more s390 updates for 6.15 merge window

- Fix machine check handler _CIF_MCCK_GUEST bit setting by adding the
   missing base register for relocated lowcore address
 
 - Fix build failure on older linkers by conditionally adding the -no-pie
   linker option only when it is supported
 
 - Fix inaccurate kernel messages in vfio-ap by providing descriptive
   error notifications for AP queue sharing violations
 
 - Fix PCI isolation logic by ensuring non-VF devices correctly return
   false in zpci_bus_is_isolated_vf()
 
 - Fix PCI DMA range map setup by using dma_direct_set_offset() to add a
   proper sentinel element, preventing potential overruns and translation
   errors
 
 - Cleanup header dependency problems with asm-offsets.c
 
 - Add fault info for unexpected low-address protection faults in user mode
 
 - Add support for HOTPLUG_SMT, replacing the arch-specific "nosmt"
   handling with common code handling
 
 - Use bitop functions to implement CPU flag helper functions to ensure
   that bits cannot get lost if modified in different contexts on a CPU
 
 - Remove unused machine_flags for the lowcore
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEE3QHqV+H2a8xAv27vjYWKoQLXFBgFAmfwbhwACgkQjYWKoQLX
 FBgmlwf5ASFl51yYziSg47NTOdCgkdE1un69VKCU7g9nzQBCFiK4PT+H/d69JHpt
 g9dHi4sW6aXooUWyqtrQbsDZSnGKvJd48wOkpqAKKKJCBx3On/7s1fi1sJXgJovo
 rSwC1cRD+yfFDNoQgXytSrRAkoPYvIPxf0aQei/8ziVNOrl7iF7nyPYpgNcZl2iz
 rQWt+o4oWhygs6lK4w9t+0V0QLL+CqTIN/tpf7qeQzNFN5WfRJBn0dtxQhK72enG
 WepU41LnZxDF5DTKhH4+PZFdLPP+YwwTGdqojW28leGy5T3/Eg0wrDaU1034Wpgd
 m5Fg03z94Vdul/rAEscaH1PLT3Ufng==
 =G5/g
 -----END PGP SIGNATURE-----

Merge tag 's390-6.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull more s390 updates from Vasily Gorbik:

 - Fix machine check handler _CIF_MCCK_GUEST bit setting by adding the
   missing base register for relocated lowcore address

 - Fix build failure on older linkers by conditionally adding the
   -no-pie linker option only when it is supported

 - Fix inaccurate kernel messages in vfio-ap by providing descriptive
   error notifications for AP queue sharing violations

 - Fix PCI isolation logic by ensuring non-VF devices correctly return
   false in zpci_bus_is_isolated_vf()

 - Fix PCI DMA range map setup by using dma_direct_set_offset() to add a
   proper sentinel element, preventing potential overruns and
   translation errors

 - Cleanup header dependency problems with asm-offsets.c

 - Add fault info for unexpected low-address protection faults in user
   mode

 - Add support for HOTPLUG_SMT, replacing the arch-specific "nosmt"
   handling with common code handling

 - Use bitop functions to implement CPU flag helper functions to ensure
   that bits cannot get lost if modified in different contexts on a CPU

 - Remove unused machine_flags for the lowcore

* tag 's390-6.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/vfio-ap: Fix no AP queue sharing allowed message written to kernel log
  s390/pci: Fix dev.dma_range_map missing sentinel element
  s390/mm: Dump fault info in case of low address protection fault
  s390/smp: Add support for HOTPLUG_SMT
  s390: Fix linker error when -no-pie option is unavailable
  s390/processor: Use bitop functions for cpu flag helper functions
  s390/asm-offsets: Remove ASM_OFFSETS_C
  s390/asm-offsets: Include ftrace_regs.h instead of ftrace.h
  s390/kvm: Split kvm_host header file
  s390/pci: Fix zpci_bus_is_isolated_vf() for non-VFs
  s390/lowcore: Remove unused machine_flags
  s390/entry: Fix setting _CIF_MCCK_GUEST with lowcore relocation
This commit is contained in:
Linus Torvalds 2025-04-04 16:58:34 -07:00
commit dd9db3bff8
20 changed files with 437 additions and 412 deletions

View File

@ -4265,10 +4265,10 @@
nosmp [SMP,EARLY] Tells an SMP kernel to act as a UP kernel,
and disable the IO APIC. legacy for "maxcpus=0".
nosmt [KNL,MIPS,PPC,S390,EARLY] Disable symmetric multithreading (SMT).
nosmt [KNL,MIPS,PPC,EARLY] Disable symmetric multithreading (SMT).
Equivalent to smt=1.
[KNL,X86,PPC] Disable symmetric multithreading (SMT).
[KNL,X86,PPC,S390] Disable symmetric multithreading (SMT).
nosmt=force: Force disable SMT, cannot be undone
via the sysfs control file.

View File

@ -240,6 +240,7 @@ config S390
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
select HAVE_VIRT_CPU_ACCOUNTING_IDLE
select HOTPLUG_SMT
select IOMMU_HELPER if PCI
select IOMMU_SUPPORT if PCI
select KASAN_VMALLOC if KASAN

View File

@ -15,7 +15,7 @@ KBUILD_CFLAGS_MODULE += -fPIC
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
KBUILD_CFLAGS += -fPIC
LDFLAGS_vmlinux := -no-pie --emit-relocs --discard-none
LDFLAGS_vmlinux := $(call ld-option,-no-pie) --emit-relocs --discard-none
extra_tools := relocs
aflags_dwarf := -Wa,-gdwarf-2
KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__

View File

@ -20,14 +20,13 @@
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/mmu_notifier.h>
#include <asm/kvm_host_types.h>
#include <asm/debug.h>
#include <asm/cpu.h>
#include <asm/fpu.h>
#include <asm/isc.h>
#include <asm/guarded_storage.h>
#define KVM_S390_BSCA_CPU_SLOTS 64
#define KVM_S390_ESCA_CPU_SLOTS 248
#define KVM_MAX_VCPUS 255
#define KVM_INTERNAL_MEM_SLOTS 1
@ -51,342 +50,6 @@
#define KVM_REQ_REFRESH_GUEST_PREFIX \
KVM_ARCH_REQ_FLAGS(6, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
union bsca_sigp_ctrl {
__u8 value;
struct {
__u8 c : 1;
__u8 r : 1;
__u8 scn : 6;
};
};
union esca_sigp_ctrl {
__u16 value;
struct {
__u8 c : 1;
__u8 reserved: 7;
__u8 scn;
};
};
struct esca_entry {
union esca_sigp_ctrl sigp_ctrl;
__u16 reserved1[3];
__u64 sda;
__u64 reserved2[6];
};
struct bsca_entry {
__u8 reserved0;
union bsca_sigp_ctrl sigp_ctrl;
__u16 reserved[3];
__u64 sda;
__u64 reserved2[2];
};
union ipte_control {
unsigned long val;
struct {
unsigned long k : 1;
unsigned long kh : 31;
unsigned long kg : 32;
};
};
/*
* Utility is defined as two bytes but having it four bytes wide
* generates more efficient code. Since the following bytes are
* reserved this makes no functional difference.
*/
union sca_utility {
__u32 val;
struct {
__u32 mtcr : 1;
__u32 : 31;
};
};
struct bsca_block {
union ipte_control ipte_control;
__u64 reserved[5];
__u64 mcn;
union sca_utility utility;
__u8 reserved2[4];
struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
};
struct esca_block {
union ipte_control ipte_control;
__u64 reserved1[6];
union sca_utility utility;
__u8 reserved2[4];
__u64 mcn[4];
__u64 reserved3[20];
struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
};
/*
* This struct is used to store some machine check info from lowcore
* for machine checks that happen while the guest is running.
* This info in host's lowcore might be overwritten by a second machine
* check from host when host is in the machine check's high-level handling.
* The size is 24 bytes.
*/
struct mcck_volatile_info {
__u64 mcic;
__u64 failing_storage_address;
__u32 ext_damage_code;
__u32 reserved;
};
#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \
CR0_MEASUREMENT_ALERT_SUBMASK)
#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \
CR14_EXTERNAL_DAMAGE_SUBMASK)
#define SIDAD_SIZE_MASK 0xff
#define sida_addr(sie_block) phys_to_virt((sie_block)->sidad & PAGE_MASK)
#define sida_size(sie_block) \
((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE)
#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
struct kvm_s390_sie_block {
atomic_t cpuflags; /* 0x0000 */
__u32 : 1; /* 0x0004 */
__u32 prefix : 18;
__u32 : 1;
__u32 ibc : 12;
__u8 reserved08[4]; /* 0x0008 */
#define PROG_IN_SIE (1<<0)
__u32 prog0c; /* 0x000c */
union {
__u8 reserved10[16]; /* 0x0010 */
struct {
__u64 pv_handle_cpu;
__u64 pv_handle_config;
};
};
#define PROG_BLOCK_SIE (1<<0)
#define PROG_REQUEST (1<<1)
atomic_t 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 */
psw_t gpsw; /* 0x0090 */
__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
#define ECD_HMAC 0x00004000
__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);
struct kvm_s390_itdb {
__u8 data[256];
};
struct sie_page {
struct kvm_s390_sie_block sie_block;
struct mcck_volatile_info mcck_info; /* 0x0200 */
__u8 reserved218[360]; /* 0x0218 */
__u64 pv_grregs[16]; /* 0x0380 */
__u8 reserved400[512]; /* 0x0400 */
struct kvm_s390_itdb itdb; /* 0x0600 */
__u8 reserved700[2304]; /* 0x0700 */
};
struct kvm_vcpu_stat {
struct kvm_vcpu_stat_generic generic;
u64 exit_userspace;

View File

@ -0,0 +1,348 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_KVM_HOST_TYPES_H
#define _ASM_KVM_HOST_TYPES_H
#include <linux/atomic.h>
#include <linux/types.h>
#define KVM_S390_BSCA_CPU_SLOTS 64
#define KVM_S390_ESCA_CPU_SLOTS 248
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
union bsca_sigp_ctrl {
__u8 value;
struct {
__u8 c : 1;
__u8 r : 1;
__u8 scn : 6;
};
};
union esca_sigp_ctrl {
__u16 value;
struct {
__u8 c : 1;
__u8 reserved: 7;
__u8 scn;
};
};
struct esca_entry {
union esca_sigp_ctrl sigp_ctrl;
__u16 reserved1[3];
__u64 sda;
__u64 reserved2[6];
};
struct bsca_entry {
__u8 reserved0;
union bsca_sigp_ctrl sigp_ctrl;
__u16 reserved[3];
__u64 sda;
__u64 reserved2[2];
};
union ipte_control {
unsigned long val;
struct {
unsigned long k : 1;
unsigned long kh : 31;
unsigned long kg : 32;
};
};
/*
* Utility is defined as two bytes but having it four bytes wide
* generates more efficient code. Since the following bytes are
* reserved this makes no functional difference.
*/
union sca_utility {
__u32 val;
struct {
__u32 mtcr : 1;
__u32 : 31;
};
};
struct bsca_block {
union ipte_control ipte_control;
__u64 reserved[5];
__u64 mcn;
union sca_utility utility;
__u8 reserved2[4];
struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
};
struct esca_block {
union ipte_control ipte_control;
__u64 reserved1[6];
union sca_utility utility;
__u8 reserved2[4];
__u64 mcn[4];
__u64 reserved3[20];
struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
};
/*
* This struct is used to store some machine check info from lowcore
* for machine checks that happen while the guest is running.
* This info in host's lowcore might be overwritten by a second machine
* check from host when host is in the machine check's high-level handling.
* The size is 24 bytes.
*/
struct mcck_volatile_info {
__u64 mcic;
__u64 failing_storage_address;
__u32 ext_damage_code;
__u32 reserved;
};
#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \
CR0_MEASUREMENT_ALERT_SUBMASK)
#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \
CR14_EXTERNAL_DAMAGE_SUBMASK)
#define SIDAD_SIZE_MASK 0xff
#define sida_addr(sie_block) phys_to_virt((sie_block)->sidad & PAGE_MASK)
#define sida_size(sie_block) \
((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE)
#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
struct kvm_s390_sie_block {
atomic_t cpuflags; /* 0x0000 */
__u32 : 1; /* 0x0004 */
__u32 prefix : 18;
__u32 : 1;
__u32 ibc : 12;
__u8 reserved08[4]; /* 0x0008 */
#define PROG_IN_SIE (1<<0)
__u32 prog0c; /* 0x000c */
union {
__u8 reserved10[16]; /* 0x0010 */
struct {
__u64 pv_handle_cpu;
__u64 pv_handle_config;
};
};
#define PROG_BLOCK_SIE (1<<0)
#define PROG_REQUEST (1<<1)
atomic_t 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 */
psw_t gpsw; /* 0x0090 */
__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
#define ECD_HMAC 0x00004000
__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);
struct kvm_s390_itdb {
__u8 data[256];
};
struct sie_page {
struct kvm_s390_sie_block sie_block;
struct mcck_volatile_info mcck_info; /* 0x0200 */
__u8 reserved218[360]; /* 0x0218 */
__u64 pv_grregs[16]; /* 0x0380 */
__u8 reserved400[512]; /* 0x0400 */
struct kvm_s390_itdb itdb; /* 0x0600 */
__u8 reserved700[2304]; /* 0x0700 */
};
#endif /* _ASM_KVM_HOST_TYPES_H */

View File

@ -164,9 +164,7 @@ struct lowcore {
__u32 spinlock_index; /* 0x03b0 */
__u8 pad_0x03b4[0x03b8-0x03b4]; /* 0x03b4 */
__u64 percpu_offset; /* 0x03b8 */
__u8 pad_0x03c0[0x03c8-0x03c0]; /* 0x03c0 */
__u64 machine_flags; /* 0x03c8 */
__u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */
__u8 pad_0x03c0[0x0400-0x03c0]; /* 0x03c0 */
__u32 return_lpswe; /* 0x0400 */
__u32 return_mcck_lpswe; /* 0x0404 */

View File

@ -31,6 +31,7 @@
#include <linux/cpumask.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
#include <linux/bitops.h>
#include <asm/fpu-types.h>
#include <asm/cpu.h>
#include <asm/page.h>
@ -62,33 +63,27 @@ static __always_inline struct pcpu *this_pcpu(void)
static __always_inline void set_cpu_flag(int flag)
{
this_pcpu()->flags |= (1UL << flag);
set_bit(flag, &this_pcpu()->flags);
}
static __always_inline void clear_cpu_flag(int flag)
{
this_pcpu()->flags &= ~(1UL << flag);
clear_bit(flag, &this_pcpu()->flags);
}
static __always_inline bool test_cpu_flag(int flag)
{
return this_pcpu()->flags & (1UL << flag);
return test_bit(flag, &this_pcpu()->flags);
}
static __always_inline bool test_and_set_cpu_flag(int flag)
{
if (test_cpu_flag(flag))
return true;
set_cpu_flag(flag);
return false;
return test_and_set_bit(flag, &this_pcpu()->flags);
}
static __always_inline bool test_and_clear_cpu_flag(int flag)
{
if (!test_cpu_flag(flag))
return false;
clear_cpu_flag(flag);
return true;
return test_and_clear_bit(flag, &this_pcpu()->flags);
}
/*
@ -97,7 +92,7 @@ static __always_inline bool test_and_clear_cpu_flag(int flag)
*/
static __always_inline bool test_cpu_flag_of(int flag, int cpu)
{
return per_cpu(pcpu_devices, cpu).flags & (1UL << flag);
return test_bit(flag, &per_cpu(pcpu_devices, cpu).flags);
}
#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)

View File

@ -9,9 +9,6 @@
#define _ASM_THREAD_INFO_H
#include <linux/bits.h>
#ifndef ASM_OFFSETS_C
#include <asm/asm-offsets.h>
#endif
/*
* General size of kernel stacks

View File

@ -61,6 +61,12 @@ static inline void topology_expect_change(void) { }
#endif /* CONFIG_SCHED_TOPOLOGY */
static inline bool topology_is_primary_thread(unsigned int cpu)
{
return smp_get_base_cpu(cpu) == cpu;
}
#define topology_is_primary_thread topology_is_primary_thread
#define POLARIZATION_UNKNOWN (-1)
#define POLARIZATION_HRZ (0)
#define POLARIZATION_VL (1)

View File

@ -5,15 +5,14 @@
* and format the required data.
*/
#define ASM_OFFSETS_C
#include <linux/kbuild.h>
#include <linux/kvm_host.h>
#include <linux/sched.h>
#include <linux/purgatory.h>
#include <linux/pgtable.h>
#include <linux/ftrace.h>
#include <linux/ftrace_regs.h>
#include <asm/kvm_host_types.h>
#include <asm/stacktrace.h>
#include <asm/ptrace.h>
int main(void)
{

View File

@ -17,6 +17,7 @@
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <asm/asm-offsets.h>
#include <asm/processor.h>
#include <asm/debug.h>
#include <asm/dis.h>

View File

@ -22,6 +22,7 @@
#include <asm/asm-extable.h>
#include <linux/memblock.h>
#include <asm/access-regs.h>
#include <asm/asm-offsets.h>
#include <asm/machine.h>
#include <asm/diag.h>
#include <asm/ebcdic.h>

View File

@ -468,7 +468,7 @@ SYM_CODE_START(mcck_int_handler)
clgrjl %r9,%r14, 4f
larl %r14,.Lsie_leave
clgrjhe %r9,%r14, 4f
lg %r10,__LC_PCPU
lg %r10,__LC_PCPU(%r13)
oi __PCPU_FLAGS+7(%r10), _CIF_MCCK_GUEST
4: BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
SIEEXIT __SF_SIE_CONTROL(%r15),%r13

View File

@ -414,7 +414,6 @@ static void __init setup_lowcore(void)
lc->clock_comparator = clock_comparator_max;
lc->current_task = (unsigned long)&init_task;
lc->lpp = LPP_MAGIC;
lc->machine_flags = get_lowcore()->machine_flags;
lc->preempt_count = get_lowcore()->preempt_count;
nmi_alloc_mcesa_early(&lc->mcesad);
lc->sys_enter_timer = get_lowcore()->sys_enter_timer;

View File

@ -99,13 +99,6 @@ __vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
static unsigned int smp_max_threads __initdata = -1U;
cpumask_t cpu_setup_mask;
static int __init early_nosmt(char *s)
{
smp_max_threads = 1;
return 0;
}
early_param("nosmt", early_nosmt);
static int __init early_smt(char *s)
{
get_option(&s, &smp_max_threads);
@ -265,7 +258,6 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = get_lowcore()->kernel_asce;
lc->user_asce = s390_invalid_asce;
lc->machine_flags = get_lowcore()->machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
abs_lc = get_abs_lowcore();
@ -809,6 +801,7 @@ void __init smp_detect_cpus(void)
mtid = boot_core_type ? sclp.mtid : sclp.mtid_cp;
mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
pcpu_set_smt(mtid);
cpu_smt_set_num_threads(smp_cpu_mtid + 1, smp_cpu_mtid + 1);
/* Print number of CPUs */
c_cpus = s_cpus = 0;

View File

@ -9,6 +9,7 @@
#include <linux/stacktrace.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <asm/asm-offsets.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
#include <asm/kprobes.h>

View File

@ -376,6 +376,7 @@ void do_protection_exception(struct pt_regs *regs)
if (unlikely(!teid.b61)) {
if (user_mode(regs)) {
/* Low-address protection in user mode: cannot happen */
dump_fault_info(regs);
die(regs, "Low-address protection");
}
/*

View File

@ -9,6 +9,7 @@
#include <linux/init.h>
#include <linux/irq.h>
#include <asm/asm-extable.h>
#include <asm/asm-offsets.h>
#include <asm/pfault.h>
#include <asm/diag.h>

View File

@ -287,23 +287,21 @@ static struct zpci_bus *zpci_bus_alloc(int topo, bool topo_is_tid)
static void pci_dma_range_setup(struct pci_dev *pdev)
{
struct zpci_dev *zdev = to_zpci(pdev);
struct bus_dma_region *map;
u64 aligned_end;
u64 aligned_end, size;
dma_addr_t dma_start;
int ret;
map = kzalloc(sizeof(*map), GFP_KERNEL);
if (!map)
return;
map->cpu_start = 0;
map->dma_start = PAGE_ALIGN(zdev->start_dma);
dma_start = PAGE_ALIGN(zdev->start_dma);
aligned_end = PAGE_ALIGN_DOWN(zdev->end_dma + 1);
if (aligned_end >= map->dma_start)
map->size = aligned_end - map->dma_start;
if (aligned_end >= dma_start)
size = aligned_end - dma_start;
else
map->size = 0;
WARN_ON_ONCE(map->size == 0);
size = 0;
WARN_ON_ONCE(size == 0);
pdev->dev.dma_range_map = map;
ret = dma_direct_set_offset(&pdev->dev, 0, dma_start, size);
if (ret)
pr_err("Failed to allocate DMA range map for %s\n", pci_name(pdev));
}
void pcibios_bus_add_device(struct pci_dev *pdev)
@ -360,6 +358,9 @@ static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev
{
struct pci_dev *pdev;
if (!zdev->vfn)
return false;
pdev = zpci_iov_find_parent_pf(zbus, zdev);
if (!pdev)
return true;

View File

@ -873,48 +873,66 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
vfio_put_device(&matrix_mdev->vdev);
}
#define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \
"already assigned to %s"
#define MDEV_SHARING_ERR "Userspace may not assign queue %02lx.%04lx to mdev: already assigned to %s"
static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *matrix_mdev,
unsigned long *apm,
unsigned long *aqm)
#define MDEV_IN_USE_ERR "Can not reserve queue %02lx.%04lx for host driver: in use by mdev"
static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *assignee,
struct ap_matrix_mdev *assigned_to,
unsigned long *apm, unsigned long *aqm)
{
unsigned long apid, apqi;
const struct device *dev = mdev_dev(matrix_mdev->mdev);
const char *mdev_name = dev_name(dev);
for_each_set_bit_inv(apid, apm, AP_DEVICES)
for_each_set_bit_inv(apid, apm, AP_DEVICES) {
for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
dev_warn(mdev_dev(assignee->mdev), MDEV_SHARING_ERR,
apid, apqi, dev_name(mdev_dev(assigned_to->mdev)));
}
}
}
static void vfio_ap_mdev_log_in_use_err(struct ap_matrix_mdev *assignee,
unsigned long *apm, unsigned long *aqm)
{
unsigned long apid, apqi;
for_each_set_bit_inv(apid, apm, AP_DEVICES) {
for_each_set_bit_inv(apqi, aqm, AP_DOMAINS)
dev_warn(dev, MDEV_SHARING_ERR, apid, apqi, mdev_name);
dev_warn(mdev_dev(assignee->mdev), MDEV_IN_USE_ERR, apid, apqi);
}
}
/**
* vfio_ap_mdev_verify_no_sharing - verify APQNs are not shared by matrix mdevs
*
* @assignee: the matrix mdev to which @mdev_apm and @mdev_aqm are being
* assigned; or, NULL if this function was called by the AP bus
* driver in_use callback to verify none of the APQNs being reserved
* for the host device driver are in use by a vfio_ap mediated device
* @mdev_apm: mask indicating the APIDs of the APQNs to be verified
* @mdev_aqm: mask indicating the APQIs of the APQNs to be verified
*
* Verifies that each APQN derived from the Cartesian product of a bitmap of
* AP adapter IDs and AP queue indexes is not configured for any matrix
* mediated device. AP queue sharing is not allowed.
* Verifies that each APQN derived from the Cartesian product of APIDs
* represented by the bits set in @mdev_apm and the APQIs of the bits set in
* @mdev_aqm is not assigned to a mediated device other than the mdev to which
* the APQN is being assigned (@assignee). AP queue sharing is not allowed.
*
* Return: 0 if the APQNs are not shared; otherwise return -EADDRINUSE.
*/
static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm,
static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *assignee,
unsigned long *mdev_apm,
unsigned long *mdev_aqm)
{
struct ap_matrix_mdev *matrix_mdev;
struct ap_matrix_mdev *assigned_to;
DECLARE_BITMAP(apm, AP_DEVICES);
DECLARE_BITMAP(aqm, AP_DOMAINS);
list_for_each_entry(matrix_mdev, &matrix_dev->mdev_list, node) {
list_for_each_entry(assigned_to, &matrix_dev->mdev_list, node) {
/*
* If the input apm and aqm are fields of the matrix_mdev
* object, then move on to the next matrix_mdev.
* If the mdev to which the mdev_apm and mdev_aqm is being
* assigned is the same as the mdev being verified
*/
if (mdev_apm == matrix_mdev->matrix.apm &&
mdev_aqm == matrix_mdev->matrix.aqm)
if (assignee == assigned_to)
continue;
memset(apm, 0, sizeof(apm));
@ -924,15 +942,16 @@ static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm,
* We work on full longs, as we can only exclude the leftover
* bits in non-inverse order. The leftover is all zeros.
*/
if (!bitmap_and(apm, mdev_apm, matrix_mdev->matrix.apm,
AP_DEVICES))
if (!bitmap_and(apm, mdev_apm, assigned_to->matrix.apm, AP_DEVICES))
continue;
if (!bitmap_and(aqm, mdev_aqm, matrix_mdev->matrix.aqm,
AP_DOMAINS))
if (!bitmap_and(aqm, mdev_aqm, assigned_to->matrix.aqm, AP_DOMAINS))
continue;
vfio_ap_mdev_log_sharing_err(matrix_mdev, apm, aqm);
if (assignee)
vfio_ap_mdev_log_sharing_err(assignee, assigned_to, apm, aqm);
else
vfio_ap_mdev_log_in_use_err(assigned_to, apm, aqm);
return -EADDRINUSE;
}
@ -961,7 +980,8 @@ static int vfio_ap_mdev_validate_masks(struct ap_matrix_mdev *matrix_mdev)
matrix_mdev->matrix.aqm))
return -EADDRNOTAVAIL;
return vfio_ap_mdev_verify_no_sharing(matrix_mdev->matrix.apm,
return vfio_ap_mdev_verify_no_sharing(matrix_mdev,
matrix_mdev->matrix.apm,
matrix_mdev->matrix.aqm);
}
@ -2516,7 +2536,7 @@ int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm)
mutex_lock(&matrix_dev->guests_lock);
mutex_lock(&matrix_dev->mdevs_lock);
ret = vfio_ap_mdev_verify_no_sharing(apm, aqm);
ret = vfio_ap_mdev_verify_no_sharing(NULL, apm, aqm);
mutex_unlock(&matrix_dev->mdevs_lock);
mutex_unlock(&matrix_dev->guests_lock);