select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
select HAVE_CONTEXT_TRACKING if PPC64
- select HAVE_TIF_NOHZ if PPC64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DYNAMIC_FTRACE
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
select HAVE_HARDLOCKUP_DETECTOR_ARCH if (PPC64 && PPC_BOOK3S)
- select HAVE_OPROFILE
select HAVE_OPTPROBES if PPC64
select HAVE_PERF_EVENTS
select HAVE_PERF_EVENTS_NMI if PPC64
bool "Enable support for 32bit binaries"
depends on PPC64
default y if !CPU_LITTLE_ENDIAN
- select COMPAT_BINFMT_ELF
select ARCH_WANT_OLD_COMPAT_IPC
select COMPAT_OLD_SIGACTION
Say N if you are unsure.
config PPC_QUEUED_SPINLOCKS
- bool "Queued spinlocks"
+ bool "Queued spinlocks" if EXPERT
depends on SMP
+ default PPC_BOOK3S_64
help
Say Y here to use queued spinlocks which give better scalability and
fairness on large SMP and NUMA systems without harming single threaded
performance.
- This option is currently experimental, the code is more complex and
- less tested so it defaults to "N" for the moment.
-
- If unsure, say "N".
-
config ARCH_CPU_PROBE_RELEASE
def_bool y
depends on HOTPLUG_CPU
def_bool y
depends on MEMORY_HOTPLUG
- config STDBINUTILS
- bool "Using standard binutils settings"
- depends on 44x
- default y
- help
- Turning this option off allows you to select 256KB PAGE_SIZE on 44x.
- Note, that kernel will be able to run only those applications,
- which had been compiled using binutils later than 2.17.50.0.3 with
- '-zmax-page-size' set to 256K (the default is 64K). Or, if using
- the older binutils, you can patch them with a trivial patch, which
- changes the ELF_MAXPAGESIZE definition from 0x10000 to 0x40000.
-
choice
prompt "Page size"
default PPC_4K_PAGES
select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
config PPC_256K_PAGES
- bool "256k page size"
- depends on 44x && !STDBINUTILS
+ bool "256k page size (Requires non-standard binutils settings)"
+ depends on 44x && !PPC_47x
help
Make the page size 256k.
- As the ELF standard only requires alignment to support page
- sizes up to 64k, you will need to compile all of your user
- space applications with a non-standard binutils settings
- (see the STDBINUTILS description for details).
-
- Say N unless you know what you are doing.
+ The kernel will only be able to run applications that have been
+ compiled with '-zmax-page-size' set to 256K (the default is 64K) using
+ binutils later than 2.17.50.0.3, or by patching the ELF_MAXPAGESIZE
+ definition from 0x10000 to 0x40000 in older versions.
endchoice
CONFIG_KALLSYMS_ALL=y
# CONFIG_SLUB_CPU_PARTIAL is not set
CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_COMPACTION is not set
# CONFIG_SUSPEND is not set
CONFIG_NET=y
+ CONFIG_NETDEVICES=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_INET=y
# CONFIG_SCSI_PROC_FS is not set
CONFIG_BLK_DEV_SD=y
# CONFIG_SCSI_LOWLEVEL is not set
+ CONFIG_ATA=y
# CONFIG_SATA_PMP is not set
+ CONFIG_SATA_AHCI_PLATFORM=y
# CONFIG_ATA_SFF is not set
# CONFIG_NET_VENDOR_3COM is not set
# CONFIG_NET_VENDOR_ADAPTEC is not set
# CONFIG_USB_OHCI_HCD_PCI is not set
CONFIG_USB_STORAGE=y
CONFIG_MMC=y
+ CONFIG_MMC_SDHCI=y
+ CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_M41T80=y
CONFIG_EXT2_FS=y
#ifdef CONFIG_PPC_PKEY
+extern u64 __ro_after_init default_uamor;
+extern u64 __ro_after_init default_amr;
+extern u64 __ro_after_init default_iamr;
+
#include <asm/mmu.h>
#include <asm/ptrace.h>
-/*
- * For kernel thread that doesn't have thread.regs return
- * default AMR/IAMR values.
+/* usage of kthread_use_mm() should inherit the
+ * AMR value of the operating address space. But, the AMR value is
+ * thread-specific and we inherit the address space and not thread
+ * access restrictions. Because of this ignore AMR value when accessing
+ * userspace via kernel thread.
*/
static inline u64 current_thread_amr(void)
{
if (current->thread.regs)
return current->thread.regs->amr;
- return AMR_KUAP_BLOCKED;
+ return default_amr;
}
static inline u64 current_thread_iamr(void)
{
if (current->thread.regs)
return current->thread.regs->iamr;
- return AMR_KUEP_BLOCKED;
+ return default_iamr;
}
#endif /* CONFIG_PPC_PKEY */
* This has no effect in terms of actually blocking things on hash,
* so it doesn't break anything.
*/
- if (!early_mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
+ if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
return AMR_KUAP_BLOCKED;
return mfspr(SPRN_AMR);
static inline void set_kuap(unsigned long value)
{
- if (!early_mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
+ if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
return;
/*
int size);
int (*enable_svm)(struct kvm *kvm);
int (*svm_off)(struct kvm *kvm);
+ int (*enable_dawr1)(struct kvm *kvm);
+ bool (*hash_v3_possible)(void);
};
extern struct kvmppc_ops *kvmppc_hv_ops;
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
struct kvm *kvm)
{ return NULL; }
- static inline void kvmppc_alloc_host_rm_ops(void) {};
- static inline void kvmppc_free_host_rm_ops(void) {};
- static inline void kvmppc_free_pimap(struct kvm *kvm) {};
+ static inline void kvmppc_alloc_host_rm_ops(void) {}
+ static inline void kvmppc_free_host_rm_ops(void) {}
+ static inline void kvmppc_free_pimap(struct kvm *kvm) {}
static inline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
{ return 0; }
static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
/* Clear i-cache for new pages */
page = pfn_to_page(pfn);
- if (!test_bit(PG_arch_1, &page->flags)) {
+ if (!test_bit(PG_dcache_clean, &page->flags)) {
flush_dcache_icache_page(page);
- set_bit(PG_arch_1, &page->flags);
+ set_bit(PG_dcache_clean, &page->flags);
}
}
prom.o traps.o setup-common.o \
udbg.o misc.o io.o misc_$(BITS).o \
of_platform.o prom_parse.o firmware.o \
- hw_breakpoint_constraints.o
+ hw_breakpoint_constraints.o interrupt.o
obj-y += ptrace/
obj-$(CONFIG_PPC64) += setup_64.o \
- paca.o nvram_64.o note.o syscall_64.o
+ paca.o nvram_64.o note.o
obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o
-obj-$(CONFIG_VDSO32) += vdso32/
+obj-$(CONFIG_VDSO32) += vdso32_wrapper.o
obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_DAWR) += dawr.o
obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
-obj-$(CONFIG_PPC64) += vdso64/
+obj-$(CONFIG_PPC64) += vdso64_wrapper.o
obj-$(CONFIG_ALTIVEC) += vecemu.o
obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o
procfs-y := proc_powerpc.o
#endif /* CONFIG_PPC_MM_SLICES */
OFFSET(PACA_EXGEN, paca_struct, exgen);
OFFSET(PACA_EXMC, paca_struct, exmc);
- OFFSET(PACA_EXSLB, paca_struct, exslb);
OFFSET(PACA_EXNMI, paca_struct, exnmi);
#ifdef CONFIG_PPC_PSERIES
OFFSET(PACALPPACAPTR, paca_struct, lppaca_ptr);
/* Interrupt register frame */
DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
- DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+ DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_WITH_PT_REGS);
STACK_PT_REGS_OFFSET(GPR0, gpr[0]);
STACK_PT_REGS_OFFSET(GPR1, gpr[1]);
STACK_PT_REGS_OFFSET(GPR2, gpr[2]);
OFFSET(VCPU_CTRL, kvm_vcpu, arch.ctrl);
OFFSET(VCPU_DABR, kvm_vcpu, arch.dabr);
OFFSET(VCPU_DABRX, kvm_vcpu, arch.dabrx);
- OFFSET(VCPU_DAWR, kvm_vcpu, arch.dawr);
- OFFSET(VCPU_DAWRX, kvm_vcpu, arch.dawrx);
+ OFFSET(VCPU_DAWR0, kvm_vcpu, arch.dawr0);
+ OFFSET(VCPU_DAWRX0, kvm_vcpu, arch.dawrx0);
+ OFFSET(VCPU_DAWR1, kvm_vcpu, arch.dawr1);
+ OFFSET(VCPU_DAWRX1, kvm_vcpu, arch.dawrx1);
OFFSET(VCPU_CIABR, kvm_vcpu, arch.ciabr);
OFFSET(VCPU_HFLAGS, kvm_vcpu, arch.hflags);
OFFSET(VCPU_DEC, kvm_vcpu, arch.dec);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
- HSTATE_FIELD(HSTATE_TID, tid);
HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
OFFSET(KVM_SPLIT_DO_NAP, kvm_split_mode, do_nap);
OFFSET(KVM_SPLIT_NAPPED, kvm_split_mode, napped);
- OFFSET(KVM_SPLIT_DO_SET, kvm_split_mode, do_set);
- OFFSET(KVM_SPLIT_DO_RESTORE, kvm_split_mode, do_restore);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_PPC_BOOK3S_64
bne .Ltabort_syscall
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
- INTERRUPT_TO_KERNEL
+ SCV_INTERRUPT_TO_KERNEL
mr r10,r1
ld r1,PACAKSAVE(r13)
std r10,0(r1)
li r11,\trapnr
std r11,_TRAP(r1)
std r12,_CCR(r1)
- std r3,ORIG_GPR3(r1)
addi r10,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
std r11,-16(r10) /* "regshere" marker */
#endif
.balign IFETCH_ALIGN_BYTES
+ .globl system_call_common_real
+ system_call_common_real:
+ ld r10,PACAKMSR(r13) /* get MSR value for kernel */
+ mtmsrd r10
+
+ .balign IFETCH_ALIGN_BYTES
.globl system_call_common
system_call_common:
_ASM_NOKPROBE_SYMBOL(system_call_common)
std r10,_LINK(r1)
std r11,_TRAP(r1)
std r12,_CCR(r1)
- std r3,ORIG_GPR3(r1)
addi r10,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
std r11,-16(r10) /* "regshere" marker */
#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
#define __ISTACK(name) .L_ISTACK_ ## name
- #define IRECONCILE .L_IRECONCILE_\name\() /* Do RECONCILE_IRQ_STATE */
#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
#define INT_DEFINE_BEGIN(n) \
.ifndef ISTACK
ISTACK=1
.endif
- .ifndef IRECONCILE
- IRECONCILE=1
- .endif
.ifndef IKUAP
IKUAP=1
.endif
kuap_save_amr_and_lock r9, r10, cr1, cr0
.endif
beq 101f /* if from kernel mode */
- ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
BEGIN_FTR_SECTION
ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
std r9,_PPR(r1)
ld r11,exception_marker@toc(r2)
std r10,RESULT(r1) /* clear regs->result */
std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
-
- .if ISTACK
- ACCOUNT_STOLEN_TIME
- .endif
-
- .if IRECONCILE
- RECONCILE_IRQ_STATE(r10, r11)
- .endif
.endm
/*
ld r1,GPR1(r1)
.endm
- #define RUNLATCH_ON \
- BEGIN_FTR_SECTION \
- ld r3, PACA_THREAD_INFO(r13); \
- ld r4,TI_LOCAL_FLAGS(r3); \
- andi. r0,r4,_TLF_RUNLATCH; \
- beql ppc64_runlatch_on_trampoline; \
- END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-
/*
* When the idle code in power4_idle puts the CPU into NAP mode,
* it has to do so in a loop, and relies on the external interrupt
*/
ISET_RI=0
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
INT_DEFINE_END(system_reset)
ld r1,PACA_NMI_EMERG_SP(r13)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY system_reset
- /*
- * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
- * the right thing. We do not want to reconcile because that goes
- * through irq tracing which we don't want in NMI.
- *
- * Save PACAIRQHAPPENED to RESULT (otherwise unused), and set HARD_DIS
- * as we are running with MSR[EE]=0.
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
addi r3,r1,STACK_FRAME_OVERHEAD
bl system_reset_exception
subi r10,r10,1
sth r10,PACA_IN_NMI(r13)
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
kuap_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
ISTACK=0
IDAR=1
IDSISR=1
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
INT_DEFINE_END(machine_check_early)
li r10,MSR_RI
mtmsrd r10,1
- /*
- * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
- * system_reset_common)
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
-
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
*
* Handling:
* - Hash MMU
- * Go to do_hash_page first to see if the HPT can be filled from an entry in
- * the Linux page table. Hash faults can hit in kernel mode in a fairly
+ * Go to do_hash_fault, which attempts to fill the HPT from an entry in the
+ * Linux page table. Hash faults can hit in kernel mode in a fairly
* arbitrary state (e.g., interrupts disabled, locks held) when accessing
* "non-bolted" regions, e.g., vmalloc space. However these should always be
- * backed by Linux page tables.
+ * backed by Linux page table entries.
*
- * If none is found, do a Linux page fault. Linux page faults can happen in
- * kernel mode due to user copy operations of course.
+ * If no entry is found the Linux page fault handler is invoked (by
+ * do_hash_fault). Linux page faults can happen in kernel mode due to user
+ * copy operations of course.
*
* KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
* MMU context, which may cause a DSI in the host, which must go to the
EXC_VIRT_END(data_access, 0x4300, 0x80)
EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
+ ld r4,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ andis. r0,r4,DSISR_DABRMATCH@h
+ bne- 1f
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x300
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ b interrupt_return
+
+ 1: bl do_break
+ /*
+ * do_break() may have changed the NV GPRS while handling a breakpoint.
+ * If so, we need to restore them with their updated values.
+ */
+ REST_NVGPRS(r1)
+ b interrupt_return
GEN_KVM data_access
* on user-handler data structures.
*
* KVM: Same as 0x300, DSLB must test for KVM guest.
- *
- * A dedicated save area EXSLB is used (XXX: but it actually need not be
- * these days, we could use EXGEN).
*/
INT_DEFINE_BEGIN(data_access_slb)
IVEC=0x380
- IAREA=PACA_EXSLB
- IRECONCILE=0
IDAR=1
IKVM_SKIP=1
IKVM_REAL=1
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
EXC_COMMON_BEGIN(data_access_slb_common)
GEN_COMMON data_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x400
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ b interrupt_return
GEN_KVM instruction_access
*/
INT_DEFINE_BEGIN(instruction_access_slb)
IVEC=0x480
- IAREA=PACA_EXSLB
- IRECONCILE=0
IISIDE=1
IDAR=1
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
EXC_COMMON_BEGIN(instruction_access_slb_common)
GEN_COMMON instruction_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
EXC_COMMON_BEGIN(hardware_interrupt_common)
GEN_COMMON hardware_interrupt
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
INT_DEFINE_END(program_check)
EXC_REAL_BEGIN(program_check, 0x700, 0x100)
+
+ #ifdef CONFIG_CPU_LITTLE_ENDIAN
+ /*
+ * There's a short window during boot where although the kernel is
+ * running little endian, any exceptions will cause the CPU to switch
+ * back to big endian. For example a WARN() boils down to a trap
+ * instruction, which will cause a program check, and we end up here but
+ * with the CPU in big endian mode. The first instruction of the program
+ * check handler (in GEN_INT_ENTRY below) is an mtsprg, which when
+ * executed in the wrong endian is an lhzu with a ~3GB displacement from
+ * r3. The content of r3 is random, so that is a load from some random
+ * location, and depending on the system can easily lead to a checkstop,
+ * or an infinitely recursive page fault.
+ *
+ * So to handle that case we have a trampoline here that can detect we
+ * are in the wrong endian and flip us back to the correct endian. We
+ * can't flip MSR[LE] using mtmsr, so we have to use rfid. That requires
+ * backing up SRR0/1 as well as a GPR. To do that we use SPRG0/2/3, as
+ * SPRG1 is already used for the paca. SPRG3 is user readable, but this
+ * trampoline is only active very early in boot, and SPRG3 will be
+ * reinitialised in vdso_getcpu_init() before userspace starts.
+ */
+ BEGIN_FTR_SECTION
+ tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8
+ b 1f // Skip trampoline if endian is correct
+ .long 0xa643707d // mtsprg 0, r11 Backup r11
+ .long 0xa6027a7d // mfsrr0 r11
+ .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2
+ .long 0xa6027b7d // mfsrr1 r11
+ .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3
+ .long 0xa600607d // mfmsr r11
+ .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE]
+ .long 0xa6037b7d // mtsrr1 r11
+ .long 0x34076039 // li r11, 0x734
+ .long 0xa6037a7d // mtsrr0 r11
+ .long 0x2400004c // rfid
+ mfsprg r11, 3
+ mtsrr1 r11 // Restore SRR1
+ mfsprg r11, 2
+ mtsrr0 r11 // Restore SRR0
+ mfsprg r11, 0 // Restore r11
+ 1:
+ END_FTR_SECTION(0, 1) // nop out after boot
+ #endif /* CONFIG_CPU_LITTLE_ENDIAN */
+
GEN_INT_ENTRY program_check, virt=0
EXC_REAL_END(program_check, 0x700, 0x100)
EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
*/
INT_DEFINE_BEGIN(fp_unavailable)
IVEC=0x800
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
EXC_COMMON_BEGIN(fp_unavailable_common)
GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
0: trap
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
b interrupt_return
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl timer_interrupt
b interrupt_return
IVEC=0x980
IHSRR=1
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
IKVM_VIRT=1
INT_DEFINE_END(hdecrementer)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
#else
- bl unknown_exception
+ bl unknown_async_exception
#endif
b interrupt_return
HMT_MEDIUM
.if ! \virt
- __LOAD_HANDLER(r10, system_call_common)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- RFI_TO_KERNEL
- b . /* prevent speculative execution */
+ __LOAD_HANDLER(r10, system_call_common_real)
+ mtctr r10
+ bctr
.else
li r10,MSR_RI
mtmsrd r10,1 /* Set RI (EE=0) */
GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r4,_DAR(r1)
- li r5,SIGSEGV
- bl bad_page_fault
+ bl do_bad_page_fault_segv
MMU_FTR_SECTION_ELSE
bl unknown_exception
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
IHSRR=1
IREALMODE_COMMON=1
ISTACK=0
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
IKVM_REAL=1
INT_DEFINE_END(hmi_exception_early)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
#else
- bl unknown_exception
+ bl unknown_async_exception
#endif
b interrupt_return
EXC_COMMON_BEGIN(h_virt_irq_common)
GEN_COMMON h_virt_irq
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
b interrupt_return
*/
INT_DEFINE_BEGIN(altivec_unavailable)
IVEC=0xf20
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
b interrupt_return
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b interrupt_return
*/
INT_DEFINE_BEGIN(vsx_unavailable)
IVEC=0xf40
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
b interrupt_return
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
b interrupt_return
INT_DEFINE_BEGIN(soft_nmi)
IVEC=0x900
ISTACK=0
- IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
INT_DEFINE_END(soft_nmi)
/*
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY soft_nmi
- /*
- * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
- * system_reset_common)
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
-
addi r3,r1,STACK_FRAME_OVERHEAD
bl soft_nmi_interrupt
li r9,0
mtmsrd r9,1
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
kuap_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS hsrr=0
RFI_TO_KERNEL
ld r11,PACA_EXRFI+EX_R11(r13)
blr
+/*
+ * The SCV entry flush happens with interrupts enabled, so it must disable
+ * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10
+ * (containing LR) does not need to be preserved here because scv entry
+ * puts 0 in the pt_regs, CTR can be clobbered for the same reason.
+ */
+TRAMP_REAL_BEGIN(scv_entry_flush_fallback)
+ li r10,0
+ mtmsrd r10,1
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ L1D_DISPLACEMENT_FLUSH
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ li r10,MSR_RI
+ mtmsrd r10,1
+ blr
+
TRAMP_REAL_BEGIN(rfi_flush_fallback)
SET_SCRATCH0(r13);
GET_PACA(r13);
* come here.
*/
- EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline)
- b __ppc64_runlatch_on
-
USE_FIXED_SECTION(virt_trampolines)
/*
* All code below __end_interrupts is treated as soft-masked. If
RFI_TO_KERNEL
1: mtlr r0
blr
-
- /*
- * Hash table stuff
- */
- .balign IFETCH_ALIGN_BYTES
- do_hash_page:
- #ifdef CONFIG_PPC_BOOK3S_64
- lis r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h
- ori r0,r0,DSISR_BAD_FAULT_64S@l
- and. r0,r5,r0 /* weird error? */
- bne- handle_page_fault /* if not, try to insert a HPTE */
-
- /*
- * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
- * don't call hash_page, just fail the fault. This is required to
- * prevent re-entrancy problems in the hash code, namely perf
- * interrupts hitting while something holds H_PAGE_BUSY, and taking a
- * hash fault. See the comment in hash_preload().
- */
- ld r11, PACA_THREAD_INFO(r13)
- lwz r0,TI_PREEMPT(r11)
- andis. r0,r0,NMI_MASK@h
- bne 77f
-
- /*
- * r3 contains the trap number
- * r4 contains the faulting address
- * r5 contains dsisr
- * r6 msr
- *
- * at return r3 = 0 for success, 1 for page fault, negative for error
- */
- bl __hash_page /* build HPTE if possible */
- cmpdi r3,0 /* see if __hash_page succeeded */
-
- /* Success */
- beq interrupt_return /* Return from exception on success */
-
- /* Error */
- blt- 13f
-
- /* Reload DAR/DSISR into r4/r5 for the DABR check below */
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- #endif /* CONFIG_PPC_BOOK3S_64 */
-
- /* Here we have a page fault that hash_page can't handle. */
- handle_page_fault:
- 11: andis. r0,r5,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_page_fault
- cmpdi r3,0
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl __bad_page_fault
- b interrupt_return
-
- /* We have a data breakpoint exception - handle it */
- handle_dabr_fault:
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_break
- /*
- * do_break() may have changed the NV GPRS while handling a breakpoint.
- * If so, we need to restore them with their updated values.
- */
- REST_NVGPRS(r1)
- b interrupt_return
-
-
- #ifdef CONFIG_PPC_BOOK3S_64
- /* We have a page fault that hash_page could handle but HV refused
- * the PTE insertion
- */
- 13: mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl low_hash_fault
- b interrupt_return
- #endif
-
- /*
- * We come here as a result of a DSI at a point where we don't want
- * to call hash_page, such as when we are accessing memory (possibly
- * user memory) inside a PMU interrupt that occurred while interrupts
- * were soft-disabled. We want to invoke the exception handler for
- * the access, or panic if there isn't a handler.
- */
- 77: addi r3,r1,STACK_FRAME_OVERHEAD
- li r5,SIGSEGV
- bl bad_page_fault
- b interrupt_return
/* System reset */
/* core99 pmac starts the seconary here by changing the vector, and
- putting it back to what it was (unknown_exception) when done. */
- EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD)
+ putting it back to what it was (unknown_async_exception) when done. */
+ EXCEPTION(0x100, Reset, unknown_async_exception, EXC_XFER_STD)
/* Machine check */
/*
MachineCheck:
EXCEPTION_PROLOG_0
#ifdef CONFIG_PPC_CHRP
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH2,r1
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, RTAS_SP(r1)
+ cmpwi cr1, r1, 0
+ bne cr1, 7f
+ mfspr r1, SPRN_SPRG_SCRATCH2
+#else
mfspr r11, SPRN_SPRG_THREAD
lwz r11, RTAS_SP(r11)
cmpwi cr1, r11, 0
bne cr1, 7f
+#endif
#endif /* CONFIG_PPC_CHRP */
EXCEPTION_PROLOG_1 for_rtas=1
7: EXCEPTION_PROLOG_2
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_CHRP
- #ifdef CONFIG_VMAP_STACK
- mfspr r4, SPRN_SPRG_THREAD
- tovirt(r4, r4)
- lwz r4, RTAS_SP(r4)
- cmpwi cr1, r4, 0
- #endif
beq cr1, machine_check_tramp
twi 31, 0, 0
#else
DO_KVM 0x300
DataAccess:
#ifdef CONFIG_VMAP_STACK
+ #ifdef CONFIG_PPC_BOOK3S_604
BEGIN_MMU_FTR_SECTION
mtspr SPRN_SPRG_SCRATCH2,r10
mfspr r10, SPRN_SPRG_THREAD
MMU_FTR_SECTION_ELSE
b 1f
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+ #endif
1: EXCEPTION_PROLOG_0 handle_dar_dsisr=1
EXCEPTION_PROLOG_1
b handle_page_fault_tramp_1
#else /* CONFIG_VMAP_STACK */
EXCEPTION_PROLOG handle_dar_dsisr=1
get_and_save_dar_dsisr_on_stack r4, r5, r11
+ #ifdef CONFIG_PPC_BOOK3S_604
BEGIN_MMU_FTR_SECTION
andis. r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
bne handle_page_fault_tramp_2 /* if not, try to put a PTE */
bl hash_page
b handle_page_fault_tramp_1
MMU_FTR_SECTION_ELSE
+ #endif
b handle_page_fault_tramp_2
+ #ifdef CONFIG_PPC_BOOK3S_604
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+ #endif
#endif /* CONFIG_VMAP_STACK */
/* Instruction access exception. */
mfspr r11, SPRN_SRR1 /* check whether user or kernel */
stw r11, SRR1(r10)
mfcr r10
+ #ifdef CONFIG_PPC_BOOK3S_604
BEGIN_MMU_FTR_SECTION
andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */
bne hash_page_isi
.Lhash_page_isi_cont:
mfspr r11, SPRN_SRR1 /* check whether user or kernel */
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+ #endif
andi. r11, r11, MSR_PR
EXCEPTION_PROLOG_1
beq 1f /* if so, try to put a PTE */
li r3,0 /* into the hash table */
mr r4,r12 /* SRR0 is fault address */
+ #ifdef CONFIG_PPC_BOOK3S_604
BEGIN_MMU_FTR_SECTION
bl hash_page
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+ #endif
#endif /* CONFIG_VMAP_STACK */
- 1: mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
- stw r4, _DAR(r11)
+ stw r5, _DSISR(r11)
+ stw r12, _DAR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
#endif
#ifndef CONFIG_TAU_INT
- #define TAUException unknown_exception
+ #define TAUException unknown_async_exception
#endif
EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD)
#ifdef CONFIG_VMAP_STACK
EXCEPTION_PROLOG_2 handle_dar_dsisr=1
#endif
- lwz r4, _DAR(r11)
lwz r5, _DSISR(r11)
/* fall through */
handle_page_fault_tramp_2:
+ andis. r0, r5, DSISR_DABRMATCH@h
+ bne- 1f
EXC_XFER_LITE(0x300, handle_page_fault)
+ 1: EXC_XFER_STD(0x300, do_break)
#ifdef CONFIG_VMAP_STACK
+ #ifdef CONFIG_PPC_BOOK3S_604
.macro save_regs_thread thread
stw r0, THR0(\thread)
stw r3, THR3(\thread)
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r10, SPRN_SPRG_SCRATCH0
rfi
+ #endif /* CONFIG_PPC_BOOK3S_604 */
stack_overflow:
vmap_stack_overflow_exception
#include <linux/pgtable.h>
#include <linux/uaccess.h>
+ #include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/cache.h>
void replay_soft_interrupts(void)
{
+ struct pt_regs regs;
+
/*
- * We use local_paca rather than get_paca() to avoid all
- * the debug_smp_processor_id() business in this low level
- * function
+ * Be careful here, calling these interrupt handlers can cause
+ * softirqs to be raised, which they may run when calling irq_exit,
+ * which will cause local_irq_enable() to be run, which can then
+ * recurse into this function. Don't keep any state across
+ * interrupt handler calls which may change underneath us.
+ *
+ * We use local_paca rather than get_paca() to avoid all the
+ * debug_smp_processor_id() business in this low level function.
*/
- unsigned char happened = local_paca->irq_happened;
- struct pt_regs regs;
ppc_save_regs(®s);
regs.softe = IRQS_ENABLED;
* This is a higher priority interrupt than the others, so
* replay it first.
*/
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) {
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) {
local_paca->irq_happened &= ~PACA_IRQ_HMI;
regs.trap = 0xe60;
handle_hmi_exception(®s);
hard_irq_disable();
}
- if (happened & PACA_IRQ_DEC) {
+ if (local_paca->irq_happened & PACA_IRQ_DEC) {
local_paca->irq_happened &= ~PACA_IRQ_DEC;
regs.trap = 0x900;
timer_interrupt(®s);
hard_irq_disable();
}
- if (happened & PACA_IRQ_EE) {
+ if (local_paca->irq_happened & PACA_IRQ_EE) {
local_paca->irq_happened &= ~PACA_IRQ_EE;
regs.trap = 0x500;
do_IRQ(®s);
hard_irq_disable();
}
- if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) {
+ if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) {
local_paca->irq_happened &= ~PACA_IRQ_DBELL;
if (IS_ENABLED(CONFIG_PPC_BOOK3E))
regs.trap = 0x280;
}
/* Book3E does not support soft-masking PMI interrupts */
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) {
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) {
local_paca->irq_happened &= ~PACA_IRQ_PMI;
regs.trap = 0xf00;
performance_monitor_exception(®s);
hard_irq_disable();
}
- happened = local_paca->irq_happened;
- if (happened & ~PACA_IRQ_HARD_DIS) {
+ if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) {
/*
* We are responding to the next interrupt, so interrupt-off
* latencies should be reset here.
}
}
+ #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+ static inline void replay_soft_interrupts_irqrestore(void)
+ {
+ unsigned long kuap_state = get_kuap();
+
+ /*
+ * Check if anything calls local_irq_enable/restore() when KUAP is
+ * disabled (user access enabled). We handle that case here by saving
+ * and re-locking AMR but we shouldn't get here in the first place,
+ * hence the warning.
+ */
+ kuap_check_amr();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(AMR_KUAP_BLOCKED);
+
+ replay_soft_interrupts();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(kuap_state);
+ }
+ #else
+ #define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
+ #endif
+
notrace void arch_local_irq_restore(unsigned long mask)
{
unsigned char irq_happened;
irq_soft_mask_set(IRQS_ALL_DISABLED);
trace_hardirqs_off();
- replay_soft_interrupts();
+ replay_soft_interrupts_irqrestore();
local_paca->irq_happened = 0;
trace_hardirqs_on();
{
unsigned int irq;
- irq_enter();
-
trace_irq_entry(regs);
/*
generic_handle_irq(irq);
trace_irq_exit(regs);
-
- irq_exit();
}
- void do_IRQ(struct pt_regs *regs)
+ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
{
struct pt_regs *old_regs = set_irq_regs(regs);
void *cursp, *irqsp, *sirqsp;
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <linux/uaccess.h>
+ #include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
}
/* If set, the threads on each CPU core have to be in the same MMU mode */
-static bool no_mixing_hpt_and_radix;
+static bool no_mixing_hpt_and_radix __read_mostly;
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
return H_UNSUPPORTED_FLAG_START;
if (value2 & DABRX_HYP)
return H_P4;
- vcpu->arch.dawr = value1;
- vcpu->arch.dawrx = value2;
+ vcpu->arch.dawr0 = value1;
+ vcpu->arch.dawrx0 = value2;
+ return H_SUCCESS;
+ case H_SET_MODE_RESOURCE_SET_DAWR1:
+ if (!kvmppc_power8_compatible(vcpu))
+ return H_P2;
+ if (!ppc_breakpoint_available())
+ return H_P2;
+ if (!cpu_has_feature(CPU_FTR_DAWR1))
+ return H_P2;
+ if (!vcpu->kvm->arch.dawr1_enabled)
+ return H_FUNCTION;
+ if (mflags)
+ return H_UNSUPPORTED_FLAG_START;
+ if (value2 & DABRX_HYP)
+ return H_P4;
+ vcpu->arch.dawr1 = value1;
+ vcpu->arch.dawrx1 = value2;
return H_SUCCESS;
case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE:
/* KVM does not support mflags=2 (AIL=2) */
*val = get_reg_val(id, vcpu->arch.vcore->vtb);
break;
case KVM_REG_PPC_DAWR:
- *val = get_reg_val(id, vcpu->arch.dawr);
+ *val = get_reg_val(id, vcpu->arch.dawr0);
break;
case KVM_REG_PPC_DAWRX:
- *val = get_reg_val(id, vcpu->arch.dawrx);
+ *val = get_reg_val(id, vcpu->arch.dawrx0);
+ break;
+ case KVM_REG_PPC_DAWR1:
+ *val = get_reg_val(id, vcpu->arch.dawr1);
+ break;
+ case KVM_REG_PPC_DAWRX1:
+ *val = get_reg_val(id, vcpu->arch.dawrx1);
break;
case KVM_REG_PPC_CIABR:
*val = get_reg_val(id, vcpu->arch.ciabr);
vcpu->arch.vcore->vtb = set_reg_val(id, *val);
break;
case KVM_REG_PPC_DAWR:
- vcpu->arch.dawr = set_reg_val(id, *val);
+ vcpu->arch.dawr0 = set_reg_val(id, *val);
break;
case KVM_REG_PPC_DAWRX:
- vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+ vcpu->arch.dawrx0 = set_reg_val(id, *val) & ~DAWRX_HYP;
+ break;
+ case KVM_REG_PPC_DAWR1:
+ vcpu->arch.dawr1 = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_DAWRX1:
+ vcpu->arch.dawrx1 = set_reg_val(id, *val) & ~DAWRX_HYP;
break;
case KVM_REG_PPC_CIABR:
vcpu->arch.ciabr = set_reg_val(id, *val);
if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm)
return false;
- /* Some POWER9 chips require all threads to be in the same MMU mode */
- if (no_mixing_hpt_and_radix &&
- kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
- return false;
-
if (n_threads < cip->max_subcore_threads)
n_threads = cip->max_subcore_threads;
if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
for_each_runnable_thread(i, vcpu, vc) {
if (signal_pending(vcpu->arch.run_task))
vcpu->arch.ret = -EINTR;
+ else if (no_mixing_hpt_and_radix &&
+ kvm_is_radix(vc->kvm) != radix_enabled())
+ vcpu->arch.ret = -EINVAL;
else if (vcpu->arch.vpa.update_pending ||
vcpu->arch.slb_shadow.update_pending ||
vcpu->arch.dtl.update_pending)
int controlled_threads;
int trap;
bool is_power8;
- bool hpt_on_radix;
/*
* Remove from the list any threads that have a signal pending
* this is a HPT guest on a radix host machine where the
* CPU threads may not be in different MMU modes.
*/
- hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
- !kvm_is_radix(vc->kvm);
- if (((controlled_threads > 1) &&
- ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
- (hpt_on_radix && vc->kvm->arch.threads_indep)) {
+ if ((controlled_threads > 1) &&
+ ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
for_each_runnable_thread(i, vcpu, vc) {
vcpu->arch.ret = -EBUSY;
kvmppc_remove_runnable(vc, vcpu);
is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
&& !cpu_has_feature(CPU_FTR_ARCH_300);
- if (split > 1 || hpt_on_radix) {
+ if (split > 1) {
sip = &split_info;
memset(&split_info, 0, sizeof(split_info));
for (sub = 0; sub < core_info.n_subcores; ++sub)
split_info.subcore_size = subcore_size;
} else {
split_info.subcore_size = 1;
- if (hpt_on_radix) {
- /* Use the split_info for LPCR/LPIDR changes */
- split_info.lpcr_req = vc->lpcr;
- split_info.lpidr_req = vc->kvm->arch.lpid;
- split_info.host_lpcr = vc->kvm->arch.host_lpcr;
- split_info.do_set = 1;
- }
}
/* order writes to split_info before kvm_split_mode pointer */
for (thr = 0; thr < controlled_threads; ++thr) {
struct paca_struct *paca = paca_ptrs[pcpu + thr];
- paca->kvm_hstate.tid = thr;
paca->kvm_hstate.napping = 0;
paca->kvm_hstate.kvm_split_mode = sip;
}
* When doing micro-threading, poke the inactive threads as well.
* This gets them to the nap instruction after kvm_do_nap,
* which reduces the time taken to unsplit later.
- * For POWER9 HPT guest on radix host, we need all the secondary
- * threads woken up so they can do the LPCR/LPIDR change.
*/
- if (cmd_bit || hpt_on_radix) {
+ if (cmd_bit) {
split_info.do_nap = 1; /* ask secondaries to nap when done */
for (thr = 1; thr < threads_per_subcore; ++thr)
if (!(active & (1 << thr)))
cpu_relax();
++loops;
}
- } else if (hpt_on_radix) {
- /* Wait for all threads to have seen final sync */
- for (thr = 1; thr < controlled_threads; ++thr) {
- struct paca_struct *paca = paca_ptrs[pcpu + thr];
-
- while (paca->kvm_hstate.kvm_split_mode) {
- HMT_low();
- barrier();
- }
- HMT_medium();
- }
+ split_info.do_nap = 0;
}
- split_info.do_nap = 0;
kvmppc_set_host_core(pcpu);
+ guest_exit_irqoff();
+
local_irq_enable();
- guest_exit();
/* Let secondaries go back to the offline loop */
for (i = 0; i < controlled_threads; ++i) {
int trap;
unsigned long host_hfscr = mfspr(SPRN_HFSCR);
unsigned long host_ciabr = mfspr(SPRN_CIABR);
- unsigned long host_dawr = mfspr(SPRN_DAWR0);
- unsigned long host_dawrx = mfspr(SPRN_DAWRX0);
+ unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
+ unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
unsigned long host_psscr = mfspr(SPRN_PSSCR);
unsigned long host_pidr = mfspr(SPRN_PID);
+ unsigned long host_dawr1 = 0;
+ unsigned long host_dawrx1 = 0;
+
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ host_dawr1 = mfspr(SPRN_DAWR1);
+ host_dawrx1 = mfspr(SPRN_DAWRX1);
+ }
/*
* P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
mtspr(SPRN_SPURR, vcpu->arch.spurr);
if (dawr_enabled()) {
- mtspr(SPRN_DAWR0, vcpu->arch.dawr);
- mtspr(SPRN_DAWRX0, vcpu->arch.dawrx);
+ mtspr(SPRN_DAWR0, vcpu->arch.dawr0);
+ mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ mtspr(SPRN_DAWR1, vcpu->arch.dawr1);
+ mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1);
+ }
}
mtspr(SPRN_CIABR, vcpu->arch.ciabr);
mtspr(SPRN_IC, vcpu->arch.ic);
(local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
mtspr(SPRN_HFSCR, host_hfscr);
mtspr(SPRN_CIABR, host_ciabr);
- mtspr(SPRN_DAWR0, host_dawr);
- mtspr(SPRN_DAWRX0, host_dawrx);
+ mtspr(SPRN_DAWR0, host_dawr0);
+ mtspr(SPRN_DAWRX0, host_dawrx0);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ mtspr(SPRN_DAWR1, host_dawr1);
+ mtspr(SPRN_DAWRX1, host_dawrx1);
+ }
mtspr(SPRN_PID, host_pidr);
/*
unsigned long host_tidr = mfspr(SPRN_TIDR);
unsigned long host_iamr = mfspr(SPRN_IAMR);
unsigned long host_amr = mfspr(SPRN_AMR);
+ unsigned long host_fscr = mfspr(SPRN_FSCR);
s64 dec;
u64 tb;
int trap, save_pmu;
if (host_amr != vcpu->arch.amr)
mtspr(SPRN_AMR, host_amr);
+ if (host_fscr != vcpu->arch.fscr)
+ mtspr(SPRN_FSCR, host_fscr);
+
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
store_fp_state(&vcpu->arch.fp);
#ifdef CONFIG_ALTIVEC
kvmppc_clear_host_core(pcpu);
- local_paca->kvm_hstate.tid = 0;
local_paca->kvm_hstate.napping = 0;
local_paca->kvm_hstate.kvm_split_mode = NULL;
kvmppc_start_thread(vcpu, vc);
kvmppc_set_host_core(pcpu);
+ guest_exit_irqoff();
+
local_irq_enable();
- guest_exit();
cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest);
do {
/*
- * The early POWER9 chips that can't mix radix and HPT threads
- * on the same core also need the workaround for the problem
- * where the TLB would prefetch entries in the guest exit path
- * for radix guests using the guest PIDR value and LPID 0.
- * The workaround is in the old path (kvmppc_run_vcpu())
- * but not the new path (kvmhv_run_single_vcpu()).
+ * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu
+ * path, which also handles hash and dependent threads mode.
*/
if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
- !no_mixing_hpt_and_radix)
+ !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
return ret;
}
+static int kvmhv_enable_dawr1(struct kvm *kvm)
+{
+ if (!cpu_has_feature(CPU_FTR_DAWR1))
+ return -ENODEV;
+
+ /* kvm == NULL means the caller is testing if the capability exists */
+ if (kvm)
+ kvm->arch.dawr1_enabled = true;
+ return 0;
+}
+
+static bool kvmppc_hash_v3_possible(void)
+{
+ if (radix_enabled() && no_mixing_hpt_and_radix)
+ return false;
+
+ return cpu_has_feature(CPU_FTR_ARCH_300) &&
+ cpu_has_feature(CPU_FTR_HVMODE);
+}
+
static struct kvmppc_ops kvm_ops_hv = {
.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
.store_to_eaddr = kvmhv_store_to_eaddr,
.enable_svm = kvmhv_enable_svm,
.svm_off = kvmhv_svm_off,
+ .enable_dawr1 = kvmhv_enable_dawr1,
+ .hash_v3_possible = kvmppc_hash_v3_possible,
};
static int kvm_init_subcore_bitmap(void)
#include <asm/asm-prototypes.h>
#include <asm/cputable.h>
+ #include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
int ptid = local_paca->kvm_hstate.ptid;
struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
- int me, ee, i, t;
- int cpu0;
+ int me, ee, i;
/* Set our bit in the threads-exiting-guest map in the 0xff00
bits of vcore->entry_exit_map */
if ((ee >> 8) == 0)
kvmhv_interrupt_vcore(vc, ee);
}
-
- /*
- * On POWER9 when running a HPT guest on a radix host (sip != NULL),
- * we have to interrupt inactive CPU threads to get them to
- * restore the host LPCR value.
- */
- if (sip->lpcr_req) {
- if (cmpxchg(&sip->do_restore, 0, 1) == 0) {
- vc = local_paca->kvm_hstate.kvm_vcore;
- cpu0 = vc->pcpu + ptid - local_paca->kvm_hstate.tid;
- for (t = 1; t < threads_per_core; ++t) {
- if (sip->napped[t])
- kvmhv_rm_send_ipi(cpu0 + t);
- }
- }
- }
}
struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
panic("Bad KVM trap");
}
-/*
- * Functions used to switch LPCR HR and UPRT bits on all threads
- * when entering and exiting HPT guests on a radix host.
- */
-
-#define PHASE_REALMODE 1 /* in real mode */
-#define PHASE_SET_LPCR 2 /* have set LPCR */
-#define PHASE_OUT_OF_GUEST 4 /* have finished executing in guest */
-#define PHASE_RESET_LPCR 8 /* have reset LPCR to host value */
-
-#define ALL(p) (((p) << 24) | ((p) << 16) | ((p) << 8) | (p))
-
-static void wait_for_sync(struct kvm_split_mode *sip, int phase)
-{
- int thr = local_paca->kvm_hstate.tid;
-
- sip->lpcr_sync.phase[thr] |= phase;
- phase = ALL(phase);
- while ((sip->lpcr_sync.allphases & phase) != phase) {
- HMT_low();
- barrier();
- }
- HMT_medium();
-}
-
-void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
-{
- int num_sets;
- unsigned long rb, set;
-
- /* wait for every other thread to get to real mode */
- wait_for_sync(sip, PHASE_REALMODE);
-
- /* Set LPCR and LPIDR */
- mtspr(SPRN_LPCR, sip->lpcr_req);
- mtspr(SPRN_LPID, sip->lpidr_req);
- isync();
-
- /*
- * P10 will flush all the congruence class with a single tlbiel
- */
- if (cpu_has_feature(CPU_FTR_ARCH_31))
- num_sets = 1;
- else
- num_sets = POWER9_TLB_SETS_RADIX;
-
- /* Invalidate the TLB on thread 0 */
- if (local_paca->kvm_hstate.tid == 0) {
- sip->do_set = 0;
- asm volatile("ptesync" : : : "memory");
- for (set = 0; set < num_sets; ++set) {
- rb = TLBIEL_INVAL_SET_LPID +
- (set << TLBIEL_INVAL_SET_SHIFT);
- asm volatile(PPC_TLBIEL(%0, %1, 0, 0, 0) : :
- "r" (rb), "r" (0));
- }
- asm volatile("ptesync" : : : "memory");
- }
-
- /* indicate that we have done so and wait for others */
- wait_for_sync(sip, PHASE_SET_LPCR);
- /* order read of sip->lpcr_sync.allphases vs. sip->do_set */
- smp_rmb();
-}
-
-/*
- * Called when a thread that has been in the guest needs
- * to reload the host LPCR value - but only on POWER9 when
- * running a HPT guest on a radix host.
- */
-void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
-{
- /* we're out of the guest... */
- wait_for_sync(sip, PHASE_OUT_OF_GUEST);
-
- mtspr(SPRN_LPID, 0);
- mtspr(SPRN_LPCR, sip->host_lpcr);
- isync();
-
- if (local_paca->kvm_hstate.tid == 0) {
- sip->do_restore = 0;
- smp_wmb(); /* order store of do_restore vs. phase */
- }
-
- wait_for_sync(sip, PHASE_RESET_LPCR);
- smp_mb();
- local_paca->kvm_hstate.kvm_split_mode = NULL;
-}
-
static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
{
vcpu->arch.ceded = 0;
#include <asm/cputable.h>
#include <linux/uaccess.h>
+ #include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/cacheflush.h>
#include <asm/dbell.h>
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
r = 1;
- };
+ }
return r;
}
r = !!(hv_enabled && radix_enabled());
break;
case KVM_CAP_PPC_MMU_HASH_V3:
- r = !!(hv_enabled && cpu_has_feature(CPU_FTR_ARCH_300) &&
- cpu_has_feature(CPU_FTR_HVMODE));
+ r = !!(hv_enabled && kvmppc_hv_ops->hash_v3_possible &&
+ kvmppc_hv_ops->hash_v3_possible());
break;
case KVM_CAP_PPC_NESTED_HV:
r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
r = hv_enabled && kvmppc_hv_ops->enable_svm &&
!kvmppc_hv_ops->enable_svm(NULL);
break;
+ case KVM_CAP_PPC_DAWR1:
+ r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
+ !kvmppc_hv_ops->enable_dawr1(NULL));
+ break;
#endif
default:
r = 0;
return emulated;
}
- int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val)
+ static int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val)
{
union kvmppc_one_reg reg;
int vmx_offset = 0;
return result;
}
- int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val)
+ static int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val)
{
union kvmppc_one_reg reg;
int vmx_offset = 0;
return result;
}
- int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val)
+ static int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val)
{
union kvmppc_one_reg reg;
int vmx_offset = 0;
return result;
}
- int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val)
+ static int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val)
{
union kvmppc_one_reg reg;
int vmx_offset = 0;
break;
r = kvm->arch.kvm_ops->enable_svm(kvm);
break;
+ case KVM_CAP_PPC_DAWR1:
+ r = -EINVAL;
+ if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_dawr1)
+ break;
+ r = kvm->arch.kvm_ops->enable_dawr1(kvm);
+ break;
#endif
default:
r = -EINVAL;
break;
if (rev) {
/* reverse 32 bytes */
- buf.d[0] = byterev_8(reg->d[3]);
- buf.d[1] = byterev_8(reg->d[2]);
- buf.d[2] = byterev_8(reg->d[1]);
- buf.d[3] = byterev_8(reg->d[0]);
- reg = &buf;
+ union vsx_reg buf32[2];
+ buf32[0].d[0] = byterev_8(reg[1].d[1]);
+ buf32[0].d[1] = byterev_8(reg[1].d[0]);
+ buf32[1].d[0] = byterev_8(reg[0].d[1]);
+ buf32[1].d[1] = byterev_8(reg[0].d[0]);
+ memcpy(mem, buf32, size);
+ } else {
+ memcpy(mem, reg, size);
}
- memcpy(mem, reg, size);
break;
case 16:
/* stxv, stxvx, stxvl, stxvll */
if ((word & 0xfe2) == 2)
op->type = SYSCALL;
else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) &&
- (word & 0xfe3) == 1)
+ (word & 0xfe3) == 1) { /* scv */
op->type = SYSCALL_VECTORED_0;
- else
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
+ } else
op->type = UNKNOWN;
return 0;
#endif
#ifdef __powerpc64__
case 1:
if (!cpu_has_feature(CPU_FTR_ARCH_31))
- return -1;
+ goto unknown_opcode;
prefix_r = GET_PREFIX_R(word);
ra = GET_PREFIX_RA(suffix);
#ifdef __powerpc64__
case 4:
+ /*
+ * There are very many instructions with this primary opcode
+ * introduced in the ISA as early as v2.03. However, the ones
+ * we currently emulate were all introduced with ISA 3.0
+ */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
switch (word & 0x3f) {
case 48: /* maddhd */
* There are other instructions from ISA 3.0 with the same
* primary opcode which do not have emulation support yet.
*/
- return -1;
+ goto unknown_opcode;
#endif
case 7: /* mulli */
case 19:
if (((word >> 1) & 0x1f) == 2) {
/* addpcis */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
imm = (short) (word & 0xffc1); /* d0 + d2 fields */
imm |= (word >> 15) & 0x3e; /* d1 field */
op->val = regs->nip + (imm << 16) + 4;
#ifdef __powerpc64__
case 265: /* modud */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
op->val = regs->gpr[ra] % regs->gpr[rb];
goto compute_done;
#endif
case 267: /* moduw */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
op->val = (unsigned int) regs->gpr[ra] %
(unsigned int) regs->gpr[rb];
goto compute_done;
#endif
case 755: /* darn */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
switch (ra & 0x3) {
case 0:
/* 32-bit conditioned */
goto compute_done;
}
- return -1;
+ goto unknown_opcode;
#ifdef __powerpc64__
case 777: /* modsd */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
op->val = (long int) regs->gpr[ra] %
(long int) regs->gpr[rb];
goto compute_done;
#endif
case 779: /* modsw */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
op->val = (int) regs->gpr[ra] %
(int) regs->gpr[rb];
goto compute_done;
#endif
case 538: /* cnttzw */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
val = (unsigned int) regs->gpr[rd];
op->val = (val ? __builtin_ctz(val) : 32);
goto logical_done;
#ifdef __powerpc64__
case 570: /* cnttzd */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
val = regs->gpr[rd];
op->val = (val ? __builtin_ctzl(val) : 64);
goto logical_done;
case 890: /* extswsli with sh_5 = 0 */
case 891: /* extswsli with sh_5 = 1 */
if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -1;
+ goto unknown_opcode;
op->type = COMPUTE + SETREG;
sh = rb | ((word & 2) << 4);
val = (signed int) regs->gpr[rd];
break;
case 268: /* lxvx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 16);
op->element_size = 16;
case 269: /* lxvl */
case 301: { /* lxvll */
int nb;
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->ea = ra ? regs->gpr[ra] : 0;
nb = regs->gpr[rb] & 0xff;
case 333: /* lxvpx */
if (!cpu_has_feature(CPU_FTR_ARCH_31))
- return -1;
+ goto unknown_opcode;
op->reg = VSX_REGISTER_XTP(rd);
op->type = MKOP(LOAD_VSX, 0, 32);
op->element_size = 32;
break;
case 364: /* lxvwsx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 4);
op->element_size = 4;
break;
case 396: /* stxvx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(STORE_VSX, 0, 16);
op->element_size = 16;
case 397: /* stxvl */
case 429: { /* stxvll */
int nb;
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->ea = ra ? regs->gpr[ra] : 0;
nb = regs->gpr[rb] & 0xff;
}
case 461: /* stxvpx */
if (!cpu_has_feature(CPU_FTR_ARCH_31))
- return -1;
+ goto unknown_opcode;
op->reg = VSX_REGISTER_XTP(rd);
op->type = MKOP(STORE_VSX, 0, 32);
op->element_size = 32;
break;
case 781: /* lxsibzx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 1);
op->element_size = 8;
break;
case 812: /* lxvh8x */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 16);
op->element_size = 2;
break;
case 813: /* lxsihzx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 2);
op->element_size = 8;
break;
case 876: /* lxvb16x */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 16);
op->element_size = 1;
break;
case 909: /* stxsibx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(STORE_VSX, 0, 1);
op->element_size = 8;
break;
case 940: /* stxvh8x */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(STORE_VSX, 0, 16);
op->element_size = 2;
break;
case 941: /* stxsihx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(STORE_VSX, 0, 2);
op->element_size = 8;
break;
case 1004: /* stxvb16x */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(STORE_VSX, 0, 16);
op->element_size = 1;
op->type = MKOP(LOAD_FP, 0, 16);
break;
case 2: /* lxsd */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd + 32;
op->type = MKOP(LOAD_VSX, 0, 8);
op->element_size = 8;
op->vsx_flags = VSX_CHECK_VEC;
break;
case 3: /* lxssp */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->reg = rd + 32;
op->type = MKOP(LOAD_VSX, 0, 4);
op->element_size = 8;
#ifdef CONFIG_VSX
case 6:
if (!cpu_has_feature(CPU_FTR_ARCH_31))
- return -1;
+ goto unknown_opcode;
op->ea = dqform_ea(word, regs);
op->reg = VSX_REGISTER_XTP(rd);
op->element_size = 32;
break;
case 1: /* lxv */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->ea = dqform_ea(word, regs);
if (word & 8)
op->reg = rd + 32;
case 2: /* stxsd with LSB of DS field = 0 */
case 6: /* stxsd with LSB of DS field = 1 */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->ea = dsform_ea(word, regs);
op->reg = rd + 32;
op->type = MKOP(STORE_VSX, 0, 8);
case 3: /* stxssp with LSB of DS field = 0 */
case 7: /* stxssp with LSB of DS field = 1 */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->ea = dsform_ea(word, regs);
op->reg = rd + 32;
op->type = MKOP(STORE_VSX, 0, 4);
break;
case 5: /* stxv */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ goto unknown_opcode;
op->ea = dqform_ea(word, regs);
if (word & 8)
op->reg = rd + 32;
break;
case 1: /* Prefixed instructions */
if (!cpu_has_feature(CPU_FTR_ARCH_31))
- return -1;
+ goto unknown_opcode;
prefix_r = GET_PREFIX_R(word);
ra = GET_PREFIX_RA(suffix);
}
+ if (OP_IS_LOAD_STORE(op->type) && (op->type & UPDATE)) {
+ switch (GETTYPE(op->type)) {
+ case LOAD:
+ if (ra == rd)
+ goto unknown_opcode;
+ fallthrough;
+ case STORE:
+ case LOAD_FP:
+ case STORE_FP:
+ if (ra == 0)
+ goto unknown_opcode;
+ }
+ }
+
#ifdef CONFIG_VSX
if ((GETTYPE(op->type) == LOAD_VSX ||
GETTYPE(op->type) == STORE_VSX) &&
return 0;
+ unknown_opcode:
+ op->type = UNKNOWN;
+ return 0;
+
logical_done:
if (word & 1)
set_cr0(regs, op);
struct perf_branch_stack bhrb_stack;
struct perf_branch_entry bhrb_entries[BHRB_MAX_ENTRIES];
u64 ic_init;
+
+ /* Store the PMC values */
+ unsigned long pmcs[MAX_HWEVENTS];
};
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
{
regs->result = 0;
}
- static inline int perf_intr_is_nmi(struct pt_regs *regs)
- {
- return 0;
- }
static inline int siar_valid(struct pt_regs *regs)
{
return false;
}
+ /*
+ * Return PMC value corresponding to the
+ * index passed.
+ */
+ unsigned long get_pmcs_ext_regs(int idx)
+ {
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+
+ return cpuhw->pmcs[idx];
+ }
+
static bool regs_use_siar(struct pt_regs *regs)
{
/*
}
/*
- * If interrupts were soft-disabled when a PMU interrupt occurs, treat
- * it as an NMI.
- */
- static inline int perf_intr_is_nmi(struct pt_regs *regs)
- {
- return (regs->softe & IRQS_DISABLED);
- }
-
- /*
* On processors like P7+ that have the SIAR-Valid bit, marked instructions
* must be sampled only if the SIAR-valid bit is set.
*
*/
static int power_check_constraints(struct cpu_hw_events *cpuhw,
u64 event_id[], unsigned int cflags[],
- int n_ev)
+ int n_ev, struct perf_event **event)
{
unsigned long mask, value, nv;
unsigned long smasks[MAX_HWEVENTS], svalues[MAX_HWEVENTS];
event_id[i] = cpuhw->alternatives[i][0];
}
if (ppmu->get_constraint(event_id[i], &cpuhw->amasks[i][0],
- &cpuhw->avalues[i][0]))
+ &cpuhw->avalues[i][0], event[i]->attr.config1))
return -1;
}
value = mask = 0;
for (j = 1; j < n_alt[i]; ++j)
ppmu->get_constraint(cpuhw->alternatives[i][j],
&cpuhw->amasks[i][j],
- &cpuhw->avalues[i][j]);
+ &cpuhw->avalues[i][j],
+ event[i]->attr.config1);
}
/* enumerate all possibilities and see if any will work */
memset(&cpuhw->mmcr, 0, sizeof(cpuhw->mmcr));
if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_events, hwc_index,
- &cpuhw->mmcr, cpuhw->event)) {
+ &cpuhw->mmcr, cpuhw->event, ppmu->flags)) {
/* shouldn't ever get here */
printk(KERN_ERR "oops compute_mmcr failed\n");
goto out;
if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
goto out;
- if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1))
+ if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1, cpuhw->event))
goto out;
event->hw.config = cpuhw->events[n0];
n = cpuhw->n_events;
if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
return -EAGAIN;
- i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n);
+ i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n, cpuhw->event);
if (i < 0)
return -EAGAIN;
local_irq_save(irq_flags);
cpuhw = this_cpu_ptr(&cpu_hw_events);
- err = power_check_constraints(cpuhw, events, cflags, n + 1);
+ err = power_check_constraints(cpuhw, events, cflags, n + 1, ctrs);
if (has_branch_stack(event)) {
u64 bhrb_filter = -1;
left += period;
if (left <= 0)
left = period;
- record = siar_valid(regs);
+
+ /*
+ * If address is not requested in the sample via
+ * PERF_SAMPLE_IP, just record that sample irrespective
+ * of SIAR valid check.
+ */
+ if (event->attr.sample_type & PERF_SAMPLE_IP)
+ record = siar_valid(regs);
+ else
+ record = 1;
+
event->hw.last_period = event->hw.sample_period;
}
if (left < 0x80000000LL)
* MMCR2. Check attr.exclude_kernel and address to drop the sample in
* these cases.
*/
- if (event->attr.exclude_kernel && record)
- if (is_kernel_addr(mfspr(SPRN_SIAR)))
- record = 0;
+ if (event->attr.exclude_kernel &&
+ (event->attr.sample_type & PERF_SAMPLE_IP) &&
+ is_kernel_addr(mfspr(SPRN_SIAR)))
+ record = 0;
/*
* Finally record data if requested.
if (event->attr.sample_type & PERF_SAMPLE_WEIGHT &&
ppmu->get_mem_weight)
- ppmu->get_mem_weight(&data.weight);
+ ppmu->get_mem_weight(&data.weight.full);
if (perf_event_overflow(event, &data, regs))
power_pmu_stop(event, 0);
int i, j;
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
struct perf_event *event;
- unsigned long val[8];
int found, active;
- int nmi;
if (cpuhw->n_limited)
freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
perf_read_regs(regs);
- /*
- * If perf interrupts hit in a local_irq_disable (soft-masked) region,
- * we consider them as NMIs. This is required to prevent hash faults on
- * user addresses when reading callchains. See the NMI test in
- * do_hash_page.
- */
- nmi = perf_intr_is_nmi(regs);
- if (nmi)
- nmi_enter();
- else
- irq_enter();
-
/* Read all the PMCs since we'll need them a bunch of times */
for (i = 0; i < ppmu->n_counter; ++i)
- val[i] = read_pmc(i + 1);
+ cpuhw->pmcs[i] = read_pmc(i + 1);
/* Try to find what caused the IRQ */
found = 0;
for (i = 0; i < ppmu->n_counter; ++i) {
- if (!pmc_overflow(val[i]))
+ if (!pmc_overflow(cpuhw->pmcs[i]))
continue;
if (is_limited_pmc(i + 1))
continue; /* these won't generate IRQs */
event = cpuhw->event[j];
if (event->hw.idx == (i + 1)) {
active = 1;
- record_and_restart(event, val[i], regs);
+ record_and_restart(event, cpuhw->pmcs[i], regs);
break;
}
}
event = cpuhw->event[i];
if (!event->hw.idx || is_limited_pmc(event->hw.idx))
continue;
- if (pmc_overflow_power7(val[event->hw.idx - 1])) {
+ if (pmc_overflow_power7(cpuhw->pmcs[event->hw.idx - 1])) {
/* event has overflowed in a buggy way*/
found = 1;
record_and_restart(event,
- val[event->hw.idx - 1],
+ cpuhw->pmcs[event->hw.idx - 1],
regs);
}
}
}
- if (!found && !nmi && printk_ratelimit())
- printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
+ if (unlikely(!found) && !arch_irq_disabled_regs(regs))
+ printk_ratelimited(KERN_WARNING "Can't find PMC that caused IRQ\n");
/*
* Reset MMCR0 to its normal value. This will set PMXE and
*/
write_mmcr0(cpuhw, cpuhw->mmcr.mmcr0);
- if (nmi)
- nmi_exit();
- else
- irq_exit();
+ /* Clear the cpuhw->pmcs */
+ memset(&cpuhw->pmcs, 0, sizeof(cpuhw->pmcs));
+
}
static void perf_event_interrupt(struct pt_regs *regs)
ms->cs_change = ms->transfer->cs_change;
/* Write out the first byte */
- ms->wcol_tx_timestamp = get_tbl();
+ ms->wcol_tx_timestamp = mftb();
if (ms->tx_buf)
out_8(ms->regs + SPI_DATA, *ms->tx_buf++);
else
* but it can also be worked around simply by retrying the
* transfer which is what we do here. */
ms->wcol_count++;
- ms->wcol_ticks += get_tbl() - ms->wcol_tx_timestamp;
- ms->wcol_tx_timestamp = get_tbl();
+ ms->wcol_ticks += mftb() - ms->wcol_tx_timestamp;
+ ms->wcol_tx_timestamp = mftb();
data = 0;
if (ms->tx_buf)
data = *(ms->tx_buf - 1);
/* Is the transfer complete? */
ms->len--;
if (ms->len == 0) {
- ms->timestamp = get_tbl();
+ ms->timestamp = mftb();
- ms->timestamp += ms->transfer->delay_usecs * tb_ticks_per_usec;
+ if (ms->transfer->delay.unit == SPI_DELAY_UNIT_USECS)
+ ms->timestamp += ms->transfer->delay.value *
+ tb_ticks_per_usec;
ms->state = mpc52xx_spi_fsmstate_wait;
return FSM_CONTINUE;
}
/* Write out the next byte */
- ms->wcol_tx_timestamp = get_tbl();
+ ms->wcol_tx_timestamp = mftb();
if (ms->tx_buf)
out_8(ms->regs + SPI_DATA, *ms->tx_buf++);
else
dev_err(&ms->master->dev, "spurious irq, status=0x%.2x\n",
status);
- if (((int)get_tbl()) - ms->timestamp < 0)
+ if (((int)mftb()) - ms->timestamp < 0)
return FSM_POLL;
ms->message->actual_length += ms->transfer->len;