 2 | 1 | ++----------+--------+--------+ +| domains | 5, 6 | 6, 7 | ++----------+--------+--------+ + +This is an invalid configuration because both guests have access to +APQN (1,6). + +AP Matrix Configuration on Linux Host +------------------------------------- -AP Matrix Configuration on Linux Host: -===================================== A linux system is a guest of the LPAR in which it is running and has access to the AP resources configured for the LPAR. The LPAR's AP matrix is configured via its Activation Profile which can be edited on the HMC. When the linux system is started, the AP bus will detect the AP devices assigned to the -LPAR and create the following in sysfs: +LPAR and create the following in sysfs:: -/sys/bus/ap -... [devices] -...... xx.yyyy -...... ... -...... cardxx -...... ... + /sys/bus/ap + ... [devices] + ...... xx.yyyy + ...... ... + ...... cardxx + ...... ... Where: - cardxx is AP adapter number xx (in hex) -....xx.yyyy is an APQN with xx specifying the APID and yyyy specifying the - APQI + +``cardxx`` + is AP adapter number xx (in hex) + +``xx.yyyy`` + is an APQN with xx specifying the APID and yyyy specifying the APQI For example, if AP adapters 5 and 6 and domains 4, 71 (0x47), 171 (0xab) and 255 (0xff) are configured for the LPAR, the sysfs representation on the linux -host system would look like this: +host system would look like this:: -/sys/bus/ap -... [devices] -...... 05.0004 -...... 05.0047 -...... 05.00ab -...... 05.00ff -...... 06.0004 -...... 06.0047 -...... 06.00ab -...... 06.00ff -...... card05 -...... card06 + /sys/bus/ap + ... [devices] + ...... 05.0004 + ...... 05.0047 + ...... 05.00ab + ...... 05.00ff + ...... 06.0004 + ...... 06.0047 + ...... 06.00ab + ...... 06.00ff + ...... card05 + ...... card06 A set of default device drivers are also created to control each type of AP -device that can be assigned to the LPAR on which a linux host is running: +device that can be assigned to the LPAR on which a linux host is running:: -/sys/bus/ap -... [drivers] -...... [cex2acard] for Crypto Express 2/3 accelerator cards -...... [cex2aqueue] for AP queues served by Crypto Express 2/3 - accelerator cards -...... [cex4card] for Crypto Express 4/5/6 accelerator and coprocessor - cards -...... [cex4queue] for AP queues served by Crypto Express 4/5/6 - accelerator and coprocessor cards -...... [pcixcccard] for Crypto Express 2/3 coprocessor cards -...... [pcixccqueue] for AP queues served by Crypto Express 2/3 - coprocessor cards + /sys/bus/ap + ... [drivers] + ...... [cex2acard] for Crypto Express 2/3 accelerator cards + ...... [cex2aqueue] for AP queues served by Crypto Express 2/3 + accelerator cards + ...... [cex4card] for Crypto Express 4/5/6 accelerator and coprocessor + cards + ...... [cex4queue] for AP queues served by Crypto Express 4/5/6 + accelerator and coprocessor cards + ...... [pcixcccard] for Crypto Express 2/3 coprocessor cards + ...... [pcixccqueue] for AP queues served by Crypto Express 2/3 + coprocessor cards Binding AP devices to device drivers ------------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + There are two sysfs files that specify bitmasks marking a subset of the APQN range as 'usable by the default AP queue device drivers' or 'not usable by the default device drivers' and thus available for use by the alternate device -driver(s). The sysfs locations of the masks are: +driver(s). The sysfs locations of the masks are:: /sys/bus/ap/apmask /sys/bus/ap/aqmask - The 'apmask' is a 256-bit mask that identifies a set of AP adapter IDs - (APID). Each bit in the mask, from left to right (i.e., from most significant - to least significant bit in big endian order), corresponds to an APID from - 0-255. If a bit is set, the APID is marked as usable only by the default AP - queue device drivers; otherwise, the APID is usable by the vfio_ap - device driver. +The ``apmask`` is a 256-bit mask that identifies a set of AP adapter IDs +(APID). Each bit in the mask, from left to right (i.e., from most significant +to least significant bit in big endian order), corresponds to an APID from +0-255. If a bit is set, the APID is marked as usable only by the default AP +queue device drivers; otherwise, the APID is usable by the vfio_ap +device driver. - The 'aqmask' is a 256-bit mask that identifies a set of AP queue indexes - (APQI). Each bit in the mask, from left to right (i.e., from most significant - to least significant bit in big endian order), corresponds to an APQI from - 0-255. If a bit is set, the APQI is marked as usable only by the default AP - queue device drivers; otherwise, the APQI is usable by the vfio_ap device - driver. +The ``aqmask`` is a 256-bit mask that identifies a set of AP queue indexes +(APQI). Each bit in the mask, from left to right (i.e., from most significant +to least significant bit in big endian order), corresponds to an APQI from +0-255. If a bit is set, the APQI is marked as usable only by the default AP +queue device drivers; otherwise, the APQI is usable by the vfio_ap device +driver. - Take, for example, the following mask: +Take, for example, the following mask:: 0x7dffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff - It indicates: +It indicates: 1, 2, 3, 4, 5, and 7-255 belong to the default drivers' pool, and 0 and 6 belong to the vfio_ap device driver's pool. - The APQN of each AP queue device assigned to the linux host is checked by the - AP bus against the set of APQNs derived from the cross product of APIDs - and APQIs marked as usable only by the default AP queue device drivers. If a - match is detected, only the default AP queue device drivers will be probed; - otherwise, the vfio_ap device driver will be probed. +The APQN of each AP queue device assigned to the linux host is checked by the +AP bus against the set of APQNs derived from the cross product of APIDs +and APQIs marked as usable only by the default AP queue device drivers. If a +match is detected, only the default AP queue device drivers will be probed; +otherwise, the vfio_ap device driver will be probed. - By default, the two masks are set to reserve all APQNs for use by the default - AP queue device drivers. There are two ways the default masks can be changed: +By default, the two masks are set to reserve all APQNs for use by the default +AP queue device drivers. There are two ways the default masks can be changed: - 1. The sysfs mask files can be edited by echoing a string into the - respective sysfs mask file in one of two formats: + 1. The sysfs mask files can be edited by echoing a string into the + respective sysfs mask file in one of two formats: - * An absolute hex string starting with 0x - like "0x12345678" - sets - the mask. If the given string is shorter than the mask, it is padded - with 0s on the right; for example, specifying a mask value of 0x41 is - the same as specifying: + * An absolute hex string starting with 0x - like "0x12345678" - sets + the mask. If the given string is shorter than the mask, it is padded + with 0s on the right; for example, specifying a mask value of 0x41 is + the same as specifying:: 0x4100000000000000000000000000000000000000000000000000000000000000 - Keep in mind that the mask reads from left to right (i.e., most - significant to least significant bit in big endian order), so the mask - above identifies device numbers 1 and 7 (01000001). + Keep in mind that the mask reads from left to right (i.e., most + significant to least significant bit in big endian order), so the mask + above identifies device numbers 1 and 7 (``01000001``). - If the string is longer than the mask, the operation is terminated with - an error (EINVAL). + If the string is longer than the mask, the operation is terminated with + an error (EINVAL). - * Individual bits in the mask can be switched on and off by specifying - each bit number to be switched in a comma separated list. Each bit - number string must be prepended with a ('+') or minus ('-') to indicate - the corresponding bit is to be switched on ('+') or off ('-'). Some - valid values are: + * Individual bits in the mask can be switched on and off by specifying + each bit number to be switched in a comma separated list. Each bit + number string must be prepended with a (``+``) or minus (``-``) to indicate + the corresponding bit is to be switched on (``+``) or off (``-``). Some + valid values are:: "+0" switches bit 0 on "-13" switches bit 13 off "+0x41" switches bit 65 on "-0xff" switches bit 255 off - The following example: + The following example:: + +0,-6,+0x47,-0xf0 - Switches bits 0 and 71 (0x47) on - Switches bits 6 and 240 (0xf0) off + Switches bits 0 and 71 (0x47) on + Switches bits 6 and 240 (0xf0) off - Note that the bits not specified in the list remain as they were before - the operation. + Note that the bits not specified in the list remain as they were before + the operation. - 2. The masks can also be changed at boot time via parameters on the kernel - command line like this: + 2. The masks can also be changed at boot time via parameters on the kernel + command line like this:: ap.apmask=0xffff ap.aqmask=0x40 - This would create the following masks: + This would create the following masks: + + apmask:: - apmask: 0xffff000000000000000000000000000000000000000000000000000000000000 - aqmask: + aqmask:: + 0x4000000000000000000000000000000000000000000000000000000000000000 - Resulting in these two pools: + Resulting in these two pools:: default drivers pool: adapter 0-15, domain 1 alternate drivers pool: adapter 16-255, domains 0, 2-255 -Configuring an AP matrix for a linux guest. ------------------------------------------- +Configuring an AP matrix for a linux guest +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + The sysfs interfaces for configuring an AP matrix for a guest are built on the VFIO mediated device framework. To configure an AP matrix for a guest, a -mediated matrix device must first be created for the /sys/devices/vfio_ap/matrix +mediated matrix device must first be created for the ``/sys/devices/vfio_ap/matrix`` device. When the vfio_ap device driver is loaded, it registers with the VFIO mediated device framework. When the driver registers, the sysfs interfaces for -creating mediated matrix devices is created: +creating mediated matrix devices is created:: -/sys/devices -... [vfio_ap] -......[matrix] -......... [mdev_supported_types] -............ [vfio_ap-passthrough] -............... create -............... [devices] + /sys/devices + ... [vfio_ap] + ......[matrix] + ......... [mdev_supported_types] + ............ [vfio_ap-passthrough] + ............... create + ............... [devices] A mediated AP matrix device is created by writing a UUID to the attribute file -named 'create', for example: +named ``create``, for example:: uuidgen > create - or +or + +:: echo $uuid > create When a mediated AP matrix device is created, a sysfs directory named after -the UUID is created in the 'devices' subdirectory: +the UUID is created in the ``devices`` subdirectory:: -/sys/devices -... [vfio_ap] -......[matrix] -......... [mdev_supported_types] -............ [vfio_ap-passthrough] -............... create -............... [devices] -.................. [$uuid] + /sys/devices + ... [vfio_ap] + ......[matrix] + ......... [mdev_supported_types] + ............ [vfio_ap-passthrough] + ............... create + ............... [devices] + .................. [$uuid] There will also be three sets of attribute files created in the mediated matrix device's sysfs directory to configure an AP matrix for the -KVM guest: +KVM guest:: -/sys/devices -... [vfio_ap] -......[matrix] -......... [mdev_supported_types] -............ [vfio_ap-passthrough] -............... create -............... [devices] -.................. [$uuid] -..................... assign_adapter -..................... assign_control_domain -..................... assign_domain -..................... matrix -..................... unassign_adapter -..................... unassign_control_domain -..................... unassign_domain + /sys/devices + ... [vfio_ap] + ......[matrix] + ......... [mdev_supported_types] + ............ [vfio_ap-passthrough] + ............... create + ............... [devices] + .................. [$uuid] + ..................... assign_adapter + ..................... assign_control_domain + ..................... assign_domain + ..................... matrix + ..................... unassign_adapter + ..................... unassign_control_domain + ..................... unassign_domain -assign_adapter +``assign_adapter`` To assign an AP adapter to the mediated matrix device, its APID is written - to the 'assign_adapter' file. This may be done multiple times to assign more + to the ``assign_adapter`` file. This may be done multiple times to assign more than one adapter. The APID may be specified using conventional semantics as a decimal, hexadecimal, or octal number. For example, to assign adapters 4, 5 and 16 to a mediated matrix device in decimal, hexadecimal and octal - respectively: + respectively:: echo 4 > assign_adapter echo 0x5 > assign_adapter @@ -373,22 +401,22 @@ assign_adapter APQNs are bound to the driver, the operation will terminate with an error (EADDRNOTAVAIL). - No APQN that can be derived from the adapter ID and the IDs of the + * No APQN that can be derived from the adapter ID and the IDs of the previously assigned domains can be assigned to another mediated matrix device. If an APQN is assigned to another mediated matrix device, the operation will terminate with an error (EADDRINUSE). -unassign_adapter - To unassign an AP adapter, its APID is written to the 'unassign_adapter' +``unassign_adapter`` + To unassign an AP adapter, its APID is written to the ``unassign_adapter`` file. This may also be done multiple times to unassign more than one adapter. -assign_domain +``assign_domain`` To assign a usage domain, the domain number is written into the - 'assign_domain' file. This may be done multiple times to assign more than one + ``assign_domain`` file. This may be done multiple times to assign more than one usage domain. The domain number is specified using conventional semantics as a decimal, hexadecimal, or octal number. For example, to assign usage domains 4, 8, and 71 to a mediated matrix device in decimal, hexadecimal and octal - respectively: + respectively:: echo 4 > assign_domain echo 0x8 > assign_domain @@ -408,23 +436,23 @@ assign_domain APQNs are bound to the driver, the operation will terminate with an error (EADDRNOTAVAIL). - No APQN that can be derived from the domain ID being assigned and the IDs + * No APQN that can be derived from the domain ID being assigned and the IDs of the previously assigned adapters can be assigned to another mediated matrix device. If an APQN is assigned to another mediated matrix device, the operation will terminate with an error (EADDRINUSE). -unassign_domain +``unassign_domain`` To unassign a usage domain, the domain number is written into the - 'unassign_domain' file. This may be done multiple times to unassign more than + ``unassign_domain`` file. This may be done multiple times to unassign more than one usage domain. -assign_control_domain +``assign_control_domain`` To assign a control domain, the domain number is written into the - 'assign_control_domain' file. This may be done multiple times to + ``assign_control_domain`` file. This may be done multiple times to assign more than one control domain. The domain number may be specified using conventional semantics as a decimal, hexadecimal, or octal number. For example, to assign control domains 4, 8, and 71 to a mediated matrix device - in decimal, hexadecimal and octal respectively: + in decimal, hexadecimal and octal respectively:: echo 4 > assign_domain echo 0x8 > assign_domain @@ -435,33 +463,34 @@ assign_control_domain allowed by the machine model. If a control domain number higher than the maximum is specified, the operation will terminate with an error (ENODEV). -unassign_control_domain +``unassign_control_domain`` To unassign a control domain, the domain number is written into the - 'unassign_domain' file. This may be done multiple times to unassign more than + ``unassign_domain`` file. This may be done multiple times to unassign more than one control domain. Notes: No changes to the AP matrix will be allowed while a guest using the mediated matrix device is running. Attempts to assign an adapter, domain or control domain will be rejected and an error (EBUSY) returned. -Starting a Linux Guest Configured with an AP Matrix: -=================================================== +Starting a Linux Guest Configured with an AP Matrix +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + To provide a mediated matrix device for use by a guest, the following option -must be specified on the QEMU command line: +must be specified on the QEMU command line:: -device vfio_ap,sysfsdev=$path-to-mdev The sysfsdev parameter specifies the path to the mediated matrix device. -There are a number of ways to specify this path: +There are a number of ways to specify this path:: -/sys/devices/vfio_ap/matrix/$uuid -/sys/bus/mdev/devices/$uuid -/sys/bus/mdev/drivers/vfio_mdev/$uuid -/sys/devices/vfio_ap/matrix/mdev_supported_types/vfio_ap-passthrough/devices/$uuid + /sys/devices/vfio_ap/matrix/$uuid + /sys/bus/mdev/devices/$uuid + /sys/bus/mdev/drivers/vfio_mdev/$uuid + /sys/devices/vfio_ap/matrix/mdev_supported_types/vfio_ap-passthrough/devices/$uuid When the linux guest is started, the guest will open the mediated matrix device's file descriptor to get information about the mediated matrix -device. The vfio_ap device driver will update the APM, AQM, and ADM fields in +device. The ``vfio_ap`` device driver will update the APM, AQM, and ADM fields in the guest's CRYCB with the adapter, usage domain and control domains assigned via the mediated matrix device's sysfs attribute files. Programs running on the linux guest will then: @@ -486,20 +515,22 @@ facilities: The AP facilities feature indicates that AP facilities are installed on the guest. This feature will be exposed for use only if the AP facilities are installed on the host system. The feature is s390-specific and is - represented as a parameter of the -cpu option on the QEMU command line: + represented as a parameter of the -cpu option on the QEMU command line:: qemu-system-s390x -cpu $model,ap=on|off - Where: + Where: - $model is the CPU model defined for the guest (defaults to the model of - the host system if not specified). + ``$model`` + is the CPU model defined for the guest (defaults to the model of + the host system if not specified). - ap=on|off indicates whether AP facilities are installed (on) or not - (off). The default for CPU models zEC12 or newer - is ap=on. AP facilities must be installed on the guest if a - vfio-ap device (-device vfio-ap,sysfsdev=$path) is configured - for the guest, or the guest will fail to start. + ``ap=on|off`` + indicates whether AP facilities are installed (on) or not + (off). The default for CPU models zEC12 or newer + is ``ap=on``. AP facilities must be installed on the guest if a + vfio-ap device (``-device vfio-ap,sysfsdev=$path``) is configured + for the guest, or the guest will fail to start. 2. Query Configuration Information (QCI) facility @@ -507,27 +538,29 @@ facilities: configuration of the AP facilities. This facility will be available only if the QCI facility is installed on the host system. The feature is s390-specific and is represented as a parameter of the -cpu option on the - QEMU command line: + QEMU command line:: qemu-system-s390x -cpu $model,apqci=on|off - Where: + Where: - $model is the CPU model defined for the guest + ``$model`` + is the CPU model defined for the guest - apqci=on|off indicates whether the QCI facility is installed (on) or - not (off). The default for CPU models zEC12 or newer - is apqci=on; for older models, QCI will not be installed. + ``apqci=on|off`` + indicates whether the QCI facility is installed (on) or + not (off). The default for CPU models zEC12 or newer + is ``apqci=on``; for older models, QCI will not be installed. - If QCI is installed (apqci=on) but AP facilities are not - (ap=off), an error message will be logged, but the guest - will be allowed to start. It makes no sense to have QCI - installed if the AP facilities are not; this is considered - an invalid configuration. + If QCI is installed (``apqci=on``) but AP facilities are not + (``ap=off``), an error message will be logged, but the guest + will be allowed to start. It makes no sense to have QCI + installed if the AP facilities are not; this is considered + an invalid configuration. - If the QCI facility is not installed, APQNs with an APQI - greater than 15 will not be detected by the AP bus - running on the guest. + If the QCI facility is not installed, APQNs with an APQI + greater than 15 will not be detected by the AP bus + running on the guest. 3. Adjunct Process Facility Test (APFT) facility @@ -535,48 +568,51 @@ facilities: AP facilities available for a given AP queue. This facility will be available only if the APFT facility is installed on the host system. The feature is s390-specific and is represented as a parameter of the -cpu option on the - QEMU command line: + QEMU command line:: qemu-system-s390x -cpu $model,apft=on|off - Where: + Where: - $model is the CPU model defined for the guest (defaults to the model of - the host system if not specified). + ``$model`` + is the CPU model defined for the guest (defaults to the model of + the host system if not specified). - apft=on|off indicates whether the APFT facility is installed (on) or - not (off). The default for CPU models zEC12 and - newer is apft=on for older models, APFT will not be - installed. + ``apft=on|off`` + indicates whether the APFT facility is installed (on) or + not (off). The default for CPU models zEC12 and + newer is ``apft=on`` for older models, APFT will not be + installed. - If APFT is installed (apft=on) but AP facilities are not - (ap=off), an error message will be logged, but the guest - will be allowed to start. It makes no sense to have APFT - installed if the AP facilities are not; this is considered - an invalid configuration. + If APFT is installed (``apft=on``) but AP facilities are not + (``ap=off``), an error message will be logged, but the guest + will be allowed to start. It makes no sense to have APFT + installed if the AP facilities are not; this is considered + an invalid configuration. - It also makes no sense to turn APFT off because the AP bus - running on the guest will not detect CEX4 and newer devices - without it. Since only CEX4 and newer devices are supported - for guest usage, no AP devices can be made accessible to a - guest started without APFT installed. + It also makes no sense to turn APFT off because the AP bus + running on the guest will not detect CEX4 and newer devices + without it. Since only CEX4 and newer devices are supported + for guest usage, no AP devices can be made accessible to a + guest started without APFT installed. + +Hot plug a vfio-ap device into a running guest +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Hot plug a vfio-ap device into a running guest: -============================================== Only one vfio-ap device can be attached to the virtual machine's ap-bus, so a vfio-ap device can be hot plugged if and only if no vfio-ap device is attached to the bus already, whether via the QEMU command line or a prior hot plug action. -To hot plug a vfio-ap device, use the QEMU device_add command: +To hot plug a vfio-ap device, use the QEMU ``device_add`` command:: (qemu) device_add vfio-ap,sysfsdev="$path-to-mdev" - Where the '$path-to-mdev' value specifies the absolute path to a mediated - device to which AP resources to be used by the guest have been assigned. +Where the ``$path-to-mdev`` value specifies the absolute path to a mediated +device to which AP resources to be used by the guest have been assigned. Note that on Linux guests, the AP devices will be created in the -/sys/bus/ap/devices directory when the AP bus subsequently performs its periodic +``/sys/bus/ap/devices`` directory when the AP bus subsequently performs its periodic scan, so there may be a short delay before the AP devices are accessible on the guest. @@ -587,66 +623,69 @@ The command will fail if: * The CPU model features for controlling guest access to AP facilities are not enabled (see 'CPU model features' subsection in the previous section). -Hot unplug a vfio-ap device from a running guest: -================================================ +Hot unplug a vfio-ap device from a running guest +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + A vfio-ap device can be unplugged from a running KVM guest if a vfio-ap device has been attached to the virtual machine's ap-bus via the QEMU command line or a prior hot plug action. -To hot unplug a vfio-ap device, use the QEMU device_del command: +To hot unplug a vfio-ap device, use the QEMU ``device_del`` command:: (qemu) device_del vfio-ap,sysfsdev="$path-to-mdev" - Where $path-to-mdev is the same as the path specified when the vfio-ap - device was attached to the virtual machine's ap-bus. +Where ``$path-to-mdev`` is the same as the path specified when the vfio-ap +device was attached to the virtual machine's ap-bus. -On a Linux guest, the AP devices will be removed from the /sys/bus/ap/devices +On a Linux guest, the AP devices will be removed from the ``/sys/bus/ap/devices`` directory on the guest when the AP bus subsequently performs its periodic scan, so there may be a short delay before the AP devices are no longer accessible by the guest. -The command will fail if the $path-to-mdev specified on the device_del command +The command will fail if the ``$path-to-mdev`` specified on the ``device_del`` command does not match the value specified when the vfio-ap device was attached to the virtual machine's ap-bus. -Example: Configure AP Matrixes for Three Linux Guests: -===================================================== +Example: Configure AP Matrices for Three Linux Guests +----------------------------------------------------- + Let's now provide an example to illustrate how KVM guests may be given access to AP facilities. For this example, we will show how to configure three guests such that executing the lszcrypt command on the guests would look like this: -Guest1 ------- -CARD.DOMAIN TYPE MODE ------------------------------- -05 CEX5C CCA-Coproc -05.0004 CEX5C CCA-Coproc -05.00ab CEX5C CCA-Coproc -06 CEX5A Accelerator -06.0004 CEX5A Accelerator -06.00ab CEX5C CCA-Coproc +Guest1:: -Guest2 ------- -CARD.DOMAIN TYPE MODE ------------------------------- -05 CEX5A Accelerator -05.0047 CEX5A Accelerator -05.00ff CEX5A Accelerator (5,4), (5,171), (6,4), (6,171), + CARD.DOMAIN TYPE MODE + ------------------------------ + 05 CEX5C CCA-Coproc + 05.0004 CEX5C CCA-Coproc + 05.00ab CEX5C CCA-Coproc + 06 CEX5A Accelerator + 06.0004 CEX5A Accelerator + 06.00ab CEX5C CCA-Coproc -Guest3 ------- -CARD.DOMAIN TYPE MODE ------------------------------- -06 CEX5A Accelerator -06.0047 CEX5A Accelerator -06.00ff CEX5A Accelerator +Guest2:: + + CARD.DOMAIN TYPE MODE + ------------------------------ + 05 CEX5A Accelerator + 05.0047 CEX5A Accelerator + 05.00ff CEX5A Accelerator + +Guest3:: + + CARD.DOMAIN TYPE MODE + ------------------------------ + 06 CEX5A Accelerator + 06.0047 CEX5A Accelerator + 06.00ff CEX5A Accelerator These are the steps: 1. Install the vfio_ap module on the linux host. The dependency chain for the vfio_ap module is: + * iommu * s390 * zcrypt @@ -657,6 +696,7 @@ These are the steps: To build the vfio_ap module, the kernel build must be configured with the following Kconfig elements selected: + * IOMMU_SUPPORT * S390 * ZCRYPT @@ -666,21 +706,21 @@ These are the steps: * VFIO_MDEV_DEVICE * KVM - If using make menuconfig select the following to build the vfio_ap module: - -> Device Drivers - -> IOMMU Hardware Support - select S390 AP IOMMU Support - -> VFIO Non-Privileged userspace driver framework - -> Mediated device driver framework - -> VFIO driver for Mediated devices - -> I/O subsystem - -> VFIO support for AP devices + If using make menuconfig select the following to build the vfio_ap module:: + -> Device Drivers + -> IOMMU Hardware Support + select S390 AP IOMMU Support + -> VFIO Non-Privileged userspace driver framework + -> Mediated device driver framework + -> VFIO driver for Mediated devices + -> I/O subsystem + -> VFIO support for AP devices 2. Secure the AP queues to be used by the three guests so that the host can not access them. To secure the AP queues 05.0004, 05.0047, 05.00ab, 05.00ff, 06.0004, 06.0047, 06.00ab, and 06.00ff for use by the vfio_ap device driver, the corresponding APQNs must be removed from the default queue drivers pool - as follows: + as follows:: echo -5,-6 > /sys/bus/ap/apmask @@ -689,19 +729,19 @@ These are the steps: This will result in AP queues 05.0004, 05.0047, 05.00ab, 05.00ff, 06.0004, 06.0047, 06.00ab, and 06.00ff getting bound to the vfio_ap device driver. The sysfs directory for the vfio_ap device driver will now contain symbolic links - to the AP queue devices bound to it: + to the AP queue devices bound to it:: - /sys/bus/ap - ... [drivers] - ...... [vfio_ap] - ......... [05.0004] - ......... [05.0047] - ......... [05.00ab] - ......... [05.00ff] - ......... [06.0004] - ......... [06.0047] - ......... [06.00ab] - ......... [06.00ff] + /sys/bus/ap + ... [drivers] + ...... [vfio_ap] + ......... [05.0004] + ......... [05.0047] + ......... [05.00ab] + ......... [05.00ff] + ......... [06.0004] + ......... [06.0047] + ......... [06.00ab] + ......... [06.00ff] Keep in mind that only type 10 and newer adapters (i.e., CEX4 and later) can be bound to the vfio_ap device driver. The reason for this is to @@ -712,153 +752,153 @@ These are the steps: The administrator, therefore, must take care to secure only AP queues that can be bound to the vfio_ap device driver. The device type for a given AP queue device can be read from the parent card's sysfs directory. For example, - to see the hardware type of the queue 05.0004: + to see the hardware type of the queue 05.0004:: - cat /sys/bus/ap/devices/card05/hwtype + cat /sys/bus/ap/devices/card05/hwtype The hwtype must be 10 or higher (CEX4 or newer) in order to be bound to the vfio_ap device driver. 3. Create the mediated devices needed to configure the AP matrixes for the three guests and to provide an interface to the vfio_ap driver for - use by the guests: + use by the guests:: - /sys/devices/vfio_ap/matrix/ - --- [mdev_supported_types] - ------ [vfio_ap-passthrough] (passthrough mediated matrix device type) - --------- create - --------- [devices] + /sys/devices/vfio_ap/matrix/ + ... [mdev_supported_types] + ...... [vfio_ap-passthrough] (passthrough mediated matrix device type) + ......... create + ......... [devices] - To create the mediated devices for the three guests: + To create the mediated devices for the three guests:: uuidgen > create uuidgen > create uuidgen > create - or + or - echo $uuid1 > create - echo $uuid2 > create - echo $uuid3 > create + :: + + echo $uuid1 > create + echo $uuid2 > create + echo $uuid3 > create This will create three mediated devices in the [devices] subdirectory named after the UUID used to create the mediated device. We'll call them $uuid1, - $uuid2 and $uuid3 and this is the sysfs directory structure after creation: + $uuid2 and $uuid3 and this is the sysfs directory structure after creation:: - /sys/devices/vfio_ap/matrix/ - --- [mdev_supported_types] - ------ [vfio_ap-passthrough] - --------- [devices] - ------------ [$uuid1] - --------------- assign_adapter - --------------- assign_control_domain - --------------- assign_domain - --------------- matrix - --------------- unassign_adapter - --------------- unassign_control_domain - --------------- unassign_domain + /sys/devices/vfio_ap/matrix/ + ... [mdev_supported_types] + ...... [vfio_ap-passthrough] + ......... [devices] + ............ [$uuid1] + ............... assign_adapter + ............... assign_control_domain + ............... assign_domain + ............... matrix + ............... unassign_adapter + ............... unassign_control_domain + ............... unassign_domain - ------------ [$uuid2] - --------------- assign_adapter - --------------- assign_control_domain - --------------- assign_domain - --------------- matrix - --------------- unassign_adapter - ----------------unassign_control_domain - ----------------unassign_domain + ............ [$uuid2] + ............... assign_adapter + ............... assign_control_domain + ............... assign_domain + ............... matrix + ............... unassign_adapter + ............... unassign_control_domain + ............... unassign_domain - ------------ [$uuid3] - --------------- assign_adapter - --------------- assign_control_domain - --------------- assign_domain - --------------- matrix - --------------- unassign_adapter - ----------------unassign_control_domain - ----------------unassign_domain + ............ [$uuid3] + ............... assign_adapter + ............... assign_control_domain + ............... assign_domain + ............... matrix + ............... unassign_adapter + ............... unassign_control_domain + ............... unassign_domain 4. The administrator now needs to configure the matrixes for the mediated devices $uuid1 (for Guest1), $uuid2 (for Guest2) and $uuid3 (for Guest3). - This is how the matrix is configured for Guest1: + This is how the matrix is configured for Guest1:: echo 5 > assign_adapter echo 6 > assign_adapter echo 4 > assign_domain echo 0xab > assign_domain - Control domains can similarly be assigned using the assign_control_domain - sysfs file. + Control domains can similarly be assigned using the assign_control_domain + sysfs file. - If a mistake is made configuring an adapter, domain or control domain, - you can use the unassign_xxx interfaces to unassign the adapter, domain or - control domain. + If a mistake is made configuring an adapter, domain or control domain, + you can use the ``unassign_xxx`` interfaces to unassign the adapter, domain or + control domain. - To display the matrix configuration for Guest1: + To display the matrix configuration for Guest1:: cat matrix - The output will display the APQNs in the format xx.yyyy, where xx is - the adapter number and yyyy is the domain number. The output for Guest1 - will look like this: + The output will display the APQNs in the format ``xx.yyyy``, where xx is + the adapter number and yyyy is the domain number. The output for Guest1 + will look like this:: 05.0004 05.00ab 06.0004 06.00ab - This is how the matrix is configured for Guest2: + This is how the matrix is configured for Guest2:: echo 5 > assign_adapter echo 0x47 > assign_domain echo 0xff > assign_domain - This is how the matrix is configured for Guest3: + This is how the matrix is configured for Guest3:: echo 6 > assign_adapter echo 0x47 > assign_domain echo 0xff > assign_domain -5. Start Guest1: +5. Start Guest1:: - /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \ - -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid1 ... + /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid1 ... -7. Start Guest2: +7. Start Guest2:: - /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \ - -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid2 ... + /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid2 ... -7. Start Guest3: +7. Start Guest3:: - /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \ - -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid3 ... + /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid3 ... When the guest is shut down, the mediated matrix devices may be removed. -Using our example again, to remove the mediated matrix device $uuid1: +Using our example again, to remove the mediated matrix device $uuid1:: /sys/devices/vfio_ap/matrix/ - --- [mdev_supported_types] - ------ [vfio_ap-passthrough] - --------- [devices] - ------------ [$uuid1] - --------------- remove + ... [mdev_supported_types] + ...... [vfio_ap-passthrough] + ......... [devices] + ............ [$uuid1] + ............... remove echo 1 > remove - This will remove all of the mdev matrix device's sysfs structures including - the mdev device itself. To recreate and reconfigure the mdev matrix device, - all of the steps starting with step 3 will have to be performed again. Note - that the remove will fail if a guest using the mdev is still running. +This will remove all of the mdev matrix device's sysfs structures including +the mdev device itself. To recreate and reconfigure the mdev matrix device, +all of the steps starting with step 3 will have to be performed again. Note +that the remove will fail if a guest using the mdev is still running. - It is not necessary to remove an mdev matrix device, but one may want to - remove it if no guest will use it during the remaining lifetime of the linux - host. If the mdev matrix device is removed, one may want to also reconfigure - the pool of adapters and queues reserved for use by the default drivers. +It is not necessary to remove an mdev matrix device, but one may want to +remove it if no guest will use it during the remaining lifetime of the linux +host. If the mdev matrix device is removed, one may want to also reconfigure +the pool of adapters and queues reserved for use by the default drivers. Limitations -=========== +----------- + * The KVM/kernel interfaces do not provide a way to prevent restoring an APQN to the default drivers pool of a queue that is still assigned to a mediated device in use by a guest. It is incumbent upon the administrator to @@ -867,10 +907,10 @@ Limitations device, such as a private key configured specifically for the guest. * Dynamically assigning AP resources to or unassigning AP resources from a - mediated matrix device - see 'Configuring an AP matrix for a linux guest' + mediated matrix device - see `Configuring an AP matrix for a linux guest`_ section above - while a running guest is using it is currently not supported. * Live guest migration is not supported for guests using AP devices. If a guest is using AP devices, the vfio-ap device configured for the guest must be - unplugged before migrating the guest (see 'Hot unplug a vfio-ap device from a - running guest' section above. + unplugged before migrating the guest (see `Hot unplug a vfio-ap device from a + running guest`_ section above.) From b6c2dbd7214b0b2396e1dcf9668c8b48ab571115 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Thu, 27 Feb 2020 04:23:41 -0500 Subject: [PATCH 7/7] s390x: Rename and use constants for short PSW address and mask Let's rename PSW_MASK_ESA_ADDR to PSW_MASK_SHORT_ADDR because we're not working with a ESA PSW which would not support the extended addressing bit. Also let's actually use it. Additionally we introduce PSW_MASK_SHORT_CTRL and use it throughout the codebase. Signed-off-by: Janosch Frank Reviewed-by: Christian Borntraeger Reviewed-by: David Hildenbrand Message-Id: <20200227092341.38558-1-frankja@linux.ibm.com> Signed-off-by: Cornelia Huck --- hw/s390x/ipl.c | 2 +- target/s390x/cpu.c | 4 ++-- target/s390x/cpu.h | 3 ++- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c index 0817874b48..9c1ecd423c 100644 --- a/hw/s390x/ipl.c +++ b/hw/s390x/ipl.c @@ -179,7 +179,7 @@ static void s390_ipl_realize(DeviceState *dev, Error **errp) /* if not Linux load the address of the (short) IPL PSW */ ipl_psw = rom_ptr(4, 4); if (ipl_psw) { - pentry = be32_to_cpu(*ipl_psw) & 0x7fffffffUL; + pentry = be32_to_cpu(*ipl_psw) & PSW_MASK_SHORT_ADDR; } else { error_setg(&err, "Could not get IPL PSW"); goto error; diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index 8da1905485..3dd396e870 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -78,13 +78,13 @@ static void s390_cpu_load_normal(CPUState *s) S390CPU *cpu = S390_CPU(s); uint64_t spsw = ldq_phys(s->as, 0); - cpu->env.psw.mask = spsw & 0xffffffff80000000ULL; + cpu->env.psw.mask = spsw & PSW_MASK_SHORT_CTRL; /* * Invert short psw indication, so SIE will report a specification * exception if it was not set. */ cpu->env.psw.mask ^= PSW_MASK_SHORTPSW; - cpu->env.psw.addr = spsw & 0x7fffffffULL; + cpu->env.psw.addr = spsw & PSW_MASK_SHORT_ADDR; s390_cpu_set_state(S390_CPU_STATE_OPERATING, cpu); } diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index 8a557fd8d1..1d17709d6e 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -276,7 +276,8 @@ extern const VMStateDescription vmstate_s390_cpu; #define PSW_MASK_RI 0x0000008000000000ULL #define PSW_MASK_64 0x0000000100000000ULL #define PSW_MASK_32 0x0000000080000000ULL -#define PSW_MASK_ESA_ADDR 0x000000007fffffffULL +#define PSW_MASK_SHORT_ADDR 0x000000007fffffffULL +#define PSW_MASK_SHORT_CTRL 0xffffffff80000000ULL #undef PSW_ASC_PRIMARY #undef PSW_ASC_ACCREG