From 947af2943576400628bba085eaa6b85143526133 Mon Sep 17 00:00:00 2001 From: Stefan Weil Date: Thu, 7 Jan 2010 00:03:52 +0100 Subject: Fix spelling of 'platform' in comments and doc Replace platfrom -> platform. This is a frequent spelling bug. Signed-off-by: Stefan Weil Signed-off-by: Jiri Kosina --- arch/powerpc/kernel/legacy_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 9ddfaef1a184..035ada5443ee 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -469,7 +469,7 @@ static int __init serial_dev_init(void) return -ENODEV; /* - * Before we register the platfrom serial devices, we need + * Before we register the platform serial devices, we need * to fixup their interrupts and their IO ports. */ DBG("Fixing serial ports interrupts and IO ports ...\n"); -- cgit v1.2.3 From 7e57cba06074da84d7c24d8c3f44040d2d8c88ac Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 8 Jan 2010 02:58:03 +0100 Subject: KVM: PPC: Use PACA backed shadow vcpu We're being horribly racy right now. All the entry and exit code hijacks random fields from the PACA that could easily be used by different code in case we get interrupted, for example by a #MC or even page fault. After discussing this with Ben, we figured it's best to reserve some more space in the PACA and just shove off some vcpu state to there. That way we can drastically improve the readability of the code, make it less racy and less complex. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_book3s.h | 2 + arch/powerpc/include/asm/kvm_book3s_64_asm.h | 19 +++ arch/powerpc/include/asm/kvm_host.h | 5 +- arch/powerpc/include/asm/kvm_ppc.h | 20 ++- arch/powerpc/include/asm/paca.h | 5 + arch/powerpc/kernel/asm-offsets.c | 33 +++- arch/powerpc/kvm/book3s.c | 4 + arch/powerpc/kvm/book3s_64_interrupts.S | 216 +++++++++------------------ arch/powerpc/kvm/book3s_64_rmhandlers.S | 32 +--- arch/powerpc/kvm/book3s_64_slb.S | 150 +++++++++++-------- 10 files changed, 249 insertions(+), 237 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 74b7369770d0..f192017d799d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -23,6 +23,7 @@ #include #include #include +#include struct kvmppc_slb { u64 esid; @@ -69,6 +70,7 @@ struct kvmppc_sid_map { struct kvmppc_vcpu_book3s { struct kvm_vcpu vcpu; + struct kvmppc_book3s_shadow_vcpu shadow_vcpu; struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct kvmppc_slb slb[64]; struct { diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h index 2e06ee8184ef..fca9404c1a7d 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h @@ -20,6 +20,8 @@ #ifndef __ASM_KVM_BOOK3S_ASM_H__ #define __ASM_KVM_BOOK3S_ASM_H__ +#ifdef __ASSEMBLY__ + #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #include @@ -55,4 +57,21 @@ kvmppc_resume_\intno: #endif /* CONFIG_KVM_BOOK3S_64_HANDLER */ +#else /*__ASSEMBLY__ */ + +struct kvmppc_book3s_shadow_vcpu { + ulong gpr[14]; + u32 cr; + u32 xer; + ulong host_r1; + ulong host_r2; + ulong handler; + ulong scratch0; + ulong scratch1; + ulong vmhandler; + ulong rmhandler; +}; + +#endif /*__ASSEMBLY__ */ + #endif /* __ASM_KVM_BOOK3S_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1201f62d0d73..d615fa8a1412 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -175,10 +175,13 @@ struct kvm_vcpu_arch { ulong gpr[32]; ulong pc; - u32 cr; ulong ctr; ulong lr; + +#ifdef CONFIG_BOOKE ulong xer; + u32 cr; +#endif ulong msr; #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d60b2f0cdcf2..89c5d79c3479 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -98,34 +98,42 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); #ifdef CONFIG_PPC_BOOK3S +/* We assume we're always acting on the current vcpu */ + static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { - vcpu->arch.gpr[num] = val; + if ( num < 14 ) + get_paca()->shadow_vcpu.gpr[num] = val; + else + vcpu->arch.gpr[num] = val; } static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) { - return vcpu->arch.gpr[num]; + if ( num < 14 ) + return get_paca()->shadow_vcpu.gpr[num]; + else + return vcpu->arch.gpr[num]; } static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) { - vcpu->arch.cr = val; + get_paca()->shadow_vcpu.cr = val; } static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) { - return vcpu->arch.cr; + return get_paca()->shadow_vcpu.cr; } static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) { - vcpu->arch.xer = val; + get_paca()->shadow_vcpu.xer = val; } static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) { - return vcpu->arch.xer; + return get_paca()->shadow_vcpu.xer; } #else diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 5e9b4ef71415..d8a693109c82 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -19,6 +19,9 @@ #include #include #include +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include +#endif register struct paca_struct *local_paca asm("r13"); @@ -135,6 +138,8 @@ struct paca_struct { u64 esid; u64 vsid; } kvm_slb[64]; /* guest SLB */ + /* We use this to store guest state in */ + struct kvmppc_book3s_shadow_vcpu shadow_vcpu; u8 kvm_slb_max; /* highest used guest slb entry */ u8 kvm_in_guest; /* are we inside the guest? */ #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a6c2b63227b3..1501e77c980c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -194,6 +194,32 @@ int main(void) DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest)); DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb)); DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max)); + DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr)); + DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer)); + DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0])); + DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1])); + DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2])); + DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3])); + DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4])); + DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5])); + DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6])); + DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7])); + DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8])); + DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9])); + DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10])); + DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11])); + DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12])); + DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13])); + DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1)); + DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2)); + DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct, + shadow_vcpu.vmhandler)); + DEFINE(PACA_KVM_RMHANDLER, offsetof(struct paca_struct, + shadow_vcpu.rmhandler)); + DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct, + shadow_vcpu.scratch0)); + DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct, + shadow_vcpu.scratch1)); #endif #endif /* CONFIG_PPC64 */ @@ -389,8 +415,6 @@ int main(void) DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); - DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); - DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr)); @@ -415,7 +439,10 @@ int main(void) DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); -#endif +#else + DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); + DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); +#endif /* CONFIG_PPC64 */ #endif #ifdef CONFIG_44x DEFINE(PGD_T_LOG2, PGD_T_LOG2); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 09ba8dbaabab..3e06eae3f2c8 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -66,12 +66,16 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb)); + memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max; } void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb)); + memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max; } diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S index d95d0d967d56..66e3b1179b32 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_64_interrupts.S @@ -28,11 +28,6 @@ #define ULONG_SIZE 8 #define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) -.macro mfpaca tmp_reg, src_reg, offset, vcpu_reg - ld \tmp_reg, (PACA_EXMC+\offset)(r13) - std \tmp_reg, VCPU_GPR(\src_reg)(\vcpu_reg) -.endm - .macro DISABLE_INTERRUPTS mfmsr r0 rldicl r0,r0,48,1 @@ -92,37 +87,30 @@ kvm_start_entry: /* Load non-volatile guest state from the vcpu */ VCPU_LOAD_NVGPRS(r4) -kvm_start_lightweight: - - ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ - ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ - - DISABLE_INTERRUPTS - /* Save R1/R2 in the PACA */ - std r1, PACAR1(r13) - std r2, (PACA_EXMC+EX_SRR0)(r13) + std r1, PACA_KVM_HOST_R1(r13) + std r2, PACA_KVM_HOST_R2(r13) + + /* XXX swap in/out on load? */ ld r3, VCPU_HIGHMEM_HANDLER(r4) - std r3, PACASAVEDMSR(r13) + std r3, PACA_KVM_VMHANDLER(r13) ld r3, VCPU_TRAMPOLINE_ENTER(r4) - mtsrr0 r3 + std r3, PACA_KVM_RMHANDLER(r13) - LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r3 +kvm_start_lightweight: - /* Load guest state in the respective registers */ - lwz r3, VCPU_CR(r4) /* r3 = vcpu->arch.cr */ - stw r3, (PACA_EXMC + EX_CCR)(r13) + ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ + ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ + /* Load some guest state in the respective registers */ ld r3, VCPU_CTR(r4) /* r3 = vcpu->arch.ctr */ mtctr r3 /* CTR = r3 */ ld r3, VCPU_LR(r4) /* r3 = vcpu->arch.lr */ mtlr r3 /* LR = r3 */ - ld r3, VCPU_XER(r4) /* r3 = vcpu->arch.xer */ - std r3, (PACA_EXMC + EX_R3)(r13) + DISABLE_INTERRUPTS /* Some guests may need to have dcbz set to 32 byte length. * @@ -142,34 +130,21 @@ kvm_start_lightweight: mtspr SPRN_HID5,r3 no_dcbz32_on: - /* Load guest GPRs */ - - ld r3, VCPU_GPR(r9)(r4) - std r3, (PACA_EXMC + EX_R9)(r13) - ld r3, VCPU_GPR(r10)(r4) - std r3, (PACA_EXMC + EX_R10)(r13) - ld r3, VCPU_GPR(r11)(r4) - std r3, (PACA_EXMC + EX_R11)(r13) - ld r3, VCPU_GPR(r12)(r4) - std r3, (PACA_EXMC + EX_R12)(r13) - ld r3, VCPU_GPR(r13)(r4) - std r3, (PACA_EXMC + EX_R13)(r13) - - ld r0, VCPU_GPR(r0)(r4) - ld r1, VCPU_GPR(r1)(r4) - ld r2, VCPU_GPR(r2)(r4) - ld r3, VCPU_GPR(r3)(r4) - ld r5, VCPU_GPR(r5)(r4) - ld r6, VCPU_GPR(r6)(r4) - ld r7, VCPU_GPR(r7)(r4) - ld r8, VCPU_GPR(r8)(r4) - ld r4, VCPU_GPR(r4)(r4) /* This sets the Magic value for the trampoline */ + /* XXX this needs to move into a safe function, so we can + be sure we don't get any interrupts */ + li r11, 1 stb r11, PACA_KVM_IN_GUEST(r13) + ld r3, PACA_KVM_RMHANDLER(r13) + mtsrr0 r3 + + LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) + mtsrr1 r3 + /* Jump to SLB patching handlder and into our guest */ RFI @@ -185,60 +160,31 @@ kvmppc_handler_highmem: /* * Register usage at this point: * - * R00 = guest R13 - * R01 = host R1 - * R02 = host R2 - * R10 = guest PC - * R11 = guest MSR - * R12 = exit handler id - * R13 = PACA - * PACA.exmc.R9 = guest R1 - * PACA.exmc.R10 = guest R10 - * PACA.exmc.R11 = guest R11 - * PACA.exmc.R12 = guest R12 - * PACA.exmc.R13 = guest R2 - * PACA.exmc.DAR = guest DAR - * PACA.exmc.DSISR = guest DSISR - * PACA.exmc.LR = guest instruction - * PACA.exmc.CCR = guest CR - * PACA.exmc.SRR0 = guest R0 + * R0 = guest last inst + * R1 = host R1 + * R2 = host R2 + * R3 = guest PC + * R4 = guest MSR + * R5 = guest DAR + * R6 = guest DSISR + * R13 = PACA + * PACA.KVM.* = guest * * */ - std r3, (PACA_EXMC+EX_R3)(r13) + /* R7 = vcpu */ + ld r7, GPR4(r1) - /* save the exit id in R3 */ - mr r3, r12 + /* Now save the guest state */ - /* R12 = vcpu */ - ld r12, GPR4(r1) + stw r0, VCPU_LAST_INST(r7) - /* Now save the guest state */ + std r3, VCPU_PC(r7) + std r4, VCPU_SHADOW_MSR(r7) + std r5, VCPU_FAULT_DEAR(r7) + std r6, VCPU_FAULT_DSISR(r7) - std r0, VCPU_GPR(r13)(r12) - std r4, VCPU_GPR(r4)(r12) - std r5, VCPU_GPR(r5)(r12) - std r6, VCPU_GPR(r6)(r12) - std r7, VCPU_GPR(r7)(r12) - std r8, VCPU_GPR(r8)(r12) - std r9, VCPU_GPR(r9)(r12) - - /* get registers from PACA */ - mfpaca r5, r0, EX_SRR0, r12 - mfpaca r5, r3, EX_R3, r12 - mfpaca r5, r1, EX_R9, r12 - mfpaca r5, r10, EX_R10, r12 - mfpaca r5, r11, EX_R11, r12 - mfpaca r5, r12, EX_R12, r12 - mfpaca r5, r2, EX_R13, r12 - - lwz r5, (PACA_EXMC+EX_LR)(r13) - stw r5, VCPU_LAST_INST(r12) - - lwz r5, (PACA_EXMC+EX_CCR)(r13) - stw r5, VCPU_CR(r12) - - ld r5, VCPU_HFLAGS(r12) + ld r5, VCPU_HFLAGS(r7) rldicl. r5, r5, 0, 63 /* CR = ((r5 & 1) == 0) */ beq no_dcbz32_off @@ -248,58 +194,42 @@ kvmppc_handler_highmem: no_dcbz32_off: - std r14, VCPU_GPR(r14)(r12) - std r15, VCPU_GPR(r15)(r12) - std r16, VCPU_GPR(r16)(r12) - std r17, VCPU_GPR(r17)(r12) - std r18, VCPU_GPR(r18)(r12) - std r19, VCPU_GPR(r19)(r12) - std r20, VCPU_GPR(r20)(r12) - std r21, VCPU_GPR(r21)(r12) - std r22, VCPU_GPR(r22)(r12) - std r23, VCPU_GPR(r23)(r12) - std r24, VCPU_GPR(r24)(r12) - std r25, VCPU_GPR(r25)(r12) - std r26, VCPU_GPR(r26)(r12) - std r27, VCPU_GPR(r27)(r12) - std r28, VCPU_GPR(r28)(r12) - std r29, VCPU_GPR(r29)(r12) - std r30, VCPU_GPR(r30)(r12) - std r31, VCPU_GPR(r31)(r12) - - /* Save guest PC (R10) */ - std r10, VCPU_PC(r12) - - /* Save guest msr (R11) */ - std r11, VCPU_SHADOW_MSR(r12) - - /* Save guest CTR (in R12) */ + std r14, VCPU_GPR(r14)(r7) + std r15, VCPU_GPR(r15)(r7) + std r16, VCPU_GPR(r16)(r7) + std r17, VCPU_GPR(r17)(r7) + std r18, VCPU_GPR(r18)(r7) + std r19, VCPU_GPR(r19)(r7) + std r20, VCPU_GPR(r20)(r7) + std r21, VCPU_GPR(r21)(r7) + std r22, VCPU_GPR(r22)(r7) + std r23, VCPU_GPR(r23)(r7) + std r24, VCPU_GPR(r24)(r7) + std r25, VCPU_GPR(r25)(r7) + std r26, VCPU_GPR(r26)(r7) + std r27, VCPU_GPR(r27)(r7) + std r28, VCPU_GPR(r28)(r7) + std r29, VCPU_GPR(r29)(r7) + std r30, VCPU_GPR(r30)(r7) + std r31, VCPU_GPR(r31)(r7) + + /* Save guest CTR */ mfctr r5 - std r5, VCPU_CTR(r12) + std r5, VCPU_CTR(r7) /* Save guest LR */ mflr r5 - std r5, VCPU_LR(r12) - - /* Save guest XER */ - mfxer r5 - std r5, VCPU_XER(r12) + std r5, VCPU_LR(r7) - /* Save guest DAR */ - ld r5, (PACA_EXMC+EX_DAR)(r13) - std r5, VCPU_FAULT_DEAR(r12) - - /* Save guest DSISR */ - lwz r5, (PACA_EXMC+EX_DSISR)(r13) - std r5, VCPU_FAULT_DSISR(r12) + /* XXX convert to safe function call */ /* Restore host msr -> SRR1 */ - ld r7, VCPU_HOST_MSR(r12) - mtsrr1 r7 + ld r6, VCPU_HOST_MSR(r7) + mtsrr1 r6 /* Restore host IP -> SRR0 */ - ld r6, VCPU_HOST_RETIP(r12) - mtsrr0 r6 + ld r5, VCPU_HOST_RETIP(r7) + mtsrr0 r5 /* * For some interrupts, we need to call the real Linux @@ -311,9 +241,9 @@ no_dcbz32_off: * r3 = address of interrupt handler (exit reason) */ - cmpwi r3, BOOK3S_INTERRUPT_EXTERNAL + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL beq call_linux_handler - cmpwi r3, BOOK3S_INTERRUPT_DECREMENTER + cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER beq call_linux_handler /* Back to Interruptable Mode! (goto kvm_return_point) */ @@ -334,12 +264,12 @@ call_linux_handler: * R7 VCPU_HOST_MSR */ - mtlr r3 + mtlr r12 - ld r5, VCPU_TRAMPOLINE_LOWMEM(r12) - mtsrr0 r5 - LOAD_REG_IMMEDIATE(r5, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r5 + ld r4, VCPU_TRAMPOLINE_LOWMEM(r7) + mtsrr0 r4 + LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) + mtsrr1 r3 RFI @@ -350,7 +280,7 @@ kvm_return_point: /* go back into the guest */ /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ - mr r5, r3 + mr r5, r12 /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S index fb7dd2e9ac88..cd9f0b609e48 100644 --- a/arch/powerpc/kvm/book3s_64_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S @@ -45,37 +45,21 @@ kvmppc_trampoline_\intno: * To distinguish, we check a magic byte in the PACA */ mfspr r13, SPRN_SPRG_PACA /* r13 = PACA */ - std r12, (PACA_EXMC + EX_R12)(r13) + std r12, PACA_KVM_SCRATCH0(r13) mfcr r12 - stw r12, (PACA_EXMC + EX_CCR)(r13) + stw r12, PACA_KVM_SCRATCH1(r13) lbz r12, PACA_KVM_IN_GUEST(r13) cmpwi r12, 0 bne ..kvmppc_handler_hasmagic_\intno /* No KVM guest? Then jump back to the Linux handler! */ - lwz r12, (PACA_EXMC + EX_CCR)(r13) + lwz r12, PACA_KVM_SCRATCH1(r13) mtcr r12 - ld r12, (PACA_EXMC + EX_R12)(r13) + ld r12, PACA_KVM_SCRATCH0(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ b kvmppc_resume_\intno /* Get back original handler */ /* Now we know we're handling a KVM guest */ ..kvmppc_handler_hasmagic_\intno: - /* Unset guest state */ - li r12, 0 - stb r12, PACA_KVM_IN_GUEST(r13) - - std r1, (PACA_EXMC+EX_R9)(r13) - std r10, (PACA_EXMC+EX_R10)(r13) - std r11, (PACA_EXMC+EX_R11)(r13) - std r2, (PACA_EXMC+EX_R13)(r13) - - mfsrr0 r10 - mfsrr1 r11 - - /* Restore R1/R2 so we can handle faults */ - ld r1, PACAR1(r13) - ld r2, (PACA_EXMC+EX_SRR0)(r13) - /* Let's store which interrupt we're handling */ li r12, \intno @@ -106,16 +90,16 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX * * Input Registers: * - * R6 = SRR0 - * R7 = SRR1 + * R5 = SRR0 + * R6 = SRR1 * LR = real-mode IP * */ .global kvmppc_handler_lowmem_trampoline kvmppc_handler_lowmem_trampoline: - mtsrr0 r6 - mtsrr1 r7 + mtsrr0 r5 + mtsrr1 r6 blr kvmppc_handler_lowmem_trampoline_end: diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 8e4478866669..7188c11ed7d1 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -51,24 +51,18 @@ kvmppc_handler_trampoline_enter: * * MSR = ~IR|DR * R13 = PACA + * R1 = host R1 + * R2 = host R2 * R9 = guest IP * R10 = guest MSR - * R11 = free - * R12 = free - * PACA[PACA_EXMC + EX_R9] = guest R9 - * PACA[PACA_EXMC + EX_R10] = guest R10 - * PACA[PACA_EXMC + EX_R11] = guest R11 - * PACA[PACA_EXMC + EX_R12] = guest R12 - * PACA[PACA_EXMC + EX_R13] = guest R13 - * PACA[PACA_EXMC + EX_CCR] = guest CR - * PACA[PACA_EXMC + EX_R3] = guest XER + * all other GPRS = free + * PACA[KVM_CR] = guest CR + * PACA[KVM_XER] = guest XER */ mtsrr0 r9 mtsrr1 r10 - mtspr SPRN_SPRG_SCRATCH0, r0 - /* Remove LPAR shadow entries */ #if SLB_NUM_BOLTED == 3 @@ -131,20 +125,27 @@ slb_do_enter: /* Enter guest */ - mfspr r0, SPRN_SPRG_SCRATCH0 - - ld r9, (PACA_EXMC+EX_R9)(r13) - ld r10, (PACA_EXMC+EX_R10)(r13) - ld r12, (PACA_EXMC+EX_R12)(r13) - - lwz r11, (PACA_EXMC+EX_CCR)(r13) + ld r0, (PACA_KVM_R0)(r13) + ld r1, (PACA_KVM_R1)(r13) + ld r2, (PACA_KVM_R2)(r13) + ld r3, (PACA_KVM_R3)(r13) + ld r4, (PACA_KVM_R4)(r13) + ld r5, (PACA_KVM_R5)(r13) + ld r6, (PACA_KVM_R6)(r13) + ld r7, (PACA_KVM_R7)(r13) + ld r8, (PACA_KVM_R8)(r13) + ld r9, (PACA_KVM_R9)(r13) + ld r10, (PACA_KVM_R10)(r13) + ld r12, (PACA_KVM_R12)(r13) + + lwz r11, (PACA_KVM_CR)(r13) mtcr r11 - ld r11, (PACA_EXMC+EX_R3)(r13) + ld r11, (PACA_KVM_XER)(r13) mtxer r11 - ld r11, (PACA_EXMC+EX_R11)(r13) - ld r13, (PACA_EXMC+EX_R13)(r13) + ld r11, (PACA_KVM_R11)(r13) + ld r13, (PACA_KVM_R13)(r13) RFI kvmppc_handler_trampoline_enter_end: @@ -162,28 +163,58 @@ kvmppc_handler_trampoline_exit: /* Register usage at this point: * - * SPRG_SCRATCH0 = guest R13 - * R01 = host R1 - * R02 = host R2 - * R10 = guest PC - * R11 = guest MSR - * R12 = exit handler id - * R13 = PACA - * PACA.exmc.CCR = guest CR - * PACA.exmc.R9 = guest R1 - * PACA.exmc.R10 = guest R10 - * PACA.exmc.R11 = guest R11 - * PACA.exmc.R12 = guest R12 - * PACA.exmc.R13 = guest R2 + * SPRG_SCRATCH0 = guest R13 + * R12 = exit handler id + * R13 = PACA + * PACA.KVM.SCRATCH0 = guest R12 + * PACA.KVM.SCRATCH1 = guest CR * */ /* Save registers */ - std r0, (PACA_EXMC+EX_SRR0)(r13) - std r9, (PACA_EXMC+EX_R3)(r13) - std r10, (PACA_EXMC+EX_LR)(r13) - std r11, (PACA_EXMC+EX_DAR)(r13) + std r0, PACA_KVM_R0(r13) + std r1, PACA_KVM_R1(r13) + std r2, PACA_KVM_R2(r13) + std r3, PACA_KVM_R3(r13) + std r4, PACA_KVM_R4(r13) + std r5, PACA_KVM_R5(r13) + std r6, PACA_KVM_R6(r13) + std r7, PACA_KVM_R7(r13) + std r8, PACA_KVM_R8(r13) + std r9, PACA_KVM_R9(r13) + std r10, PACA_KVM_R10(r13) + std r11, PACA_KVM_R11(r13) + + /* Restore R1/R2 so we can handle faults */ + ld r1, PACA_KVM_HOST_R1(r13) + ld r2, PACA_KVM_HOST_R2(r13) + + /* Save guest PC and MSR in GPRs */ + mfsrr0 r3 + mfsrr1 r4 + + /* Get scratch'ed off registers */ + mfspr r9, SPRN_SPRG_SCRATCH0 + std r9, PACA_KVM_R13(r13) + + ld r8, PACA_KVM_SCRATCH0(r13) + std r8, PACA_KVM_R12(r13) + + lwz r7, PACA_KVM_SCRATCH1(r13) + stw r7, PACA_KVM_CR(r13) + + /* Save more register state */ + + mfxer r6 + stw r6, PACA_KVM_XER(r13) + + mfdar r5 + mfdsisr r6 + + /* Unset guest state */ + li r9, 0 + stb r9, PACA_KVM_IN_GUEST(r13) /* * In order for us to easily get the last instruction, @@ -207,7 +238,8 @@ ld_last_inst: ori r11, r9, MSR_DR /* Enable paging for data */ mtmsr r11 /* 2) fetch the instruction */ - lwz r0, 0(r10) + /* XXX implement PACA_KVM_IN_GUEST=2 path to safely jump over this */ + lwz r0, 0(r3) /* 3) disable paging again */ mtmsr r9 @@ -233,29 +265,27 @@ no_ld_last_inst: slb_do_exit: - /* Restore registers */ - - ld r11, (PACA_EXMC+EX_DAR)(r13) - ld r10, (PACA_EXMC+EX_LR)(r13) - ld r9, (PACA_EXMC+EX_R3)(r13) - - /* Save last inst */ - stw r0, (PACA_EXMC+EX_LR)(r13) - - /* Save DAR and DSISR before going to paged mode */ - mfdar r0 - std r0, (PACA_EXMC+EX_DAR)(r13) - mfdsisr r0 - stw r0, (PACA_EXMC+EX_DSISR)(r13) + /* Register usage at this point: + * + * R0 = guest last inst + * R1 = host R1 + * R2 = host R2 + * R3 = guest PC + * R4 = guest MSR + * R5 = guest DAR + * R6 = guest DSISR + * R12 = exit handler id + * R13 = PACA + * PACA.KVM.* = guest * + * + */ /* RFI into the highmem handler */ - mfmsr r0 - ori r0, r0, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ - mtsrr1 r0 - ld r0, PACASAVEDMSR(r13) /* Highmem handler address */ - mtsrr0 r0 - - mfspr r0, SPRN_SPRG_SCRATCH0 + mfmsr r7 + ori r7, r7, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ + mtsrr1 r7 + ld r8, PACA_KVM_VMHANDLER(r13) /* Highmem handler address */ + mtsrr0 r8 RFI kvmppc_handler_trampoline_exit_end: -- cgit v1.2.3 From 021ec9c69f8b7b20f46296cc76cc4cb341b25191 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 8 Jan 2010 02:58:06 +0100 Subject: KVM: PPC: Call SLB patching code in interrupt safe manner Currently we're racy when doing the transition from IR=1 to IR=0, from the module memory entry code to the real mode SLB switching code. To work around that I took a look at the RTAS entry code which is faced with a similar problem and did the same thing: A small helper in linear mapped memory that does mtmsr with IR=0 and then RFIs info the actual handler. Thanks to that trick we can safely take page faults in the entry code and only need to be really wary of what to do as of the SLB switching part. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_book3s.h | 1 + arch/powerpc/include/asm/kvm_book3s_64_asm.h | 1 - arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kernel/asm-offsets.c | 3 +-- arch/powerpc/kvm/book3s.c | 1 + arch/powerpc/kvm/book3s_64_exports.c | 1 + arch/powerpc/kvm/book3s_64_interrupts.S | 25 +++++++------------------ arch/powerpc/kvm/book3s_64_rmhandlers.S | 18 ++++++++++++++++++ arch/powerpc/kvm/book3s_64_slb.S | 4 ++++ 9 files changed, 34 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index f192017d799d..c91be0ff0232 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -121,6 +121,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, extern u32 kvmppc_trampoline_lowmem; extern u32 kvmppc_trampoline_enter; +extern void kvmppc_rmcall(ulong srr0, ulong srr1); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h index fca9404c1a7d..183461b48407 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h @@ -69,7 +69,6 @@ struct kvmppc_book3s_shadow_vcpu { ulong scratch0; ulong scratch1; ulong vmhandler; - ulong rmhandler; }; #endif /*__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d615fa8a1412..f7215e622dfd 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -167,6 +167,7 @@ struct kvm_vcpu_arch { ulong trampoline_lowmem; ulong trampoline_enter; ulong highmem_handler; + ulong rmcall; ulong host_paca_phys; struct kvmppc_mmu mmu; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 1501e77c980c..ee9935442f0e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -214,8 +214,6 @@ int main(void) DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2)); DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct, shadow_vcpu.vmhandler)); - DEFINE(PACA_KVM_RMHANDLER, offsetof(struct paca_struct, - shadow_vcpu.rmhandler)); DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct, shadow_vcpu.scratch0)); DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct, @@ -438,6 +436,7 @@ int main(void) DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); + DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); #else DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 3e06eae3f2c8..13173922b678 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -919,6 +919,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; + vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; vcpu->arch.shadow_msr = MSR_USER64; diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_64_exports.c index 5b2db38ed86c..99b07125c529 100644 --- a/arch/powerpc/kvm/book3s_64_exports.c +++ b/arch/powerpc/kvm/book3s_64_exports.c @@ -22,3 +22,4 @@ EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter); EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem); +EXPORT_SYMBOL_GPL(kvmppc_rmcall); diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S index 3c0ba5513077..33aef5345f6b 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_64_interrupts.S @@ -95,17 +95,14 @@ kvm_start_entry: ld r3, VCPU_HIGHMEM_HANDLER(r4) std r3, PACA_KVM_VMHANDLER(r13) - ld r3, VCPU_TRAMPOLINE_ENTER(r4) - std r3, PACA_KVM_RMHANDLER(r13) - kvm_start_lightweight: ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ /* Load some guest state in the respective registers */ - ld r3, VCPU_CTR(r4) /* r3 = vcpu->arch.ctr */ - mtctr r3 /* CTR = r3 */ + ld r5, VCPU_CTR(r4) /* r5 = vcpu->arch.ctr */ + /* will be swapped in by rmcall */ ld r3, VCPU_LR(r4) /* r3 = vcpu->arch.lr */ mtlr r3 /* LR = r3 */ @@ -131,22 +128,14 @@ kvm_start_lightweight: no_dcbz32_on: - /* This sets the Magic value for the trampoline */ - - /* XXX this needs to move into a safe function, so we can - be sure we don't get any interrupts */ - - li r11, 1 - stb r11, PACA_KVM_IN_GUEST(r13) - - ld r3, PACA_KVM_RMHANDLER(r13) - mtsrr0 r3 + ld r6, VCPU_RMCALL(r4) + mtctr r6 - LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r3 + ld r3, VCPU_TRAMPOLINE_ENTER(r4) + LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR)) /* Jump to SLB patching handlder and into our guest */ - RFI + bctr /* * This is the handler in module memory. It gets jumped at from the diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S index 9ad1c2645d6f..e7091c9459a8 100644 --- a/arch/powerpc/kvm/book3s_64_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S @@ -140,6 +140,24 @@ kvmppc_handler_lowmem_trampoline: blr kvmppc_handler_lowmem_trampoline_end: +/* + * Call a function in real mode + * + * Input Registers: + * + * R3 = function + * R4 = MSR + * R5 = CTR + * + */ +_GLOBAL(kvmppc_rmcall) + mtmsr r4 /* Disable relocation, so mtsrr + doesn't get interrupted */ + mtctr r5 + mtsrr0 r3 + mtsrr1 r4 + RFI + .global kvmppc_trampoline_lowmem kvmppc_trampoline_lowmem: .long kvmppc_handler_lowmem_trampoline - _stext diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index d07b88617b2c..35b762722187 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -63,6 +63,10 @@ kvmppc_handler_trampoline_enter: mtsrr0 r9 mtsrr1 r10 + /* Activate guest mode, so faults get handled by KVM */ + li r11, KVM_GUEST_MODE_GUEST + stb r11, PACA_KVM_IN_GUEST(r13) + /* Remove LPAR shadow entries */ #if SLB_NUM_BOLTED == 3 -- cgit v1.2.3 From fbad5f1dfdd097ca282ee3a796986e11eb5a971f Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 15 Jan 2010 14:49:09 +0100 Subject: KVM: PPC: Export __giveup_vsx We need to explicitly only giveup VSX in KVM, so let's export that specific function to module space. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/powerpc/kernel/ppc_ksyms.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 425451453e96..ab3e392ac63c 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -107,6 +107,7 @@ EXPORT_SYMBOL(giveup_altivec); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX EXPORT_SYMBOL(giveup_vsx); +EXPORT_SYMBOL_GPL(__giveup_vsx); #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE EXPORT_SYMBOL(giveup_spe); -- cgit v1.2.3 From f7adbba1e5d464b0d449adac1eb2519be6be9728 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 15 Jan 2010 14:49:13 +0100 Subject: KVM: PPC: Keep SRR1 flags around in shadow_msr SRR1 stores more information that just the MSR value. It also stores valuable information about the type of interrupt we received, for example whether the storage interrupt we just got was because of a missing htab entry or not. We use that information to speed up the exit path. Now if we get preempted before we can interpret the shadow_msr values, we get into vcpu_put which then calls the MSR handler, which then sets all the SRR1 information bits in shadow_msr to 0. Great. So let's preserve the SRR1 specific bits in shadow_msr whenever we set the MSR. They don't hurt. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kvm/book3s.c | 13 +++++++------ arch/powerpc/kvm/book3s_64_interrupts.S | 2 +- 4 files changed, 10 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index c30a70c6b931..715aa6baf6f0 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -198,6 +198,7 @@ struct kvm_vcpu_arch { ulong msr; #ifdef CONFIG_PPC64 ulong shadow_msr; + ulong shadow_srr1; ulong hflags; ulong guest_owned_ext; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ee9935442f0e..957ceb7059c5 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -433,6 +433,7 @@ int main(void) DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2)); DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); + DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 2cb181396f82..58f5200fc09b 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -524,14 +524,14 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, /* Page not found in guest PTE entries */ vcpu->arch.dear = vcpu->arch.fault_dear; to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); + vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EPERM) { /* Storage protection */ vcpu->arch.dear = vcpu->arch.fault_dear; to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); + vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EINVAL) { /* Page not found in guest SLB */ @@ -693,7 +693,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_INST_STORAGE: vcpu->stat.pf_instruc++; /* only care about PTEG not found errors, but leave NX alone */ - if (vcpu->arch.shadow_msr & 0x40000000) { + if (vcpu->arch.shadow_srr1 & 0x40000000) { r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr); vcpu->stat.sp_instruc++; } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && @@ -705,7 +705,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, */ kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); } else { - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000); + vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); r = RESUME_GUEST; @@ -753,7 +753,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, enum emulation_result er; ulong flags; - flags = (vcpu->arch.shadow_msr & 0x1f0000ull); + flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; if (vcpu->arch.msr & MSR_PR) { #ifdef EXIT_DEBUG @@ -808,7 +808,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, break; default: /* Ugh - bork here! What did we get? */ - printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, vcpu->arch.pc, vcpu->arch.shadow_msr); + printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", + exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1); r = RESUME_HOST; BUG(); break; diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S index 2ff0b2137e6f..c1584d0cbce8 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_64_interrupts.S @@ -169,7 +169,7 @@ kvmppc_handler_highmem: stw r0, VCPU_LAST_INST(r7) std r3, VCPU_PC(r7) - std r4, VCPU_SHADOW_MSR(r7) + std r4, VCPU_SHADOW_SRR1(r7) std r5, VCPU_FAULT_DEAR(r7) std r6, VCPU_FAULT_DSISR(r7) -- cgit v1.2.3 From 9d6df3fdfc470c313b7ea13dbe8a63fb21ab7365 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 25 Feb 2010 18:04:33 -0600 Subject: powerpc/perf: Build callchain code regardless of hardware event support. It's also useful for software events, as well as future support for other types of hardware counters. Signed-off-by: Scott Wood Acked-by: Paul Mackerras Signed-off-by: Kumar Gala --- arch/powerpc/kernel/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c002b0410219..93fd1629f10e 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -98,7 +98,8 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o -obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o perf_callchain.o +obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o +obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o -- cgit v1.2.3 From a11106544f33c104706ae42d27219a409b67478e Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 25 Feb 2010 18:09:45 -0600 Subject: powerpc/perf: e500 support This implements perf_event support for the Freescale embedded performance monitor, based on the existing perf_event.c that supports server/classic chips. Some limitations: - Performance monitor interrupts are regular EE interrupts, and thus you can't profile places with interrupts disabled. We may want to implement soft IRQ-disabling, with perfmon interrupts exempted and treated as NMIs. - When trying to schedule multiple event groups at once, and using restricted events, situations could arise where scheduling fails even though it would be possible. Consider three groups, each with two events. One group has restricted events, the others don't. The two non-restricted groups are scheduled, then one is removed, which happens to occupy the two counters that can't do restricted events. The remaining non-restricted group will not be moved to the non-restricted-capable counters to make room if the restricted group tries to be scheduled. Signed-off-by: Scott Wood Acked-by: Paul Mackerras Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/perf_event.h | 109 +---- arch/powerpc/include/asm/perf_event_fsl_emb.h | 50 ++ arch/powerpc/include/asm/perf_event_server.h | 110 +++++ arch/powerpc/include/asm/reg_fsl_emb.h | 2 +- arch/powerpc/kernel/Makefile | 4 + arch/powerpc/kernel/cputable.c | 2 +- arch/powerpc/kernel/e500-pmu.c | 129 +++++ arch/powerpc/kernel/perf_event_fsl_emb.c | 654 ++++++++++++++++++++++++++ arch/powerpc/platforms/Kconfig.cputype | 10 + 9 files changed, 970 insertions(+), 100 deletions(-) create mode 100644 arch/powerpc/include/asm/perf_event_fsl_emb.h create mode 100644 arch/powerpc/include/asm/perf_event_server.h create mode 100644 arch/powerpc/kernel/e500-pmu.c create mode 100644 arch/powerpc/kernel/perf_event_fsl_emb.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 3288ce3997e0..e6d4ce69b126 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -1,110 +1,23 @@ /* - * Performance event support - PowerPC-specific definitions. + * Performance event support - hardware-specific disambiguation * - * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * For now this is a compile-time decision, but eventually it should be + * runtime. This would allow multiplatform perf event support for e300 (fsl + * embedded perf counters) plus server/classic, and would accommodate + * devices other than the core which provide their own performance counters. + * + * Copyright 2010 Freescale Semiconductor, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include - -#include - -#define MAX_HWEVENTS 8 -#define MAX_EVENT_ALTERNATIVES 8 -#define MAX_LIMITED_HWCOUNTERS 2 - -/* - * This struct provides the constants and functions needed to - * describe the PMU on a particular POWER-family CPU. - */ -struct power_pmu { - const char *name; - int n_counter; - int max_alternatives; - unsigned long add_fields; - unsigned long test_adder; - int (*compute_mmcr)(u64 events[], int n_ev, - unsigned int hwc[], unsigned long mmcr[]); - int (*get_constraint)(u64 event_id, unsigned long *mskp, - unsigned long *valp); - int (*get_alternatives)(u64 event_id, unsigned int flags, - u64 alt[]); - void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); - int (*limited_pmc_event)(u64 event_id); - u32 flags; - int n_generic; - int *generic_events; - int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX]; -}; - -/* - * Values for power_pmu.flags - */ -#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ -#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ - -/* - * Values for flags to get_alternatives() - */ -#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ -#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ -#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ - -extern int register_power_pmu(struct power_pmu *); -struct pt_regs; -extern unsigned long perf_misc_flags(struct pt_regs *regs); -extern unsigned long perf_instruction_pointer(struct pt_regs *regs); - -#define PERF_EVENT_INDEX_OFFSET 1 - -/* - * Only override the default definitions in include/linux/perf_event.h - * if we have hardware PMU support. - */ #ifdef CONFIG_PPC_PERF_CTRS -#define perf_misc_flags(regs) perf_misc_flags(regs) +#include #endif -/* - * The power_pmu.get_constraint function returns a 32/64-bit value and - * a 32/64-bit mask that express the constraints between this event_id and - * other events. - * - * The value and mask are divided up into (non-overlapping) bitfields - * of three different types: - * - * Select field: this expresses the constraint that some set of bits - * in MMCR* needs to be set to a specific value for this event_id. For a - * select field, the mask contains 1s in every bit of the field, and - * the value contains a unique value for each possible setting of the - * MMCR* bits. The constraint checking code will ensure that two events - * that set the same field in their masks have the same value in their - * value dwords. - * - * Add field: this expresses the constraint that there can be at most - * N events in a particular class. A field of k bits can be used for - * N <= 2^(k-1) - 1. The mask has the most significant bit of the field - * set (and the other bits 0), and the value has only the least significant - * bit of the field set. In addition, the 'add_fields' and 'test_adder' - * in the struct power_pmu for this processor come into play. The - * add_fields value contains 1 in the LSB of the field, and the - * test_adder contains 2^(k-1) - 1 - N in the field. - * - * NAND field: this expresses the constraint that you may not have events - * in all of a set of classes. (For example, on PPC970, you can't select - * events from the FPU, ISU and IDU simultaneously, although any two are - * possible.) For N classes, the field is N+1 bits wide, and each class - * is assigned one bit from the least-significant N bits. The mask has - * only the most-significant bit set, and the value has only the bit - * for the event_id's class set. The test_adder has the least significant - * bit set in the field. - * - * If an event_id is not subject to the constraint expressed by a particular - * field, then it will have 0 in both the mask and value for that field. - */ +#ifdef CONFIG_FSL_EMB_PERF_EVENT +#include +#endif diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h new file mode 100644 index 000000000000..718a9fa94e68 --- /dev/null +++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h @@ -0,0 +1,50 @@ +/* + * Performance event support - Freescale embedded specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include + +#define MAX_HWEVENTS 4 + +/* event flags */ +#define FSL_EMB_EVENT_VALID 1 +#define FSL_EMB_EVENT_RESTRICTED 2 + +/* upper half of event flags is PMLCb */ +#define FSL_EMB_EVENT_THRESHMUL 0x0000070000000000ULL +#define FSL_EMB_EVENT_THRESH 0x0000003f00000000ULL + +struct fsl_emb_pmu { + const char *name; + int n_counter; /* total number of counters */ + + /* + * The number of contiguous counters starting at zero that + * can hold restricted events, or zero if there are no + * restricted events. + * + * This isn't a very flexible method of expressing constraints, + * but it's very simple and is adequate for existing chips. + */ + int n_restricted; + + /* Returns event flags and PMLCb (FSL_EMB_EVENT_*) */ + u64 (*xlate_event)(u64 event_id); + + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +int register_fsl_emb_pmu(struct fsl_emb_pmu *); diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h new file mode 100644 index 000000000000..8f1df1208d23 --- /dev/null +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -0,0 +1,110 @@ +/* + * Performance event support - PowerPC classic/server specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include + +#define MAX_HWEVENTS 8 +#define MAX_EVENT_ALTERNATIVES 8 +#define MAX_LIMITED_HWCOUNTERS 2 + +/* + * This struct provides the constants and functions needed to + * describe the PMU on a particular POWER-family CPU. + */ +struct power_pmu { + const char *name; + int n_counter; + int max_alternatives; + unsigned long add_fields; + unsigned long test_adder; + int (*compute_mmcr)(u64 events[], int n_ev, + unsigned int hwc[], unsigned long mmcr[]); + int (*get_constraint)(u64 event_id, unsigned long *mskp, + unsigned long *valp); + int (*get_alternatives)(u64 event_id, unsigned int flags, + u64 alt[]); + void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); + int (*limited_pmc_event)(u64 event_id); + u32 flags; + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +/* + * Values for power_pmu.flags + */ +#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ +#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ + +/* + * Values for flags to get_alternatives() + */ +#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ +#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ +#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ + +extern int register_power_pmu(struct power_pmu *); + +struct pt_regs; +extern unsigned long perf_misc_flags(struct pt_regs *regs); +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); + +#define PERF_EVENT_INDEX_OFFSET 1 + +/* + * Only override the default definitions in include/linux/perf_event.h + * if we have hardware PMU support. + */ +#ifdef CONFIG_PPC_PERF_CTRS +#define perf_misc_flags(regs) perf_misc_flags(regs) +#endif + +/* + * The power_pmu.get_constraint function returns a 32/64-bit value and + * a 32/64-bit mask that express the constraints between this event_id and + * other events. + * + * The value and mask are divided up into (non-overlapping) bitfields + * of three different types: + * + * Select field: this expresses the constraint that some set of bits + * in MMCR* needs to be set to a specific value for this event_id. For a + * select field, the mask contains 1s in every bit of the field, and + * the value contains a unique value for each possible setting of the + * MMCR* bits. The constraint checking code will ensure that two events + * that set the same field in their masks have the same value in their + * value dwords. + * + * Add field: this expresses the constraint that there can be at most + * N events in a particular class. A field of k bits can be used for + * N <= 2^(k-1) - 1. The mask has the most significant bit of the field + * set (and the other bits 0), and the value has only the least significant + * bit of the field set. In addition, the 'add_fields' and 'test_adder' + * in the struct power_pmu for this processor come into play. The + * add_fields value contains 1 in the LSB of the field, and the + * test_adder contains 2^(k-1) - 1 - N in the field. + * + * NAND field: this expresses the constraint that you may not have events + * in all of a set of classes. (For example, on PPC970, you can't select + * events from the FPU, ISU and IDU simultaneously, although any two are + * possible.) For N classes, the field is N+1 bits wide, and each class + * is assigned one bit from the least-significant N bits. The mask has + * only the most-significant bit set, and the value has only the bit + * for the event_id's class set. The test_adder has the least significant + * bit set in the field. + * + * If an event_id is not subject to the constraint expressed by a particular + * field, then it will have 0 in both the mask and value for that field. + */ diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index 0de404dfee8b..77bb71cfd991 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -31,7 +31,7 @@ #define PMLCA_FCM0 0x08000000 /* Freeze when PMM==0 */ #define PMLCA_CE 0x04000000 /* Condition Enable */ -#define PMLCA_EVENT_MASK 0x007f0000 /* Event field */ +#define PMLCA_EVENT_MASK 0x00ff0000 /* Event field */ #define PMLCA_EVENT_SHIFT 16 #define PMRN_PMLCB0 0x110 /* PM Local Control B0 */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 93fd1629f10e..877326320e74 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -99,11 +99,15 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o + obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o +obj-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o +obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o + obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o ifneq ($(CONFIG_PPC_INDIRECT_IO),y) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 2fc82bac3bbc..8af4949434b2 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1808,7 +1808,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", /* xxx - galak, e500mc? */ + .oprofile_cpu_type = "ppc/e500mc", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e500mc, .machine_check = machine_check_e500, diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c new file mode 100644 index 000000000000..7c07de0d8943 --- /dev/null +++ b/arch/powerpc/kernel/e500-pmu.c @@ -0,0 +1,129 @@ +/* + * Performance counter support for e500 family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include +#include + +/* + * Map of generic hardware event types to hardware events + * Zero if unsupported + */ +static int e500_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 1, + [PERF_COUNT_HW_INSTRUCTIONS] = 2, + [PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12, + [PERF_COUNT_HW_BRANCH_MISSES] = 15, +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + /* + * D-cache misses are not split into read/write/prefetch; + * use raw event 41. + */ + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 27, 0 }, + [C(OP_WRITE)] = { 28, 0 }, + [C(OP_PREFETCH)] = { 29, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 2, 60 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + /* + * Assuming LL means L2, it's not a good match for this model. + * It allocates only on L1 castout or explicit prefetch, and + * does not have separate read/write events (but it does have + * separate instruction/data events). + */ + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + /* + * There are data/instruction MMU misses, but that's a miss on + * the chip's internal level-one TLB which is probably not + * what the user wants. Instead, unified level-two TLB misses + * are reported here. + */ + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 26, 66 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 12, 15 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +static int num_events = 128; + +/* Upper half of event id is PMLCb, for threshold events */ +static u64 e500_xlate_event(u64 event_id) +{ + u32 event_low = (u32)event_id; + u64 ret; + + if (event_low >= num_events) + return 0; + + ret = FSL_EMB_EVENT_VALID; + + if (event_low >= 76 && event_low <= 81) { + ret |= FSL_EMB_EVENT_RESTRICTED; + ret |= event_id & + (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH); + } else if (event_id & + (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)) { + /* Threshold requested on non-threshold event */ + return 0; + } + + return ret; +} + +static struct fsl_emb_pmu e500_pmu = { + .name = "e500 family", + .n_counter = 4, + .n_restricted = 2, + .xlate_event = e500_xlate_event, + .n_generic = ARRAY_SIZE(e500_generic_events), + .generic_events = e500_generic_events, + .cache_events = &e500_cache_events, +}; + +static int init_e500_pmu(void) +{ + if (!cur_cpu_spec->oprofile_cpu_type) + return -ENODEV; + + if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500mc")) + num_events = 256; + else if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500")) + return -ENODEV; + + return register_fsl_emb_pmu(&e500_pmu); +} + +arch_initcall(init_e500_pmu); diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c new file mode 100644 index 000000000000..369872f6cf78 --- /dev/null +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -0,0 +1,654 @@ +/* + * Performance event support - Freescale Embedded Performance Monitor + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct cpu_hw_events { + int n_events; + int disabled; + u8 pmcs_enabled; + struct perf_event *event[MAX_HWEVENTS]; +}; +static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +static struct fsl_emb_pmu *ppmu; + +/* Number of perf_events counting hardware events */ +static atomic_t num_events; +/* Used to avoid races in calling reserve/release_pmc_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +/* + * 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) +{ +#ifdef __powerpc64__ + return !regs->softe; +#else + return 0; +#endif +} + +static void perf_event_interrupt(struct pt_regs *regs); + +/* + * Read one performance monitor counter (PMC). + */ +static unsigned long read_pmc(int idx) +{ + unsigned long val; + + switch (idx) { + case 0: + val = mfpmr(PMRN_PMC0); + break; + case 1: + val = mfpmr(PMRN_PMC1); + break; + case 2: + val = mfpmr(PMRN_PMC2); + break; + case 3: + val = mfpmr(PMRN_PMC3); + break; + default: + printk(KERN_ERR "oops trying to read PMC%d\n", idx); + val = 0; + } + return val; +} + +/* + * Write one PMC. + */ +static void write_pmc(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMC0, val); + break; + case 1: + mtpmr(PMRN_PMC1, val); + break; + case 2: + mtpmr(PMRN_PMC2, val); + break; + case 3: + mtpmr(PMRN_PMC3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMC%d\n", idx); + } + + isync(); +} + +/* + * Write one local control A register + */ +static void write_pmlca(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMLCA0, val); + break; + case 1: + mtpmr(PMRN_PMLCA1, val); + break; + case 2: + mtpmr(PMRN_PMLCA2, val); + break; + case 3: + mtpmr(PMRN_PMLCA3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMLCA%d\n", idx); + } + + isync(); +} + +/* + * Write one local control B register + */ +static void write_pmlcb(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMLCB0, val); + break; + case 1: + mtpmr(PMRN_PMLCB1, val); + break; + case 2: + mtpmr(PMRN_PMLCB2, val); + break; + case 3: + mtpmr(PMRN_PMLCB3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMLCB%d\n", idx); + } + + isync(); +} + +static void fsl_emb_pmu_read(struct perf_event *event) +{ + s64 val, delta, prev; + + /* + * Performance monitor interrupts come even when interrupts + * are soft-disabled, as long as interrupts are hard-enabled. + * Therefore we treat them like NMIs. + */ + do { + prev = atomic64_read(&event->hw.prev_count); + barrier(); + val = read_pmc(event->hw.idx); + } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + + /* The counters are only 32 bits wide */ + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &event->count); + atomic64_sub(delta, &event->hw.period_left); +} + +/* + * Disable all events to prevent PMU interrupts and to allow + * events to be added or removed. + */ +void hw_perf_disable(void) +{ + struct cpu_hw_events *cpuhw; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!cpuhw->disabled) { + cpuhw->disabled = 1; + + /* + * Check if we ever enabled the PMU on this cpu. + */ + if (!cpuhw->pmcs_enabled) { + ppc_enable_pmcs(); + cpuhw->pmcs_enabled = 1; + } + + if (atomic_read(&num_events)) { + /* + * Set the 'freeze all counters' bit, and disable + * interrupts. The barrier is to make sure the + * mtpmr has been executed and the PMU has frozen + * the events before we return. + */ + + mtpmr(PMRN_PMGC0, PMGC0_FAC); + isync(); + } + } + local_irq_restore(flags); +} + +/* + * Re-enable all events if disable == 0. + * If we were previously disabled and events were added, then + * put the new config on the PMU. + */ +void hw_perf_enable(void) +{ + struct cpu_hw_events *cpuhw; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_events); + if (!cpuhw->disabled) + goto out; + + cpuhw->disabled = 0; + ppc_set_pmu_inuse(cpuhw->n_events != 0); + + if (cpuhw->n_events > 0) { + mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE); + isync(); + } + + out: + local_irq_restore(flags); +} + +static int collect_events(struct perf_event *group, int max_count, + struct perf_event *ctrs[]) +{ + int n = 0; + struct perf_event *event; + + if (!is_software_event(group)) { + if (n >= max_count) + return -1; + ctrs[n] = group; + n++; + } + list_for_each_entry(event, &group->sibling_list, group_entry) { + if (!is_software_event(event) && + event->state != PERF_EVENT_STATE_OFF) { + if (n >= max_count) + return -1; + ctrs[n] = event; + n++; + } + } + return n; +} + +/* perf must be disabled, context locked on entry */ +static int fsl_emb_pmu_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw; + int ret = -EAGAIN; + int num_counters = ppmu->n_counter; + u64 val; + int i; + + cpuhw = &get_cpu_var(cpu_hw_events); + + if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) + num_counters = ppmu->n_restricted; + + /* + * Allocate counters from top-down, so that restricted-capable + * counters are kept free as long as possible. + */ + for (i = num_counters - 1; i >= 0; i--) { + if (cpuhw->event[i]) + continue; + + break; + } + + if (i < 0) + goto out; + + event->hw.idx = i; + cpuhw->event[i] = event; + ++cpuhw->n_events; + + val = 0; + if (event->hw.sample_period) { + s64 left = atomic64_read(&event->hw.period_left); + if (left < 0x80000000L) + val = 0x80000000L - left; + } + atomic64_set(&event->hw.prev_count, val); + write_pmc(i, val); + perf_event_update_userpage(event); + + write_pmlcb(i, event->hw.config >> 32); + write_pmlca(i, event->hw.config_base); + + ret = 0; + out: + put_cpu_var(cpu_hw_events); + return ret; +} + +/* perf must be disabled, context locked on entry */ +static void fsl_emb_pmu_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw; + int i = event->hw.idx; + + if (i < 0) + goto out; + + fsl_emb_pmu_read(event); + + cpuhw = &get_cpu_var(cpu_hw_events); + + WARN_ON(event != cpuhw->event[event->hw.idx]); + + write_pmlca(i, 0); + write_pmlcb(i, 0); + write_pmc(i, 0); + + cpuhw->event[i] = NULL; + event->hw.idx = -1; + + /* + * TODO: if at least one restricted event exists, and we + * just freed up a non-restricted-capable counter, and + * there is a restricted-capable counter occupied by + * a non-restricted event, migrate that event to the + * vacated counter. + */ + + cpuhw->n_events--; + + out: + put_cpu_var(cpu_hw_events); +} + +/* + * Re-enable interrupts on a event after they were throttled + * because they were coming too fast. + * + * Context is locked on entry, but perf is not disabled. + */ +static void fsl_emb_pmu_unthrottle(struct perf_event *event) +{ + s64 val, left; + unsigned long flags; + + if (event->hw.idx < 0 || !event->hw.sample_period) + return; + local_irq_save(flags); + perf_disable(); + fsl_emb_pmu_read(event); + left = event->hw.sample_period; + event->hw.last_period = left; + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + write_pmc(event->hw.idx, val); + atomic64_set(&event->hw.prev_count, val); + atomic64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + perf_enable(); + local_irq_restore(flags); +} + +static struct pmu fsl_emb_pmu = { + .enable = fsl_emb_pmu_enable, + .disable = fsl_emb_pmu_disable, + .read = fsl_emb_pmu_read, + .unthrottle = fsl_emb_pmu_unthrottle, +}; + +/* + * Release the PMU if this is the last perf_event. + */ +static void hw_perf_event_destroy(struct perf_event *event) +{ + if (!atomic_add_unless(&num_events, -1, 1)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_dec_return(&num_events) == 0) + release_pmc_hardware(); + mutex_unlock(&pmc_reserve_mutex); + } +} + +/* + * Translate a generic cache event_id config to a raw event_id code. + */ +static int hw_perf_cache_event(u64 config, u64 *eventp) +{ + unsigned long type, op, result; + int ev; + + if (!ppmu->cache_events) + return -EINVAL; + + /* unpack config */ + type = config & 0xff; + op = (config >> 8) & 0xff; + result = (config >> 16) & 0xff; + + if (type >= PERF_COUNT_HW_CACHE_MAX || + op >= PERF_COUNT_HW_CACHE_OP_MAX || + result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ev = (*ppmu->cache_events)[type][op][result]; + if (ev == 0) + return -EOPNOTSUPP; + if (ev == -1) + return -EINVAL; + *eventp = ev; + return 0; +} + +const struct pmu *hw_perf_event_init(struct perf_event *event) +{ + u64 ev; + struct perf_event *events[MAX_HWEVENTS]; + int n; + int err; + int num_restricted; + int i; + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + ev = event->attr.config; + if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) + return ERR_PTR(-EOPNOTSUPP); + ev = ppmu->generic_events[ev]; + break; + + case PERF_TYPE_HW_CACHE: + err = hw_perf_cache_event(event->attr.config, &ev); + if (err) + return ERR_PTR(err); + break; + + case PERF_TYPE_RAW: + ev = event->attr.config; + break; + + default: + return ERR_PTR(-EINVAL); + } + + event->hw.config = ppmu->xlate_event(ev); + if (!(event->hw.config & FSL_EMB_EVENT_VALID)) + return ERR_PTR(-EINVAL); + + /* + * If this is in a group, check if it can go on with all the + * other hardware events in the group. We assume the event + * hasn't been linked into its leader's sibling list at this point. + */ + n = 0; + if (event->group_leader != event) { + n = collect_events(event->group_leader, + ppmu->n_counter - 1, events); + if (n < 0) + return ERR_PTR(-EINVAL); + } + + if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) { + num_restricted = 0; + for (i = 0; i < n; i++) { + if (events[i]->hw.config & FSL_EMB_EVENT_RESTRICTED) + num_restricted++; + } + + if (num_restricted >= ppmu->n_restricted) + return ERR_PTR(-EINVAL); + } + + event->hw.idx = -1; + + event->hw.config_base = PMLCA_CE | PMLCA_FCM1 | + (u32)((ev << 16) & PMLCA_EVENT_MASK); + + if (event->attr.exclude_user) + event->hw.config_base |= PMLCA_FCU; + if (event->attr.exclude_kernel) + event->hw.config_base |= PMLCA_FCS; + if (event->attr.exclude_idle) + return ERR_PTR(-ENOTSUPP); + + event->hw.last_period = event->hw.sample_period; + atomic64_set(&event->hw.period_left, event->hw.last_period); + + /* + * See if we need to reserve the PMU. + * If no events are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * reserve_pmc_hardware or release_pmc_hardware. + */ + err = 0; + if (!atomic_inc_not_zero(&num_events)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&num_events) == 0 && + reserve_pmc_hardware(perf_event_interrupt)) + err = -EBUSY; + else + atomic_inc(&num_events); + mutex_unlock(&pmc_reserve_mutex); + + mtpmr(PMRN_PMGC0, PMGC0_FAC); + isync(); + } + event->destroy = hw_perf_event_destroy; + + if (err) + return ERR_PTR(err); + return &fsl_emb_pmu; +} + +/* + * A counter has overflowed; update its count and record + * things if requested. Note that interrupts are hard-disabled + * here so there is no possibility of being interrupted. + */ +static void record_and_restart(struct perf_event *event, unsigned long val, + struct pt_regs *regs, int nmi) +{ + u64 period = event->hw.sample_period; + s64 prev, delta, left; + int record = 0; + + /* we don't have to worry about interrupts here */ + prev = atomic64_read(&event->hw.prev_count); + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &event->count); + + /* + * See if the total period for this event has expired, + * and update for the next period. + */ + val = 0; + left = atomic64_read(&event->hw.period_left) - delta; + if (period) { + if (left <= 0) { + left += period; + if (left <= 0) + left = period; + record = 1; + } + if (left < 0x80000000LL) + val = 0x80000000LL - left; + } + + /* + * Finally record data if requested. + */ + if (record) { + struct perf_sample_data data = { + .period = event->hw.last_period, + }; + + if (perf_event_overflow(event, nmi, &data, regs)) { + /* + * Interrupts are coming too fast - throttle them + * by setting the event to 0, so it will be + * at least 2^30 cycles until the next interrupt + * (assuming each event counts at most 2 counts + * per cycle). + */ + val = 0; + left = ~0ULL >> 1; + } + } + + write_pmc(event->hw.idx, val); + atomic64_set(&event->hw.prev_count, val); + atomic64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); +} + +static void perf_event_interrupt(struct pt_regs *regs) +{ + int i; + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct perf_event *event; + unsigned long val; + int found = 0; + int nmi; + + nmi = perf_intr_is_nmi(regs); + if (nmi) + nmi_enter(); + else + irq_enter(); + + for (i = 0; i < ppmu->n_counter; ++i) { + event = cpuhw->event[i]; + + val = read_pmc(i); + if ((int)val < 0) { + if (event) { + /* event has overflowed */ + found = 1; + record_and_restart(event, val, regs, nmi); + } else { + /* + * Disabled counter is negative, + * reset it just in case. + */ + write_pmc(i, 0); + } + } + } + + /* PMM will keep counters frozen until we return from the interrupt. */ + mtmsr(mfmsr() | MSR_PMM); + mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE); + isync(); + + if (nmi) + nmi_exit(); + else + irq_exit(); +} + +void hw_perf_event_setup(int cpu) +{ + struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); + + memset(cpuhw, 0, sizeof(*cpuhw)); +} + +int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) +{ + if (ppmu) + return -EBUSY; /* something's already registered */ + + ppmu = pmu; + pr_info("%s performance monitor hardware support registered\n", + pmu->name); + + return 0; +} diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index fa0f690d3867..a8aae0b54579 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -144,6 +144,16 @@ config FSL_EMB_PERFMON and some e300 cores (c3 and c4). Select this only if your core supports the Embedded Performance Monitor APU +config FSL_EMB_PERF_EVENT + bool + depends on FSL_EMB_PERFMON && PERF_EVENTS && !PPC_PERF_CTRS + default y + +config FSL_EMB_PERF_EVENT_E500 + bool + depends on FSL_EMB_PERF_EVENT && E500 + default y + config 4xx bool depends on 40x || 44x -- cgit v1.2.3 From 52cf25d0ab7f78eeecc59ac652ed5090f69b619e Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Tue, 19 Jan 2010 02:58:23 +0100 Subject: Driver core: Constify struct sysfs_ops in struct kobj_type Constify struct sysfs_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy Acked-by: David Teigland Acked-by: Matt Domsch Acked-by: Maciej Sosnowski Acked-by: Hans J. Koch Acked-by: Pekka Enberg Acked-by: Jens Axboe Acked-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- Documentation/kobject.txt | 2 +- arch/ia64/kernel/topology.c | 2 +- arch/powerpc/kernel/cacheinfo.c | 2 +- arch/sh/kernel/cpu/sh4/sq.c | 2 +- arch/x86/kernel/cpu/intel_cacheinfo.c | 2 +- arch/x86/kernel/cpu/mcheck/mce_amd.c | 2 +- block/blk-integrity.c | 2 +- block/blk-sysfs.c | 2 +- block/elevator.c | 2 +- drivers/base/bus.c | 4 ++-- drivers/base/class.c | 2 +- drivers/base/core.c | 2 +- drivers/base/sys.c | 4 ++-- drivers/block/pktcdvd.c | 2 +- drivers/cpufreq/cpufreq.c | 2 +- drivers/cpuidle/sysfs.c | 4 ++-- drivers/dma/ioat/dma.c | 2 +- drivers/dma/ioat/dma.h | 2 +- drivers/edac/edac_device_sysfs.c | 6 +++--- drivers/edac/edac_mc_sysfs.c | 4 ++-- drivers/edac/edac_pci_sysfs.c | 4 ++-- drivers/firmware/edd.c | 2 +- drivers/firmware/efivars.c | 2 +- drivers/firmware/iscsi_ibft.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 2 +- drivers/gpu/drm/ttm/ttm_memory.c | 2 +- drivers/infiniband/core/cm.c | 2 +- drivers/infiniband/core/sysfs.c | 2 +- drivers/md/dm-sysfs.c | 2 +- drivers/md/md.c | 4 ++-- drivers/net/ibmveth.c | 2 +- drivers/net/iseries_veth.c | 4 ++-- drivers/parisc/pdc_stable.c | 2 +- drivers/pci/hotplug/fakephp.c | 2 +- drivers/pci/slot.c | 2 +- drivers/uio/uio.c | 4 ++-- drivers/uwb/wlp/sysfs.c | 3 +-- drivers/video/omap2/dss/manager.c | 2 +- drivers/video/omap2/dss/overlay.c | 2 +- drivers/xen/sys-hypervisor.c | 2 +- fs/btrfs/sysfs.c | 4 ++-- fs/dlm/lockspace.c | 2 +- fs/ext4/super.c | 2 +- fs/gfs2/sys.c | 2 +- fs/ocfs2/cluster/masklog.c | 2 +- fs/sysfs/file.c | 8 ++++---- include/linux/kobject.h | 4 ++-- kernel/params.c | 2 +- lib/kobject.c | 2 +- mm/slub.c | 2 +- net/bridge/br_private.h | 2 +- net/bridge/br_sysfs_if.c | 2 +- samples/kobject/kset-example.c | 2 +- 54 files changed, 69 insertions(+), 70 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt index c79ab996dada..bdb13817e1e9 100644 --- a/Documentation/kobject.txt +++ b/Documentation/kobject.txt @@ -266,7 +266,7 @@ kobj_type: struct kobj_type { void (*release)(struct kobject *); - struct sysfs_ops *sysfs_ops; + const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; }; diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 8f060352e129..b3a5818088d9 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -282,7 +282,7 @@ static ssize_t cache_show(struct kobject * kobj, struct attribute * attr, char * return ret; } -static struct sysfs_ops cache_sysfs_ops = { +static const struct sysfs_ops cache_sysfs_ops = { .show = cache_show }; diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index bb37b1d19a58..01fe9ce28379 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -642,7 +642,7 @@ static struct kobj_attribute *cache_index_opt_attrs[] = { &cache_assoc_attr, }; -static struct sysfs_ops cache_index_ops = { +static const struct sysfs_ops cache_index_ops = { .show = cache_index_show, }; diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index fc065f9da6e5..14726eef1ce0 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -326,7 +326,7 @@ static struct attribute *sq_sysfs_attrs[] = { NULL, }; -static struct sysfs_ops sq_sysfs_ops = { +static const struct sysfs_ops sq_sysfs_ops = { .show = sq_sysfs_show, .store = sq_sysfs_store, }; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index eddb1bdd1b8f..b3eeb66c0a51 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -903,7 +903,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = show, .store = store, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 83a3d1f4efca..cda932ca3ade 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -388,7 +388,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops threshold_ops = { +static const struct sysfs_ops threshold_ops = { .show = show, .store = store, }; diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 15c630813b1c..96e83c2bdb94 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -278,7 +278,7 @@ static struct attribute *integrity_attrs[] = { NULL, }; -static struct sysfs_ops integrity_ops = { +static const struct sysfs_ops integrity_ops = { .show = &integrity_attr_show, .store = &integrity_attr_store, }; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e85442415db3..2ae2cb3f362f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -450,7 +450,7 @@ static void blk_release_queue(struct kobject *kobj) kmem_cache_free(blk_requestq_cachep, q); } -static struct sysfs_ops queue_sysfs_ops = { +static const struct sysfs_ops queue_sysfs_ops = { .show = queue_attr_show, .store = queue_attr_store, }; diff --git a/block/elevator.c b/block/elevator.c index ee3a883840f2..df75676f6671 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -892,7 +892,7 @@ elv_attr_store(struct kobject *kobj, struct attribute *attr, return error; } -static struct sysfs_ops elv_sysfs_ops = { +static const struct sysfs_ops elv_sysfs_ops = { .show = elv_attr_show, .store = elv_attr_store, }; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 2afe599eb35d..cca1aa10054c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -70,7 +70,7 @@ static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops driver_sysfs_ops = { +static const struct sysfs_ops driver_sysfs_ops = { .show = drv_attr_show, .store = drv_attr_store, }; @@ -115,7 +115,7 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops bus_sysfs_ops = { +static const struct sysfs_ops bus_sysfs_ops = { .show = bus_attr_show, .store = bus_attr_store, }; diff --git a/drivers/base/class.c b/drivers/base/class.c index 2e297cc4cd3d..0147f476b8a9 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -63,7 +63,7 @@ static void class_release(struct kobject *kobj) kfree(cp); } -static struct sysfs_ops class_sysfs_ops = { +static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; diff --git a/drivers/base/core.c b/drivers/base/core.c index 58ec1069f4b0..b0d6646a2814 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -100,7 +100,7 @@ static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops dev_sysfs_ops = { +static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 747c99e0568b..8980feec5d14 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -54,7 +54,7 @@ sysdev_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = sysdev_show, .store = sysdev_store, }; @@ -104,7 +104,7 @@ static ssize_t sysdev_class_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops sysfs_class_ops = { +static const struct sysfs_ops sysfs_class_ops = { .show = sysdev_class_show, .store = sysdev_class_store, }; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 73d815d3f1b2..39c8514442eb 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -284,7 +284,7 @@ static ssize_t kobj_pkt_store(struct kobject *kobj, return len; } -static struct sysfs_ops kobj_pkt_ops = { +static const struct sysfs_ops kobj_pkt_ops = { .show = kobj_pkt_show, .store = kobj_pkt_store }; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 67bc2ece7b4b..2d5d575e889d 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -766,7 +766,7 @@ static void cpufreq_sysfs_release(struct kobject *kobj) complete(&policy->kobj_unregister); } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = show, .store = store, }; diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index c9cefacabf37..8719b36e1a4d 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -195,7 +195,7 @@ static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr, return ret; } -static struct sysfs_ops cpuidle_sysfs_ops = { +static const struct sysfs_ops cpuidle_sysfs_ops = { .show = cpuidle_show, .store = cpuidle_store, }; @@ -281,7 +281,7 @@ static ssize_t cpuidle_state_show(struct kobject * kobj, return ret; } -static struct sysfs_ops cpuidle_state_sysfs_ops = { +static const struct sysfs_ops cpuidle_state_sysfs_ops = { .show = cpuidle_state_show, }; diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index af14c9a5b8d4..0099340b9616 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -1138,7 +1138,7 @@ ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page) return entry->show(&chan->common, page); } -struct sysfs_ops ioat_sysfs_ops = { +const struct sysfs_ops ioat_sysfs_ops = { .show = ioat_attr_show, }; diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index 4f747a254074..86b97ac8774e 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -346,7 +346,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan, unsigned long *phys_complete); void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type); void ioat_kobject_del(struct ioatdma_device *device); -extern struct sysfs_ops ioat_sysfs_ops; +extern const struct sysfs_ops ioat_sysfs_ops; extern struct ioat_sysfs_entry ioat_version_attr; extern struct ioat_sysfs_entry ioat_cap_attr; #endif /* IOATDMA_H */ diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 53764577035f..5fdedbc0f545 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -137,7 +137,7 @@ static ssize_t edac_dev_ctl_info_store(struct kobject *kobj, } /* edac_dev file operations for an 'ctl_info' */ -static struct sysfs_ops device_ctl_info_ops = { +static const struct sysfs_ops device_ctl_info_ops = { .show = edac_dev_ctl_info_show, .store = edac_dev_ctl_info_store }; @@ -373,7 +373,7 @@ static ssize_t edac_dev_instance_store(struct kobject *kobj, } /* edac_dev file operations for an 'instance' */ -static struct sysfs_ops device_instance_ops = { +static const struct sysfs_ops device_instance_ops = { .show = edac_dev_instance_show, .store = edac_dev_instance_store }; @@ -476,7 +476,7 @@ static ssize_t edac_dev_block_store(struct kobject *kobj, } /* edac_dev file operations for a 'block' */ -static struct sysfs_ops device_block_ops = { +static const struct sysfs_ops device_block_ops = { .show = edac_dev_block_show, .store = edac_dev_block_store }; diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index e1d4ce083481..88840e9fa3e0 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -245,7 +245,7 @@ static ssize_t csrowdev_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops csrowfs_ops = { +static const struct sysfs_ops csrowfs_ops = { .show = csrowdev_show, .store = csrowdev_store }; @@ -575,7 +575,7 @@ static ssize_t mcidev_store(struct kobject *kobj, struct attribute *attr, } /* Intermediate show/store table */ -static struct sysfs_ops mci_ops = { +static const struct sysfs_ops mci_ops = { .show = mcidev_show, .store = mcidev_store }; diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index fb60a877d768..bef94e3d9944 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -121,7 +121,7 @@ static ssize_t edac_pci_instance_store(struct kobject *kobj, } /* fs_ops table */ -static struct sysfs_ops pci_instance_ops = { +static const struct sysfs_ops pci_instance_ops = { .show = edac_pci_instance_show, .store = edac_pci_instance_store }; @@ -261,7 +261,7 @@ static ssize_t edac_pci_dev_store(struct kobject *kobj, return -EIO; } -static struct sysfs_ops edac_pci_sysfs_ops = { +static const struct sysfs_ops edac_pci_sysfs_ops = { .show = edac_pci_dev_show, .store = edac_pci_dev_store }; diff --git a/drivers/firmware/edd.c b/drivers/firmware/edd.c index 9e4f59dc7f1e..110e24e50883 100644 --- a/drivers/firmware/edd.c +++ b/drivers/firmware/edd.c @@ -122,7 +122,7 @@ edd_attr_show(struct kobject * kobj, struct attribute *attr, char *buf) return ret; } -static struct sysfs_ops edd_attr_ops = { +static const struct sysfs_ops edd_attr_ops = { .show = edd_attr_show, }; diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index f4f709d1370b..082f06ecd327 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -362,7 +362,7 @@ static ssize_t efivar_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops efivar_attr_ops = { +static const struct sysfs_ops efivar_attr_ops = { .show = efivar_attr_show, .store = efivar_attr_store, }; diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index a3600e3ed0fa..ed2801c378de 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -519,7 +519,7 @@ static ssize_t ibft_show_attribute(struct kobject *kobj, return ret; } -static struct sysfs_ops ibft_attr_ops = { +static const struct sysfs_ops ibft_attr_ops = { .show = ibft_show_attribute, }; diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 20f645743ead..d59f7cad2269 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -74,7 +74,7 @@ static struct attribute *def_attrs[] = { NULL }; -static struct sysfs_ops memmap_attr_ops = { +static const struct sysfs_ops memmap_attr_ops = { .show = memmap_attr_show, }; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index c7320ce4567d..89c38c49066f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -128,7 +128,7 @@ static struct attribute *ttm_bo_global_attrs[] = { NULL }; -static struct sysfs_ops ttm_bo_global_ops = { +static const struct sysfs_ops ttm_bo_global_ops = { .show = &ttm_bo_global_show }; diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index f5245c02b8fd..eb143e04d402 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -152,7 +152,7 @@ static struct attribute *ttm_mem_zone_attrs[] = { NULL }; -static struct sysfs_ops ttm_mem_zone_ops = { +static const struct sysfs_ops ttm_mem_zone_ops = { .show = &ttm_mem_zone_show, .store = &ttm_mem_zone_store }; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 5130fc55b8e2..764787ebe8d8 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3597,7 +3597,7 @@ static ssize_t cm_show_counter(struct kobject *obj, struct attribute *attr, atomic_long_read(&group->counter[cm_attr->index])); } -static struct sysfs_ops cm_counter_ops = { +static const struct sysfs_ops cm_counter_ops = { .show = cm_show_counter }; diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 158a214da2f7..1558bb7fc74d 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -79,7 +79,7 @@ static ssize_t port_attr_show(struct kobject *kobj, return port_attr->show(p, port_attr, buf); } -static struct sysfs_ops port_sysfs_ops = { +static const struct sysfs_ops port_sysfs_ops = { .show = port_attr_show }; diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index f91b40942e07..84d2b91e4efb 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -75,7 +75,7 @@ static struct attribute *dm_attrs[] = { NULL, }; -static struct sysfs_ops dm_sysfs_ops = { +static const struct sysfs_ops dm_sysfs_ops = { .show = dm_attr_show, }; diff --git a/drivers/md/md.c b/drivers/md/md.c index a20a71e5efd3..fdc1890b6ac5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2642,7 +2642,7 @@ static void rdev_free(struct kobject *ko) mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj); kfree(rdev); } -static struct sysfs_ops rdev_sysfs_ops = { +static const struct sysfs_ops rdev_sysfs_ops = { .show = rdev_attr_show, .store = rdev_attr_store, }; @@ -4059,7 +4059,7 @@ static void md_free(struct kobject *ko) kfree(mddev); } -static struct sysfs_ops md_sysfs_ops = { +static const struct sysfs_ops md_sysfs_ops = { .show = md_attr_show, .store = md_attr_store, }; diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index f2b937966950..0bc777bac9b4 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -1577,7 +1577,7 @@ static struct attribute * veth_pool_attrs[] = { NULL, }; -static struct sysfs_ops veth_pool_ops = { +static const struct sysfs_ops veth_pool_ops = { .show = veth_pool_show, .store = veth_pool_store, }; diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c index 966de5d69521..e6e972d9b7ca 100644 --- a/drivers/net/iseries_veth.c +++ b/drivers/net/iseries_veth.c @@ -384,7 +384,7 @@ static struct attribute *veth_cnx_default_attrs[] = { NULL }; -static struct sysfs_ops veth_cnx_sysfs_ops = { +static const struct sysfs_ops veth_cnx_sysfs_ops = { .show = veth_cnx_attribute_show }; @@ -441,7 +441,7 @@ static struct attribute *veth_port_default_attrs[] = { NULL }; -static struct sysfs_ops veth_port_sysfs_ops = { +static const struct sysfs_ops veth_port_sysfs_ops = { .show = veth_port_attribute_show }; diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index 0bc5d474b168..1062b8ffe244 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -481,7 +481,7 @@ pdcspath_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops pdcspath_attr_ops = { +static const struct sysfs_ops pdcspath_attr_ops = { .show = pdcspath_attr_show, .store = pdcspath_attr_store, }; diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c index 6151389fd903..0a894efd4b9b 100644 --- a/drivers/pci/hotplug/fakephp.c +++ b/drivers/pci/hotplug/fakephp.c @@ -73,7 +73,7 @@ static void legacy_release(struct kobject *kobj) } static struct kobj_type legacy_ktype = { - .sysfs_ops = &(struct sysfs_ops){ + .sysfs_ops = &(const struct sysfs_ops){ .store = legacy_store, .show = legacy_show }, .release = &legacy_release, diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index 49c9e6c9779a..f75a44d37fbe 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -29,7 +29,7 @@ static ssize_t pci_slot_attr_store(struct kobject *kobj, return attribute->store ? attribute->store(slot, buf, len) : -EIO; } -static struct sysfs_ops pci_slot_sysfs_ops = { +static const struct sysfs_ops pci_slot_sysfs_ops = { .show = pci_slot_attr_show, .store = pci_slot_attr_store, }; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index e941367dd28f..4de382acd8f2 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -129,7 +129,7 @@ static ssize_t map_type_show(struct kobject *kobj, struct attribute *attr, return entry->show(mem, buf); } -static struct sysfs_ops map_sysfs_ops = { +static const struct sysfs_ops map_sysfs_ops = { .show = map_type_show, }; @@ -217,7 +217,7 @@ static ssize_t portio_type_show(struct kobject *kobj, struct attribute *attr, return entry->show(port, buf); } -static struct sysfs_ops portio_sysfs_ops = { +static const struct sysfs_ops portio_sysfs_ops = { .show = portio_type_show, }; diff --git a/drivers/uwb/wlp/sysfs.c b/drivers/uwb/wlp/sysfs.c index 0370399ff4bb..6627c94cc854 100644 --- a/drivers/uwb/wlp/sysfs.c +++ b/drivers/uwb/wlp/sysfs.c @@ -615,8 +615,7 @@ ssize_t wlp_wss_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static -struct sysfs_ops wss_sysfs_ops = { +static const struct sysfs_ops wss_sysfs_ops = { .show = wlp_wss_attr_show, .store = wlp_wss_attr_store, }; diff --git a/drivers/video/omap2/dss/manager.c b/drivers/video/omap2/dss/manager.c index 913142d4cab1..9acef00c47ea 100644 --- a/drivers/video/omap2/dss/manager.c +++ b/drivers/video/omap2/dss/manager.c @@ -341,7 +341,7 @@ static ssize_t manager_attr_store(struct kobject *kobj, struct attribute *attr, return manager_attr->store(manager, buf, size); } -static struct sysfs_ops manager_sysfs_ops = { +static const struct sysfs_ops manager_sysfs_ops = { .show = manager_attr_show, .store = manager_attr_store, }; diff --git a/drivers/video/omap2/dss/overlay.c b/drivers/video/omap2/dss/overlay.c index 0c5bea263ac6..aed3f3194347 100644 --- a/drivers/video/omap2/dss/overlay.c +++ b/drivers/video/omap2/dss/overlay.c @@ -320,7 +320,7 @@ static ssize_t overlay_attr_store(struct kobject *kobj, struct attribute *attr, return overlay_attr->store(overlay, buf, size); } -static struct sysfs_ops overlay_sysfs_ops = { +static const struct sysfs_ops overlay_sysfs_ops = { .show = overlay_attr_show, .store = overlay_attr_store, }; diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index ae5cb05a1a1c..bb71ab2336c8 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -426,7 +426,7 @@ static ssize_t hyp_sysfs_store(struct kobject *kobj, return 0; } -static struct sysfs_ops hyp_sysfs_ops = { +static const struct sysfs_ops hyp_sysfs_ops = { .show = hyp_sysfs_show, .store = hyp_sysfs_store, }; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index a240b6fa81df..4ce16ef702a3 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -164,12 +164,12 @@ static void btrfs_root_release(struct kobject *kobj) complete(&root->kobj_unregister); } -static struct sysfs_ops btrfs_super_attr_ops = { +static const struct sysfs_ops btrfs_super_attr_ops = { .show = btrfs_super_attr_show, .store = btrfs_super_attr_store, }; -static struct sysfs_ops btrfs_root_attr_ops = { +static const struct sysfs_ops btrfs_root_attr_ops = { .show = btrfs_root_attr_show, .store = btrfs_root_attr_store, }; diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 26a8bd40400a..f994a7dfda85 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -148,7 +148,7 @@ static void lockspace_kobj_release(struct kobject *k) kfree(ls); } -static struct sysfs_ops dlm_attr_ops = { +static const struct sysfs_ops dlm_attr_ops = { .show = dlm_attr_show, .store = dlm_attr_store, }; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2b83b96cb2eb..ce84a6ed4a48 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2358,7 +2358,7 @@ static void ext4_sb_release(struct kobject *kobj) } -static struct sysfs_ops ext4_attr_ops = { +static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, }; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 543503010ed0..419042f7f0b6 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -49,7 +49,7 @@ static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, return a->store ? a->store(sdp, buf, len) : len; } -static struct sysfs_ops gfs2_attr_ops = { +static const struct sysfs_ops gfs2_attr_ops = { .show = gfs2_attr_show, .store = gfs2_attr_store, }; diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index b39da877b12f..3bb928a2bf7d 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -136,7 +136,7 @@ static ssize_t mlog_store(struct kobject *obj, struct attribute *attr, return mlog_mask_store(mlog_attr->mask, buf, count); } -static struct sysfs_ops mlog_attr_ops = { +static const struct sysfs_ops mlog_attr_ops = { .show = mlog_show, .store = mlog_store, }; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 50b725bcc3f3..ced2299f1c9a 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -53,7 +53,7 @@ struct sysfs_buffer { size_t count; loff_t pos; char * page; - struct sysfs_ops * ops; + const struct sysfs_ops * ops; struct mutex mutex; int needs_read_fill; int event; @@ -75,7 +75,7 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops * ops = buffer->ops; int ret = 0; ssize_t count; @@ -199,7 +199,7 @@ flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops * ops = buffer->ops; int rc; /* need attr_sd for attr and ops, its parent for kobj */ @@ -335,7 +335,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; struct sysfs_buffer *buffer; - struct sysfs_ops *ops; + const struct sysfs_ops *ops; int error = -EACCES; char *p; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 57a1eaae9096..3950d3c2850d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -106,7 +106,7 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); - struct sysfs_ops *sysfs_ops; + const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; }; @@ -132,7 +132,7 @@ struct kobj_attribute { const char *buf, size_t count); }; -extern struct sysfs_ops kobj_sysfs_ops; +extern const struct sysfs_ops kobj_sysfs_ops; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. diff --git a/kernel/params.c b/kernel/params.c index 48370be3c0a1..68396d73c838 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -722,7 +722,7 @@ static ssize_t module_attr_store(struct kobject *kobj, return ret; } -static struct sysfs_ops module_sysfs_ops = { +static const struct sysfs_ops module_sysfs_ops = { .show = module_attr_show, .store = module_attr_store, }; diff --git a/lib/kobject.c b/lib/kobject.c index cecf5a0ef6e1..8115eb1bbf4d 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -700,7 +700,7 @@ static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -struct sysfs_ops kobj_sysfs_ops = { +const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; diff --git a/mm/slub.c b/mm/slub.c index a26753c12dcd..a2b8969ba6d0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4390,7 +4390,7 @@ static void kmem_cache_release(struct kobject *kobj) kfree(s); } -static struct sysfs_ops slab_sysfs_ops = { +static const struct sysfs_ops slab_sysfs_ops = { .show = slab_attr_show, .store = slab_attr_store, }; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1cf2cef78584..fef0384e3c0b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -423,7 +423,7 @@ extern void br_ifinfo_notify(int event, struct net_bridge_port *port); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ -extern struct sysfs_ops brport_sysfs_ops; +extern const struct sysfs_ops brport_sysfs_ops; extern int br_sysfs_addif(struct net_bridge_port *p); /* br_sysfs_br.c */ diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 696596cd3384..0b9916489d6b 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -238,7 +238,7 @@ static ssize_t brport_store(struct kobject * kobj, return ret; } -struct sysfs_ops brport_sysfs_ops = { +const struct sysfs_ops brport_sysfs_ops = { .show = brport_show, .store = brport_store, }; diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c index 7c6088140528..3b126d1f8599 100644 --- a/samples/kobject/kset-example.c +++ b/samples/kobject/kset-example.c @@ -87,7 +87,7 @@ static ssize_t foo_attr_store(struct kobject *kobj, } /* Our custom sysfs_ops that we will associate with our ktype later on */ -static struct sysfs_ops foo_sysfs_ops = { +static const struct sysfs_ops foo_sysfs_ops = { .show = foo_attr_show, .store = foo_attr_store, }; -- cgit v1.2.3 From 1426d5a3bd07589534286375998c0c8c6fdc5260 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 28 Jan 2010 13:23:22 +0000 Subject: powerpc: Dynamically allocate pacas On 64-bit kernels we currently have a 512 byte struct paca_struct for each cpu (usually just called "the paca"). Currently they are statically allocated, which means a kernel built for a large number of cpus will waste a lot of space if it's booted on a machine with few cpus. We can avoid that by only allocating the number of pacas we need at boot. However this is complicated by the fact that we need to access the paca before we know how many cpus there are in the system. The solution is to dynamically allocate enough space for NR_CPUS pacas, but then later in boot when we know how many cpus we have, we free any unused pacas. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/paca.h | 18 +++++- arch/powerpc/kernel/head_64.S | 6 +- arch/powerpc/kernel/paca.c | 93 +++++++++++++++++++++++------- arch/powerpc/kernel/prom.c | 3 + arch/powerpc/kernel/setup-common.c | 3 + arch/powerpc/kernel/setup_64.c | 12 ++-- arch/powerpc/platforms/iseries/exception.S | 25 +++++--- 7 files changed, 118 insertions(+), 42 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index d8a693109c82..a011603d4079 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -14,6 +14,9 @@ #define _ASM_POWERPC_PACA_H #ifdef __KERNEL__ +#ifdef CONFIG_PPC64 + +#include #include #include #include @@ -145,8 +148,19 @@ struct paca_struct { #endif }; -extern struct paca_struct paca[]; -extern void initialise_pacas(void); +extern struct paca_struct *paca; +extern __initdata struct paca_struct boot_paca; +extern void initialise_paca(struct paca_struct *new_paca, int cpu); + +extern void allocate_pacas(void); +extern void free_unused_pacas(void); + +#else /* CONFIG_PPC64 */ + +static inline void allocate_pacas(void) { }; +static inline void free_unused_pacas(void) { }; + +#endif /* CONFIG_PPC64 */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PACA_H */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 925807488022..b24b7001ae19 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -219,7 +219,8 @@ generic_secondary_common_init: * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. */ - LOAD_REG_ADDR(r13, paca) /* Get base vaddr of paca array */ + LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ + ld r13,0(r13) /* Get base vaddr of paca array */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ @@ -536,7 +537,8 @@ _GLOBAL(pmac_secondary_start) mtmsrd r3 /* RI on */ /* Set up a paca value for this processor. */ - LOAD_REG_ADDR(r4,paca) /* Get base vaddr of paca array */ + LOAD_REG_ADDR(r4,paca) /* Load paca pointer */ + ld r4,0(r4) /* Get base vaddr of paca array */ mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r4 /* for this processor. */ mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG*/ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index d16b1ea55d44..0c40c6f476fe 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -9,11 +9,15 @@ #include #include +#include +#include #include #include #include #include +#include +#include /* This symbol is provided by the linker - let it fill in the paca * field correctly */ @@ -70,37 +74,82 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = { * processors. The processor VPD array needs one entry per physical * processor (not thread). */ -struct paca_struct paca[NR_CPUS]; +struct paca_struct *paca; EXPORT_SYMBOL(paca); -void __init initialise_pacas(void) -{ - int cpu; +struct paca_struct boot_paca; - /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB - * of the TOC can be addressed using a single machine instruction. - */ +void __init initialise_paca(struct paca_struct *new_paca, int cpu) +{ + /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB + * of the TOC can be addressed using a single machine instruction. + */ unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL; - /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { - struct paca_struct *new_paca = &paca[cpu]; - #ifdef CONFIG_PPC_BOOK3S - new_paca->lppaca_ptr = &lppaca[cpu]; + new_paca->lppaca_ptr = &lppaca[cpu]; #else - new_paca->kernel_pgd = swapper_pg_dir; + new_paca->kernel_pgd = swapper_pg_dir; #endif - new_paca->lock_token = 0x8000; - new_paca->paca_index = cpu; - new_paca->kernel_toc = kernel_toc; - new_paca->kernelbase = (unsigned long) _stext; - new_paca->kernel_msr = MSR_KERNEL; - new_paca->hw_cpu_id = 0xffff; - new_paca->__current = &init_task; + new_paca->lock_token = 0x8000; + new_paca->paca_index = cpu; + new_paca->kernel_toc = kernel_toc; + new_paca->kernelbase = (unsigned long) _stext; + new_paca->kernel_msr = MSR_KERNEL; + new_paca->hw_cpu_id = 0xffff; + new_paca->__current = &init_task; #ifdef CONFIG_PPC_STD_MMU_64 - new_paca->slb_shadow_ptr = &slb_shadow[cpu]; + new_paca->slb_shadow_ptr = &slb_shadow[cpu]; #endif /* CONFIG_PPC_STD_MMU_64 */ +} + +static int __initdata paca_size; + +void __init allocate_pacas(void) +{ + int nr_cpus, cpu, limit; + + /* + * We can't take SLB misses on the paca, and we want to access them + * in real mode, so allocate them within the RMA and also within + * the first segment. On iSeries they must be within the area mapped + * by the HV, which is HvPagesToMap * HVPAGESIZE bytes. + */ + limit = min(0x10000000ULL, lmb.rmo_size); + if (firmware_has_feature(FW_FEATURE_ISERIES)) + limit = min(limit, HvPagesToMap * HVPAGESIZE); + + nr_cpus = NR_CPUS; + /* On iSeries we know we can never have more than 64 cpus */ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + nr_cpus = min(64, nr_cpus); + + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); + + paca = __va(lmb_alloc_base(paca_size, PAGE_SIZE, limit)); + memset(paca, 0, paca_size); + + printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", + paca_size, nr_cpus, paca); + + /* Can't use for_each_*_cpu, as they aren't functional yet */ + for (cpu = 0; cpu < nr_cpus; cpu++) + initialise_paca(&paca[cpu], cpu); +} + +void __init free_unused_pacas(void) +{ + int new_size; + + new_size = PAGE_ALIGN(sizeof(struct paca_struct) * num_possible_cpus()); + + if (new_size >= paca_size) + return; + + lmb_free(__pa(paca) + new_size, paca_size - new_size); + + printk(KERN_DEBUG "Freed %u bytes for unused pacas\n", + paca_size - new_size); - } + paca_size = new_size; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 43238b2054b6..05131d634e73 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -721,6 +722,8 @@ void __init early_init_devtree(void *params) * FIXME .. and the initrd too? */ move_device_tree(); + allocate_pacas(); + DBG("Scanning CPUs ...\n"); /* Retreive CPU related informations from the flat tree diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 03dd6a248198..48f0a008b20b 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -493,6 +494,8 @@ void __init smp_setup_cpu_maps(void) * here will have to be reworked */ cpu_init_thread_core_maps(nthreads); + + free_unused_pacas(); } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6568406b2a30..63547394048c 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -144,9 +144,9 @@ early_param("smt-enabled", early_smt_enabled); #endif /* CONFIG_SMP */ /* Put the paca pointer into r13 and SPRG_PACA */ -void __init setup_paca(int cpu) +static void __init setup_paca(struct paca_struct *new_paca) { - local_paca = &paca[cpu]; + local_paca = new_paca; mtspr(SPRN_SPRG_PACA, local_paca); #ifdef CONFIG_PPC_BOOK3E mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); @@ -176,14 +176,12 @@ void __init early_setup(unsigned long dt_ptr) { /* -------- printk is _NOT_ safe to use here ! ------- */ - /* Fill in any unititialised pacas */ - initialise_pacas(); - /* Identify CPU type */ identify_cpu(0, mfspr(SPRN_PVR)); /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ - setup_paca(0); + initialise_paca(&boot_paca, 0); + setup_paca(&boot_paca); /* Initialize lockdep early or else spinlocks will blow */ lockdep_init(); @@ -203,7 +201,7 @@ void __init early_setup(unsigned long dt_ptr) early_init_devtree(__va(dt_ptr)); /* Now we know the logical id of our boot cpu, setup the paca. */ - setup_paca(boot_cpuid); + setup_paca(&paca[boot_cpuid]); /* Fix up paca fields required for the boot cpu */ get_paca()->cpu_start = 1; diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index 5369653dcf6a..fba5bf915073 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -43,17 +43,14 @@ system_reset_iSeries: LOAD_REG_ADDR(r23, alpaca) li r0,ALPACA_SIZE sub r23,r13,r23 - divdu r23,r23,r0 /* r23 has cpu number */ - LOAD_REG_ADDR(r13, paca) - mulli r0,r23,PACA_SIZE - add r13,r13,r0 - mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ - mfmsr r24 - ori r24,r24,MSR_RI - mtmsrd r24 /* RI on */ - mr r24,r23 + divdu r24,r23,r0 /* r24 has cpu number */ cmpwi 0,r24,0 /* Are we processor 0? */ bne 1f + LOAD_REG_ADDR(r13, boot_paca) + mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ + mfmsr r23 + ori r23,r23,MSR_RI + mtmsrd r23 /* RI on */ b .__start_initialization_iSeries /* Start up the first processor */ 1: mfspr r4,SPRN_CTRLF li r5,CTRL_RUNLATCH /* Turn off the run light */ @@ -86,6 +83,16 @@ system_reset_iSeries: #endif 2: + /* Load our paca now that it's been allocated */ + LOAD_REG_ADDR(r13, paca) + ld r13,0(r13) + mulli r0,r24,PACA_SIZE + add r13,r13,r0 + mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ + mfmsr r23 + ori r23,r23,MSR_RI + mtmsrd r23 /* RI on */ + HMT_LOW #ifdef CONFIG_SMP lbz r23,PACAPROCSTART(r13) /* Test if this processor -- cgit v1.2.3 From 856f70a368022645a08fbecc5d30ec218f13232d Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Tue, 23 Feb 2010 09:43:17 +0000 Subject: powerpc/booke: Fix a couple typos in the advanced ptrace code powerpc/booke: Fix a couple typos in the advanced ptrace code Found and fixed a couple typos in the advanced ptrace patches. (These patches are currently in benh's next tree.) Signed-off-by: Dave Kleikamp Cc: Benjamin Herrenschmidt Cc: linuxppc-dev list Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/reg_booke.h | 4 ++-- arch/powerpc/kernel/ptrace.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 8808d307fe7e..414d434a66d0 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -421,8 +421,8 @@ /* Bit definitions related to the DBCR2. */ #define DBCR2_DAC1US 0xC0000000 /* Data Addr Cmp 1 Sup/User */ #define DBCR2_DAC1ER 0x30000000 /* Data Addr Cmp 1 Eff/Real */ -#define DBCR2_DAC2US 0x00000000 /* Data Addr Cmp 2 Sup/User */ -#define DBCR2_DAC2ER 0x00000000 /* Data Addr Cmp 2 Eff/Real */ +#define DBCR2_DAC2US 0x0C000000 /* Data Addr Cmp 2 Sup/User */ +#define DBCR2_DAC2ER 0x03000000 /* Data Addr Cmp 2 Eff/Real */ #define DBCR2_DAC12M 0x00800000 /* DAC 1-2 range enable */ #define DBCR2_DAC12MM 0x00400000 /* DAC 1-2 Mask mode*/ #define DBCR2_DAC12MX 0x00C00000 /* DAC 1-2 range eXclusive */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index d9b05866615f..0efa2e3f40c6 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1070,7 +1070,7 @@ static int del_dac(struct task_struct *child, int slot) child->thread.dvc1 = 0; #endif } else if (slot == 2) { - if (child->thread.dac1 == 0) + if (child->thread.dac2 == 0) return -ENOENT; #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE -- cgit v1.2.3 From 8dbce53cc249a76e9450708d291fce5a7e29c6a1 Mon Sep 17 00:00:00 2001 From: Vaidyanathan Srinivasan Date: Mon, 1 Mar 2010 02:58:09 +0000 Subject: powerpc: Reset kernel stack on cpu online from cede state Cpu hotplug (offline) without dlpar operation will place cpu in cede state and the extended_cede_processor() function will return when resumed. Kernel stack pointer needs to be reset before start_secondary() is called to continue the online operation. Added new function start_secondary_resume() to do the above steps. Signed-off-by: Vaidyanathan Srinivasan Cc: Gautham R Shenoy Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/head_64.S | 11 +++++++++++ arch/powerpc/platforms/pseries/hotplug-cpu.c | 9 ++++----- arch/powerpc/platforms/pseries/offline_states.h | 1 + 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b24b7001ae19..bed9a29ee383 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -617,6 +617,17 @@ _GLOBAL(start_secondary_prolog) std r3,0(r1) /* Zero the stack frame pointer */ bl .start_secondary b . +/* + * Reset stack pointer and call start_secondary + * to continue with online operation when woken up + * from cede in cpu offline. + */ +_GLOBAL(start_secondary_resume) + ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ + li r3,0 + std r3,0(r1) /* Zero the stack frame pointer */ + bl .start_secondary + b . #endif /* diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index d1b124e44d77..349e0af9389a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -146,12 +146,11 @@ static void pseries_mach_cpu_die(void) unregister_slb_shadow(hwcpu, __pa(get_slb_shadow())); /* - * NOTE: Calling start_secondary() here for now to - * start new context. - * However, need to do it cleanly by resetting the - * stack pointer. + * Call to start_secondary_resume() will not return. + * Kernel stack will be reset and start_secondary() + * will be called to continue the online operation. */ - start_secondary(); + start_secondary_resume(); } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h index 202d8692c6a2..75a6f480d931 100644 --- a/arch/powerpc/platforms/pseries/offline_states.h +++ b/arch/powerpc/platforms/pseries/offline_states.h @@ -35,4 +35,5 @@ static inline void set_default_offline_state(int cpu) extern enum cpu_state_vals get_preferred_offline_state(int cpu); extern int start_secondary(void); +extern void start_secondary_resume(void); #endif -- cgit v1.2.3 From 30124d11097e371e42052144d8a3f4a78d26e09f Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Mon, 1 Mar 2010 04:57:34 +0000 Subject: powerpc/booke: Fix breakpoint/watchpoint one-shot behavior Another fix for the extended ptrace patches in the -next tree. The handling of breakpoints and watchpoints is inconsistent. When a breakpoint or watchpoint is hit, the interrupt handler is clearing the proper bits in the dbcr* registers, but leaving the dac* and iac* registers alone. The ptrace code to delete the break/watchpoints checks the dac* and iac* registers for zero to determine if they are enabled. Instead, they should check the dbcr* bits. Signed-off-by: Dave Kleikamp Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ptrace.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 0efa2e3f40c6..ed2cfe17d25e 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -940,7 +940,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) { switch (slot) { case 1: - if (child->thread.iac1 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC1) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) { @@ -952,7 +952,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) child->thread.dbcr0 &= ~DBCR0_IAC1; break; case 2: - if (child->thread.iac2 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC2) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) @@ -963,7 +963,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) break; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 case 3: - if (child->thread.iac3 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC3) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) { @@ -975,7 +975,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) child->thread.dbcr0 &= ~DBCR0_IAC3; break; case 4: - if (child->thread.iac4 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC4) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) @@ -1054,7 +1054,7 @@ static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) static int del_dac(struct task_struct *child, int slot) { if (slot == 1) { - if (child->thread.dac1 == 0) + if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) return -ENOENT; child->thread.dac1 = 0; @@ -1070,7 +1070,7 @@ static int del_dac(struct task_struct *child, int slot) child->thread.dvc1 = 0; #endif } else if (slot == 2) { - if (child->thread.dac2 == 0) + if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) return -ENOENT; #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE -- cgit v1.2.3 From dc1d628a67a8f042e711ea5accc0beedc3ef0092 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Mar 2010 15:55:04 +0100 Subject: perf: Provide generic perf_sample_data initialization This makes it easier to extend perf_sample_data and fixes a bug on arm and sparc, which failed to set ->raw to NULL, which can cause crashes when combined with PERF_SAMPLE_RAW. It also optimizes PowerPC and tracepoint, because the struct initialization is forced to zero out the whole structure. Signed-off-by: Peter Zijlstra Acked-by: Jean Pihet Reviewed-by: Frederic Weisbecker Acked-by: David S. Miller Cc: Jamie Iles Cc: Paul Mackerras Cc: Stephane Eranian Cc: stable@kernel.org LKML-Reference: <20100304140100.315416040@chello.nl> Signed-off-by: Ingo Molnar --- arch/arm/kernel/perf_event.c | 4 ++-- arch/powerpc/kernel/perf_event.c | 8 ++++---- arch/sparc/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 3 +-- arch/x86/kernel/cpu/perf_event_intel.c | 6 ++---- include/linux/perf_event.h | 7 +++++++ kernel/perf_event.c | 21 ++++++++------------- 7 files changed, 25 insertions(+), 26 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index c54ceb3d1f97..3875d99cc40f 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -965,7 +965,7 @@ armv6pmu_handle_irq(int irq_num, */ armv6_pmcr_write(pmcr); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { @@ -1945,7 +1945,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index b6cf8f1f4d35..5120bd44f69a 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * Finally record data if requested. */ if (record) { - struct perf_sample_data data = { - .addr = ~0ULL, - .period = event->hw.last_period, - }; + struct perf_sample_data data; + + perf_sample_data_init(&data, ~0ULL); + data.period = event->hw.last_period; if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 9f2b2bac8b2b..6504208f375f 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1189,7 +1189,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 97cddbf32936..42aafd11e170 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1097,8 +1097,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 73102df8bfc1..44b60c852107 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -590,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void) ds->bts_index = ds->bts_buffer_base; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - data.addr = 0; - data.raw = NULL; regs.ip = 0; /* @@ -742,8 +741,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 ack, status; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 90e0521b1690..6f8cd7da1a01 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -801,6 +801,13 @@ struct perf_sample_data { struct perf_raw_record *raw; }; +static inline +void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +{ + data->addr = addr; + data->raw = NULL; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e68745053013..4393b9e73740 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4108,8 +4108,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, if (rctx < 0) return; - data.addr = addr; - data.raw = NULL; + perf_sample_data_init(&data, addr); do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); @@ -4154,11 +4153,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) struct perf_event *event; u64 period; - event = container_of(hrtimer, struct perf_event, hw.hrtimer); + event = container_of(hrtimer, struct perf_event, hw.hrtimer); event->pmu->read(event); - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; regs = get_irq_regs(); /* @@ -4322,17 +4320,15 @@ static const struct pmu perf_ops_task_clock = { void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size) { + struct pt_regs *regs = get_irq_regs(); + struct perf_sample_data data; struct perf_raw_record raw = { .size = entry_size, .data = record, }; - struct perf_sample_data data = { - .addr = addr, - .raw = &raw, - }; - - struct pt_regs *regs = get_irq_regs(); + perf_sample_data_init(&data, addr); + data.raw = &raw; if (!regs) regs = task_pt_regs(current); @@ -4448,8 +4444,7 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; - sample.raw = NULL; - sample.addr = bp->attr.bp_addr; + perf_sample_data_init(&sample, bp->attr.bp_addr); if (!perf_exclude_event(bp, regs)) perf_swevent_add(bp, 1, 1, &sample, regs); -- cgit v1.2.3 From 3f6da3905398826d85731247e7fbcf53400c18bd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Mar 2010 13:01:18 +0100 Subject: perf: Rework and fix the arch CPU-hotplug hooks Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug notifiers. This has the advantage of reducing the static weak interface as well as exposing all hotplug actions to the PMU. Use this to fix x86 hotplug usage where we did things in ONLINE which should have been done in UP_PREPARE or STARTING. Signed-off-by: Peter Zijlstra Cc: Paul Mundt Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo LKML-Reference: <20100305154128.736225361@chello.nl> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/perf_event.c | 21 +++++++++- arch/sh/kernel/perf_event.c | 20 +++++++++- arch/x86/kernel/cpu/perf_event.c | 70 ++++++++++++++++++++-------------- arch/x86/kernel/cpu/perf_event_amd.c | 60 ++++++++++++----------------- arch/x86/kernel/cpu/perf_event_intel.c | 5 ++- include/linux/perf_event.h | 16 ++++++++ kernel/perf_event.c | 15 -------- 7 files changed, 126 insertions(+), 81 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 5120bd44f69a..fbe101d7505d 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1287,7 +1287,7 @@ static void perf_event_interrupt(struct pt_regs *regs) irq_exit(); } -void hw_perf_event_setup(int cpu) +static void power_pmu_setup(int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); @@ -1297,6 +1297,23 @@ void hw_perf_event_setup(int cpu) cpuhw->mmcr[0] = MMCR0_FC; } +static int __cpuinit +power_pmu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + power_pmu_setup(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + int register_power_pmu(struct power_pmu *pmu) { if (ppmu) @@ -1314,5 +1331,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ + perf_cpu_notifier(power_pmu_notifier); + return 0; } diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7ff0943e7a08..9f253e9cce01 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -275,13 +275,30 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) return &pmu; } -void hw_perf_event_setup(int cpu) +static void sh_pmu_setup(int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); memset(cpuhw, 0, sizeof(struct cpu_hw_events)); } +static int __cpuinit +sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + sh_pmu_setup(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + void hw_perf_enable(void) { if (!sh_pmu_initialized()) @@ -308,5 +325,6 @@ int register_sh_pmu(struct sh_pmu *pmu) WARN_ON(pmu->num_events > MAX_HWEVENTS); + perf_cpu_notifier(sh_pmu_notifier); return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 42aafd11e170..585d5608ae6b 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -157,6 +157,11 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + + void (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); }; static struct x86_pmu x86_pmu __read_mostly; @@ -293,7 +298,7 @@ static inline bool bts_available(void) return x86_pmu.enable_bts != NULL; } -static inline void init_debug_store_on_cpu(int cpu) +static void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -305,7 +310,7 @@ static inline void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static inline void fini_debug_store_on_cpu(int cpu) +static void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -1337,6 +1342,39 @@ undo: #include "perf_event_p6.c" #include "perf_event_intel.c" +static int __cpuinit +x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + if (x86_pmu.cpu_prepare) + x86_pmu.cpu_prepare(cpu); + break; + + case CPU_STARTING: + if (x86_pmu.cpu_starting) + x86_pmu.cpu_starting(cpu); + break; + + case CPU_DYING: + if (x86_pmu.cpu_dying) + x86_pmu.cpu_dying(cpu); + break; + + case CPU_DEAD: + if (x86_pmu.cpu_dead) + x86_pmu.cpu_dead(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + static void __init pmu_check_apic(void) { if (cpu_has_apic) @@ -1415,6 +1453,8 @@ void __init init_hw_perf_events(void) pr_info("... max period: %016Lx\n", x86_pmu.max_period); pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); pr_info("... event mask: %016Lx\n", perf_event_mask); + + perf_cpu_notifier(x86_pmu_notifier); } static inline void x86_pmu_read(struct perf_event *event) @@ -1674,29 +1714,3 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } - -void hw_perf_event_setup_online(int cpu) -{ - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_online(cpu); - break; - default: - return; - } -} - -void hw_perf_event_setup_offline(int cpu) -{ - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_offline(cpu); - break; - default: - return; - } -} diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 8f3dbfda3c4f..014528ba7d57 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -271,28 +271,6 @@ done: return &emptyconstraint; } -static __initconst struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints, - .put_event_constraints = amd_put_event_constraints -}; - static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) { struct amd_nb *nb; @@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu) raw_spin_unlock(&amd_nb_lock); } +static __initconst struct x86_pmu amd_pmu = { + .name = "AMD", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, + .event_map = amd_pmu_event_map, + .raw_event = amd_pmu_raw_event, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_events = 4, + .event_bits = 48, + .event_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints, + .put_event_constraints = amd_put_event_constraints, + + .cpu_prepare = amd_pmu_cpu_online, + .cpu_dead = amd_pmu_cpu_offline, +}; + static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -390,11 +393,6 @@ static __init int amd_pmu_init(void) memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - /* - * explicitly initialize the boot cpu, other cpus will get - * the cpu hotplug callbacks from smp_init() - */ - amd_pmu_cpu_online(smp_processor_id()); return 0; } @@ -405,12 +403,4 @@ static int amd_pmu_init(void) return 0; } -static void amd_pmu_cpu_online(int cpu) -{ -} - -static void amd_pmu_cpu_offline(int cpu) -{ -} - #endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 44b60c852107..12e811a7d747 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -870,7 +870,10 @@ static __initconst struct x86_pmu intel_pmu = { .max_period = (1ULL << 31) - 1, .enable_bts = intel_pmu_enable_bts, .disable_bts = intel_pmu_disable_bts, - .get_event_constraints = intel_get_event_constraints + .get_event_constraints = intel_get_event_constraints, + + .cpu_starting = init_debug_store_on_cpu, + .cpu_dying = fini_debug_store_on_cpu, }; static __init int intel_pmu_init(void) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6f8cd7da1a01..80acbf3d5de1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -936,5 +936,21 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_output_put(handle, x) \ perf_output_copy((handle), &(x), sizeof(x)) +/* + * This has to have a higher priority than migration_notifier in sched.c. + */ +#define perf_cpu_notifier(fn) \ +do { \ + static struct notifier_block fn##_nb __cpuinitdata = \ + { .notifier_call = fn, .priority = 20 }; \ + fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_STARTING, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ + (void *)(unsigned long)smp_processor_id()); \ + register_cpu_notifier(&fn##_nb); \ +} while (0) + #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 4393b9e73740..73329dedb5ad 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -81,10 +81,6 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event) void __weak hw_perf_disable(void) { barrier(); } void __weak hw_perf_enable(void) { barrier(); } -void __weak hw_perf_event_setup(int cpu) { barrier(); } -void __weak hw_perf_event_setup_online(int cpu) { barrier(); } -void __weak hw_perf_event_setup_offline(int cpu) { barrier(); } - int __weak hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, @@ -5382,8 +5378,6 @@ static void __cpuinit perf_event_init_cpu(int cpu) spin_lock(&perf_resource_lock); cpuctx->max_pertask = perf_max_events - perf_reserved_percpu; spin_unlock(&perf_resource_lock); - - hw_perf_event_setup(cpu); } #ifdef CONFIG_HOTPLUG_CPU @@ -5423,20 +5417,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) perf_event_init_cpu(cpu); break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - hw_perf_event_setup_online(cpu); - break; - case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: perf_event_exit_cpu(cpu); break; - case CPU_DEAD: - hw_perf_event_setup_offline(cpu); - break; - default: break; } -- cgit v1.2.3 From 85cfabbcd10f8d112feee6e2ec64ee78033b6d3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Mar 2010 13:06:56 +0100 Subject: perf, ppc: Fix compile error due to new cpu notifiers Fix: arch/powerpc/kernel/perf_event.c:1334: error: 'power_pmu_notifier' undeclared (first use in this function) arch/powerpc/kernel/perf_event.c:1334: error: (Each undeclared identifier is reported only once arch/powerpc/kernel/perf_event.c:1334: error: for each function it appears in.) arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'power_pmu_notifier' arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'register_cpu_notifier' Due to commit 3f6da390 (perf: Rework and fix the arch CPU-hotplug hooks). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/perf_event.c | 2 +- include/linux/perf_event.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index fbe101d7505d..08460a2e9f41 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1298,7 +1298,7 @@ static void power_pmu_setup(int cpu) } static int __cpuinit -power_pmu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 70cffd052c04..95477038a72a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -453,6 +453,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 -- cgit v1.2.3 From baed7fc9b580bd3fb8252ff1d9b36eaf1f86b670 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:18 -0800 Subject: Add generic sys_ipc wrapper Add a generic implementation of the ipc demultiplexer syscall. Except for s390 and sparc64 all implementations of the sys_ipc are nearly identical. There are slight differences in the types of the parameters, where mips and powerpc as the only 64-bit architectures with sys_ipc use unsigned long for the "third" argument as it gets casted to a pointer later, while it traditionally is an "int" like most other paramters. frv goes even further and uses unsigned long for all parameters execept for "ptr" which is a pointer type everywhere. The change from int to unsigned long for "third" and back to "int" for the others on frv should be fine due to the in-register calling conventions for syscalls (we already had a similar issue with the generic sys_ptrace), but I'd prefer to have the arch maintainers looks over this in details. Except for that h8300, m68k and m68knommu lack an impplementation of the semtimedop sub call which this patch adds, and various architectures have gets used - at least on i386 it seems superflous as the compat code on x86-64 and ia64 doesn't even bother to implement it. [akpm@linux-foundation.org: add sys_ipc to sys_ni.c] Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Reviewed-by: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Acked-by: Jesper Nilsson Acked-by: Russell King Acked-by: David Howells Acked-by: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/unistd.h | 1 + arch/arm/kernel/sys_arm.c | 82 -------------------------- arch/arm/kernel/sys_oabi-compat.c | 3 - arch/cris/include/asm/unistd.h | 1 + arch/cris/kernel/sys_cris.c | 78 ------------------------- arch/frv/include/asm/unistd.h | 1 + arch/frv/kernel/sys_frv.c | 89 ---------------------------- arch/h8300/include/asm/unistd.h | 1 + arch/h8300/kernel/sys_h8300.c | 88 ---------------------------- arch/m32r/include/asm/unistd.h | 1 + arch/m32r/kernel/sys_m32r.c | 81 -------------------------- arch/m68k/include/asm/unistd.h | 1 + arch/m68k/kernel/sys_m68k.c | 81 -------------------------- arch/m68knommu/kernel/sys_m68k.c | 86 --------------------------- arch/mips/include/asm/unistd.h | 1 + arch/mips/kernel/syscall.c | 88 ---------------------------- arch/mn10300/include/asm/unistd.h | 1 + arch/mn10300/kernel/sys_mn10300.c | 88 ---------------------------- arch/powerpc/include/asm/syscalls.h | 2 - arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/syscalls.c | 94 ------------------------------ arch/s390/kernel/entry.h | 2 +- arch/s390/kernel/sys_s390.c | 2 +- arch/s390/kernel/syscalls.S | 2 +- arch/sh/include/asm/syscalls.h | 2 - arch/sh/include/asm/unistd_32.h | 1 + arch/sh/include/asm/unistd_64.h | 1 + arch/sh/kernel/sys_sh.c | 104 --------------------------------- arch/sparc/include/asm/unistd.h | 4 +- arch/sparc/kernel/sys_sparc_32.c | 113 ------------------------------------ arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/sparc/kernel/systbls.h | 2 +- arch/sparc/kernel/systbls_64.S | 2 +- arch/um/sys-i386/syscalls.c | 86 --------------------------- arch/x86/include/asm/syscalls.h | 1 - arch/x86/include/asm/unistd_32.h | 1 + arch/x86/kernel/sys_i386_32.c | 85 --------------------------- include/linux/syscalls.h | 2 + ipc/Makefile | 2 +- ipc/syscall.c | 99 +++++++++++++++++++++++++++++++ kernel/sys_ni.c | 1 + 41 files changed, 124 insertions(+), 1259 deletions(-) create mode 100644 ipc/syscall.c (limited to 'arch/powerpc/kernel') diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index e6eeb2d29953..dd2bf53000fe 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -448,6 +448,7 @@ #if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) #define __ARCH_WANT_SYS_TIME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_UTIME diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index a2e0e6f2ea7f..4350f75e578c 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -28,88 +28,6 @@ #include #include -#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, int third, - void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user(&tmp,(struct ipc_kludge __user *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, (struct msqid_ds __user *)ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *)ptr, second, &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong __user *)third); - } - case 1: /* Of course, we don't support iBCS2! */ - return -EINVAL; - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} -#endif - /* Fork a new task - this creates a new program thread. * This is called indirectly via a small wrapper */ diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index d59a0cd537f0..33ff678e32f2 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -346,9 +346,6 @@ asmlinkage long sys_oabi_semop(int semid, struct oabi_sembuf __user *tsops, return sys_oabi_semtimedop(semid, tsops, nsops, NULL); } -extern asmlinkage int sys_ipc(uint call, int first, int second, int third, - void __user *ptr, long fifth); - asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, void __user *ptr, long fifth) { diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h index 8cffd22623fd..f6fad83b3a8c 100644 --- a/arch/cris/include/asm/unistd.h +++ b/arch/cris/include/asm/unistd.h @@ -352,6 +352,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/cris/kernel/sys_cris.c b/arch/cris/kernel/sys_cris.c index 22f9d6cd947f..7aa036ec78ff 100644 --- a/arch/cris/kernel/sys_cris.c +++ b/arch/cris/kernel/sys_cris.c @@ -33,81 +33,3 @@ sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, /* bug(?): 8Kb pages here */ return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. (same as arch/i386) - */ - -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h index be6ef0f5cd42..b28da499e22a 100644 --- a/arch/frv/include/asm/unistd.h +++ b/arch/frv/include/asm/unistd.h @@ -354,6 +354,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM /* #define __ARCH_WANT_SYS_GETHOSTNAME */ +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE /* #define __ARCH_WANT_SYS_SGETMASK */ /* #define __ARCH_WANT_SYS_SIGNAL */ diff --git a/arch/frv/kernel/sys_frv.c b/arch/frv/kernel/sys_frv.c index 1d3d4c9e2521..9c4980825bbb 100644 --- a/arch/frv/kernel/sys_frv.c +++ b/arch/frv/kernel/sys_frv.c @@ -42,92 +42,3 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff >> (PAGE_SHIFT - 12)); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage long sys_ipc(unsigned long call, - unsigned long first, - unsigned long second, - unsigned long third, - void __user *ptr, - unsigned long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat (first, (char __user *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h index 54dab4726954..50f2c5a36591 100644 --- a/arch/h8300/include/asm/unistd.h +++ b/arch/h8300/include/asm/unistd.h @@ -336,6 +336,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index 1f13fd6e5309..f9b3f44da69f 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -26,94 +26,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, (struct sembuf *)ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void **) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, - (struct ipc_kludge *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char *) ptr, - second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong *) third); - } - } - case SHMDT: - return sys_shmdt ((char *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds *) ptr); - default: - return -EINVAL; - } - - return -EINVAL; -} - /* sys_cacheflush -- no support. */ asmlinkage int sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h index cf701c933249..76125777483c 100644 --- a/arch/m32r/include/asm/unistd.h +++ b/arch/m32r/include/asm/unistd.h @@ -339,6 +339,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index d3c865c5a6ba..cf2e7279ce9b 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -76,87 +76,6 @@ asmlinkage int sys_tas(int __user *addr) return oldval; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds __user *) ptr); - case SHMAT: { - ulong raddr; - - if (!access_ok(VERIFY_WRITE, (ulong __user *) third, - sizeof(ulong))) - return -EFAULT; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - asmlinkage int sys_uname(struct old_utsname __user * name) { int err; diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index d801154310ea..60b15d0aa072 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -351,6 +351,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 7b309e7b6cef..77896692eb0a 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -46,87 +46,6 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user *__user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -ENOSYS; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, ptr, second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, ptr, sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, ptr); - default: - return -ENOSYS; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - } - case SHMDT: - return sys_shmdt (ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, ptr); - default: - return -ENOSYS; - } - - return -EINVAL; -} - /* Convert virtual (user) address VADDR to physical address PADDR */ #define virt_to_phys_040(vaddr) \ ({ \ diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c index 3e371cc9fd91..d65e9c4c930c 100644 --- a/arch/m68knommu/kernel/sys_m68k.c +++ b/arch/m68knommu/kernel/sys_m68k.c @@ -27,92 +27,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, (struct sembuf *)ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void **) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, - (struct ipc_kludge *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - } - case SHMDT: - return sys_shmdt (ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, ptr); - default: - return -ENOSYS; - } - - return -EINVAL; -} - /* sys_cacheflush -- flush (part of) the processor cache. */ asmlinkage int sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 65c679ecbe6b..97fe472095f2 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -1004,6 +1004,7 @@ #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_UTIME diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3f7f466190b4..257bf0141775 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -406,94 +406,6 @@ _sys_sysmips(nabi_no_regargs struct pt_regs regs) return -EINVAL; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, int, second, - unsigned long, third, void __user *, ptr, long, fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user *__user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, - (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - unsigned long raddr; - ret = do_shmat(first, (char __user *) ptr, second, - &raddr); - if (ret) - return ret; - return put_user(raddr, (unsigned long __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat(first, (char __user *) ptr, second, - (unsigned long *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - /* * No implemented yet ... */ diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h index d13a56e99bad..9d056f515929 100644 --- a/arch/mn10300/include/asm/unistd.h +++ b/arch/mn10300/include/asm/unistd.h @@ -363,6 +363,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c index bef69d6daf15..815f1355fad4 100644 --- a/arch/mn10300/kernel/sys_mn10300.c +++ b/arch/mn10300/kernel/sys_mn10300.c @@ -31,91 +31,3 @@ asmlinkage long old_mmap(unsigned long addr, unsigned long len, return -EINVAL; return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage long sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, - (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *) ptr, second, - &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat(first, (char __user *) ptr, second, - (ulong *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -EINVAL; - } -} diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index eb8eb400c664..23bb74e7f946 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -35,8 +35,6 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act, struct sigaction __user *oact, size_t sigsetsize); -asmlinkage int sys_ipc(uint call, int first, unsigned long second, - long third, void __user *ptr, long fifth); asmlinkage long ppc64_personality(unsigned long personality); asmlinkage int ppc_rtas(struct rtas_args __user *uargs); asmlinkage time_t sys64_time(time_t __user * tloc); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index f6ca76176766..c13821fe8741 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -364,6 +364,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 3370e62e43d4..5251221e7a5a 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -42,100 +42,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -int sys_ipc(uint call, int first, unsigned long second, long third, - void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - ret = -ENOSYS; - switch (call) { - case SEMOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, NULL); - break; - case SEMTIMEDOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, - (const struct timespec __user *) fifth); - break; - case SEMGET: - ret = sys_semget (first, (int)second, third); - break; - case SEMCTL: { - union semun fourth; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = get_user(fourth.__pad, (void __user * __user *)ptr))) - break; - ret = sys_semctl(first, (int)second, third, fourth); - break; - } - case MSGSND: - ret = sys_msgsnd(first, (struct msgbuf __user *)ptr, - (size_t)second, third); - break; - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp)) ? -EFAULT : 0)) - break; - ret = sys_msgrcv(first, tmp.msgp, (size_t) second, - tmp.msgtyp, third); - break; - } - default: - ret = sys_msgrcv (first, (struct msgbuf __user *) ptr, - (size_t)second, fifth, third); - break; - } - break; - case MSGGET: - ret = sys_msgget((key_t)first, (int)second); - break; - case MSGCTL: - ret = sys_msgctl(first, (int)second, - (struct msqid_ds __user *)ptr); - break; - case SHMAT: { - ulong raddr; - ret = do_shmat(first, (char __user *)ptr, (int)second, &raddr); - if (ret) - break; - ret = put_user(raddr, (ulong __user *) third); - break; - } - case SHMDT: - ret = sys_shmdt((char __user *)ptr); - break; - case SHMGET: - ret = sys_shmget(first, (size_t)second, third); - break; - case SHMCTL: - ret = sys_shmctl(first, (int)second, - (struct shmid_ds __user *)ptr); - break; - } - - return ret; -} - static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long off, int shift) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 5de54d2af0b2..15fd68b196c0 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -30,7 +30,7 @@ struct fadvise64_64_args; struct old_sigaction; long sys_mmap2(struct s390_mmap_arg_struct __user *arg); -long sys_ipc(uint call, int first, unsigned long second, +long sys_s390_ipc(uint call, int first, unsigned long second, unsigned long third, void __user *ptr); long sys_s390_newuname(struct new_utsname __user *name); long sys_s390_personality(unsigned long personality); diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index b2563509b5a9..b8b78092ab7c 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -64,7 +64,7 @@ out: * * This is really horribly ugly. */ -SYSCALL_DEFINE5(ipc, uint, call, int, first, unsigned long, second, +SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, unsigned long, third, void __user *, ptr) { struct ipc_kludge tmp; diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 2a24766567af..990ac8b321c8 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -125,7 +125,7 @@ NI_SYSCALL /* vm86old for i386 */ SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4_wrapper) SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper) /* 115 */ SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) -SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper) +SYSCALL(sys_s390_ipc,sys_s390_ipc,sys32_ipc_wrapper) SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h index c1e2b8deb837..c1ce2862f7be 100644 --- a/arch/sh/include/asm/syscalls.h +++ b/arch/sh/include/asm/syscalls.h @@ -11,8 +11,6 @@ asmlinkage int old_mmap(unsigned long addr, unsigned long len, asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth); asmlinkage int sys_uname(struct old_utsname __user *name); #ifdef CONFIG_SUPERH32 diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index 365744b05269..a48f65e2e429 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -358,6 +358,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h index 25de158aac3a..7709b2b8f752 100644 --- a/arch/sh/include/asm/unistd_64.h +++ b/arch/sh/include/asm/unistd_64.h @@ -398,6 +398,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 71399cde03b5..c18cfaa67fdd 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -53,110 +53,6 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMTIMEDOP) - switch (call) { - case SEMOP: - return sys_semtimedop(first, - (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, - (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: - { - struct ipc_kludge tmp; - - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds __user *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, - second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat (first, (char __user *) ptr, - second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -EINVAL; - } - - return -EINVAL; -} - /* sys_cacheflush -- flush (part of) the processor cache. */ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, int op) { diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index cb4b9bfd0d87..d0b3b01ac9d4 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -432,7 +432,9 @@ #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#ifndef __32bit_syscall_numbers__ +#ifdef __32bit_syscall_numbers__ +#define __ARCH_WANT_SYS_IPC +#else #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #endif diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 3a82e65d8db2..ee995b7dae7e 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -98,119 +98,6 @@ out: return error; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ - -asmlinkage int sys_ipc (uint call, int first, int second, int third, void __user *ptr, long fifth) -{ - int version, err; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - goto out; - case SEMTIMEDOP: - err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, (const struct timespec __user *) fifth); - goto out; - case SEMGET: - err = sys_semget (first, second, third); - goto out; - case SEMCTL: { - union semun fourth; - err = -EINVAL; - if (!ptr) - goto out; - err = -EFAULT; - if (get_user(fourth.__pad, - (void __user * __user *)ptr)) - goto out; - err = sys_semctl (first, second, third, fourth); - goto out; - } - default: - err = -ENOSYS; - goto out; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - err = sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - goto out; - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - err = -EINVAL; - if (!ptr) - goto out; - err = -EFAULT; - if (copy_from_user(&tmp, (struct ipc_kludge __user *) ptr, sizeof (tmp))) - goto out; - err = sys_msgrcv (first, tmp.msgp, second, tmp.msgtyp, third); - goto out; - } - case 1: default: - err = sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - goto out; - } - case MSGGET: - err = sys_msgget ((key_t) first, second); - goto out; - case MSGCTL: - err = sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - goto out; - default: - err = -ENOSYS; - goto out; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - case 0: default: { - ulong raddr; - err = do_shmat (first, (char __user *) ptr, second, &raddr); - if (err) - goto out; - err = -EFAULT; - if (put_user (raddr, (ulong __user *) third)) - goto out; - err = 0; - goto out; - } - case 1: /* iBCS2 emulator entry point */ - err = -EINVAL; - goto out; - } - case SHMDT: - err = sys_shmdt ((char __user *)ptr); - goto out; - case SHMGET: - err = sys_shmget (first, second, third); - goto out; - case SHMCTL: - err = sys_shmctl (first, second, (struct shmid_ds __user *) ptr); - goto out; - default: - err = -ENOSYS; - goto out; - } - else - err = -ENOSYS; -out: - return err; -} - int sparc_mmap_check(unsigned long addr, unsigned long len) { if (ARCH_SUN4C && diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index cb1bef6f14b7..45410e939628 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -426,7 +426,7 @@ out: * This is really horribly ugly. */ -SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, +SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second, unsigned long, third, void __user *, ptr, long, fifth) { long err; diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h index 68312fe8da74..2c331c37e748 100644 --- a/arch/sparc/kernel/systbls.h +++ b/arch/sparc/kernel/systbls.h @@ -10,7 +10,7 @@ struct new_utsname; extern asmlinkage unsigned long sys_getpagesize(void); extern asmlinkage long sparc_pipe(struct pt_regs *regs); -extern asmlinkage long sys_ipc(unsigned int call, int first, +extern asmlinkage long sys_sparc_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 17614251fb6d..30ca2b1d3a17 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -136,7 +136,7 @@ sys_call_table: /*200*/ .word sys_ssetmask, sys_nis_syscall, sys_newlstat, sys_uselib, sys_nis_syscall .word sys_readahead, sys_socketcall, sys_syslog, sys_lookup_dcookie, sys_fadvise64 /*210*/ .word sys_fadvise64_64, sys_tgkill, sys_waitpid, sys_swapoff, sys_sysinfo - .word sys_ipc, sys_nis_syscall, sys_clone, sys_ioprio_get, sys_adjtimex + .word sys_sparc_ipc, sys_nis_syscall, sys_clone, sys_ioprio_get, sys_adjtimex /*220*/ .word sys_nis_syscall, sys_ni_syscall, sys_delete_module, sys_ni_syscall, sys_getpgid .word sys_bdflush, sys_sysfs, sys_nis_syscall, sys_setfsuid, sys_setfsgid /*230*/ .word sys_select, sys_nis_syscall, sys_splice, sys_stime, sys_statfs64 diff --git a/arch/um/sys-i386/syscalls.c b/arch/um/sys-i386/syscalls.c index d0aa8f125ee6..70ca357393b8 100644 --- a/arch/um/sys-i386/syscalls.c +++ b/arch/um/sys-i386/syscalls.c @@ -34,92 +34,6 @@ long sys_clone(unsigned long clone_flags, unsigned long newsp, return ret; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -long sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *) ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *) ptr, - second, - (const struct timespec __user *) fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - panic("msgrcv with version != 0"); - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat (first, (char *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds *) ptr); - default: - return -ENOSYS; - } -} - long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 86ab6a0623fd..50f6a569f0d1 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -54,7 +54,6 @@ unsigned long sys_sigreturn(struct pt_regs *); struct oldold_utsname; struct old_utsname; -asmlinkage int sys_ipc(uint, int, int, int, void __user *, long); asmlinkage int sys_uname(struct old_utsname __user *); asmlinkage int sys_olduname(struct oldold_utsname __user *); diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index daa65d9aae95..45e64a17b86e 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -354,6 +354,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 7955e90c8341..8b5c348fdcf2 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -24,91 +24,6 @@ #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat(first, (char __user *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - /* * Old cruft */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b60907e3b0d5..fbb61ae70e06 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -684,6 +684,8 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); asmlinkage long sys_shmget(key_t key, size_t size, int flag); asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); +asmlinkage long sys_ipc(unsigned int call, int first, int second, + unsigned long third, void __user *ptr, long fifth); asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr); asmlinkage long sys_mq_unlink(const char __user *name); diff --git a/ipc/Makefile b/ipc/Makefile index 4e1955ea815d..9075e172e52c 100644 --- a/ipc/Makefile +++ b/ipc/Makefile @@ -3,7 +3,7 @@ # obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o -obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o +obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o obj_mq-$(CONFIG_COMPAT) += compat_mq.o obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y) diff --git a/ipc/syscall.c b/ipc/syscall.c new file mode 100644 index 000000000000..355a3da9ec73 --- /dev/null +++ b/ipc/syscall.c @@ -0,0 +1,99 @@ +/* + * sys_ipc() is the old de-multiplexer for the SysV IPC calls. + * + * This is really horribly ugly, and new architectures should just wire up + * the individual syscalls instead. + */ +#include + +#ifdef __ARCH_WANT_SYS_IPC +#include +#include +#include +#include +#include + +SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, int, second, + unsigned long, third, void __user *, ptr, long, fifth) +{ + int version, ret; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + switch (call) { + case SEMOP: + return sys_semtimedop(first, (struct sembuf __user *)ptr, + second, NULL); + case SEMTIMEDOP: + return sys_semtimedop(first, (struct sembuf __user *)ptr, + second, + (const struct timespec __user *)fifth); + + case SEMGET: + return sys_semget(first, second, third); + case SEMCTL: { + union semun fourth; + if (!ptr) + return -EINVAL; + if (get_user(fourth.__pad, (void __user * __user *) ptr)) + return -EFAULT; + return sys_semctl(first, second, third, fourth); + } + + case MSGSND: + return sys_msgsnd(first, (struct msgbuf __user *) ptr, + second, third); + case MSGRCV: + switch (version) { + case 0: { + struct ipc_kludge tmp; + if (!ptr) + return -EINVAL; + + if (copy_from_user(&tmp, + (struct ipc_kludge __user *) ptr, + sizeof(tmp))) + return -EFAULT; + return sys_msgrcv(first, tmp.msgp, second, + tmp.msgtyp, third); + } + default: + return sys_msgrcv(first, + (struct msgbuf __user *) ptr, + second, fifth, third); + } + case MSGGET: + return sys_msgget((key_t) first, second); + case MSGCTL: + return sys_msgctl(first, second, (struct msqid_ds __user *)ptr); + + case SHMAT: + switch (version) { + default: { + unsigned long raddr; + ret = do_shmat(first, (char __user *)ptr, + second, &raddr); + if (ret) + return ret; + return put_user(raddr, (unsigned long __user *) third); + } + case 1: + /* + * This was the entry point for kernel-originating calls + * from iBCS2 in 2.2 days. + */ + return -EINVAL; + } + case SHMDT: + return sys_shmdt((char __user *)ptr); + case SHMGET: + return sys_shmget(first, second, third); + case SHMCTL: + return sys_shmctl(first, second, + (struct shmid_ds __user *) ptr); + default: + return -ENOSYS; + } +} +#endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 695384f12a7d..70f2ea758ffe 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -126,6 +126,7 @@ cond_syscall(sys_setreuid16); cond_syscall(sys_setuid16); cond_syscall(sys_vm86old); cond_syscall(sys_vm86); +cond_syscall(sys_ipc); cond_syscall(compat_sys_ipc); cond_syscall(compat_sys_sysctl); cond_syscall(sys_flock); -- cgit v1.2.3 From e28cbf22933d0c0ccaf3c4c27a1a263b41f73859 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:19 -0800 Subject: improve sys_newuname() for compat architectures On an architecture that supports 32-bit compat we need to override the reported machine in uname with the 32-bit value. Instead of doing this separately in every architecture introduce a COMPAT_UTS_MACHINE define in and apply it directly in sys_newuname(). Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/compat.h | 3 ++- arch/mips/include/asm/compat.h | 3 ++- arch/mips/kernel/linux32.c | 16 ---------------- arch/mips/kernel/scall64-n32.S | 2 +- arch/mips/kernel/scall64-o32.S | 2 +- arch/parisc/include/asm/compat.h | 3 ++- arch/parisc/kernel/sys_parisc.c | 15 --------------- arch/parisc/kernel/syscall_table.S | 2 +- arch/powerpc/include/asm/compat.h | 3 ++- arch/powerpc/include/asm/syscalls.h | 2 -- arch/powerpc/include/asm/systbl.h | 2 +- arch/powerpc/kernel/syscalls.c | 13 ------------- arch/s390/include/asm/compat.h | 3 ++- arch/s390/kernel/compat_wrapper.S | 2 +- arch/s390/kernel/entry.h | 2 -- arch/s390/kernel/sys_s390.c | 11 ----------- arch/s390/kernel/syscalls.S | 2 +- arch/sparc/include/asm/compat.h | 3 ++- arch/sparc/kernel/sys_sparc_64.c | 11 ----------- arch/sparc/kernel/systbls.h | 3 --- arch/sparc/kernel/systbls_64.S | 4 ++-- arch/um/sys-x86_64/syscall_table.c | 5 ----- arch/um/sys-x86_64/syscalls.c | 14 -------------- arch/x86/include/asm/compat.h | 3 ++- arch/x86/include/asm/syscalls.h | 3 --- arch/x86/include/asm/unistd_64.h | 2 +- arch/x86/kernel/sys_x86_64.c | 12 ------------ kernel/sys.c | 13 +++++++++++++ 28 files changed, 36 insertions(+), 123 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index dfcf75b8426d..f90edc85b509 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -5,7 +5,8 @@ */ #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "i686\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index f58aed354bfd..613f6912dfc1 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -8,7 +8,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "mips\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index bde79ef602e6..a39d0597a375 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -249,22 +249,6 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz, } #endif -SYSCALL_DEFINE1(32_newuname, struct new_utsname __user *, name) -{ - int ret = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof *name)) - ret = -EFAULT; - up_read(&uts_sem); - - if (current->personality == PER_LINUX32 && !ret) - if (copy_to_user(name->machine, "mips\0\0\0", 8)) - ret = -EFAULT; - - return ret; -} - SYSCALL_DEFINE1(32_personality, unsigned long, personality) { int ret; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 66b5a48676dd..44337ba03717 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -181,7 +181,7 @@ EXPORT(sysn32_call_table) PTR sys_exit PTR compat_sys_wait4 PTR sys_kill /* 6060 */ - PTR sys_32_newuname + PTR sys_newuname PTR sys_semget PTR sys_semop PTR sys_n32_semctl diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 515f9eab2b28..813689ef2384 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -325,7 +325,7 @@ sys_call_table: PTR sys32_sigreturn PTR sys32_clone /* 4120 */ PTR sys_setdomainname - PTR sys_32_newuname + PTR sys_newuname PTR sys_ni_syscall /* sys_modify_ldt */ PTR compat_sys_adjtimex PTR sys_mprotect /* 4125 */ diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 7f32611a7a5e..02b77baa5da6 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -7,7 +7,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "parisc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 9147391afb03..c9b932260f47 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -234,18 +234,3 @@ long parisc_personality(unsigned long personality) return err; } - -long parisc_newuname(struct new_utsname __user *name) -{ - int err = sys_newuname(name); - -#ifdef CONFIG_COMPAT - if (!err && personality(current->personality) == PER_LINUX32) { - if (__put_user(0, name->machine + 6) || - __put_user(0, name->machine + 7)) - err = -EFAULT; - } -#endif - - return err; -} diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index de5f6dab48b7..3d52c978738f 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -127,7 +127,7 @@ ENTRY_SAME(socketpair) ENTRY_SAME(setpgid) ENTRY_SAME(send) - ENTRY_OURS(newuname) + ENTRY_SAME(newuname) ENTRY_SAME(umask) /* 60 */ ENTRY_SAME(chroot) ENTRY_COMP(ustat) diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 4774c2f92232..396d21a80058 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -7,7 +7,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "ppc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 23bb74e7f946..4084e567d28e 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -7,7 +7,6 @@ #include #include -struct new_utsname; struct pt_regs; struct rtas_args; struct sigaction; @@ -38,7 +37,6 @@ asmlinkage long sys_rt_sigaction(int sig, asmlinkage long ppc64_personality(unsigned long personality); asmlinkage int ppc_rtas(struct rtas_args __user *uargs); asmlinkage time_t sys64_time(time_t __user * tloc); -asmlinkage long ppc_newuname(struct new_utsname __user * name); asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 07d2d19ab5e9..a5ee345b6a5c 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -125,7 +125,7 @@ SYSCALL_SPU(fsync) SYS32ONLY(sigreturn) PPC_SYS(clone) COMPAT_SYS_SPU(setdomainname) -PPC_SYS_SPU(newuname) +SYSCALL_SPU(newuname) SYSCALL(ni_syscall) COMPAT_SYS_SPU(adjtimex) SYSCALL_SPU(mprotect) diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 5251221e7a5a..69d3c5d50a54 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -132,19 +132,6 @@ static inline int override_machine(char __user *mach) return 0; } -long ppc_newuname(struct new_utsname __user * name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - int sys_uname(struct old_utsname __user *name) { int err = 0; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 01a08020bc0e..104f2007f097 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -35,7 +35,8 @@ extern long psw32_user_bits; -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "s390\0\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 30de2d0e52bb..672ce52341b4 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -547,7 +547,7 @@ sys32_setdomainname_wrapper: .globl sys32_newuname_wrapper sys32_newuname_wrapper: llgtr %r2,%r2 # struct new_utsname * - jg sys_s390_newuname # branch to system call + jg sys_newuname # branch to system call .globl compat_sys_adjtimex_wrapper compat_sys_adjtimex_wrapper: diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 15fd68b196c0..eb15c12ec158 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -24,7 +24,6 @@ int __cpuinit start_secondary(void *cpuvoid); void __init startup_init(void); void die(const char * str, struct pt_regs * regs, long err); -struct new_utsname; struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; @@ -32,7 +31,6 @@ struct old_sigaction; long sys_mmap2(struct s390_mmap_arg_struct __user *arg); long sys_s390_ipc(uint call, int first, unsigned long second, unsigned long third, void __user *ptr); -long sys_s390_newuname(struct new_utsname __user *name); long sys_s390_personality(unsigned long personality); long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low, size_t len, int advice); diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index b8b78092ab7c..7b6b0f81a283 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -131,17 +131,6 @@ SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, } #ifdef CONFIG_64BIT -SYSCALL_DEFINE1(s390_newuname, struct new_utsname __user *, name) -{ - int ret = sys_newuname(name); - - if (personality(current->personality) == PER_LINUX32 && !ret) { - ret = copy_to_user(name->machine, "s390\0\0\0\0", 8); - if (ret) ret = -EFAULT; - } - return ret; -} - SYSCALL_DEFINE1(s390_personality, unsigned long, personality) { int ret; diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 990ac8b321c8..201ce6bed34e 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -130,7 +130,7 @@ SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) -SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper) +SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 0e706257918f..5016f76ea98a 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -5,7 +5,8 @@ */ #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "sparc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 45410e939628..3d435c42e6db 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -510,17 +510,6 @@ out: return err; } -SYSCALL_DEFINE1(sparc64_newuname, struct new_utsname __user *, name) -{ - int ret = sys_newuname(name); - - if (current->personality == PER_LINUX32 && !ret) { - ret = (copy_to_user(name->machine, "sparc\0\0", 8) - ? -EFAULT : 0); - } - return ret; -} - SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { int ret; diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h index 2c331c37e748..118759cd7342 100644 --- a/arch/sparc/kernel/systbls.h +++ b/arch/sparc/kernel/systbls.h @@ -6,15 +6,12 @@ #include #include -struct new_utsname; - extern asmlinkage unsigned long sys_getpagesize(void); extern asmlinkage long sparc_pipe(struct pt_regs *regs); extern asmlinkage long sys_sparc_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); -extern asmlinkage long sparc64_newuname(struct new_utsname __user *name); extern asmlinkage long sparc64_personality(unsigned long personality); extern asmlinkage long sys64_munmap(unsigned long addr, size_t len); extern asmlinkage unsigned long sys64_mremap(unsigned long addr, diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 30ca2b1d3a17..9db058dd039e 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -55,7 +55,7 @@ sys_call_table32: /*170*/ .word sys32_lsetxattr, sys32_fsetxattr, sys_getxattr, sys_lgetxattr, compat_sys_getdents .word sys_setsid, sys_fchdir, sys32_fgetxattr, sys_listxattr, sys_llistxattr /*180*/ .word sys32_flistxattr, sys_removexattr, sys_lremovexattr, compat_sys_sigpending, sys_ni_syscall - .word sys32_setpgid, sys32_fremovexattr, sys32_tkill, sys32_exit_group, sys_sparc64_newuname + .word sys32_setpgid, sys32_fremovexattr, sys32_tkill, sys32_exit_group, sys_newuname /*190*/ .word sys32_init_module, sys_sparc64_personality, sys_remap_file_pages, sys32_epoll_create, sys32_epoll_ctl .word sys32_epoll_wait, sys32_ioprio_set, sys_getppid, sys32_sigaction, sys_sgetmask /*200*/ .word sys32_ssetmask, sys_sigsuspend, compat_sys_newlstat, sys_uselib, compat_sys_old_readdir @@ -130,7 +130,7 @@ sys_call_table: /*170*/ .word sys_lsetxattr, sys_fsetxattr, sys_getxattr, sys_lgetxattr, sys_getdents .word sys_setsid, sys_fchdir, sys_fgetxattr, sys_listxattr, sys_llistxattr /*180*/ .word sys_flistxattr, sys_removexattr, sys_lremovexattr, sys_nis_syscall, sys_ni_syscall - .word sys_setpgid, sys_fremovexattr, sys_tkill, sys_exit_group, sys_sparc64_newuname + .word sys_setpgid, sys_fremovexattr, sys_tkill, sys_exit_group, sys_newuname /*190*/ .word sys_init_module, sys_sparc64_personality, sys_remap_file_pages, sys_epoll_create, sys_epoll_ctl .word sys_epoll_wait, sys_ioprio_set, sys_getppid, sys_nis_syscall, sys_sgetmask /*200*/ .word sys_ssetmask, sys_nis_syscall, sys_newlstat, sys_uselib, sys_nis_syscall diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/um/sys-x86_64/syscall_table.c index dd21d69715e6..47d469e7e7ce 100644 --- a/arch/um/sys-x86_64/syscall_table.c +++ b/arch/um/sys-x86_64/syscall_table.c @@ -26,11 +26,6 @@ /* On UML we call it this way ("old" means it's not mmap2) */ #define sys_mmap old_mmap -/* - * On x86-64 sys_uname is actually sys_newuname plus a compatibility trick. - * See arch/x86_64/kernel/sys_x86_64.c - */ -#define sys_uname sys_uname64 #define stub_clone sys_clone #define stub_fork sys_fork diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/um/sys-x86_64/syscalls.c index f1199fd34d38..f3d82bb6e15a 100644 --- a/arch/um/sys-x86_64/syscalls.c +++ b/arch/um/sys-x86_64/syscalls.c @@ -12,20 +12,6 @@ #include "asm/uaccess.h" #include "os.h" -asmlinkage long sys_uname64(struct new_utsname __user * name) -{ - int err; - - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) { unsigned long *ptr = addr, tmp; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 9a9c7bdc923d..306160e58b48 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -8,7 +8,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "i686\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 50f6a569f0d1..47cd606c3537 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -68,11 +68,8 @@ int sys_vm86(unsigned long, unsigned long, struct pt_regs *); long sys_arch_prctl(int, unsigned long); /* kernel/sys_x86_64.c */ -struct new_utsname; - asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -asmlinkage long sys_uname(struct new_utsname __user *); #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALLS_H */ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 4843f7ba754a..83e2d6dc5038 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -146,7 +146,7 @@ __SYSCALL(__NR_wait4, sys_wait4) #define __NR_kill 62 __SYSCALL(__NR_kill, sys_kill) #define __NR_uname 63 -__SYSCALL(__NR_uname, sys_uname) +__SYSCALL(__NR_uname, sys_newuname) #define __NR_semget 64 __SYSCALL(__NR_semget, sys_semget) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 8aa2057efd12..ff14a5044ce6 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -209,15 +209,3 @@ bottomup: return addr; } - - -SYSCALL_DEFINE1(uname, struct new_utsname __user *, name) -{ - int err; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - return err ? -EFAULT : 0; -} diff --git a/kernel/sys.c b/kernel/sys.c index 9814e43fb23b..e483eb5530e4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -1114,6 +1115,15 @@ out: DECLARE_RWSEM(uts_sem); +#ifdef COMPAT_UTS_MACHINE +#define override_architecture(name) \ + (current->personality == PER_LINUX32 && \ + copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ + sizeof(COMPAT_UTS_MACHINE))) +#else +#define override_architecture(name) 0 +#endif + SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { int errno = 0; @@ -1122,6 +1132,9 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) if (copy_to_user(name, utsname(), sizeof *name)) errno = -EFAULT; up_read(&uts_sem); + + if (!errno && override_architecture(name)) + errno = -EFAULT; return errno; } -- cgit v1.2.3 From 5cacdb4add1b1e50fe75edc50ebbb7bddd9cf5e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:21 -0800 Subject: Add generic sys_olduname() Add generic implementations of the old and really old uname system calls. Note that sh only implements sys_olduname but not sys_oldolduname, but I'm not going to bother with another ifdef for that special case. m32r implemented an old uname but never wired it up, so kill it, too. Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/kernel/sys_m32r.c | 11 -------- arch/mips/include/asm/unistd.h | 1 + arch/mips/kernel/syscall.c | 42 ----------------------------- arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/syscalls.c | 57 --------------------------------------- arch/sh/include/asm/syscalls.h | 3 --- arch/sh/include/asm/unistd_32.h | 1 + arch/sh/include/asm/unistd_64.h | 1 + arch/sh/kernel/sys_sh.c | 11 -------- arch/um/kernel/syscall.c | 45 ------------------------------- arch/x86/ia32/ia32entry.S | 4 +-- arch/x86/ia32/sys_ia32.c | 52 ----------------------------------- arch/x86/include/asm/sys_ia32.h | 5 ---- arch/x86/include/asm/syscalls.h | 7 ----- arch/x86/include/asm/unistd_32.h | 1 + arch/x86/include/asm/unistd_64.h | 1 + arch/x86/kernel/sys_i386_32.c | 49 --------------------------------- include/linux/syscalls.h | 4 +++ kernel/sys.c | 54 +++++++++++++++++++++++++++++++++++++ 19 files changed, 66 insertions(+), 284 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index cf2e7279ce9b..0a00f467edfa 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -76,17 +76,6 @@ asmlinkage int sys_tas(int __user *addr) return oldval; } -asmlinkage int sys_uname(struct old_utsname __user * name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} - asmlinkage int sys_cacheflush(void *addr, int bytes, int cache) { /* This should flush more selectively ... */ diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 97fe472095f2..1b5a6648eb86 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -1014,6 +1014,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 257bf0141775..e96b1c30c7aa 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -215,48 +215,6 @@ out: return error; } -/* - * Compacrapability ... - */ -SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) -{ - if (name && !copy_to_user(name, utsname(), sizeof (*name))) - return 0; - return -EFAULT; -} - -/* - * Compacrapability ... - */ -SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) -{ - int error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error -= __put_user(0, name->sysname + __OLD_UTS_LEN); - error -= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error -= __put_user(0, name->nodename + __OLD_UTS_LEN); - error -= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error -= __put_user(0, name->release + __OLD_UTS_LEN); - error -= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error -= __put_user(0, name->version + __OLD_UTS_LEN); - error -= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error = __put_user(0, name->machine + __OLD_UTS_LEN); - error = error ? -EFAULT : 0; - - return error; -} - SYSCALL_DEFINE1(set_thread_area, unsigned long, addr) { struct thread_info *ti = task_thread_info(current); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index c13821fe8741..f0a10266e7f7 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -377,6 +377,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 69d3c5d50a54..f2496f2faecc 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -116,63 +116,6 @@ long ppc64_personality(unsigned long personality) } #endif -#ifdef CONFIG_PPC64 -#define OVERRIDE_MACHINE (personality(current->personality) == PER_LINUX32) -#else -#define OVERRIDE_MACHINE 0 -#endif - -static inline int override_machine(char __user *mach) -{ - if (OVERRIDE_MACHINE) { - /* change ppc64 to ppc */ - if (__put_user(0, mach+3) || __put_user(0, mach+4)) - return -EFAULT; - } - return 0; -} - -int sys_uname(struct old_utsname __user *name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - -int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= override_machine(name->machine); - up_read(&uts_sem); - - return error? -EFAULT: 0; -} - long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, u32 len_high, u32 len_low) { diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h index c1ce2862f7be..507725af2e54 100644 --- a/arch/sh/include/asm/syscalls.h +++ b/arch/sh/include/asm/syscalls.h @@ -3,15 +3,12 @@ #ifdef __KERNEL__ -struct old_utsname; - asmlinkage int old_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, int fd, unsigned long off); asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); -asmlinkage int sys_uname(struct old_utsname __user *name); #ifdef CONFIG_SUPERH32 # include "syscalls_32.h" diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index a48f65e2e429..0e7f0fc8f086 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -371,6 +371,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h index 7709b2b8f752..0580c33a1e04 100644 --- a/arch/sh/include/asm/unistd_64.h +++ b/arch/sh/include/asm/unistd_64.h @@ -411,6 +411,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index c18cfaa67fdd..81f58371613d 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -93,14 +93,3 @@ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, int op) up_read(¤t->mm->mmap_sem); return 0; } - -asmlinkage int sys_uname(struct old_utsname __user *name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index cccab850c27e..4393173923f5 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -51,51 +51,6 @@ long old_mmap(unsigned long addr, unsigned long len, return err; } -long sys_uname(struct old_utsname __user * name) -{ - long err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} - -long sys_olduname(struct oldold_utsname __user * name) -{ - long error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= __put_user(0, name->machine + __OLD_UTS_LEN); - - up_read(&uts_sem); - - error = error ? -EFAULT : 0; - - return error; -} - int kernel_execve(const char *filename, char *const argv[], char *const envp[]) { mm_segment_t fs; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 34f821802c23..59b4556a5b92 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -563,7 +563,7 @@ ia32_sys_call_table: .quad quiet_ni_syscall /* old mpx syscall holder */ .quad sys_setpgid .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys32_olduname + .quad sys_olduname .quad sys_umask /* 60 */ .quad sys_chroot .quad compat_sys_ustat @@ -613,7 +613,7 @@ ia32_sys_call_table: .quad compat_sys_newstat .quad compat_sys_newlstat .quad compat_sys_newfstat - .quad sys32_uname + .quad sys_uname .quad stub32_iopl /* 110 */ .quad sys_vhangup .quad quiet_ni_syscall /* old "idle" system call */ diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 56c99f46e289..74c35431b7d8 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -448,58 +448,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd, return ret; } -asmlinkage long sys32_olduname(struct oldold_utsname __user *name) -{ - char *arch = "x86_64"; - int err; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - err = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - err |= __put_user(0, name->sysname+__OLD_UTS_LEN); - err |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - err |= __put_user(0, name->nodename+__OLD_UTS_LEN); - err |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - err |= __put_user(0, name->release+__OLD_UTS_LEN); - err |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - err |= __put_user(0, name->version+__OLD_UTS_LEN); - - if (personality(current->personality) == PER_LINUX32) - arch = "i686"; - - err |= __copy_to_user(&name->machine, arch, strlen(arch) + 1); - - up_read(&uts_sem); - - err = err ? -EFAULT : 0; - - return err; -} - -long sys32_uname(struct old_utsname __user *name) -{ - int err; - - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 7d348d803669..3ad421784ae7 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -54,11 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -struct oldold_utsname; -struct old_utsname; -asmlinkage long sys32_olduname(struct oldold_utsname __user *); -long sys32_uname(struct old_utsname __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 47cd606c3537..5c044b43e9a7 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -50,13 +50,6 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); unsigned long sys_sigreturn(struct pt_regs *); -/* kernel/sys_i386_32.c */ -struct oldold_utsname; -struct old_utsname; - -asmlinkage int sys_uname(struct old_utsname __user *); -asmlinkage int sys_olduname(struct oldold_utsname __user *); - /* kernel/vm86_32.c */ int sys_vm86old(struct vm86_struct __user *, struct pt_regs *); int sys_vm86(unsigned long, unsigned long, struct pt_regs *); diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 45e64a17b86e..beb9b5f8f8a4 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -367,6 +367,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLD_MMAP #define __ARCH_WANT_SYS_OLD_SELECT #define __ARCH_WANT_SYS_OLDUMOUNT diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 83e2d6dc5038..ff4307b0e81e 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -680,6 +680,7 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg) #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 8b5c348fdcf2..196552bb412c 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -24,55 +24,6 @@ #include -/* - * Old cruft - */ -asmlinkage int sys_uname(struct old_utsname __user *name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - return err? -EFAULT:0; -} - -asmlinkage int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= __put_user(0, name->machine + __OLD_UTS_LEN); - - up_read(&uts_sem); - - error = error ? -EFAULT : 0; - - return error; -} - - /* * Do a system call from kernel instead of calling sys_execve so we * end up with proper pt_regs. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fbb61ae70e06..44f2ad0e8825 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -31,6 +31,8 @@ struct msqid_ds; struct new_utsname; struct nfsctl_arg; struct __old_kernel_stat; +struct oldold_utsname; +struct old_utsname; struct pollfd; struct rlimit; struct rusage; @@ -655,6 +657,8 @@ asmlinkage long sys_gethostname(char __user *name, int len); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); asmlinkage long sys_newuname(struct new_utsname __user *name); +asmlinkage long sys_uname(struct old_utsname __user *); +asmlinkage long sys_olduname(struct oldold_utsname __user *); asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); diff --git a/kernel/sys.c b/kernel/sys.c index e483eb5530e4..8298878f4f71 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1138,6 +1138,60 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) return errno; } +#ifdef __ARCH_WANT_SYS_OLD_UNAME +/* + * Old cruft + */ +SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) +{ + int error = 0; + + if (!name) + return -EFAULT; + + down_read(&uts_sem); + if (copy_to_user(name, utsname(), sizeof(*name))) + error = -EFAULT; + up_read(&uts_sem); + + if (!error && override_architecture(name)) + error = -EFAULT; + return error; +} + +SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) +{ + int error; + + if (!name) + return -EFAULT; + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) + return -EFAULT; + + down_read(&uts_sem); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + __OLD_UTS_LEN); + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, + __OLD_UTS_LEN); + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &utsname()->release, + __OLD_UTS_LEN); + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &utsname()->version, + __OLD_UTS_LEN); + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &utsname()->machine, + __OLD_UTS_LEN); + error |= __put_user(0, name->machine + __OLD_UTS_LEN); + up_read(&uts_sem); + + if (!error && override_architecture(name)) + error = -EFAULT; + return error ? -EFAULT : 0; +} +#endif + SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; -- cgit v1.2.3 From 6e6c70e6910d21443ab0f894bab52b9ea653ef27 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 10 Mar 2010 15:23:40 -0800 Subject: dma-mapping: powerpc: use generic pci_set_dma_mask and pci_set_consistent_dma_mask This converts powerpc to use the generic pci_set_dma_mask and pci_set_consistent_dma_mask (drivers/pci/pci.c). The generic pci_set_dma_mask does what powerpc's pci_set_dma_mask does. Unlike powerpc's pci_set_consistent_dma_mask, the gneric pci_set_consistent_dma_mask sets only coherent_dma_mask. It doesn't work for powerpc? pci_set_consistent_dma_mask API should set only coherent_dma_mask? Signed-off-by: FUJITA Tomonori Acked-by: Benjamin Herrenschmidt Cc: Jesse Barnes Cc: Greg KH Cc: Kay Sievers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/dma-mapping.h | 3 --- arch/powerpc/kernel/pci-common.c | 15 --------------- 2 files changed, 18 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 80a973bb9e71..c85ef230135b 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -127,9 +127,6 @@ static inline int dma_supported(struct device *dev, u64 mask) return dma_ops->dma_supported(dev, mask); } -/* We have our own implementation of pci_set_dma_mask() */ -#define HAVE_ARCH_PCI_SET_DMA_MASK - static inline int dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2597f9545d8a..f3c42ce516e7 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -63,21 +63,6 @@ struct dma_map_ops *get_pci_dma_ops(void) } EXPORT_SYMBOL(get_pci_dma_ops); -int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - int rc; - - rc = dma_set_mask(&dev->dev, mask); - dev->dev.coherent_dma_mask = dev->dma_mask; - - return rc; -} - struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; -- cgit v1.2.3 From 9d296cfa69b3d4abc9d556986d544f0727988eed Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Tue, 16 Mar 2010 23:39:56 -0500 Subject: powerpc/fsl-booke: Get coherent bit from PTE We shouldn't be always setting 'M' in the TLB entry since its reasonable for somethings to be mapped non-coherent. The PTE should have 'M' set properly. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/head_fsl_booke.S | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 25793bb0e782..a7cf4934342c 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -746,9 +746,6 @@ finish_tlb_load: rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ #else rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif -#ifdef CONFIG_SMP - ori r12, r12, MAS2_M #endif mtspr SPRN_MAS2, r12 -- cgit v1.2.3 From 9eff26ea48bfbe2885b158742a7512a097ec911b Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 18 Mar 2010 16:05:13 +1100 Subject: powerpc/perf_events: Fix call-graph recording, add perf_arch_fetch_caller_regs This implements a powerpc version of perf_arch_fetch_caller_regs to get correct call-graphs. It's implemented in assembly because that way we can be sure there isn't a stack frame for perf_arch_fetch_caller_regs. If it was in C, gcc might or might not create a stack frame for it, which would affect the number of levels we have to skip. With this, we see results from perf record -e lock:lock_acquire like this: # Samples: 24878 # # Overhead Command Shared Object Symbol # ........ .............. ................. ...... # 14.99% perf [kernel.kallsyms] [k] ._raw_spin_lock | --- ._raw_spin_lock | |--25.00%-- .alloc_fd | (nil) | | | |--50.00%-- .anon_inode_getfd | | .sys_perf_event_open | | syscall_exit | | syscall | | create_counter | | __cmd_record | | run_builtin | | main | | 0xfd2e704 | | 0xfd2e8c0 | | (nil) ... etc. Signed-off-by: Paul Mackerras Acked-by: Benjamin Herrenschmidt Cc: anton@samba.org Cc: linuxppc-dev@ozlabs.org Cc: Peter Zijlstra Cc: Frederic Weisbecker LKML-Reference: <20100318050513.GA6575@drongo> Signed-off-by: Ingo Molnar --- arch/powerpc/include/asm/asm-compat.h | 2 ++ arch/powerpc/kernel/misc.S | 28 ++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index c1b475a941eb..a9b91ed3d4b9 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -28,6 +28,7 @@ #define PPC_LLARX(t, a, b, eh) PPC_LDARX(t, a, b, eh) #define PPC_STLCX stringify_in_c(stdcx.) #define PPC_CNTLZL stringify_in_c(cntlzd) +#define PPC_LR_STKOFF 16 /* Move to CR, single-entry optimized version. Only available * on POWER4 and later. @@ -51,6 +52,7 @@ #define PPC_STLCX stringify_in_c(stwcx.) #define PPC_CNTLZL stringify_in_c(cntlzw) #define PPC_MTOCRF stringify_in_c(mtcrf) +#define PPC_LR_STKOFF 4 #endif diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 2d29752cbe16..b485a87c94e1 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -127,3 +127,31 @@ _GLOBAL(__setup_cpu_power7) _GLOBAL(__restore_cpu_power7) /* place holder */ blr + +#ifdef CONFIG_EVENT_TRACING +/* + * Get a minimal set of registers for our caller's nth caller. + * r3 = regs pointer, r5 = n. + * + * We only get R1 (stack pointer), NIP (next instruction pointer) + * and LR (link register). These are all we can get in the + * general case without doing complicated stack unwinding, but + * fortunately they are enough to do a stack backtrace, which + * is all we need them for. + */ +_GLOBAL(perf_arch_fetch_caller_regs) + mr r6,r1 + cmpwi r5,0 + mflr r4 + ble 2f + mtctr r5 +1: PPC_LL r6,0(r6) + bdnz 1b + PPC_LL r4,PPC_LR_STKOFF(r6) +2: PPC_LL r7,0(r6) + PPC_LL r7,PPC_LR_STKOFF(r7) + PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3) + PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) + blr +#endif /* CONFIG_EVENT_TRACING */ -- cgit v1.2.3 From 09156a7a409cf93d1ca2706bf05d714879a5b7ea Mon Sep 17 00:00:00 2001 From: Márton Németh Date: Sat, 6 Mar 2010 22:43:55 +0000 Subject: powerpc: Do not call prink when CONFIG_PRINTK is not defined MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When printk() is disabled (CONFIG_PRINTK) at menu item General setup -> Configure standard kernel features (for small systems) -> Enable support for printk then there should be no printk() calls at all. Signed-off-by: Márton Németh Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/head_fsl_booke.S | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index a7cf4934342c..725526547994 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -884,13 +884,17 @@ KernelSPE: lwz r3,_MSR(r1) oris r3,r3,MSR_SPE@h stw r3,_MSR(r1) /* enable use of SPE after return */ +#ifdef CONFIG_PRINTK lis r3,87f@h ori r3,r3,87f@l mr r4,r2 /* current */ lwz r5,_NIP(r1) bl printk +#endif b ret_from_except +#ifdef CONFIG_PRINTK 87: .string "SPE used in kernel (task=%p, pc=%x) \n" +#endif .align 4,0 #endif /* CONFIG_SPE */ -- cgit v1.2.3 From a93272969c6b1d59883fcbb04845420bd72c9a20 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 16 Mar 2010 13:16:25 +0000 Subject: powerpc: Fix swiotlb to respect the boot option powerpc initializes swiotlb before parsing the kernel boot options so swiotlb options (e.g. specifying the swiotlb buffer size) are ignored. Any time before freeing bootmem works for swiotlb so this patch moves powerpc's swiotlb initialization after parsing the kernel boot options, mem_init (as x86 does). Signed-off-by: FUJITA Tomonori Tested-by: Becky Bruce Tested-by: Albert Herranz Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/setup_32.c | 6 ------ arch/powerpc/kernel/setup_64.c | 6 ------ arch/powerpc/mm/mem.c | 6 ++++++ 3 files changed, 6 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index b152de3e64d4..8f58986c2ad9 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -39,7 +39,6 @@ #include #include #include -#include #include "setup.h" @@ -343,11 +342,6 @@ void __init setup_arch(char **cmdline_p) ppc_md.setup_arch(); if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); -#ifdef CONFIG_SWIOTLB - if (ppc_swiotlb_enable) - swiotlb_init(1); -#endif - paging_init(); /* Initialize the MMU context management stuff */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 63547394048c..914389158a9b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -61,7 +61,6 @@ #include #include #include -#include #include #include "setup.h" @@ -541,11 +540,6 @@ void __init setup_arch(char **cmdline_p) if (ppc_md.setup_arch) ppc_md.setup_arch(); -#ifdef CONFIG_SWIOTLB - if (ppc_swiotlb_enable) - swiotlb_init(1); -#endif - paging_init(); /* Initialize the MMU context management stuff */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 311224cdb7ad..448f972b22f5 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "mmu_decl.h" @@ -320,6 +321,11 @@ void __init mem_init(void) struct page *page; unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize; +#ifdef CONFIG_SWIOTLB + if (ppc_swiotlb_enable) + swiotlb_init(1); +#endif + num_physpages = lmb.memory.size >> PAGE_SHIFT; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); -- cgit v1.2.3 From 191aee58b6568cf8143901bfa3f57a9b8faa6f1c Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 2 Mar 2010 14:25:38 +0000 Subject: powerpc: Remove IOMMU_VMERGE config option The description says: Cause IO segments sent to a device for DMA to be merged virtually by the IOMMU when they happen to have been allocated contiguously. This doesn't add pressure to the IOMMU allocator. However, some drivers don't support getting large merged segments coming back from *_map_sg(). Most drivers don't have this problem; it is safe to say Y here. It's out of date. Long ago, drivers didn't have a way to tell IOMMUs about their segment length limit (that is, the maximum segment length that they can handle). So IOMMUs merged as many segments as possible and gave too large segments to drivers. dma_get_max_seg_size() was introduced to solve the above problem. Device drives can use the API to tell IOMMU about the maximum segment length that they can handle. In addition, the default limit (64K) should be safe for everyone. So this config option seems to be unnecessary. Note that this config option just enables users to disable the virtual merging by default. Users can still disable the virtual merging by the boot parameter. Signed-off-by: FUJITA Tomonori Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 13 ------------- arch/powerpc/kernel/iommu.c | 7 +------ 2 files changed, 1 insertion(+), 19 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 8a54eb8e3768..2e19500921f9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -313,19 +313,6 @@ config 8XX_MINIMAL_FPEMU It is recommended that you build a soft-float userspace instead. -config IOMMU_VMERGE - bool "Enable IOMMU virtual merging" - depends on PPC64 - default y - help - Cause IO segments sent to a device for DMA to be merged virtually - by the IOMMU when they happen to have been allocated contiguously. - This doesn't add pressure to the IOMMU allocator. However, some - drivers don't support getting large merged segments coming back - from *_map_sg(). - - Most drivers don't have this problem; it is safe to say Y here. - config IOMMU_HELPER def_bool PPC64 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 5547ae6e6b0b..ec94f906ea43 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -42,12 +42,7 @@ #define DBG(...) -#ifdef CONFIG_IOMMU_VMERGE -static int novmerge = 0; -#else -static int novmerge = 1; -#endif - +static int novmerge; static int protect4gb = 1; static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int); -- cgit v1.2.3