aboutsummaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/include/asm/barrier.h2
-rw-r--r--arch/s390/include/asm/cio.h1
-rw-r--r--arch/s390/include/asm/elf.h20
-rw-r--r--arch/s390/include/asm/ipl.h3
-rw-r--r--arch/s390/include/asm/kvm_host.h57
-rw-r--r--arch/s390/include/asm/pci_dma.h4
-rw-r--r--arch/s390/include/asm/sclp.h8
-rw-r--r--arch/s390/include/asm/trace/diag.h6
-rw-r--r--arch/s390/include/uapi/asm/kvm.h5
-rw-r--r--arch/s390/include/uapi/asm/socket.h3
-rw-r--r--arch/s390/include/uapi/asm/unistd.h19
-rw-r--r--arch/s390/kernel/compat_wrapper.c1
-rw-r--r--arch/s390/kernel/diag.c4
-rw-r--r--arch/s390/kernel/dis.c17
-rw-r--r--arch/s390/kernel/head.S95
-rw-r--r--arch/s390/kernel/ipl.c65
-rw-r--r--arch/s390/kernel/process.c6
-rw-r--r--arch/s390/kernel/processor.c6
-rw-r--r--arch/s390/kernel/sclp.c2
-rw-r--r--arch/s390/kernel/setup.c12
-rw-r--r--arch/s390/kernel/syscalls.S1
-rw-r--r--arch/s390/kernel/trace.c6
-rw-r--r--arch/s390/kvm/diag.c11
-rw-r--r--arch/s390/kvm/gaccess.c38
-rw-r--r--arch/s390/kvm/intercept.c7
-rw-r--r--arch/s390/kvm/interrupt.c140
-rw-r--r--arch/s390/kvm/kvm-s390.c306
-rw-r--r--arch/s390/kvm/kvm-s390.h7
-rw-r--r--arch/s390/kvm/priv.c2
-rw-r--r--arch/s390/kvm/sigp.c8
-rw-r--r--arch/s390/kvm/trace-s390.h6
-rw-r--r--arch/s390/mm/init.c30
-rw-r--r--arch/s390/mm/mmap.c60
-rw-r--r--arch/s390/mm/pgtable.c4
-rw-r--r--arch/s390/net/bpf_jit_comp.c13
-rw-r--r--arch/s390/pci/pci_dma.c87
36 files changed, 646 insertions, 416 deletions
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index d68e11e0df5e..7ffd0b19135c 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
-#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_store_release(p, v) \
do { \
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index 0c5d8ee657f0..d1e7b0a0feeb 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -312,6 +312,7 @@ extern void css_schedule_reprobe(void);
extern void reipl_ccw_dev(struct ccw_dev_id *id);
struct cio_iplinfo {
+ u8 ssid;
u16 devno;
int is_qdio;
};
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 3ad48f22de78..08e34a5dc909 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -104,6 +104,9 @@
#define HWCAP_S390_TE 1024
#define HWCAP_S390_VXRS 2048
+/* Internal bits, not exposed via elf */
+#define HWCAP_INT_SIE 1UL
+
/*
* These are used to set parameters in the core dumps.
*/
@@ -169,6 +172,10 @@ extern unsigned int vdso_enabled;
extern unsigned long elf_hwcap;
#define ELF_HWCAP (elf_hwcap)
+/* Internal hardware capabilities, not exposed via elf */
+
+extern unsigned long int_hwcap;
+
/* This yields a string that ld.so will use to load implementation
specific libraries for optimization. This is more specific in
intent than poking at uname or /proc/cpuinfo.
@@ -206,9 +213,16 @@ do { \
} while (0)
#endif /* CONFIG_COMPAT */
-extern unsigned long mmap_rnd_mask;
-
-#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask)
+/*
+ * Cache aliasing on the latest machines calls for a mapping granularity
+ * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
+ * of up to 1GB. For 31-bit processes the virtual address space is limited,
+ * use no alignment and limit the randomization to 8MB.
+ */
+#define BRK_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ffffUL)
+#define MMAP_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ff80UL)
+#define MMAP_ALIGN_MASK (is_32bit_task() ? 0 : 0x7fUL)
+#define STACK_RND_MASK MMAP_RND_MASK
#define ARCH_DLINFO \
do { \
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 39ae6a359747..86634e71b69f 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -64,7 +64,8 @@ struct ipl_block_fcp {
struct ipl_block_ccw {
u8 reserved1[84];
- u8 reserved2[2];
+ u16 reserved2 : 13;
+ u8 ssid : 3;
u16 devno;
u8 vm_flags;
u8 reserved3[3];
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index efaac2c3bb77..6742414dbd6f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -25,7 +25,9 @@
#include <asm/fpu/api.h>
#include <asm/isc.h>
-#define KVM_MAX_VCPUS 64
+#define KVM_S390_BSCA_CPU_SLOTS 64
+#define KVM_S390_ESCA_CPU_SLOTS 248
+#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS
#define KVM_USER_MEM_SLOTS 32
/*
@@ -37,12 +39,41 @@
#define KVM_IRQCHIP_NUM_PINS 4096
#define KVM_HALT_POLL_NS_DEFAULT 0
+/* s390-specific vcpu->requests bit members */
+#define KVM_REQ_ENABLE_IBS 8
+#define KVM_REQ_DISABLE_IBS 9
+
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
-struct sca_entry {
+union bsca_sigp_ctrl {
+ __u8 value;
+ struct {
+ __u8 c : 1;
+ __u8 r : 1;
+ __u8 scn : 6;
+ };
+} __packed;
+
+union esca_sigp_ctrl {
+ __u16 value;
+ struct {
+ __u8 c : 1;
+ __u8 reserved: 7;
+ __u8 scn;
+ };
+} __packed;
+
+struct esca_entry {
+ union esca_sigp_ctrl sigp_ctrl;
+ __u16 reserved1[3];
+ __u64 sda;
+ __u64 reserved2[6];
+} __packed;
+
+struct bsca_entry {
__u8 reserved0;
- __u8 sigp_ctrl;
+ union bsca_sigp_ctrl sigp_ctrl;
__u16 reserved[3];
__u64 sda;
__u64 reserved2[2];
@@ -57,14 +88,22 @@ union ipte_control {
};
};
-struct sca_block {
+struct bsca_block {
union ipte_control ipte_control;
__u64 reserved[5];
__u64 mcn;
__u64 reserved2;
- struct sca_entry cpu[64];
+ struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
} __attribute__((packed));
+struct esca_block {
+ union ipte_control ipte_control;
+ __u64 reserved1[7];
+ __u64 mcn[4];
+ __u64 reserved2[20];
+ struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
+} __packed;
+
#define CPUSTAT_STOPPED 0x80000000
#define CPUSTAT_WAIT 0x10000000
#define CPUSTAT_ECALL_PEND 0x08000000
@@ -182,7 +221,8 @@ struct kvm_s390_sie_block {
__u64 pp; /* 0x01de */
__u8 reserved1e6[2]; /* 0x01e6 */
__u64 itdba; /* 0x01e8 */
- __u8 reserved1f0[16]; /* 0x01f0 */
+ __u64 riccbd; /* 0x01f0 */
+ __u8 reserved1f8[8]; /* 0x01f8 */
} __attribute__((packed));
struct kvm_s390_itdb {
@@ -585,11 +625,14 @@ struct kvm_s390_crypto_cb {
};
struct kvm_arch{
- struct sca_block *sca;
+ void *sca;
+ int use_esca;
+ rwlock_t sca_lock;
debug_info_t *dbf;
struct kvm_s390_float_interrupt float_int;
struct kvm_device *flic;
struct gmap *gmap;
+ unsigned long mem_limit;
int css_support;
int use_irqchip;
int use_cmma;
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 7a7abf1a5537..1aac41e83ea1 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -195,5 +195,7 @@ void zpci_dma_exit_device(struct zpci_dev *);
void dma_free_seg_table(unsigned long);
unsigned long *dma_alloc_cpu_table(void);
void dma_cleanup_tables(unsigned long *);
-void dma_update_cpu_trans(unsigned long *, void *, dma_addr_t, int);
+unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr);
+void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags);
+
#endif
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 821dde5f425d..dea883f85d66 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -29,7 +29,10 @@ struct sclp_ipl_info {
struct sclp_core_entry {
u8 core_id;
- u8 reserved0[2];
+ u8 reserved0;
+ u8 : 4;
+ u8 sief2 : 1;
+ u8 : 3;
u8 : 3;
u8 siif : 1;
u8 sigpif : 1;
@@ -53,6 +56,9 @@ struct sclp_info {
unsigned char has_sigpif : 1;
unsigned char has_core_type : 1;
unsigned char has_sprp : 1;
+ unsigned char has_hvs : 1;
+ unsigned char has_esca : 1;
+ unsigned char has_sief2 : 1;
unsigned int ibc;
unsigned int mtid;
unsigned int mtid_cp;
diff --git a/arch/s390/include/asm/trace/diag.h b/arch/s390/include/asm/trace/diag.h
index 776f307960cc..cc6cfe7889da 100644
--- a/arch/s390/include/asm/trace/diag.h
+++ b/arch/s390/include/asm/trace/diag.h
@@ -19,7 +19,7 @@
#define TRACE_INCLUDE_PATH asm/trace
#define TRACE_INCLUDE_FILE diag
-TRACE_EVENT(diagnose,
+TRACE_EVENT(s390_diagnose,
TP_PROTO(unsigned short nr),
TP_ARGS(nr),
TP_STRUCT__entry(
@@ -32,9 +32,9 @@ TRACE_EVENT(diagnose,
);
#ifdef CONFIG_TRACEPOINTS
-void trace_diagnose_norecursion(int diag_nr);
+void trace_s390_diagnose_norecursion(int diag_nr);
#else
-static inline void trace_diagnose_norecursion(int diag_nr) { }
+static inline void trace_s390_diagnose_norecursion(int diag_nr) { }
#endif
#endif /* _TRACE_S390_DIAG_H */
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index ef1a5fcc6c66..fe84bd5fe7ce 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -66,6 +66,8 @@ struct kvm_s390_io_adapter_req {
#define KVM_S390_VM_MEM_CLR_CMMA 1
#define KVM_S390_VM_MEM_LIMIT_SIZE 2
+#define KVM_S390_NO_MEM_LIMIT U64_MAX
+
/* kvm attributes for KVM_S390_VM_TOD */
#define KVM_S390_VM_TOD_LOW 0
#define KVM_S390_VM_TOD_HIGH 1
@@ -151,6 +153,7 @@ struct kvm_guest_debug_arch {
#define KVM_SYNC_ARCH0 (1UL << 4)
#define KVM_SYNC_PFAULT (1UL << 5)
#define KVM_SYNC_VRS (1UL << 6)
+#define KVM_SYNC_RICCB (1UL << 7)
/* definition of registers in kvm_run */
struct kvm_sync_regs {
__u64 prefix; /* prefix register */
@@ -168,6 +171,8 @@ struct kvm_sync_regs {
__u64 vrs[32][2]; /* vector registers */
__u8 reserved[512]; /* for future vector expansion */
__u32 fpc; /* only valid with vector registers */
+ __u8 padding[52]; /* riccb needs to be 64byte aligned */
+ __u8 riccb[64]; /* runtime instrumentation controls block */
};
#define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 296942d56e6a..d02e89d14fef 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -91,4 +91,7 @@
#define SO_ATTACH_BPF 50
#define SO_DETACH_BPF SO_DETACH_FILTER
+#define SO_ATTACH_REUSEPORT_CBPF 51
+#define SO_ATTACH_REUSEPORT_EBPF 52
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index a848adba1504..34ec202472c6 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -192,14 +192,14 @@
#define __NR_set_tid_address 252
#define __NR_fadvise64 253
#define __NR_timer_create 254
-#define __NR_timer_settime (__NR_timer_create+1)
-#define __NR_timer_gettime (__NR_timer_create+2)
-#define __NR_timer_getoverrun (__NR_timer_create+3)
-#define __NR_timer_delete (__NR_timer_create+4)
-#define __NR_clock_settime (__NR_timer_create+5)
-#define __NR_clock_gettime (__NR_timer_create+6)
-#define __NR_clock_getres (__NR_timer_create+7)
-#define __NR_clock_nanosleep (__NR_timer_create+8)
+#define __NR_timer_settime 255
+#define __NR_timer_gettime 256
+#define __NR_timer_getoverrun 257
+#define __NR_timer_delete 258
+#define __NR_clock_settime 259
+#define __NR_clock_gettime 260
+#define __NR_clock_getres 261
+#define __NR_clock_nanosleep 262
/* Number 263 is reserved for vserver */
#define __NR_statfs64 265
#define __NR_fstatfs64 266
@@ -309,7 +309,8 @@
#define __NR_recvfrom 371
#define __NR_recvmsg 372
#define __NR_shutdown 373
-#define NR_syscalls 374
+#define __NR_mlock2 374
+#define NR_syscalls 375
/*
* There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 09f194052df3..fac4eeddef91 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -176,3 +176,4 @@ COMPAT_SYSCALL_WRAP4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
+COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index f98766ede4e1..48b37b8357e6 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -121,14 +121,14 @@ device_initcall(show_diag_stat_init);
void diag_stat_inc(enum diag_stat_enum nr)
{
this_cpu_inc(diag_stat.counter[nr]);
- trace_diagnose(diag_map[nr].code);
+ trace_s390_diagnose(diag_map[nr].code);
}
EXPORT_SYMBOL(diag_stat_inc);
void diag_stat_inc_norecursion(enum diag_stat_enum nr)
{
this_cpu_inc(diag_stat.counter[nr]);
- trace_diagnose_norecursion(diag_map[nr].code);
+ trace_s390_diagnose_norecursion(diag_map[nr].code);
}
EXPORT_SYMBOL(diag_stat_inc_norecursion);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 8140d10c6785..6e72961608f0 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
}
if (separator)
ptr += sprintf(ptr, "%c", separator);
+ /*
+ * Use four '%' characters below because of the
+ * following two conversions:
+ *
+ * 1) sprintf: %%%%r -> %%r
+ * 2) printk : %%r -> %r
+ */
if (operand->flags & OPERAND_GPR)
- ptr += sprintf(ptr, "%%r%i", value);
+ ptr += sprintf(ptr, "%%%%r%i", value);
else if (operand->flags & OPERAND_FPR)
- ptr += sprintf(ptr, "%%f%i", value);
+ ptr += sprintf(ptr, "%%%%f%i", value);
else if (operand->flags & OPERAND_AR)
- ptr += sprintf(ptr, "%%a%i", value);
+ ptr += sprintf(ptr, "%%%%a%i", value);
else if (operand->flags & OPERAND_CR)
- ptr += sprintf(ptr, "%%c%i", value);
+ ptr += sprintf(ptr, "%%%%c%i", value);
else if (operand->flags & OPERAND_VR)
- ptr += sprintf(ptr, "%%v%i", value);
+ ptr += sprintf(ptr, "%%%%v%i", value);
else if (operand->flags & OPERAND_PCREL)
ptr += sprintf(ptr, "%lx", (signed int) value
+ addr);
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 1255c6c5353e..301ee9c70688 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -26,6 +26,7 @@
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/page.h>
+#include <asm/ptrace.h>
#define ARCH_OFFSET 4
@@ -59,19 +60,6 @@ __HEAD
.long 0x020006e0,0x20000050
.org 0x200
-#
-# subroutine to set architecture mode
-#
-.Lsetmode:
- mvi __LC_AR_MODE_ID,1 # set esame flag
- slr %r0,%r0 # set cpuid to zero
- lhi %r1,2 # mode 2 = esame (dump)
- sigp %r1,%r0,0x12 # switch to esame mode
- bras %r13,0f
- .fill 16,4,0x0
-0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
- sam31 # switch to 31 bit addressing mode
- br %r14
#
# subroutine to wait for end I/O
@@ -159,7 +147,14 @@ __HEAD
.long 0x02200050,0x00000000
iplstart:
- bas %r14,.Lsetmode # Immediately switch to 64 bit mode
+ mvi __LC_AR_MODE_ID,1 # set esame flag
+ slr %r0,%r0 # set cpuid to zero
+ lhi %r1,2 # mode 2 = esame (dump)
+ sigp %r1,%r0,0x12 # switch to esame mode
+ bras %r13,0f
+ .fill 16,4,0x0
+0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
+ sam31 # switch to 31 bit addressing mode
lh %r1,0xb8 # test if subchannel number
bct %r1,.Lnoload # is valid
l %r1,0xb8 # load ipl subchannel number
@@ -269,71 +264,6 @@ iplstart:
.Lcpuid:.fill 8,1,0
#
-# SALIPL loader support. Based on a patch by Rob van der Heij.
-# This entry point is called directly from the SALIPL loader and
-# doesn't need a builtin ipl record.
-#
- .org 0x800
-ENTRY(start)
- stm %r0,%r15,0x07b0 # store registers
- bas %r14,.Lsetmode # Immediately switch to 64 bit mode
- basr %r12,%r0
-.base:
- l %r11,.parm
- l %r8,.cmd # pointer to command buffer
-
- ltr %r9,%r9 # do we have SALIPL parameters?
- bp .sk8x8
-
- mvc 0(64,%r8),0x00b0 # copy saved registers
- xc 64(240-64,%r8),0(%r8) # remainder of buffer
- tr 0(64,%r8),.lowcase
- b .gotr
-.sk8x8:
- mvc 0(240,%r8),0(%r9) # copy iplparms into buffer
-.gotr:
- slr %r0,%r0
- st %r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11)
- st %r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11)
- j startup # continue with startup
-.cmd: .long COMMAND_LINE # address of command line buffer
-.parm: .long PARMAREA
-.lowcase:
- .byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07
- .byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f
- .byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17
- .byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f
- .byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27
- .byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f
- .byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37
- .byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f
- .byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47
- .byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f
- .byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57
- .byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f
- .byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67
- .byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f
- .byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77
- .byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f
-
- .byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87
- .byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f
- .byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97
- .byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f
- .byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7
- .byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf
- .byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7
- .byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf
- .byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87 # .abcdefg
- .byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf # hi
- .byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97 # .jklmnop
- .byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf # qr
- .byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 # ..stuvwx
- .byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef # yz
- .byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7
- .byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
-
-#
# startup-code at 0x10000, running in absolute addressing mode
# this is called either by the ipl loader or directly by PSW restart
# or linload or SALIPL
@@ -364,7 +294,7 @@ ENTRY(startup_kdump)
bras %r13,0f
.fill 16,4,0x0
0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
- sam31 # switch to 31 bit addressing mode
+ sam64 # switch to 64 bit addressing mode
basr %r13,0 # get base
.LPG0:
xc 0x200(256),0x200 # partially clear lowcore
@@ -395,7 +325,7 @@ ENTRY(startup_kdump)
jnz 1b
j 4f
2: l %r15,.Lstack-.LPG0(%r13)
- ahi %r15,-96
+ ahi %r15,-STACK_FRAME_OVERHEAD
la %r2,.Lals_string-.LPG0(%r13)
l %r3,.Lsclp_print-.LPG0(%r13)
basr %r14,%r3
@@ -429,8 +359,7 @@ ENTRY(startup_kdump)
.long 1, 0xc0000000
#endif
4:
- /* Continue with 64bit startup code in head64.S */
- sam64 # switch to 64 bit mode
+ /* Continue with startup code in head64.S */
jg startup_continue
.align 8
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f6d8acd7e136..b1f0a90f933b 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -121,6 +121,7 @@ static char *dump_type_str(enum dump_type type)
* Must be in data section since the bss section
* is not cleared when these are accessed.
*/
+static u8 ipl_ssid __attribute__((__section__(".data"))) = 0;
static u16 ipl_devno __attribute__((__section__(".data"))) = 0;
u32 ipl_flags __attribute__((__section__(".data"))) = 0;
@@ -197,6 +198,33 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \
return snprintf(page, PAGE_SIZE, _format, ##args); \
}
+#define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \
+static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ const char *buf, size_t len) \
+{ \
+ unsigned long long ssid, devno; \
+ \
+ if (sscanf(buf, "0.%llx.%llx\n", &ssid, &devno) != 2) \
+ return -EINVAL; \
+ \
+ if (ssid > __MAX_SSID || devno > __MAX_SUBCHANNEL) \
+ return -EINVAL; \
+ \
+ _ipl_blk.ssid = ssid; \
+ _ipl_blk.devno = devno; \
+ return len; \
+}
+
+#define DEFINE_IPL_CCW_ATTR_RW(_prefix, _name, _ipl_blk) \
+IPL_ATTR_SHOW_FN(_prefix, _name, "0.%x.%04x\n", \
+ _ipl_blk.ssid, _ipl_blk.devno); \
+IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk); \
+static struct kobj_attribute sys_##_prefix##_##_name##_attr = \
+ __ATTR(_name, (S_IRUGO | S_IWUSR), \
+ sys_##_prefix##_##_name##_show, \
+ sys_##_prefix##_##_name##_store) \
+
#define DEFINE_IPL_ATTR_RO(_prefix, _name, _format, _value) \
IPL_ATTR_SHOW_FN(_prefix, _name, _format, _value) \
static struct kobj_attribute sys_##_prefix##_##_name##_attr = \
@@ -395,7 +423,7 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
switch (ipl_info.type) {
case IPL_TYPE_CCW:
- return sprintf(page, "0.0.%04x\n", ipl_devno);
+ return sprintf(page, "0.%x.%04x\n", ipl_ssid, ipl_devno);
case IPL_TYPE_FCP:
case IPL_TYPE_FCP_DUMP:
return sprintf(page, "0.0.%04x\n", ipl->ipl_info.fcp.devno);
@@ -687,21 +715,14 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr,
char *buf, loff_t off, size_t count)
{
+ size_t scpdata_len = count;
size_t padding;
- size_t scpdata_len;
-
- if (off < 0)
- return -EINVAL;
- if (off >= DIAG308_SCPDATA_SIZE)
- return -ENOSPC;
- if (count > DIAG308_SCPDATA_SIZE - off)
- count = DIAG308_SCPDATA_SIZE - off;
-
- memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count);
- scpdata_len = off + count;
+ if (off)
+ return -EINVAL;
+ memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count);
if (scpdata_len % 8) {
padding = 8 - (scpdata_len % 8);
memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len,
@@ -717,7 +738,7 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
}
static struct bin_attribute sys_reipl_fcp_scp_data_attr =
__BIN_ATTR(scp_data, (S_IRUGO | S_IWUSR), reipl_fcp_scpdata_read,
- reipl_fcp_scpdata_write, PAGE_SIZE);
+ reipl_fcp_scpdata_write, DIAG308_SCPDATA_SIZE);
static struct bin_attribute *reipl_fcp_bin_attrs[] = {
&sys_reipl_fcp_scp_data_attr,
@@ -814,9 +835,7 @@ static struct attribute_group reipl_fcp_attr_group = {
};
/* CCW reipl device attributes */
-
-DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n",
- reipl_block_ccw->ipl_info.ccw.devno);
+DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw);
/* NSS wrapper */
static ssize_t reipl_nss_loadparm_show(struct kobject *kobj,
@@ -1056,8 +1075,8 @@ static void __reipl_run(void *unused)
switch (reipl_method) {
case REIPL_METHOD_CCW_CIO:
+ devid.ssid = reipl_block_ccw->ipl_info.ccw.ssid;
devid.devno = reipl_block_ccw->ipl_info.ccw.devno;
- devid.ssid = 0;
reipl_ccw_dev(&devid);
break;
case REIPL_METHOD_CCW_VM:
@@ -1192,6 +1211,7 @@ static int __init reipl_ccw_init(void)
reipl_block_ccw_init(reipl_block_ccw);
if (ipl_info.type == IPL_TYPE_CCW) {
+ reipl_block_ccw->ipl_info.ccw.ssid = ipl_ssid;
reipl_block_ccw->ipl_info.ccw.devno = ipl_devno;
reipl_block_ccw_fill_parms(reipl_block_ccw);
}
@@ -1336,9 +1356,7 @@ static struct attribute_group dump_fcp_attr_group = {
};
/* CCW dump device attributes */
-
-DEFINE_IPL_ATTR_RW(dump_ccw, device, "0.0.%04llx\n", "0.0.%llx\n",
- dump_block_ccw->ipl_info.ccw.devno);
+DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw);
static struct attribute *dump_ccw_attrs[] = {
&sys_dump_ccw_device_attr.attr,
@@ -1418,8 +1436,8 @@ static void __dump_run(void *unused)
switch (dump_method) {
case DUMP_METHOD_CCW_CIO:
+ devid.ssid = dump_block_ccw->ipl_info.ccw.ssid;
devid.devno = dump_block_ccw->ipl_info.ccw.devno;
- devid.ssid = 0;
reipl_ccw_dev(&devid);
break;
case DUMP_METHOD_CCW_VM:
@@ -1939,14 +1957,14 @@ void __init setup_ipl(void)
ipl_info.type = get_ipl_type();
switch (ipl_info.type) {
case IPL_TYPE_CCW:
+ ipl_info.data.ccw.dev_id.ssid = ipl_ssid;
ipl_info.data.ccw.dev_id.devno = ipl_devno;
- ipl_info.data.ccw.dev_id.ssid = 0;
break;
case IPL_TYPE_FCP:
case IPL_TYPE_FCP_DUMP:
+ ipl_info.data.fcp.dev_id.ssid = 0;
ipl_info.data.fcp.dev_id.devno =
IPL_PARMBLOCK_START->ipl_info.fcp.devno;
- ipl_info.data.fcp.dev_id.ssid = 0;
ipl_info.data.fcp.wwpn = IPL_PARMBLOCK_START->ipl_info.fcp.wwpn;
ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun;
break;
@@ -1978,6 +1996,7 @@ void __init ipl_save_parameters(void)
if (cio_get_iplinfo(&iplinfo))
return;
+ ipl_ssid = iplinfo.ssid;
ipl_devno = iplinfo.devno;
ipl_flags |= IPL_DEVNO_VALID;
if (!iplinfo.is_qdio)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 688a3aad9c79..114ee8b96f17 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -243,11 +243,7 @@ unsigned long arch_align_stack(unsigned long sp)
static inline unsigned long brk_rnd(void)
{
- /* 8MB for 32bit, 1GB for 64bit */
- if (is_32bit_task())
- return (get_random_int() & 0x7ffUL) << PAGE_SHIFT;
- else
- return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT;
+ return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT;
}
unsigned long arch_randomize_brk(struct mm_struct *mm)
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 7ce00e7a709a..647128d5b983 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -61,6 +61,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
"edat", "etf3eh", "highgprs", "te", "vx"
};
+ static const char * const int_hwcap_str[] = {
+ "sie"
+ };
unsigned long n = (unsigned long) v - 1;
int i;
@@ -75,6 +78,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
seq_printf(m, "%s ", hwcap_str[i]);
+ for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
+ if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
+ seq_printf(m, "%s ", int_hwcap_str[i]);
seq_puts(m, "\n");
show_cacheinfo(m);
}
diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c
index fa0bdff1d413..9fe7781a45cd 100644
--- a/arch/s390/kernel/sclp.c
+++ b/arch/s390/kernel/sclp.c
@@ -21,7 +21,7 @@ static void _sclp_wait_int(void)
__ctl_load(cr0_new, 0, 0);
psw_ext_save = S390_lowcore.external_new_psw;
- psw_mask = __extract_psw() & (PSW_MASK_EA | PSW_MASK_BA);
+ psw_mask = __extract_psw();
S390_lowcore.external_new_psw.mask = psw_mask;
psw_wait.mask = psw_mask | PSW_MASK_EXT | PSW_MASK_WAIT;
S390_lowcore.ext_int_code = 0;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ce0cbd6ba7ca..dc83ae66a730 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -80,6 +80,8 @@ EXPORT_SYMBOL(console_irq);
unsigned long elf_hwcap __read_mostly = 0;
char elf_platform[ELF_PLATFORM_SIZE];
+unsigned long int_hwcap = 0;
+
int __initdata memory_end_set;
unsigned long __initdata memory_end;
unsigned long __initdata max_physmem_end;
@@ -764,9 +766,6 @@ static int __init setup_hwcaps(void)
get_cpu_id(&cpu_id);
add_device_randomness(&cpu_id, sizeof(cpu_id));
switch (cpu_id.machine) {
- case 0x9672:
- strcpy(elf_platform, "g5");
- break;
case 0x2064:
case 0x2066:
default: /* Use "z900" as default for 64 bit kernels. */
@@ -796,6 +795,13 @@ static int __init setup_hwcaps(void)
strcpy(elf_platform, "z13");
break;
}
+
+ /*
+ * Virtualization support HWCAP_INT_SIE is bit 0.
+ */
+ if (sclp.has_sief2)
+ int_hwcap |= HWCAP_INT_SIE;
+
return 0;
}
arch_initcall(setup_hwcaps);
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 8c56929c8d82..5378c3ea1b98 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -382,3 +382,4 @@ SYSCALL(sys_sendmsg,compat_sys_sendmsg) /* 370 */
SYSCALL(sys_recvfrom,compat_sys_recvfrom)
SYSCALL(sys_recvmsg,compat_sys_recvmsg)
SYSCALL(sys_shutdown,sys_shutdown)
+SYSCALL(sys_mlock2,compat_sys_mlock2)
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 73239bb576c4..21a5df99552b 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -9,11 +9,11 @@
#define CREATE_TRACE_POINTS
#include <asm/trace/diag.h>
-EXPORT_TRACEPOINT_SYMBOL(diagnose);
+EXPORT_TRACEPOINT_SYMBOL(s390_diagnose);
static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth);
-void trace_diagnose_norecursion(int diag_nr)
+void trace_s390_diagnose_norecursion(int diag_nr)
{
unsigned long flags;
unsigned int *depth;
@@ -22,7 +22,7 @@ void trace_diagnose_norecursion(int diag_nr)
depth = this_cpu_ptr(&diagnose_trace_depth);
if (*depth == 0) {
(*depth)++;
- trace_diagnose(diag_nr);
+ trace_s390_diagnose(diag_nr);
(*depth)--;
}
local_irq_restore(flags);
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5fbfb88f8477..05f7de9869a9 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -155,10 +155,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tcpu;
int tid;
- int i;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
vcpu->stat.diagnose_9c++;
@@ -167,12 +165,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
if (tid == vcpu->vcpu_id)
return 0;
- kvm_for_each_vcpu(i, tcpu, kvm)
- if (tcpu->vcpu_id == tid) {
- kvm_vcpu_yield_to(tcpu);
- break;
- }
-
+ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+ if (tcpu)
+ kvm_vcpu_yield_to(tcpu);
return 0;
}
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a7559f7207df..d30db40437dc 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,10 +259,14 @@ struct aste {
int ipte_lock_held(struct kvm_vcpu *vcpu)
{
- union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+ if (vcpu->arch.sie_block->eca & 1) {
+ int rc;
- if (vcpu->arch.sie_block->eca & 1)
- return ic->kh != 0;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ return rc;
+ }
return vcpu->kvm->arch.ipte_lock_count != 0;
}
@@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count++;
if (vcpu->kvm->arch.ipte_lock_count > 1)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.k) {
+ if (old.k) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
}
@@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count--;
if (vcpu->kvm->arch.ipte_lock_count)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
wake_up(&vcpu->kvm->arch.ipte_wq);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,24 +321,29 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.kg) {
+ if (old.kg) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
new.kh++;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
}
static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
@@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
if (!new.kh)
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
if (!new.kh)
wake_up(&vcpu->kvm->arch.ipte_wq);
}
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b4a5aa110cec..d53c10753c46 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -54,9 +54,6 @@ void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
static int handle_noop(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
- case 0x0:
- vcpu->stat.exit_null++;
- break;
case 0x10:
vcpu->stat.exit_external_request++;
break;
@@ -338,8 +335,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
{
+ if (kvm_is_ucontrol(vcpu->kvm))
+ return -EOPNOTSUPP;
+
switch (vcpu->arch.sie_block->icptcode) {
- case 0x00:
case 0x10:
case 0x18:
return handle_noop(vcpu);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 373e32346d68..62ec925aa196 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -34,6 +34,106 @@
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+ int c, scn;
+
+ if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+ return 0;
+
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl sigp_ctrl =
+ sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+ c = sigp_ctrl.c;
+ scn = sigp_ctrl.scn;
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl sigp_ctrl =
+ sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+ c = sigp_ctrl.c;
+ scn = sigp_ctrl.scn;
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+
+ if (src_id)
+ *src_id = scn;
+
+ return c;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+ int expect, rc;
+
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+ new_val.scn = src_id;
+ new_val.c = 1;
+ old_val.c = 0;
+
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+ new_val.scn = src_id;
+ new_val.c = 1;
+ old_val.c = 0;
+
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+
+ if (rc != expect) {
+ /* another external call is pending */
+ return -EBUSY;
+ }
+ atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+ return 0;
+}
+
+static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc, expect;
+
+ atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union esca_sigp_ctrl old = *sigp_ctrl;
+
+ expect = old.value;
+ rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union bsca_sigp_ctrl old = *sigp_ctrl;
+
+ expect = old.value;
+ rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ WARN_ON(rc != expect); /* cannot clear? */
+}
+
int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -792,13 +892,11 @@ static const deliver_irq_t deliver_irq_funcs[] = {
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
if (!sclp.has_sigpif)
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
- return (sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+ return sca_ext_call_pending(vcpu, NULL);
}
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -909,9 +1007,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
memset(&li->irq, 0, sizeof(li->irq));
spin_unlock(&li->lock);
- /* clear pending external calls set by sigp interpretation facility */
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+ sca_clear_ext_call(vcpu);
}
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -1003,21 +1099,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
return 0;
}
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
- unsigned char new_val, old_val;
- uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
- new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
- old_val = *sigp_ctrl & ~SIGP_CTRL_C;
- if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
- /* another external call is pending */
- return -EBUSY;
- }
- atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
- return 0;
-}
-
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1030,12 +1111,11 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
src_id, 0);
/* sending vcpu invalid */
- if (src_id >= KVM_MAX_VCPUS ||
- kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+ if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
return -EINVAL;
if (sclp.has_sigpif)
- return __inject_extcall_sigpif(vcpu, src_id);
+ return sca_inject_ext_call(vcpu, src_id);
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
@@ -1110,6 +1190,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
irq->u.emerg.code, 0);
+ /* sending vcpu invalid */
+ if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
+ return -EINVAL;
+
set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
@@ -2200,7 +2284,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li,
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
{
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+ int scn;
unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
unsigned long pending_irqs;
@@ -2240,14 +2324,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
}
}
- if ((sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) &
- CPUSTAT_ECALL_PEND)) {
+ if (sca_ext_call_pending(vcpu, &scn)) {
if (n + sizeof(irq) > len)
return -ENOBUFS;
memset(&irq, 0, sizeof(irq));
irq.type = KVM_S390_INT_EXTERNAL_CALL;
- irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+ irq.u.extcall.code = scn;
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fe2f1c722dc..5927c61d322a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -246,7 +246,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
- r = KVM_MAX_VCPUS;
+ r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+ : KVM_S390_BSCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
@@ -257,6 +258,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_VECTOR_REGISTERS:
r = MACHINE_HAS_VX;
break;
+ case KVM_CAP_S390_RI:
+ r = test_facility(64);
+ break;
default:
r = 0;
}
@@ -283,6 +287,8 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
}
/* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
@@ -342,15 +348,33 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
r = 0;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
- if (MACHINE_HAS_VX) {
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ r = -EBUSY;
+ } else if (MACHINE_HAS_VX) {
set_kvm_facility(kvm->arch.model.fac->mask, 129);
set_kvm_facility(kvm->arch.model.fac->list, 129);
r = 0;
} else
r = -EINVAL;
+ mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
r ? "(not available)" : "(success)");
break;
+ case KVM_CAP_S390_RI:
+ r = -EINVAL;
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ r = -EBUSY;
+ } else if (test_facility(64)) {
+ set_kvm_facility(kvm->arch.model.fac->mask, 64);
+ set_kvm_facility(kvm->arch.model.fac->list, 64);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
+ r ? "(not available)" : "(success)");
+ break;
case KVM_CAP_S390_USER_STSI:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
kvm->arch.user_stsi = 1;
@@ -371,8 +395,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
- kvm->arch.gmap->asce_end);
- if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+ kvm->arch.mem_limit);
+ if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
ret = -EFAULT;
break;
default:
@@ -424,9 +448,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
if (get_user(new_limit, (u64 __user *)attr->addr))
return -EFAULT;
- if (new_limit > kvm->arch.gmap->asce_end)
+ if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+ new_limit > kvm->arch.mem_limit)
return -E2BIG;
+ if (!new_limit)
+ return -EINVAL;
+
+ /* gmap_alloc takes last usable address */
+ if (new_limit != KVM_S390_NO_MEM_LIMIT)
+ new_limit -= 1;
+
ret = -EBUSY;
mutex_lock(&kvm->lock);
if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -443,7 +475,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
}
}
mutex_unlock(&kvm->lock);
- VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
+ VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+ VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+ (void *) kvm->arch.gmap->asce);
break;
}
default:
@@ -1020,7 +1054,7 @@ static int kvm_s390_apxa_installed(void)
u8 config[128];
int cc;
- if (test_facility(2) && test_facility(12)) {
+ if (test_facility(12)) {
cc = kvm_s390_query_ap_config(config);
if (cc)
@@ -1071,6 +1105,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
return 0;
}
+static void sca_dispose(struct kvm *kvm)
+{
+ if (kvm->arch.use_esca)
+ free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
+ else
+ free_page((unsigned long)(kvm->arch.sca));
+ kvm->arch.sca = NULL;
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int i, rc;
@@ -1094,14 +1137,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
rc = -ENOMEM;
- kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+ kvm->arch.use_esca = 0; /* start with basic SCA */
+ rwlock_init(&kvm->arch.sca_lock);
+ kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
if (!kvm->arch.sca)
goto out_err;
spin_lock(&kvm_lock);
sca_offset += 16;
- if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+ if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
- kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+ kvm->arch.sca = (struct bsca_block *)
+ ((char *) kvm->arch.sca + sca_offset);
spin_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
@@ -1153,8 +1199,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (type & KVM_VM_S390_UCONTROL) {
kvm->arch.gmap = NULL;
+ kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
} else {
- kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+ if (sclp.hamax == U64_MAX)
+ kvm->arch.mem_limit = TASK_MAX_SIZE;
+ else
+ kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+ sclp.hamax + 1);
+ kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
if (!kvm->arch.gmap)
goto out_err;
kvm->arch.gmap->private = kvm;
@@ -1166,14 +1218,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
- KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+ KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
out_err:
kfree(kvm->arch.crypto.crycb);
free_page((unsigned long)kvm->arch.model.fac);
debug_unregister(kvm->arch.dbf);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
return rc;
}
@@ -1184,14 +1236,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
kvm_s390_clear_local_irqs(vcpu);
kvm_clear_async_pf_completion_queue(vcpu);
- if (!kvm_is_ucontrol(vcpu->kvm)) {
- clear_bit(63 - vcpu->vcpu_id,
- (unsigned long *) &vcpu->kvm->arch.sca->mcn);
- if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
- (__u64) vcpu->arch.sie_block)
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
- }
- smp_mb();
+ if (!kvm_is_ucontrol(vcpu->kvm))
+ sca_del_vcpu(vcpu);
if (kvm_is_ucontrol(vcpu->kvm))
gmap_free(vcpu->arch.gmap);
@@ -1224,14 +1270,14 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
free_page((unsigned long)kvm->arch.model.fac);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
kfree(kvm->arch.crypto.crycb);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
- KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+ KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
/* Section: vcpu related */
@@ -1245,6 +1291,117 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
return 0;
}
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+
+ sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+ d->sda = s->sda;
+ d->sigp_ctrl.c = s->sigp_ctrl.c;
+ d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+ int i;
+
+ d->ipte_control = s->ipte_control;
+ d->mcn[0] = s->mcn;
+ for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+ sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+static int sca_switch_to_extended(struct kvm *kvm)
+{
+ struct bsca_block *old_sca = kvm->arch.sca;
+ struct esca_block *new_sca;
+ struct kvm_vcpu *vcpu;
+ unsigned int vcpu_idx;
+ u32 scaol, scaoh;
+
+ new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+ if (!new_sca)
+ return -ENOMEM;
+
+ scaoh = (u32)((u64)(new_sca) >> 32);
+ scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+ kvm_s390_vcpu_block_all(kvm);
+ write_lock(&kvm->arch.sca_lock);
+
+ sca_copy_b_to_e(new_sca, old_sca);
+
+ kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+ vcpu->arch.sie_block->scaoh = scaoh;
+ vcpu->arch.sie_block->scaol = scaol;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ }
+ kvm->arch.sca = new_sca;
+ kvm->arch.use_esca = 1;
+
+ write_unlock(&kvm->arch.sca_lock);
+ kvm_s390_vcpu_unblock_all(kvm);
+
+ free_page((unsigned long)old_sca);
+
+ VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+ old_sca, kvm->arch.sca);
+ return 0;
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+ int rc;
+
+ if (id < KVM_S390_BSCA_CPU_SLOTS)
+ return true;
+ if (!sclp.has_esca)
+ return false;
+
+ mutex_lock(&kvm->lock);
+ rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
+ mutex_unlock(&kvm->lock);
+
+ return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1255,6 +1412,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
KVM_SYNC_CRS |
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT;
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
if (test_kvm_facility(vcpu->kvm, 129))
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
@@ -1365,8 +1524,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
preempt_enable();
mutex_unlock(&vcpu->kvm->lock);
- if (!kvm_is_ucontrol(vcpu->kvm))
+ if (!kvm_is_ucontrol(vcpu->kvm)) {
vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+ sca_add_vcpu(vcpu);
+ }
+
}
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1435,10 +1597,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
}
+ vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
if (vcpu->kvm->arch.use_cmma) {
@@ -1461,7 +1626,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
struct sie_page *sie_page;
int rc = -EINVAL;
- if (id >= KVM_MAX_VCPUS)
+ if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
goto out;
rc = -ENOMEM;
@@ -1478,20 +1643,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
vcpu->arch.sie_block->icpua = id;
- if (!kvm_is_ucontrol(kvm)) {
- if (!kvm->arch.sca) {
- WARN_ON_ONCE(1);
- goto out_free_cpu;
- }
- if (!kvm->arch.sca->cpu[id].sda)
- kvm->arch.sca->cpu[id].sda =
- (__u64) vcpu->arch.sie_block;
- vcpu->arch.sie_block->scaoh =
- (__u32)(((__u64)kvm->arch.sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
- set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
- }
-
spin_lock_init(&vcpu->arch.local_int.lock);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
vcpu->arch.local_int.wq = &vcpu->wq;
@@ -1505,15 +1656,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
*/
vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
GFP_KERNEL);
- if (!vcpu->arch.guest_fpregs.fprs) {
- rc = -ENOMEM;
+ if (!vcpu->arch.guest_fpregs.fprs)
goto out_free_sie_block;
- }
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
goto out_free_sie_block;
- VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+ VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
vcpu->arch.sie_block);
trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
@@ -2009,7 +2158,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
*/
kvm_check_async_pf_completion(vcpu);
- memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+ vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+ vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
if (need_resched())
schedule();
@@ -2067,8 +2217,6 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
- int rc = -1;
-
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2076,40 +2224,36 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
if (guestdbg_enabled(vcpu))
kvm_s390_restore_guest_per_regs(vcpu);
- if (exit_reason >= 0) {
- rc = 0;
+ vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+ vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
+
+ if (vcpu->arch.sie_block->icptcode > 0) {
+ int rc = kvm_handle_sie_intercept(vcpu);
+
+ if (rc != -EOPNOTSUPP)
+ return rc;
+ vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+ vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+ vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+ vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+ return -EREMOTE;
+ } else if (exit_reason != -EFAULT) {
+ vcpu->stat.exit_null++;
+ return 0;
} else if (kvm_is_ucontrol(vcpu->kvm)) {
vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
vcpu->run->s390_ucontrol.trans_exc_code =
current->thread.gmap_addr;
vcpu->run->s390_ucontrol.pgm_code = 0x10;
- rc = -EREMOTE;
-
+ return -EREMOTE;
} else if (current->thread.gmap_pfault) {
trace_kvm_s390_major_guest_pfault(vcpu);
current->thread.gmap_pfault = 0;
- if (kvm_arch_setup_async_pf(vcpu)) {
- rc = 0;
- } else {
- gpa_t gpa = current->thread.gmap_addr;
- rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
- }
+ if (kvm_arch_setup_async_pf(vcpu))
+ return 0;
+ return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
}
-
- if (rc == -1)
- rc = vcpu_post_run_fault_in_sie(vcpu);
-
- memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
- if (rc == 0) {
- if (kvm_is_ucontrol(vcpu->kvm))
- /* Don't exit for host interrupts. */
- rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
- else
- rc = kvm_handle_sie_intercept(vcpu);
- }
-
- return rc;
+ return vcpu_post_run_fault_in_sie(vcpu);
}
static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2229,18 +2373,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = 0;
}
- if (rc == -EOPNOTSUPP) {
- /* intercept cannot be handled in-kernel, prepare kvm-run */
- kvm_run->exit_reason = KVM_EXIT_S390_SIEIC;
- kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
- kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
- kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
- rc = 0;
- }
-
if (rc == -EREMOTE) {
- /* intercept was handled, but userspace support is needed
- * kvm_run has been prepared by the handler */
+ /* userspace support is needed, kvm_run has been prepared */
rc = 0;
}
@@ -2732,6 +2866,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
if (mem->memory_size & 0xffffful)
return -EINVAL;
+ if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+ return -EINVAL;
+
return 0;
}
@@ -2763,6 +2900,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
static int __init kvm_s390_init(void)
{
+ if (!sclp.has_sief2) {
+ pr_info("SIE not available\n");
+ return -ENODEV;
+ }
+
return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1e70e00d3c5e..df1abada1f36 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -340,4 +340,11 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+ struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+ return &sca->ipte_control;
+}
#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 77191b85ea7a..d76b51cb4b62 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -660,7 +660,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
- if (!MACHINE_HAS_PFMF)
+ if (!test_kvm_facility(vcpu->kvm, 8))
return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index da690b69f9fe..77c22d685c7a 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
u16 cpu_addr, u32 parameter, u64 *status_reg)
{
int rc;
- struct kvm_vcpu *dst_vcpu;
+ struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
- if (cpu_addr >= KVM_MAX_VCPUS)
- return SIGP_CC_NOT_OPERATIONAL;
-
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
if (!dst_vcpu)
return SIGP_CC_NOT_OPERATIONAL;
@@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
if (order_code == SIGP_EXTERNAL_CALL) {
- dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
BUG_ON(dest_vcpu == NULL);
kvm_s390_vcpu_wakeup(dest_vcpu);
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index cc1d6c68356f..396485bca191 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu,
__entry->sie_block = sie_block;
),
- TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
- __entry->vcpu, __entry->sie_block)
+ TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+ __entry->id, __entry->vcpu, __entry->sie_block)
);
TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css,
__entry->kvm = kvm;
),
- TP_printk("enabling channel I/O support (kvm @ %p)\n",
+ TP_printk("enabling channel I/O support (kvm @ %pK)\n",
__entry->kvm)
);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index c3c07d3505ba..c722400c7697 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -48,37 +48,13 @@ EXPORT_SYMBOL(zero_page_mask);
static void __init setup_zero_pages(void)
{
- struct cpuid cpu_id;
unsigned int order;
struct page *page;
int i;
- get_cpu_id(&cpu_id);
- switch (cpu_id.machine) {
- case 0x9672: /* g5 */
- case 0x2064: /* z900 */
- case 0x2066: /* z900 */
- case 0x2084: /* z990 */
- case 0x2086: /* z990 */
- case 0x2094: /* z9-109 */
- case 0x2096: /* z9-109 */
- order = 0;
- break;
- case 0x2097: /* z10 */
- case 0x2098: /* z10 */
- case 0x2817: /* z196 */
- case 0x2818: /* z196 */
- order = 2;
- break;
- case 0x2827: /* zEC12 */
- case 0x2828: /* zEC12 */
- order = 5;
- break;
- case 0x2964: /* z13 */
- default:
- order = 7;
- break;
- }
+ /* Latest machines require a mapping granularity of 512KB */
+ order = 7;
+
/* Limit number of empty zero pages for small memory sizes */
while (order > 2 && (totalram_pages >> 10) < (1UL << order))
order--;
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 6e552af08c76..ea01477b4aa6 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -31,9 +31,6 @@
#include <linux/security.h>
#include <asm/pgalloc.h>
-unsigned long mmap_rnd_mask;
-static unsigned long mmap_align_mask;
-
static unsigned long stack_maxrandom_size(void)
{
if (!(current->flags & PF_RANDOMIZE))
@@ -62,10 +59,7 @@ static inline int mmap_is_legacy(void)
unsigned long arch_mmap_rnd(void)
{
- if (is_32bit_task())
- return (get_random_int() & 0x7ff) << PAGE_SHIFT;
- else
- return (get_random_int() & mmap_rnd_mask) << PAGE_SHIFT;
+ return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT;
}
static unsigned long mmap_base_legacy(unsigned long rnd)
@@ -92,7 +86,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
- int do_color_align;
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
@@ -108,15 +101,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
return addr;
}
- do_color_align = 0;
- if (filp || (flags & MAP_SHARED))
- do_color_align = !is_32bit_task();
-
info.flags = 0;
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = TASK_SIZE;
- info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0;
+ if (filp || (flags & MAP_SHARED))
+ info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
+ else
+ info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
return vm_unmapped_area(&info);
}
@@ -130,7 +122,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
- int do_color_align;
/* requested length too big for entire address space */
if (len > TASK_SIZE - mmap_min_addr)
@@ -148,15 +139,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
return addr;
}
- do_color_align = 0;
- if (filp || (flags & MAP_SHARED))
- do_color_align = !is_32bit_task();
-
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = max(PAGE_SIZE, mmap_min_addr);
info.high_limit = mm->mmap_base;
- info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0;
+ if (filp || (flags & MAP_SHARED))
+ info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
+ else
+ info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
addr = vm_unmapped_area(&info);
@@ -254,35 +244,3 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
mm->get_unmapped_area = s390_get_unmapped_area_topdown;
}
}
-
-static int __init setup_mmap_rnd(void)
-{
- struct cpuid cpu_id;
-
- get_cpu_id(&cpu_id);
- switch (cpu_id.machine) {
- case 0x9672:
- case 0x2064:
- case 0x2066:
- case 0x2084:
- case 0x2086:
- case 0x2094:
- case 0x2096:
- case 0x2097:
- case 0x2098:
- case 0x2817:
- case 0x2818:
- case 0x2827:
- case 0x2828:
- mmap_rnd_mask = 0x7ffUL;
- mmap_align_mask = 0UL;
- break;
- case 0x2964: /* z13 */
- default:
- mmap_rnd_mask = 0x3ff80UL;
- mmap_align_mask = 0x7fUL;
- break;
- }
- return 0;
-}
-early_initcall(setup_mmap_rnd);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 54ef3bc01b43..63b039899a5e 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -133,7 +133,7 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
/**
* gmap_alloc - allocate a guest address space
* @mm: pointer to the parent mm_struct
- * @limit: maximum size of the gmap address space
+ * @limit: maximum address of the gmap address space
*
* Returns a guest address space structure.
*/
@@ -402,7 +402,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
if ((from | to | len) & (PMD_SIZE - 1))
return -EINVAL;
if (len == 0 || from + len < from || to + len < to ||
- from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+ from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
return -EINVAL;
flush = 0;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9a0c4c22e536..3c0bfc1f2694 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -408,7 +408,7 @@ static void emit_load_skb_data_hlen(struct bpf_jit *jit)
* Save registers and create stack frame if necessary.
* See stack frame layout desription in "bpf_jit.h"!
*/
-static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
+static void bpf_jit_prologue(struct bpf_jit *jit)
{
if (jit->seen & SEEN_TAIL_CALL) {
/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
@@ -448,15 +448,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
STK_OFF_SKBP);
- /* Clear A (%b0) and X (%b7) registers for converted BPF programs */
- if (is_classic) {
- if (REG_SEEN(BPF_REG_A))
- /* lghi %ba,0 */
- EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
- if (REG_SEEN(BPF_REG_X))
- /* lghi %bx,0 */
- EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
- }
}
/*
@@ -1245,7 +1236,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
jit->lit = jit->lit_start;
jit->prg = 0;
- bpf_jit_prologue(jit, bpf_prog_was_classic(fp));
+ bpf_jit_prologue(jit);
for (i = 0; i < fp->len; i += insn_count) {
insn_count = bpf_jit_insn(jit, fp, i);
if (insn_count < 0)
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 37d10f74425a..32da0a6ecec2 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -33,7 +33,7 @@ unsigned long *dma_alloc_cpu_table(void)
return NULL;
for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
- *entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED;
+ *entry = ZPCI_TABLE_INVALID;
return table;
}
@@ -51,7 +51,7 @@ static unsigned long *dma_alloc_page_table(void)
return NULL;
for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
- *entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED;
+ *entry = ZPCI_PTE_INVALID;
return table;
}
@@ -95,7 +95,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *entry)
return pto;
}
-static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
+unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
{
unsigned long *sto, *pto;
unsigned int rtx, sx, px;
@@ -114,20 +114,10 @@ static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr
return &pto[px];
}
-void dma_update_cpu_trans(unsigned long *dma_table, void *page_addr,
- dma_addr_t dma_addr, int flags)
+void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags)
{
- unsigned long *entry;
-
- entry = dma_walk_cpu_trans(dma_table, dma_addr);
- if (!entry) {
- WARN_ON_ONCE(1);
- return;
- }
-
if (flags & ZPCI_PTE_INVALID) {
invalidate_pt_entry(entry);
- return;
} else {
set_pt_pfaa(entry, page_addr);
validate_pt_entry(entry);
@@ -146,18 +136,25 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
u8 *page_addr = (u8 *) (pa & PAGE_MASK);
dma_addr_t start_dma_addr = dma_addr;
unsigned long irq_flags;
+ unsigned long *entry;
int i, rc = 0;
if (!nr_pages)
return -EINVAL;
spin_lock_irqsave(&zdev->dma_table_lock, irq_flags);
- if (!zdev->dma_table)
+ if (!zdev->dma_table) {
+ rc = -EINVAL;
goto no_refresh;
+ }
for (i = 0; i < nr_pages; i++) {
- dma_update_cpu_trans(zdev->dma_table, page_addr, dma_addr,
- flags);
+ entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+ if (!entry) {
+ rc = -ENOMEM;
+ goto undo_cpu_trans;
+ }
+ dma_update_cpu_trans(entry, page_addr, flags);
page_addr += PAGE_SIZE;
dma_addr += PAGE_SIZE;
}
@@ -176,6 +173,18 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
nr_pages * PAGE_SIZE);
+undo_cpu_trans:
+ if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) {
+ flags = ZPCI_PTE_INVALID;
+ while (i-- > 0) {
+ page_addr -= PAGE_SIZE;
+ dma_addr -= PAGE_SIZE;
+ entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+ if (!entry)
+ break;
+ dma_update_cpu_trans(entry, page_addr, flags);
+ }
+ }
no_refresh:
spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
@@ -260,6 +269,16 @@ out:
spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
}
+static inline void zpci_err_dma(unsigned long rc, unsigned long addr)
+{
+ struct {
+ unsigned long rc;
+ unsigned long addr;
+ } __packed data = {rc, addr};
+
+ zpci_err_hex(&data, sizeof(data));
+}
+
static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction direction,
@@ -270,33 +289,40 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
unsigned long pa = page_to_phys(page) + offset;
int flags = ZPCI_PTE_VALID;
dma_addr_t dma_addr;
+ int ret;
/* This rounds up number of pages based on size and offset */
nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
- if (iommu_page_index == -1)
+ if (iommu_page_index == -1) {
+ ret = -ENOSPC;
goto out_err;
+ }
/* Use rounded up size */
size = nr_pages * PAGE_SIZE;
dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE;
- if (dma_addr + size > zdev->end_dma)
+ if (dma_addr + size > zdev->end_dma) {
+ ret = -ERANGE;
goto out_free;
+ }
if (direction == DMA_NONE || direction == DMA_TO_DEVICE)
flags |= ZPCI_TABLE_PROTECTED;
- if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
- atomic64_add(nr_pages, &zdev->mapped_pages);
- return dma_addr + (offset & ~PAGE_MASK);
- }
+ ret = dma_update_trans(zdev, pa, dma_addr, size, flags);
+ if (ret)
+ goto out_free;
+
+ atomic64_add(nr_pages, &zdev->mapped_pages);
+ return dma_addr + (offset & ~PAGE_MASK);
out_free:
dma_free_iommu(zdev, iommu_page_index, nr_pages);
out_err:
zpci_err("map error:\n");
- zpci_err_hex(&pa, sizeof(pa));
+ zpci_err_dma(ret, pa);
return DMA_ERROR_CODE;
}
@@ -306,14 +332,16 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
{
struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
unsigned long iommu_page_index;
- int npages;
+ int npages, ret;
npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
dma_addr = dma_addr & PAGE_MASK;
- if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
- ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) {
+ ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
+ ZPCI_PTE_INVALID);
+ if (ret) {
zpci_err("unmap error:\n");
- zpci_err_hex(&dma_addr, sizeof(dma_addr));
+ zpci_err_dma(ret, dma_addr);
+ return;
}
atomic64_add(npages, &zdev->unmapped_pages);
@@ -338,8 +366,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
pa = page_to_phys(page);
memset((void *) pa, 0, size);
- map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
- size, DMA_BIDIRECTIONAL, NULL);
+ map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL);
if (dma_mapping_error(dev, map)) {
free_pages(pa, get_order(size));
return NULL;