From 600715dcdf567c86f8b2c6173fcfb4b873e25a19 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 11 Sep 2008 01:31:45 -0700 Subject: generic: add phys_addr_t for holding physical addresses Add a kernel-wide "phys_addr_t" which is guaranteed to be able to hold any physical address. By default it equals the word size of the architecture, but a 32-bit architecture can set ARCH_PHYS_ADDR_T_64BIT if it needs a 64-bit phys_addr_t. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/powerpc/Kconfig | 3 +++ arch/powerpc/include/asm/types.h | 7 ------- 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 587da5e0990f..f5f83ee60411 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -22,6 +22,9 @@ config WORD_SIZE config PPC_MERGE def_bool y +config ARCH_PHYS_ADDR_T_64BIT + def_bool PPC64 || PHYS_64BIT + config MMU bool default y diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h index d3374bc865ba..c646f34c4e8b 100644 --- a/arch/powerpc/include/asm/types.h +++ b/arch/powerpc/include/asm/types.h @@ -48,13 +48,6 @@ typedef struct { typedef __vector128 vector128; -/* Physical address used by some IO functions */ -#if defined(CONFIG_PPC64) || defined(CONFIG_PHYS_64BIT) -typedef u64 phys_addr_t; -#else -typedef u32 phys_addr_t; -#endif - #ifdef __powerpc64__ typedef u64 dma_addr_t; #else -- cgit v1.2.3 From 8308c54d7e312f7a03e2ce2057d0837e6fe3843f Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 11 Sep 2008 01:31:50 -0700 Subject: generic: redefine resource_size_t as phys_addr_t There's no good reason why a resource_size_t shouldn't just be a physical address, so simply redefine it in terms of phys_addr_t. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/powerpc/platforms/Kconfig.cputype | 1 - arch/powerpc/sysdev/ppc4xx_pci.c | 16 ++++++---------- arch/x86/Kconfig | 1 - arch/x86/kernel/e820.c | 4 +--- drivers/pci/setup-bus.c | 9 ++++----- include/linux/types.h | 8 ++------ 6 files changed, 13 insertions(+), 26 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 7f6512733862..be852fd407a8 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -135,7 +135,6 @@ config PTE_64BIT config PHYS_64BIT bool 'Large physical address support' if E500 depends on 44x || E500 - select RESOURCES_64BIT default y if 44x ---help--- This option enables kernel support for larger than 32-bit physical diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index fb368dfde5d4..e8a76d9539db 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -41,13 +41,10 @@ extern unsigned long total_memory; #define U64_TO_U32_LOW(val) ((u32)((val) & 0x00000000ffffffffULL)) #define U64_TO_U32_HIGH(val) ((u32)((val) >> 32)) -#ifdef CONFIG_RESOURCES_64BIT -#define RES_TO_U32_LOW(val) U64_TO_U32_LOW(val) -#define RES_TO_U32_HIGH(val) U64_TO_U32_HIGH(val) -#else -#define RES_TO_U32_LOW(val) (val) -#define RES_TO_U32_HIGH(val) (0) -#endif +#define RES_TO_U32_LOW(val) \ + ((sizeof(resource_size_t) > sizeof(u32)) ? U64_TO_U32_LOW(val) : (val)) +#define RES_TO_U32_HIGH(val) \ + ((sizeof(resource_size_t) > sizeof(u32)) ? U64_TO_U32_HIGH(val) : (0)) static inline int ppc440spe_revA(void) { @@ -145,12 +142,11 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, /* Use that */ res->start = pci_addr; -#ifndef CONFIG_RESOURCES_64BIT /* Beware of 32 bits resources */ - if ((pci_addr + size) > 0x100000000ull) + if (sizeof(resource_size_t) == sizeof(u32) && + (pci_addr + size) > 0x100000000ull) res->end = 0xffffffff; else -#endif res->end = res->start + size - 1; break; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a0ffb5188c8c..b4e1875f9861 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -925,7 +925,6 @@ config X86_PAE def_bool n prompt "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G - select RESOURCES_64BIT help PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 66e48aa2dd1b..477f4bb7e552 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1276,12 +1276,10 @@ void __init e820_reserve_resources(void) res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); for (i = 0; i < e820.nr_map; i++) { end = e820.map[i].addr + e820.map[i].size - 1; -#ifndef CONFIG_RESOURCES_64BIT - if (end > 0x100000000ULL) { + if (end != (resource_size_t)end) { res++; continue; } -#endif res->name = e820_type_to_string(e820.map[i].type); res->start = e820.map[i].addr; res->end = end; diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 1aad599816f7..f250a90ee450 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -378,11 +378,10 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long align = 0; min_align = 0; for (order = 0; order <= max_order; order++) { -#ifdef CONFIG_RESOURCES_64BIT - resource_size_t align1 = 1ULL << (order + 20); -#else - resource_size_t align1 = 1U << (order + 20); -#endif + resource_size_t align1 = 1; + + align1 <<= (order + 20); + if (!align) min_align = align1; else if (ALIGN(align + min_align, min_align) < align1) diff --git a/include/linux/types.h b/include/linux/types.h index 022c668496da..f24f7beb47df 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -191,18 +191,14 @@ typedef __u32 __bitwise __wsum; #ifdef __KERNEL__ typedef unsigned __bitwise__ gfp_t; -#ifdef CONFIG_RESOURCES_64BIT -typedef u64 resource_size_t; -#else -typedef u32 resource_size_t; -#endif - #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; #else typedef u32 phys_addr_t; #endif +typedef phys_addr_t resource_size_t; + struct ustat { __kernel_daddr_t f_tfree; __kernel_ino_t f_tinode; -- cgit v1.2.3 From 5b9261d93e5fa3db4995d5b77b5ed365166e001c Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 29 Sep 2008 11:11:47 -0400 Subject: sputrace: use marker_synchronize_unregister() We need a marker_synchronize_unregister() before the end of exit() to make sure every probe callers have exited the non preemptible section and thus are not executing the probe code anymore. Signed-off-by: Mathieu Desnoyers Acked-by: Jeremy Kerr Signed-off-by: Ingo Molnar --- arch/powerpc/platforms/cell/spufs/sputrace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c index 92d20e993ede..2ece399f2862 100644 --- a/arch/powerpc/platforms/cell/spufs/sputrace.c +++ b/arch/powerpc/platforms/cell/spufs/sputrace.c @@ -232,6 +232,7 @@ static void __exit sputrace_exit(void) remove_proc_entry("sputrace", NULL); kfree(sputrace_log); + marker_synchronize_unregister(); } module_init(sputrace_init); -- cgit v1.2.3 From 12f67556023389a6be929a56617142a8e8ab20fe Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 14 Jul 2008 14:00:02 +0200 Subject: KVM: ppc: enable KVM_TRACE building for powerpc This patch enables KVM_TRACE to build for PowerPC arch. This means just adding sections to Kconfig and Makefile. Signed-off-by: Jerone Young Signed-off-by: Christian Ehrhardt Signed-off-by: Avi Kivity --- arch/powerpc/kvm/Kconfig | 11 +++++++++++ arch/powerpc/kvm/Makefile | 6 ++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 6b076010213b..53aaa66b25e5 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -37,6 +37,17 @@ config KVM_BOOKE_HOST Provides host support for KVM on Book E PowerPC processors. Currently this works on 440 processors only. +config KVM_TRACE + bool "KVM trace support" + depends on KVM && MARKERS && SYSFS + select RELAY + select DEBUG_FS + default n + ---help--- + This option allows reading a trace of kvm-related events through + relayfs. Note the ABI is not considered stable and will be + modified in future updates. + source drivers/virtio/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 04e3449e1f42..2a5d4397ac4b 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -4,9 +4,11 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) -kvm-objs := $(common-objs) powerpc.o emulate.o booke_guest.o +common-objs-$(CONFIG_KVM_TRACE) += $(addprefix ../../../virt/kvm/, kvm_trace.o) + +kvm-objs := $(common-objs-y) powerpc.o emulate.o booke_guest.o obj-$(CONFIG_KVM) += kvm.o AFLAGS_booke_interrupts.o := -I$(obj) -- cgit v1.2.3 From 31711f2294b38d8334efaf7dbac6da4781fd151e Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 14 Jul 2008 14:00:03 +0200 Subject: KVM: ppc: adds trace points for ppc tlb activity This patch adds trace points to track powerpc TLB activities using the KVM_TRACE infrastructure. Signed-off-by: Jerone Young Signed-off-by: Christian Ehrhardt Signed-off-by: Avi Kivity --- arch/powerpc/kvm/44x_tlb.c | 15 ++++++++++++++- arch/powerpc/kvm/emulate.c | 4 ++++ include/linux/kvm.h | 3 +++ 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 5a5602da5091..a207d16b9dbb 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -175,6 +176,10 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, stlbe->word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf); stlbe->word2 = kvmppc_44x_tlb_shadow_attrib(flags, vcpu->arch.msr & MSR_PR); + + KVMTRACE_5D(STLB_WRITE, vcpu, victim, + stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, + handler); } void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, @@ -204,6 +209,9 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, kvmppc_44x_shadow_release(vcpu, i); stlbe->word0 = 0; + KVMTRACE_5D(STLB_INVAL, vcpu, i, + stlbe->tid, stlbe->word0, stlbe->word1, + stlbe->word2, handler); } up_write(¤t->mm->mmap_sem); } @@ -217,8 +225,13 @@ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) /* XXX Replace loop with fancy data structures. */ down_write(¤t->mm->mmap_sem); for (i = 0; i <= tlb_44x_hwater; i++) { + struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; + kvmppc_44x_shadow_release(vcpu, i); - vcpu->arch.shadow_tlb[i].word0 = 0; + stlbe->word0 = 0; + KVMTRACE_5D(STLB_INVAL, vcpu, i, + stlbe->tid, stlbe->word0, stlbe->word1, + stlbe->word2, handler); } up_write(¤t->mm->mmap_sem); } diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 8c605d0a5488..4a3e274bac12 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -170,6 +170,10 @@ static int kvmppc_emul_tlbwe(struct kvm_vcpu *vcpu, u32 inst) kvmppc_mmu_map(vcpu, eaddr, raddr >> PAGE_SHIFT, asid, flags); } + KVMTRACE_5D(GTLB_WRITE, vcpu, index, + tlbe->tid, tlbe->word0, tlbe->word1, tlbe->word2, + handler); + return EMULATE_DONE; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 5d08f11bb27f..e21a5050d4d6 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -471,5 +471,8 @@ struct kvm_trace_rec { #define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) #define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) #define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) +#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) +#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) +#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) #endif -- cgit v1.2.3 From 3b4bd7969f7b61a1ab455bff084ee4f0a2411055 Mon Sep 17 00:00:00 2001 From: Christian Ehrhardt Date: Mon, 14 Jul 2008 14:00:04 +0200 Subject: KVM: ppc: trace powerpc instruction emulation This patch adds a trace point for the instruction emulation on embedded powerpc utilizing the KVM_TRACE interface. Signed-off-by: Christian Ehrhardt Signed-off-by: Avi Kivity --- arch/powerpc/kvm/emulate.c | 2 ++ include/linux/kvm.h | 1 + 2 files changed, 3 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 4a3e274bac12..c3ed63b22210 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -769,6 +769,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) break; } + KVMTRACE_3D(PPC_INSTR, vcpu, inst, vcpu->arch.pc, emulated, entryexit); + if (advance) vcpu->arch.pc += 4; /* Advance past emulated instruction. */ diff --git a/include/linux/kvm.h b/include/linux/kvm.h index e21a5050d4d6..d29b64881447 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -474,5 +474,6 @@ struct kvm_trace_rec { #define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) #define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) #define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) +#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) #endif -- cgit v1.2.3 From 6a0ab738ef42d87951b3980f61b1f4cbb14d4171 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 25 Jul 2008 13:54:49 -0500 Subject: KVM: ppc: guest breakpoint support Allow host userspace to program hardware debug registers to set breakpoints inside guests. Signed-off-by: Jerone Young Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 5 +++ arch/powerpc/kvm/booke_guest.c | 15 +++++++ arch/powerpc/kvm/booke_interrupts.S | 11 ++++- arch/powerpc/kvm/powerpc.c | 84 ++++++++++++++++++++++++++++++++++++- 4 files changed, 113 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 2655e2a4831e..23bad40b0ea6 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -86,6 +86,11 @@ struct kvm_vcpu_arch { u32 host_stack; u32 host_pid; + u32 host_dbcr0; + u32 host_dbcr1; + u32 host_dbcr2; + u32 host_iac[4]; + u32 host_msr; u64 fpr[32]; u32 gpr[32]; diff --git a/arch/powerpc/kvm/booke_guest.c b/arch/powerpc/kvm/booke_guest.c index 9c8ad850c6e3..3cca079975e1 100644 --- a/arch/powerpc/kvm/booke_guest.c +++ b/arch/powerpc/kvm/booke_guest.c @@ -410,6 +410,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, break; } + case BOOKE_INTERRUPT_DEBUG: { + u32 dbsr; + + vcpu->arch.pc = mfspr(SPRN_CSRR0); + + /* clear IAC events in DBSR register */ + dbsr = mfspr(SPRN_DBSR); + dbsr &= DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4; + mtspr(SPRN_DBSR, dbsr); + + run->exit_reason = KVM_EXIT_DEBUG; + r = RESUME_HOST; + break; + } + default: printk(KERN_EMERG "exit_nr %d\n", exit_nr); BUG(); diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 3b653b5309b8..8eaba2613ffd 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -42,7 +42,8 @@ #define HOST_STACK_LR (HOST_STACK_SIZE + 4) /* In caller stack frame. */ #define NEED_INST_MASK ((1<arch.host_iac[0]); + mtspr(SPRN_IAC2, vcpu->arch.host_iac[1]); + mtspr(SPRN_IAC3, vcpu->arch.host_iac[2]); + mtspr(SPRN_IAC4, vcpu->arch.host_iac[3]); + mtspr(SPRN_DBCR1, vcpu->arch.host_dbcr1); + mtspr(SPRN_DBCR2, vcpu->arch.host_dbcr2); + mtspr(SPRN_DBCR0, vcpu->arch.host_dbcr0); + mtmsr(vcpu->arch.host_msr); +} + +static void kvmppc_load_guest_debug_registers(struct kvm_vcpu *vcpu) +{ + struct kvm_guest_debug *dbg = &vcpu->guest_debug; + u32 dbcr0 = 0; + + vcpu->arch.host_msr = mfmsr(); + kvmppc_disable_debug_interrupts(); + + /* Save host debug register state. */ + vcpu->arch.host_iac[0] = mfspr(SPRN_IAC1); + vcpu->arch.host_iac[1] = mfspr(SPRN_IAC2); + vcpu->arch.host_iac[2] = mfspr(SPRN_IAC3); + vcpu->arch.host_iac[3] = mfspr(SPRN_IAC4); + vcpu->arch.host_dbcr0 = mfspr(SPRN_DBCR0); + vcpu->arch.host_dbcr1 = mfspr(SPRN_DBCR1); + vcpu->arch.host_dbcr2 = mfspr(SPRN_DBCR2); + + /* set registers up for guest */ + + if (dbg->bp[0]) { + mtspr(SPRN_IAC1, dbg->bp[0]); + dbcr0 |= DBCR0_IAC1 | DBCR0_IDM; + } + if (dbg->bp[1]) { + mtspr(SPRN_IAC2, dbg->bp[1]); + dbcr0 |= DBCR0_IAC2 | DBCR0_IDM; + } + if (dbg->bp[2]) { + mtspr(SPRN_IAC3, dbg->bp[2]); + dbcr0 |= DBCR0_IAC3 | DBCR0_IDM; + } + if (dbg->bp[3]) { + mtspr(SPRN_IAC4, dbg->bp[3]); + dbcr0 |= DBCR0_IAC4 | DBCR0_IDM; + } + + mtspr(SPRN_DBCR0, dbcr0); + mtspr(SPRN_DBCR1, 0); + mtspr(SPRN_DBCR2, 0); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + if (vcpu->guest_debug.enabled) + kvmppc_load_guest_debug_registers(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + if (vcpu->guest_debug.enabled) + kvmppc_restore_host_debug_state(vcpu); } int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) { - return -ENOTSUPP; + int i; + + vcpu->guest_debug.enabled = dbg->enabled; + if (vcpu->guest_debug.enabled) { + for (i=0; i < ARRAY_SIZE(vcpu->guest_debug.bp); i++) { + if (dbg->breakpoints[i].enabled) + vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; + else + vcpu->guest_debug.bp[i] = 0; + } + } + + return 0; } static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu, -- cgit v1.2.3 From 20754c2495a791b5b429c0da63394c86ade978e7 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 25 Jul 2008 13:54:51 -0500 Subject: KVM: ppc: Stop saving host TLB state We're saving the host TLB state to memory on every exit, but never using it. Originally I had thought that we'd want to restore host TLB for heavyweight exits, but that could actually hurt when context switching to an unrelated host process (i.e. not qemu). Since this decreases the performance penalty of all exits, this patch improves guest boot time by about 15%. Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 2 -- arch/powerpc/kernel/asm-offsets.c | 1 - arch/powerpc/kvm/booke_interrupts.S | 17 +++-------------- 3 files changed, 3 insertions(+), 17 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 23bad40b0ea6..dc3a7562bae4 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -81,8 +81,6 @@ struct kvm_vcpu_arch { struct tlbe shadow_tlb[PPC44x_TLB_SIZE]; /* Pages which are referenced in the shadow TLB. */ struct page *shadow_pages[PPC44x_TLB_SIZE]; - /* Copy of the host's TLB. */ - struct tlbe host_tlb[PPC44x_TLB_SIZE]; u32 host_stack; u32 host_pid; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 92768d3006f7..594064953951 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -356,7 +356,6 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); - DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb)); DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 8eaba2613ffd..3e88dfa1dbe4 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -342,26 +342,15 @@ lightweight_exit: andc r6, r5, r6 mtmsr r6 - /* Save the host's non-pinned TLB mappings, and load the guest mappings - * over them. Leave the host's "pinned" kernel mappings in place. */ - /* XXX optimization: use generation count to avoid swapping unmodified - * entries. */ + /* Load the guest mappings, leaving the host's "pinned" kernel mappings + * in place. */ + /* XXX optimization: load only modified guest entries. */ mfspr r10, SPRN_MMUCR /* Save host MMUCR. */ lis r8, tlb_44x_hwater@ha lwz r8, tlb_44x_hwater@l(r8) - addi r3, r4, VCPU_HOST_TLB - 4 addi r9, r4, VCPU_SHADOW_TLB - 4 li r6, 0 1: - /* Save host entry. */ - tlbre r7, r6, PPC44x_TLB_PAGEID - mfspr r5, SPRN_MMUCR - stwu r5, 4(r3) - stwu r7, 4(r3) - tlbre r7, r6, PPC44x_TLB_XLAT - stwu r7, 4(r3) - tlbre r7, r6, PPC44x_TLB_ATTRIB - stwu r7, 4(r3) /* Load guest entry. */ lwzu r7, 4(r9) mtspr SPRN_MMUCR, r7 -- cgit v1.2.3 From 83aae4a8098eb8a40a2e9dab3714354182143b4f Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 25 Jul 2008 13:54:52 -0500 Subject: KVM: ppc: Write only modified shadow entries into the TLB on exit Track which TLB entries need to be written, instead of overwriting everything below the high water mark. Typically only a single guest TLB entry will be modified in a single exit. Guest boot time performance improvement: about 15%. Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 3 +++ arch/powerpc/include/asm/kvm_ppc.h | 3 +++ arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kvm/44x_tlb.c | 9 ++++++- arch/powerpc/kvm/booke_interrupts.S | 51 ++++++++++++++++++++++++------------- arch/powerpc/kvm/powerpc.c | 15 +++++++++++ 6 files changed, 64 insertions(+), 18 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index dc3a7562bae4..4338b03da8f9 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -82,6 +82,9 @@ struct kvm_vcpu_arch { /* Pages which are referenced in the shadow TLB. */ struct page *shadow_pages[PPC44x_TLB_SIZE]; + /* Track which TLB entries we've modified in the current exit. */ + u8 shadow_tlb_mod[PPC44x_TLB_SIZE]; + u32 host_stack; u32 host_pid; u32 host_dbcr0; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index a8b068792260..8e7e42959903 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -65,6 +65,9 @@ extern void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, gva_t eend, u32 asid); extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); +/* XXX Book E specific */ +extern void kvmppc_tlbe_set_modified(struct kvm_vcpu *vcpu, unsigned int i); + extern void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu); static inline void kvmppc_queue_exception(struct kvm_vcpu *vcpu, int exception) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 594064953951..1631d670b9ed 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -357,6 +357,7 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb)); + DEFINE(VCPU_SHADOW_MOD, offsetof(struct kvm_vcpu, arch.shadow_tlb_mod)); 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)); diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index a207d16b9dbb..06a5fcfc4d33 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -125,6 +125,11 @@ static void kvmppc_44x_shadow_release(struct kvm_vcpu *vcpu, } } +void kvmppc_tlbe_set_modified(struct kvm_vcpu *vcpu, unsigned int i) +{ + vcpu->arch.shadow_tlb_mod[i] = 1; +} + /* Caller must ensure that the specified guest TLB entry is safe to insert into * the shadow TLB. */ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, @@ -172,10 +177,10 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, * use host large pages in the future. */ stlbe->word0 = (gvaddr & PAGE_MASK) | PPC44x_TLB_VALID | PPC44x_TLB_TS | PPC44x_TLB_4K; - stlbe->word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf); stlbe->word2 = kvmppc_44x_tlb_shadow_attrib(flags, vcpu->arch.msr & MSR_PR); + kvmppc_tlbe_set_modified(vcpu, victim); KVMTRACE_5D(STLB_WRITE, vcpu, victim, stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, @@ -209,6 +214,7 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, kvmppc_44x_shadow_release(vcpu, i); stlbe->word0 = 0; + kvmppc_tlbe_set_modified(vcpu, i); KVMTRACE_5D(STLB_INVAL, vcpu, i, stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, handler); @@ -229,6 +235,7 @@ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) kvmppc_44x_shadow_release(vcpu, i); stlbe->word0 = 0; + kvmppc_tlbe_set_modified(vcpu, i); KVMTRACE_5D(STLB_INVAL, vcpu, i, stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, handler); diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 3e88dfa1dbe4..564ea32ecbac 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -335,7 +335,7 @@ lightweight_exit: lwz r3, VCPU_PID(r4) mtspr SPRN_PID, r3 - /* Prevent all TLB updates. */ + /* Prevent all asynchronous TLB updates. */ mfmsr r5 lis r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@h ori r6, r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l @@ -344,28 +344,45 @@ lightweight_exit: /* Load the guest mappings, leaving the host's "pinned" kernel mappings * in place. */ - /* XXX optimization: load only modified guest entries. */ mfspr r10, SPRN_MMUCR /* Save host MMUCR. */ - lis r8, tlb_44x_hwater@ha - lwz r8, tlb_44x_hwater@l(r8) - addi r9, r4, VCPU_SHADOW_TLB - 4 - li r6, 0 + li r5, PPC44x_TLB_SIZE + lis r5, tlb_44x_hwater@ha + lwz r5, tlb_44x_hwater@l(r5) + mtctr r5 + addi r9, r4, VCPU_SHADOW_TLB + addi r5, r4, VCPU_SHADOW_MOD + li r3, 0 1: + lbzx r7, r3, r5 + cmpwi r7, 0 + beq 3f + /* Load guest entry. */ - lwzu r7, 4(r9) + mulli r11, r3, TLBE_BYTES + add r11, r11, r9 + lwz r7, 0(r11) mtspr SPRN_MMUCR, r7 - lwzu r7, 4(r9) - tlbwe r7, r6, PPC44x_TLB_PAGEID - lwzu r7, 4(r9) - tlbwe r7, r6, PPC44x_TLB_XLAT - lwzu r7, 4(r9) - tlbwe r7, r6, PPC44x_TLB_ATTRIB - /* Increment index. */ - addi r6, r6, 1 - cmpw r6, r8 - blt 1b + lwz r7, 4(r11) + tlbwe r7, r3, PPC44x_TLB_PAGEID + lwz r7, 8(r11) + tlbwe r7, r3, PPC44x_TLB_XLAT + lwz r7, 12(r11) + tlbwe r7, r3, PPC44x_TLB_ATTRIB +3: + addi r3, r3, 1 /* Increment index. */ + bdnz 1b + mtspr SPRN_MMUCR, r10 /* Restore host MMUCR. */ + /* Clear bitmap of modified TLB entries */ + li r5, PPC44x_TLB_SIZE>>2 + mtctr r5 + addi r5, r4, VCPU_SHADOW_MOD - 4 + li r6, 0 +1: + stwu r6, 4(r5) + bdnz 1b + iccci 0, 0 /* XXX hack */ /* Load some guest volatiles. */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b75607180ddb..90a6fc422b23 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -27,6 +27,7 @@ #include #include #include +#include gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) @@ -307,14 +308,28 @@ static void kvmppc_load_guest_debug_registers(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + int i; + if (vcpu->guest_debug.enabled) kvmppc_load_guest_debug_registers(vcpu); + + /* Mark every guest entry in the shadow TLB entry modified, so that they + * will all be reloaded on the next vcpu run (instead of being + * demand-faulted). */ + for (i = 0; i <= tlb_44x_hwater; i++) + kvmppc_tlbe_set_modified(vcpu, i); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { if (vcpu->guest_debug.enabled) kvmppc_restore_host_debug_state(vcpu); + + /* Don't leave guest TLB entries resident when being de-scheduled. */ + /* XXX It would be nice to differentiate between heavyweight exit and + * sched_out here, since we could avoid the TLB flush for heavyweight + * exits. */ + _tlbia(); } int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, -- cgit v1.2.3 From 49dd2c492895828a90ecdf889e7fe9cfb40a82a7 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 25 Jul 2008 13:54:53 -0500 Subject: KVM: powerpc: Map guest userspace with TID=0 mappings When we use TID=N userspace mappings, we must ensure that kernel mappings have been destroyed when entering userspace. Using TID=1/TID=0 for kernel/user mappings and running userspace with PID=0 means that userspace can't access the kernel mappings, but the kernel can directly access userspace. The net is that we don't need to flush the TLB on privilege switches, but we do on guest context switches (which are far more infrequent). Guest boot time performance improvement: about 30%. Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 4 ++++ arch/powerpc/include/asm/kvm_ppc.h | 9 +++++++++ arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kvm/44x_tlb.c | 39 ++++++++++++++++++++++--------------- arch/powerpc/kvm/booke_guest.c | 2 ++ arch/powerpc/kvm/booke_interrupts.S | 2 +- arch/powerpc/kvm/emulate.c | 2 +- 7 files changed, 41 insertions(+), 19 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 4338b03da8f9..34b52b7180cd 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -129,7 +129,11 @@ struct kvm_vcpu_arch { u32 ivor[16]; u32 ivpr; u32 pir; + + u32 shadow_pid; u32 pid; + u32 swap_pid; + u32 pvr; u32 ccr0; u32 ccr1; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 8e7e42959903..8931ba729d2b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -64,6 +64,7 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, extern void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, gva_t eend, u32 asid); extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); +extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); /* XXX Book E specific */ extern void kvmppc_tlbe_set_modified(struct kvm_vcpu *vcpu, unsigned int i); @@ -95,4 +96,12 @@ static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr) kvm_vcpu_block(vcpu); } +static inline void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 new_pid) +{ + if (vcpu->arch.pid != new_pid) { + vcpu->arch.pid = new_pid; + vcpu->arch.swap_pid = 1; + } +} + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 1631d670b9ed..52649da344fb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -369,7 +369,7 @@ int main(void) DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); - DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid)); + DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 06a5fcfc4d33..3594bbd1f618 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -170,7 +170,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, /* XXX what about AS? */ - stlbe->tid = asid & 0xff; + stlbe->tid = !(asid & 0xff); /* Force TS=1 for all guest mappings. */ /* For now we hardcode 4KB mappings, but it will be important to @@ -190,7 +190,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, gva_t eend, u32 asid) { - unsigned int pid = asid & 0xff; + unsigned int pid = !(asid & 0xff); int i; /* XXX Replace loop with fancy data structures. */ @@ -222,23 +222,30 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, up_write(¤t->mm->mmap_sem); } -/* Invalidate all mappings, so that when they fault back in they will get the - * proper permission bits. */ +/* Invalidate all mappings on the privilege switch after PID has been changed. + * The guest always runs with PID=1, so we must clear the entire TLB when + * switching address spaces. */ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) { int i; - /* XXX Replace loop with fancy data structures. */ - down_write(¤t->mm->mmap_sem); - for (i = 0; i <= tlb_44x_hwater; i++) { - struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; - - kvmppc_44x_shadow_release(vcpu, i); - stlbe->word0 = 0; - kvmppc_tlbe_set_modified(vcpu, i); - KVMTRACE_5D(STLB_INVAL, vcpu, i, - stlbe->tid, stlbe->word0, stlbe->word1, - stlbe->word2, handler); + if (vcpu->arch.swap_pid) { + /* XXX Replace loop with fancy data structures. */ + down_write(¤t->mm->mmap_sem); + for (i = 0; i <= tlb_44x_hwater; i++) { + struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; + + /* Future optimization: clear only userspace mappings. */ + kvmppc_44x_shadow_release(vcpu, i); + stlbe->word0 = 0; + kvmppc_tlbe_set_modified(vcpu, i); + KVMTRACE_5D(STLB_INVAL, vcpu, i, + stlbe->tid, stlbe->word0, stlbe->word1, + stlbe->word2, handler); + } + up_write(¤t->mm->mmap_sem); + vcpu->arch.swap_pid = 0; } - up_write(¤t->mm->mmap_sem); + + vcpu->arch.shadow_pid = !usermode; } diff --git a/arch/powerpc/kvm/booke_guest.c b/arch/powerpc/kvm/booke_guest.c index 3cca079975e1..7b2591e26bae 100644 --- a/arch/powerpc/kvm/booke_guest.c +++ b/arch/powerpc/kvm/booke_guest.c @@ -486,6 +486,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.msr = 0; vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */ + vcpu->arch.shadow_pid = 1; + /* Eye-catching number so we know if the guest takes an interrupt * before it's programmed its own IVPR. */ vcpu->arch.ivpr = 0x55550000; diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 564ea32ecbac..95e165baf85f 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -332,7 +332,7 @@ lightweight_exit: mfspr r3, SPRN_PID stw r3, VCPU_HOST_PID(r4) - lwz r3, VCPU_PID(r4) + lwz r3, VCPU_SHADOW_PID(r4) mtspr SPRN_PID, r3 /* Prevent all asynchronous TLB updates. */ diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index c3ed63b22210..0fce4fbdc20d 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -508,7 +508,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) case SPRN_MMUCR: vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break; case SPRN_PID: - vcpu->arch.pid = vcpu->arch.gpr[rs]; break; + kvmppc_set_pid(vcpu, vcpu->arch.gpr[rs]); break; case SPRN_CCR0: vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break; case SPRN_CCR1: -- cgit v1.2.3 From 0bd595fc222583ca260f259698f72e9946c6e524 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Thu, 11 Sep 2008 10:04:29 -0500 Subject: KVM: ppc: kvmppc_44x_shadow_release() does not require mmap_sem to be locked And it gets in the way of get_user_pages_fast(). Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/kvm/44x_tlb.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 3594bbd1f618..7b11fd7be542 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -110,7 +110,6 @@ static int kvmppc_44x_tlbe_is_writable(struct tlbe *tlbe) return tlbe->word2 & (PPC44x_TLB_SW|PPC44x_TLB_UW); } -/* Must be called with mmap_sem locked for writing. */ static void kvmppc_44x_shadow_release(struct kvm_vcpu *vcpu, unsigned int index) { @@ -150,17 +149,16 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, /* Get reference to new page. */ down_read(¤t->mm->mmap_sem); new_page = gfn_to_page(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); if (is_error_page(new_page)) { printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn); kvm_release_page_clean(new_page); - up_read(¤t->mm->mmap_sem); return; } hpaddr = page_to_phys(new_page); /* Drop reference to old page. */ kvmppc_44x_shadow_release(vcpu, victim); - up_read(¤t->mm->mmap_sem); vcpu->arch.shadow_pages[victim] = new_page; @@ -194,7 +192,6 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, int i; /* XXX Replace loop with fancy data structures. */ - down_write(¤t->mm->mmap_sem); for (i = 0; i <= tlb_44x_hwater; i++) { struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; unsigned int tid; @@ -219,7 +216,6 @@ void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, gva_t eaddr, stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, handler); } - up_write(¤t->mm->mmap_sem); } /* Invalidate all mappings on the privilege switch after PID has been changed. @@ -231,7 +227,6 @@ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) if (vcpu->arch.swap_pid) { /* XXX Replace loop with fancy data structures. */ - down_write(¤t->mm->mmap_sem); for (i = 0; i <= tlb_44x_hwater; i++) { struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i]; @@ -243,7 +238,6 @@ void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) stlbe->tid, stlbe->word0, stlbe->word1, stlbe->word2, handler); } - up_write(¤t->mm->mmap_sem); vcpu->arch.swap_pid = 0; } -- cgit v1.2.3 From 4c2155ce81c193788082d4b8cdbc26d79edebc58 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 16 Sep 2008 20:54:47 -0300 Subject: KVM: switch to get_user_pages_fast Convert gfn_to_pfn to use get_user_pages_fast, which can do lockless pagetable lookups on x86. Kernel compilation on 4-way guest is 3.7% faster on VMX. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/powerpc/kvm/44x_tlb.c | 2 -- arch/x86/kvm/mmu.c | 23 +++++++++-------------- arch/x86/kvm/paging_tmpl.h | 8 +------- arch/x86/kvm/vmx.c | 4 ---- arch/x86/kvm/x86.c | 6 ------ virt/kvm/kvm_main.c | 10 +++++----- 6 files changed, 15 insertions(+), 38 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 7b11fd7be542..2e227a412bc2 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -147,9 +147,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, stlbe = &vcpu->arch.shadow_tlb[victim]; /* Get reference to new page. */ - down_read(¤t->mm->mmap_sem); new_page = gfn_to_page(vcpu->kvm, gfn); - up_read(¤t->mm->mmap_sem); if (is_error_page(new_page)) { printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn); kvm_release_page_clean(new_page); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index bce3e25ec79b..5779a2323e23 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -405,16 +405,19 @@ static int host_largepage_backed(struct kvm *kvm, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr; + int ret = 0; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) - return 0; + return ret; + down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); if (vma && is_vm_hugetlb_page(vma)) - return 1; + ret = 1; + up_read(¤t->mm->mmap_sem); - return 0; + return ret; } static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn) @@ -1140,9 +1143,7 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) if (gpa == UNMAPPED_GVA) return NULL; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); return page; } @@ -1330,16 +1331,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) pfn_t pfn; unsigned long mmu_seq; - down_read(¤t->mm->mmap_sem); if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { gfn &= ~(KVM_PAGES_PER_HPAGE-1); largepage = 1; } mmu_seq = vcpu->kvm->mmu_notifier_seq; - /* implicit mb(), we'll read before PT lock is unlocked */ + smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); - up_read(¤t->mm->mmap_sem); /* mmio */ if (is_error_pfn(pfn)) { @@ -1488,15 +1487,13 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, if (r) return r; - down_read(¤t->mm->mmap_sem); if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { gfn &= ~(KVM_PAGES_PER_HPAGE-1); largepage = 1; } mmu_seq = vcpu->kvm->mmu_notifier_seq; - /* implicit mb(), we'll read before PT lock is unlocked */ + smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); - up_read(¤t->mm->mmap_sem); if (is_error_pfn(pfn)) { kvm_release_pfn_clean(pfn); return 1; @@ -1809,15 +1806,13 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; - down_read(¤t->mm->mmap_sem); if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) { gfn &= ~(KVM_PAGES_PER_HPAGE-1); vcpu->arch.update_pte.largepage = 1; } vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq; - /* implicit mb(), we'll read before PT lock is unlocked */ + smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); - up_read(¤t->mm->mmap_sem); if (is_error_pfn(pfn)) { kvm_release_pfn_clean(pfn); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index b671f61be41e..6dd08e096e24 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -102,14 +102,10 @@ static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, pt_element_t *table; struct page *page; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(kvm, table_gfn); - up_read(¤t->mm->mmap_sem); table = kmap_atomic(page, KM_USER0); - ret = CMPXCHG(&table[index], orig_pte, new_pte); - kunmap_atomic(table, KM_USER0); kvm_release_page_dirty(page); @@ -418,7 +414,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, return 0; } - down_read(¤t->mm->mmap_sem); if (walker.level == PT_DIRECTORY_LEVEL) { gfn_t large_gfn; large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1); @@ -428,9 +423,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, } } mmu_seq = vcpu->kvm->mmu_notifier_seq; - /* implicit mb(), we'll read before PT lock is unlocked */ + smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, walker.gfn); - up_read(¤t->mm->mmap_sem); /* mmio */ if (is_error_pfn(pfn)) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 046a91b5a4ba..025bf4011abc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2010,9 +2010,7 @@ static int alloc_apic_access_page(struct kvm *kvm) if (r) goto out; - down_read(¤t->mm->mmap_sem); kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); - up_read(¤t->mm->mmap_sem); out: up_write(&kvm->slots_lock); return r; @@ -2034,10 +2032,8 @@ static int alloc_identity_pagetable(struct kvm *kvm) if (r) goto out; - down_read(¤t->mm->mmap_sem); kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); out: up_write(&kvm->slots_lock); return r; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 61eddbeabeb4..108f07267e87 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -946,10 +946,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* ...but clean it before doing the actual write */ vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); - down_read(¤t->mm->mmap_sem); vcpu->arch.time_page = gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); if (is_error_page(vcpu->arch.time_page)) { kvm_release_page_clean(vcpu->arch.time_page); @@ -2322,9 +2320,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, val = *(u64 *)new; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); kaddr = kmap_atomic(page, KM_USER0); set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); @@ -3089,9 +3085,7 @@ static void vapic_enter(struct kvm_vcpu *vcpu) if (!apic || !apic->vapic_addr) return; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); vcpu->arch.apic->vapic_page = page; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2907d05cfcc3..cd34f73513d3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -723,9 +723,6 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_hva); -/* - * Requires current->mm->mmap_sem to be held - */ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { struct page *page[1]; @@ -741,20 +738,23 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) return page_to_pfn(bad_page); } - npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page, - NULL); + npages = get_user_pages_fast(addr, 1, 1, page); if (unlikely(npages != 1)) { struct vm_area_struct *vma; + down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); + if (vma == NULL || addr < vma->vm_start || !(vma->vm_flags & VM_PFNMAP)) { + up_read(¤t->mm->mmap_sem); get_page(bad_page); return page_to_pfn(bad_page); } pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + up_read(¤t->mm->mmap_sem); BUG_ON(!is_mmio_pfn(pfn)); } else pfn = page_to_pfn(page[0]); -- cgit v1.2.3 From 463baa8a0947f858d6db1c56d87eeaf1176ba7bb Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 16 Oct 2008 20:29:07 +1100 Subject: powerpc: fix linux-next build failure Today's linux-next build (powerpc allyesconfig) failed like this: In file included from arch/powerpc/include/asm/mmu-hash64.h:17, from arch/powerpc/include/asm/mmu.h:8, from arch/powerpc/include/asm/pgtable.h:8, from arch/powerpc/mm/slb.c:20: arch/powerpc/include/asm/page.h:76: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'memstart_addr' arch/powerpc/include/asm/page.h:77: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'kernstart_addr' Caused by commit 600715dcdf567c86f8b2c6173fcfb4b873e25a19 ("generic: add phys_addr_t for holding physical addresses") from the tip-core tree. This only fails if CONFIG_RELOCATABLE is set. So include that instead of asm/types.h in asm/page.h for the CONFIG_RELOCATABLE case. Signed-off-by: Stephen Rothwell Cc: ppc-dev Cc: Andrew Morton Cc: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/powerpc/include/asm/page.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index e088545cb3f5..94fe5138b30f 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -10,9 +10,13 @@ * 2 of the License, or (at your option) any later version. */ +#ifndef __ASSEMBLY__ +#include +#else +#include +#endif #include #include -#include /* * On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software -- cgit v1.2.3 From 0b59268285ca6cdc46191f2995bf632088e3e277 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 16 Oct 2008 15:39:57 +0200 Subject: [PATCH] remove unused ibcs2/PER_SVR4 in SET_PERSONALITY The SET_PERSONALITY macro is always called with a second argument of 0. Remove the ibcs argument and the various tests to set the PER_SVR4 personality. Signed-off-by: Martin Schwidefsky --- arch/alpha/include/asm/elf.h | 4 ++-- arch/arm/include/asm/elf.h | 2 +- arch/avr32/include/asm/elf.h | 2 +- arch/blackfin/include/asm/elf.h | 2 +- arch/h8300/include/asm/elf.h | 2 +- arch/ia64/ia32/binfmt_elf32.c | 2 +- arch/ia64/ia32/ia32priv.h | 4 ++-- arch/ia64/include/asm/elf.h | 2 +- arch/m68knommu/include/asm/elf.h | 2 +- arch/mips/include/asm/elf.h | 10 +++------- arch/parisc/kernel/binfmt_elf32.c | 2 +- arch/powerpc/include/asm/elf.h | 4 ++-- arch/s390/include/asm/elf.h | 8 +++----- arch/sh/include/asm/elf.h | 2 +- arch/sparc/include/asm/elf_32.h | 2 +- arch/sparc/include/asm/elf_64.h | 6 ++---- fs/binfmt_elf.c | 6 +++--- include/asm-cris/elf.h | 2 +- include/asm-frv/elf.h | 2 +- include/asm-m32r/elf.h | 2 +- include/asm-m68k/elf.h | 2 +- include/asm-mn10300/elf.h | 2 +- include/asm-parisc/elf.h | 2 +- include/asm-um/elf-i386.h | 2 +- include/asm-um/elf-ppc.h | 2 +- include/asm-um/elf-x86_64.h | 2 +- include/asm-x86/elf.h | 4 ++-- include/asm-xtensa/elf.h | 2 +- 28 files changed, 39 insertions(+), 47 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h index fc1002ea1e0c..5c75c1b2352a 100644 --- a/arch/alpha/include/asm/elf.h +++ b/arch/alpha/include/asm/elf.h @@ -144,9 +144,9 @@ extern int dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task); : amask (AMASK_CIX) ? "ev6" : "ev67"); \ }) -#define SET_PERSONALITY(EX, IBCS2) \ +#define SET_PERSONALITY(EX) \ set_personality(((EX).e_flags & EF_ALPHA_32BIT) \ - ? PER_LINUX_32BIT : (IBCS2) ? PER_SVR4 : PER_LINUX) + ? PER_LINUX_32BIT : PER_LINUX) extern int alpha_l1i_cacheshape; extern int alpha_l1d_cacheshape; diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index 5be016980c19..a58378c343b9 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -107,6 +107,6 @@ extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int); #define ELF_PLAT_INIT(_r, load_addr) (_r)->ARM_r0 = 0 extern void elf_set_personality(const struct elf32_hdr *); -#define SET_PERSONALITY(ex, ibcs2) elf_set_personality(&(ex)) +#define SET_PERSONALITY(ex) elf_set_personality(&(ex)) #endif diff --git a/arch/avr32/include/asm/elf.h b/arch/avr32/include/asm/elf.h index 64ce40ee1d58..d5d1d41c600a 100644 --- a/arch/avr32/include/asm/elf.h +++ b/arch/avr32/include/asm/elf.h @@ -103,6 +103,6 @@ typedef struct user_fpu_struct elf_fpregset_t; #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX_32BIT) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX_32BIT) #endif /* __ASM_AVR32_ELF_H */ diff --git a/arch/blackfin/include/asm/elf.h b/arch/blackfin/include/asm/elf.h index 67a03a8a353e..cdbfcfc30f6a 100644 --- a/arch/blackfin/include/asm/elf.h +++ b/arch/blackfin/include/asm/elf.h @@ -122,6 +122,6 @@ do { \ #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif diff --git a/arch/h8300/include/asm/elf.h b/arch/h8300/include/asm/elf.h index a8b57d1f4128..94e2284c8816 100644 --- a/arch/h8300/include/asm/elf.h +++ b/arch/h8300/include/asm/elf.h @@ -55,7 +55,7 @@ typedef unsigned long elf_fpregset_t; #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #define R_H8_NONE 0 #define R_H8_DIR32 1 diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c index 4f0c30c38e99..f92bdaac8976 100644 --- a/arch/ia64/ia32/binfmt_elf32.c +++ b/arch/ia64/ia32/binfmt_elf32.c @@ -41,7 +41,7 @@ randomize_stack_top(unsigned long stack_top); #define elf_map elf32_map #undef SET_PERSONALITY -#define SET_PERSONALITY(ex, ibcs2) elf32_set_personality() +#define SET_PERSONALITY(ex) elf32_set_personality() #define elf_read_implies_exec(ex, have_pt_gnu_stack) (!(have_pt_gnu_stack)) diff --git a/arch/ia64/ia32/ia32priv.h b/arch/ia64/ia32/ia32priv.h index dd0c53687a96..0f15349c3c6b 100644 --- a/arch/ia64/ia32/ia32priv.h +++ b/arch/ia64/ia32/ia32priv.h @@ -332,8 +332,8 @@ void ia64_elf32_init(struct pt_regs *regs); #define ELF_PLATFORM NULL #ifdef __KERNEL__ -# define SET_PERSONALITY(EX,IBCS2) \ - (current->personality = (IBCS2) ? PER_SVR4 : PER_LINUX) +# define SET_PERSONALITY(EX) \ + (current->personality = PER_LINUX) #endif #define IA32_EFLAG 0x200 diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h index 2acb6b6543c9..86eddee029cb 100644 --- a/arch/ia64/include/asm/elf.h +++ b/arch/ia64/include/asm/elf.h @@ -202,7 +202,7 @@ extern void ia64_elf_core_copy_regs (struct pt_regs *src, elf_gregset_t dst); relevant until we have real hardware to play with... */ #define ELF_PLATFORM NULL -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #define elf_read_implies_exec(ex, executable_stack) \ ((executable_stack!=EXSTACK_DISABLE_X) && ((ex).e_flags & EF_IA_64_LINUX_EXECUTABLE_STACK) != 0) diff --git a/arch/m68knommu/include/asm/elf.h b/arch/m68knommu/include/asm/elf.h index 27f0ec70fba8..b8046837f384 100644 --- a/arch/m68knommu/include/asm/elf.h +++ b/arch/m68knommu/include/asm/elf.h @@ -105,6 +105,6 @@ typedef struct user_m68kfp_struct elf_fpregset_t; #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index f69f7acba637..a8eac1697b3d 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -247,10 +247,8 @@ extern struct mips_abi mips_abi_n32; #ifdef CONFIG_32BIT -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ do { \ - if (ibcs2) \ - set_personality(PER_SVR4); \ set_personality(PER_LINUX); \ \ current->thread.abi = &mips_abi; \ @@ -296,7 +294,7 @@ do { \ #define __SET_PERSONALITY32(ex) do { } while (0) #endif -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ do { \ clear_thread_flag(TIF_32BIT_REGS); \ clear_thread_flag(TIF_32BIT_ADDR); \ @@ -306,9 +304,7 @@ do { \ else \ current->thread.abi = &mips_abi; \ \ - if (ibcs2) \ - set_personality(PER_SVR4); \ - else if (current->personality != PER_LINUX32) \ + if (current->personality != PER_LINUX32) \ set_personality(PER_LINUX); \ } while (0) diff --git a/arch/parisc/kernel/binfmt_elf32.c b/arch/parisc/kernel/binfmt_elf32.c index ecb10a4f63c6..f61692d2b557 100644 --- a/arch/parisc/kernel/binfmt_elf32.c +++ b/arch/parisc/kernel/binfmt_elf32.c @@ -85,7 +85,7 @@ struct elf_prpsinfo32 * could set a processor dependent flag in the thread_struct. */ -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ set_thread_flag(TIF_32BIT); \ current->thread.map_base = DEFAULT_MAP_BASE32; \ current->thread.task_size = DEFAULT_TASK_SIZE32 \ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 64c6ee22eefd..d812929390e4 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -232,7 +232,7 @@ typedef elf_vrregset_t elf_fpxregset_t; #endif /* __powerpc64__ */ #ifdef __powerpc64__ -# define SET_PERSONALITY(ex, ibcs2) \ +# define SET_PERSONALITY(ex) \ do { \ unsigned long new_flags = 0; \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ @@ -256,7 +256,7 @@ do { \ # define elf_read_implies_exec(ex, exec_stk) (test_thread_flag(TIF_32BIT) ? \ (exec_stk != EXSTACK_DISABLE_X) : 0) #else -# define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +# define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif /* __powerpc64__ */ extern int dcache_bsize; diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 3cad56923815..261785ab5b22 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -166,13 +166,11 @@ extern char elf_platform[]; #define ELF_PLATFORM (elf_platform) #ifndef __s390x__ -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #else /* __s390x__ */ -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ do { \ - if (ibcs2) \ - set_personality(PER_SVR4); \ - else if (current->personality != PER_LINUX32) \ + if (current->personality != PER_LINUX32) \ set_personality(PER_LINUX); \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ set_thread_flag(TIF_31BIT); \ diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index f01449a8d378..ee02db110f0d 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -189,7 +189,7 @@ do { \ } while (0) #endif -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX_32BIT) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX_32BIT) struct task_struct; extern int dump_task_regs (struct task_struct *, elf_gregset_t *); extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *); diff --git a/arch/sparc/include/asm/elf_32.h b/arch/sparc/include/asm/elf_32.h index b7ab60547827..381a1b5256d6 100644 --- a/arch/sparc/include/asm/elf_32.h +++ b/arch/sparc/include/asm/elf_32.h @@ -137,6 +137,6 @@ typedef struct { #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif /* !(__ASMSPARC_ELF_H) */ diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index 0818a1308f4e..425c2f9be6d5 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -195,7 +195,7 @@ static inline unsigned int sparc64_elf_hwcap(void) #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ do { unsigned long new_flags = current_thread_info()->flags; \ new_flags &= _TIF_32BIT; \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ @@ -208,9 +208,7 @@ do { unsigned long new_flags = current_thread_info()->flags; \ else \ clear_thread_flag(TIF_ABI_PENDING); \ /* flush_thread will update pgd cache */ \ - if (ibcs2) \ - set_personality(PER_SVR4); \ - else if (current->personality != PER_LINUX32) \ + if (current->personality != PER_LINUX32) \ set_personality(PER_LINUX); \ } while (0) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 655ed8d30a86..c76afa26edf7 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -683,7 +683,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) * switch really is going to happen - do this in * flush_thread(). - akpm */ - SET_PERSONALITY(loc->elf_ex, 0); + SET_PERSONALITY(loc->elf_ex); interpreter = open_exec(elf_interpreter); retval = PTR_ERR(interpreter); @@ -734,7 +734,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) goto out_free_dentry; } else { /* Executables without an interpreter also need a personality */ - SET_PERSONALITY(loc->elf_ex, 0); + SET_PERSONALITY(loc->elf_ex); } /* Flush all traces of the currently running executable */ @@ -748,7 +748,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) /* Do this immediately, since STACK_TOP as used in setup_arg_pages may depend on the personality. */ - SET_PERSONALITY(loc->elf_ex, 0); + SET_PERSONALITY(loc->elf_ex); if (elf_read_implies_exec(loc->elf_ex, executable_stack)) current->personality |= READ_IMPLIES_EXEC; diff --git a/include/asm-cris/elf.h b/include/asm-cris/elf.h index 001f64ad11e8..f0d17fbc81ba 100644 --- a/include/asm-cris/elf.h +++ b/include/asm-cris/elf.h @@ -88,6 +88,6 @@ typedef unsigned long elf_fpregset_t; #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif diff --git a/include/asm-frv/elf.h b/include/asm-frv/elf.h index 9fb946bb7dc9..7279ec07d62e 100644 --- a/include/asm-frv/elf.h +++ b/include/asm-frv/elf.h @@ -137,6 +137,6 @@ do { \ #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif diff --git a/include/asm-m32r/elf.h b/include/asm-m32r/elf.h index 67bcd77494a5..0cc34c94bf2b 100644 --- a/include/asm-m32r/elf.h +++ b/include/asm-m32r/elf.h @@ -129,6 +129,6 @@ typedef elf_fpreg_t elf_fpregset_t; intent than poking at uname or /proc/cpuinfo. */ #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif /* _ASM_M32R__ELF_H */ diff --git a/include/asm-m68k/elf.h b/include/asm-m68k/elf.h index 14ea42152b97..0b0f49eb876b 100644 --- a/include/asm-m68k/elf.h +++ b/include/asm-m68k/elf.h @@ -114,6 +114,6 @@ typedef struct user_m68kfp_struct elf_fpregset_t; #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif diff --git a/include/asm-mn10300/elf.h b/include/asm-mn10300/elf.h index 256a70466ca4..bf09f8bb392e 100644 --- a/include/asm-mn10300/elf.h +++ b/include/asm-mn10300/elf.h @@ -141,7 +141,7 @@ do { \ #define ELF_PLATFORM (NULL) #ifdef __KERNEL__ -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) #endif #endif /* _ASM_ELF_H */ diff --git a/include/asm-parisc/elf.h b/include/asm-parisc/elf.h index d0a4a8262818..7fa675799e6d 100644 --- a/include/asm-parisc/elf.h +++ b/include/asm-parisc/elf.h @@ -236,7 +236,7 @@ typedef unsigned long elf_greg_t; #define ELF_PLATFORM ("PARISC\0") -#define SET_PERSONALITY(ex, ibcs2) \ +#define SET_PERSONALITY(ex) \ current->personality = PER_LINUX; \ current->thread.map_base = DEFAULT_MAP_BASE; \ current->thread.task_size = DEFAULT_TASK_SIZE \ diff --git a/include/asm-um/elf-i386.h b/include/asm-um/elf-i386.h index 23d6893e8617..d0da9d7c5371 100644 --- a/include/asm-um/elf-i386.h +++ b/include/asm-um/elf-i386.h @@ -86,7 +86,7 @@ extern long elf_aux_hwcap; extern char * elf_aux_platform; #define ELF_PLATFORM (elf_aux_platform) -#define SET_PERSONALITY(ex, ibcs2) do { } while (0) +#define SET_PERSONALITY(ex) do { } while (0) extern unsigned long vsyscall_ehdr; extern unsigned long vsyscall_end; diff --git a/include/asm-um/elf-ppc.h b/include/asm-um/elf-ppc.h index d3b90b7ac3e9..af9463cd8ce5 100644 --- a/include/asm-um/elf-ppc.h +++ b/include/asm-um/elf-ppc.h @@ -5,7 +5,7 @@ extern long elf_aux_hwcap; #define ELF_HWCAP (elf_aux_hwcap) -#define SET_PERSONALITY(ex, ibcs2) do ; while(0) +#define SET_PERSONALITY(ex) do ; while(0) #define ELF_EXEC_PAGESIZE 4096 diff --git a/include/asm-um/elf-x86_64.h b/include/asm-um/elf-x86_64.h index 3b2d5224a7e1..6e8a9195e952 100644 --- a/include/asm-um/elf-x86_64.h +++ b/include/asm-um/elf-x86_64.h @@ -114,6 +114,6 @@ extern long elf_aux_hwcap; #define ELF_PLATFORM "x86_64" -#define SET_PERSONALITY(ex, ibcs2) do ; while(0) +#define SET_PERSONALITY(ex) do ; while(0) #endif diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h index 5c4745bec906..26bc15f01e78 100644 --- a/include/asm-x86/elf.h +++ b/include/asm-x86/elf.h @@ -186,7 +186,7 @@ do { \ set_fs(USER_DS); \ } while (0) -#define COMPAT_SET_PERSONALITY(ex, ibcs2) \ +#define COMPAT_SET_PERSONALITY(ex) \ do { \ if (test_thread_flag(TIF_IA32)) \ clear_thread_flag(TIF_ABI_PENDING); \ @@ -267,7 +267,7 @@ extern int force_personality32; For the moment, we have only optimizations for the Intel generations, but that could change... */ -#define SET_PERSONALITY(ex, ibcs2) set_personality_64bit() +#define SET_PERSONALITY(ex) set_personality_64bit() /* * An executable for which elf_read_implies_exec() returns TRUE will diff --git a/include/asm-xtensa/elf.h b/include/asm-xtensa/elf.h index ca6e5101a2cb..c3f53e755ca5 100644 --- a/include/asm-xtensa/elf.h +++ b/include/asm-xtensa/elf.h @@ -189,7 +189,7 @@ typedef struct { #endif } elf_xtregs_t; -#define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX_32BIT) +#define SET_PERSONALITY(ex) set_personality(PER_LINUX_32BIT) struct task_struct; -- cgit v1.2.3 From f7a5000f7a8924e9c5fad1801616601d6dc65a17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Oct 2008 22:02:05 -0700 Subject: compat: move cp_compat_stat to common code struct stat / compat_stat is the same on all architectures, so cp_compat_stat should be, too. Turns out it is, except that various architectures have slightly and some high2lowuid/high2lowgid or the direct assignment instead of the SET_UID/SET_GID that expands to the correct one anyway. This patch replaces the arch-specific cp_compat_stat implementations with a common one based on the x86-64 one. Signed-off-by: Christoph Hellwig Acked-by: David S. Miller [ sparc bits ] Acked-by: Kyle McMartin [ parisc bits ] Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/ia32/sys_ia32.c | 35 ----------------------------- arch/mips/kernel/linux32.c | 35 ----------------------------- arch/parisc/kernel/sys_parisc32.c | 47 --------------------------------------- arch/powerpc/kernel/sys_ppc32.c | 36 ------------------------------ arch/s390/kernel/compat_linux.c | 35 ----------------------------- arch/sparc64/kernel/sys_sparc32.c | 35 ----------------------------- arch/x86/ia32/sys_ia32.c | 35 ----------------------------- fs/compat.c | 39 ++++++++++++++++++++++++++++++++ include/linux/compat.h | 1 - 9 files changed, 39 insertions(+), 259 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index bf196cbb3796..2362a8eefb30 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -118,41 +118,6 @@ sys32_execve (char __user *name, compat_uptr_t __user *argv, compat_uptr_t __use return error; } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) -{ - compat_ino_t ino; - int err; - - if ((u64) stat->size > MAX_NON_LFS || - !old_valid_dev(stat->dev) || - !old_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - if (clear_user(ubuf, sizeof(*ubuf))) - return -EFAULT; - - err = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev); - err |= __put_user(ino, &ubuf->st_ino); - err |= __put_user(stat->mode, &ubuf->st_mode); - err |= __put_user(stat->nlink, &ubuf->st_nlink); - err |= __put_user(high2lowuid(stat->uid), &ubuf->st_uid); - err |= __put_user(high2lowgid(stat->gid), &ubuf->st_gid); - err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev); - err |= __put_user(stat->size, &ubuf->st_size); - err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime); - err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec); - err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime); - err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec); - err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime); - err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec); - err |= __put_user(stat->blksize, &ubuf->st_blksize); - err |= __put_user(stat->blocks, &ubuf->st_blocks); - return err; -} #if PAGE_SHIFT > IA32_PAGE_SHIFT diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 2fefb14414b7..89223a9bff2c 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -63,41 +63,6 @@ #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL)) #endif -/* - * Revalidate the inode. This is required for proper NFS attribute caching. - */ - -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - struct compat_stat tmp; - - if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) - return -EOVERFLOW; - - memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = new_encode_dev(stat->dev); - tmp.st_ino = stat->ino; - if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) - return -EOVERFLOW; - tmp.st_mode = stat->mode; - tmp.st_nlink = stat->nlink; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); - tmp.st_rdev = new_encode_dev(stat->rdev); - tmp.st_size = stat->size; - tmp.st_atime = stat->atime.tv_sec; - tmp.st_mtime = stat->mtime.tv_sec; - tmp.st_ctime = stat->ctime.tv_sec; -#ifdef STAT_HAVE_NSEC - tmp.st_atime_nsec = stat->atime.tv_nsec; - tmp.st_mtime_nsec = stat->mtime.tv_nsec; - tmp.st_ctime_nsec = stat->ctime.tv_nsec; -#endif - tmp.st_blocks = stat->blocks; - tmp.st_blksize = stat->blksize; - return copy_to_user(statbuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; -} - asmlinkage unsigned long sys32_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 71efd6a28e2a..2c3af17e049c 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -237,53 +237,6 @@ int sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - compat_ino_t ino; - int err; - - if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) || - !new_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - err = put_user(new_encode_dev(stat->dev), &statbuf->st_dev); - err |= put_user(ino, &statbuf->st_ino); - err |= put_user(stat->mode, &statbuf->st_mode); - err |= put_user(stat->nlink, &statbuf->st_nlink); - err |= put_user(0, &statbuf->st_reserved1); - err |= put_user(0, &statbuf->st_reserved2); - err |= put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev); - err |= put_user(stat->size, &statbuf->st_size); - err |= put_user(stat->atime.tv_sec, &statbuf->st_atime); - err |= put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); - err |= put_user(stat->mtime.tv_sec, &statbuf->st_mtime); - err |= put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); - err |= put_user(stat->ctime.tv_sec, &statbuf->st_ctime); - err |= put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); - err |= put_user(stat->blksize, &statbuf->st_blksize); - err |= put_user(stat->blocks, &statbuf->st_blocks); - err |= put_user(0, &statbuf->__unused1); - err |= put_user(0, &statbuf->__unused2); - err |= put_user(0, &statbuf->__unused3); - err |= put_user(0, &statbuf->__unused4); - err |= put_user(0, &statbuf->__unused5); - err |= put_user(0, &statbuf->st_fstype); /* not avail */ - err |= put_user(0, &statbuf->st_realdev); /* not avail */ - err |= put_user(0, &statbuf->st_basemode); /* not avail */ - err |= put_user(0, &statbuf->st_spareshort); - err |= put_user(stat->uid, &statbuf->st_uid); - err |= put_user(stat->gid, &statbuf->st_gid); - err |= put_user(0, &statbuf->st_spare4[0]); - err |= put_user(0, &statbuf->st_spare4[1]); - err |= put_user(0, &statbuf->st_spare4[2]); - - return err; -} - /*** copied from mips64 ***/ /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index ff7de7b0797e..d00599bb24a1 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -61,42 +61,6 @@ asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - compat_ino_t ino; - long err; - - if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) || - !new_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - err = access_ok(VERIFY_WRITE, statbuf, sizeof(*statbuf)) ? 0 : -EFAULT; - err |= __put_user(new_encode_dev(stat->dev), &statbuf->st_dev); - err |= __put_user(ino, &statbuf->st_ino); - err |= __put_user(stat->mode, &statbuf->st_mode); - err |= __put_user(stat->nlink, &statbuf->st_nlink); - err |= __put_user(stat->uid, &statbuf->st_uid); - err |= __put_user(stat->gid, &statbuf->st_gid); - err |= __put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev); - err |= __put_user(stat->size, &statbuf->st_size); - err |= __put_user(stat->atime.tv_sec, &statbuf->st_atime); - err |= __put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); - err |= __put_user(stat->mtime.tv_sec, &statbuf->st_mtime); - err |= __put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); - err |= __put_user(stat->ctime.tv_sec, &statbuf->st_ctime); - err |= __put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); - err |= __put_user(stat->blksize, &statbuf->st_blksize); - err |= __put_user(stat->blocks, &statbuf->st_blocks); - err |= __put_user(0, &statbuf->__unused4[0]); - err |= __put_user(0, &statbuf->__unused4[1]); - - return err; -} - /* Note: it is necessary to treat option as an unsigned int, * with the corresponding cast to a signed int to insure that the * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 98e246dc0233..9b471d785ec1 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -362,41 +362,6 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned return sys_ftruncate(fd, (high << 32) | low); } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - compat_ino_t ino; - int err; - - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - err = put_user(old_encode_dev(stat->dev), &statbuf->st_dev); - err |= put_user(stat->ino, &statbuf->st_ino); - err |= put_user(stat->mode, &statbuf->st_mode); - err |= put_user(stat->nlink, &statbuf->st_nlink); - err |= put_user(high2lowuid(stat->uid), &statbuf->st_uid); - err |= put_user(high2lowgid(stat->gid), &statbuf->st_gid); - err |= put_user(old_encode_dev(stat->rdev), &statbuf->st_rdev); - err |= put_user(stat->size, &statbuf->st_size); - err |= put_user(stat->atime.tv_sec, &statbuf->st_atime); - err |= put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); - err |= put_user(stat->mtime.tv_sec, &statbuf->st_mtime); - err |= put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); - err |= put_user(stat->ctime.tv_sec, &statbuf->st_ctime); - err |= put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); - err |= put_user(stat->blksize, &statbuf->st_blksize); - err |= put_user(stat->blocks, &statbuf->st_blocks); -/* fixme - err |= put_user(0, &statbuf->__unused4[0]); - err |= put_user(0, &statbuf->__unused4[1]); -*/ - return err; -} - asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval) { diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 3320c9d0075f..73a33dc3bcca 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -148,41 +148,6 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned return sys_ftruncate(fd, (high << 32) | low); } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - compat_ino_t ino; - int err; - - if (stat->size > MAX_NON_LFS || !old_valid_dev(stat->dev) || - !old_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - err = put_user(old_encode_dev(stat->dev), &statbuf->st_dev); - err |= put_user(stat->ino, &statbuf->st_ino); - err |= put_user(stat->mode, &statbuf->st_mode); - err |= put_user(stat->nlink, &statbuf->st_nlink); - err |= put_user(high2lowuid(stat->uid), &statbuf->st_uid); - err |= put_user(high2lowgid(stat->gid), &statbuf->st_gid); - err |= put_user(old_encode_dev(stat->rdev), &statbuf->st_rdev); - err |= put_user(stat->size, &statbuf->st_size); - err |= put_user(stat->atime.tv_sec, &statbuf->st_atime); - err |= put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); - err |= put_user(stat->mtime.tv_sec, &statbuf->st_mtime); - err |= put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); - err |= put_user(stat->ctime.tv_sec, &statbuf->st_ctime); - err |= put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); - err |= put_user(stat->blksize, &statbuf->st_blksize); - err |= put_user(stat->blocks, &statbuf->st_blocks); - err |= put_user(0, &statbuf->__unused4[0]); - err |= put_user(0, &statbuf->__unused4[1]); - - return err; -} - static int cp_compat_stat64(struct kstat *stat, struct compat_stat64 __user *statbuf) { diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index beda4232ce69..4d3ad8d78a4d 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -49,41 +49,6 @@ #define AA(__x) ((unsigned long)(__x)) -int cp_compat_stat(struct kstat *kbuf, struct compat_stat __user *ubuf) -{ - compat_ino_t ino; - - typeof(ubuf->st_uid) uid = 0; - typeof(ubuf->st_gid) gid = 0; - SET_UID(uid, kbuf->uid); - SET_GID(gid, kbuf->gid); - if (!old_valid_dev(kbuf->dev) || !old_valid_dev(kbuf->rdev)) - return -EOVERFLOW; - if (kbuf->size >= 0x7fffffff) - return -EOVERFLOW; - ino = kbuf->ino; - if (sizeof(ino) < sizeof(kbuf->ino) && ino != kbuf->ino) - return -EOVERFLOW; - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct compat_stat)) || - __put_user(old_encode_dev(kbuf->dev), &ubuf->st_dev) || - __put_user(ino, &ubuf->st_ino) || - __put_user(kbuf->mode, &ubuf->st_mode) || - __put_user(kbuf->nlink, &ubuf->st_nlink) || - __put_user(uid, &ubuf->st_uid) || - __put_user(gid, &ubuf->st_gid) || - __put_user(old_encode_dev(kbuf->rdev), &ubuf->st_rdev) || - __put_user(kbuf->size, &ubuf->st_size) || - __put_user(kbuf->atime.tv_sec, &ubuf->st_atime) || - __put_user(kbuf->atime.tv_nsec, &ubuf->st_atime_nsec) || - __put_user(kbuf->mtime.tv_sec, &ubuf->st_mtime) || - __put_user(kbuf->mtime.tv_nsec, &ubuf->st_mtime_nsec) || - __put_user(kbuf->ctime.tv_sec, &ubuf->st_ctime) || - __put_user(kbuf->ctime.tv_nsec, &ubuf->st_ctime_nsec) || - __put_user(kbuf->blksize, &ubuf->st_blksize) || - __put_user(kbuf->blocks, &ubuf->st_blocks)) - return -EFAULT; - return 0; -} asmlinkage long sys32_truncate64(char __user *filename, unsigned long offset_low, diff --git a/fs/compat.c b/fs/compat.c index aae13d31612f..5f9ec449c799 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -137,6 +137,45 @@ asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval _ return compat_sys_futimesat(AT_FDCWD, filename, t); } +static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) +{ + compat_ino_t ino = stat->ino; + typeof(ubuf->st_uid) uid = 0; + typeof(ubuf->st_gid) gid = 0; + int err; + + SET_UID(uid, stat->uid); + SET_GID(gid, stat->gid); + + if ((u64) stat->size > MAX_NON_LFS || + !old_valid_dev(stat->dev) || + !old_valid_dev(stat->rdev)) + return -EOVERFLOW; + if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) + return -EOVERFLOW; + + if (clear_user(ubuf, sizeof(*ubuf))) + return -EFAULT; + + err = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev); + err |= __put_user(ino, &ubuf->st_ino); + err |= __put_user(stat->mode, &ubuf->st_mode); + err |= __put_user(stat->nlink, &ubuf->st_nlink); + err |= __put_user(uid, &ubuf->st_uid); + err |= __put_user(gid, &ubuf->st_gid); + err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev); + err |= __put_user(stat->size, &ubuf->st_size); + err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime); + err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec); + err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime); + err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec); + err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime); + err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec); + err |= __put_user(stat->blksize, &ubuf->st_blksize); + err |= __put_user(stat->blocks, &ubuf->st_blocks); + return err; +} + asmlinkage long compat_sys_newstat(char __user * filename, struct compat_stat __user *statbuf) { diff --git a/include/linux/compat.h b/include/linux/compat.h index cf8d11cad5ae..999dddd8d939 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -78,7 +78,6 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; -extern int cp_compat_stat(struct kstat *, struct compat_stat __user *); extern int get_compat_timespec(struct timespec *, const struct compat_timespec __user *); extern int put_compat_timespec(const struct timespec *, struct compat_timespec __user *); -- cgit v1.2.3 From b418da16dd44810e5d5a22bba377cca80512a524 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Oct 2008 22:02:06 -0700 Subject: compat: generic compat get/settimeofday Nothing arch specific in get/settimeofday. The details of the timeval conversion varied a little from arch to arch, but all with the same results. Also add an extern declaration for sys_tz to linux/time.h because externs in .c files are fowned upon. I'll kill the externs in various other files in a sparate patch. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Hellwig Acked-by: David S. Miller [ sparc bits ] Cc: "Luck, Tony" Cc: Ralf Baechle Acked-by: Kyle McMartin Cc: Matthew Wilcox Cc: Grant Grundler Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/ia32/ia32_entry.S | 4 +-- arch/ia64/ia32/sys_ia32.c | 56 ------------------------------- arch/mips/kernel/linux32.c | 66 ------------------------------------- arch/mips/kernel/scall64-n32.S | 4 +-- arch/mips/kernel/scall64-o32.S | 4 +-- arch/parisc/kernel/sys_parisc32.c | 58 --------------------------------- arch/parisc/kernel/syscall_table.S | 4 +-- arch/powerpc/kernel/sys_ppc32.c | 63 ----------------------------------- arch/s390/kernel/compat_linux.c | 67 -------------------------------------- arch/s390/kernel/compat_linux.h | 4 --- arch/s390/kernel/compat_wrapper.S | 12 +++---- arch/s390/kernel/syscalls.S | 4 +-- arch/sparc64/kernel/sys_sparc32.c | 62 ----------------------------------- arch/sparc64/kernel/systbls.S | 4 +-- arch/x86/ia32/ia32entry.S | 4 +-- arch/x86/ia32/sys_ia32.c | 64 ------------------------------------ include/linux/compat.h | 5 +++ include/linux/time.h | 2 ++ kernel/compat.c | 58 +++++++++++++++++++++++++++++++++ 19 files changed, 85 insertions(+), 460 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index ff88c48c5d19..53505bb04771 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -251,8 +251,8 @@ ia32_syscall_table: data8 compat_sys_setrlimit /* 75 */ data8 compat_sys_old_getrlimit data8 compat_sys_getrusage - data8 sys32_gettimeofday - data8 sys32_settimeofday + data8 compat_sys_gettimeofday + data8 compat_sys_settimeofday data8 sys32_getgroups16 /* 80 */ data8 sys32_setgroups16 data8 sys32_old_select diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 2362a8eefb30..f4430bb4bbdc 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1113,68 +1113,12 @@ sys32_pipe (int __user *fd) return retval; } -static inline long -get_tv32 (struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->tv_sec, &i->tv_sec) | __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long -put_tv32 (struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | __put_user(i->tv_usec, &o->tv_usec))); -} - asmlinkage unsigned long sys32_alarm (unsigned int seconds) { return alarm_setitimer(seconds); } -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long -sys32_gettimeofday (struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage long -sys32_settimeofday (struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timeval ktv; - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_tv32(&ktv, tv)) - return -EFAULT; - kts.tv_sec = ktv.tv_sec; - kts.tv_nsec = ktv.tv_usec * 1000; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - struct sel_arg_struct { unsigned int n; unsigned int inp; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 89223a9bff2c..aa2c55e3b55f 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -133,72 +133,6 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long __dummy, return sys_ftruncate(fd, merge_64(a2, a3)); } -static inline long -get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->tv_sec, &i->tv_sec) | - __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long -put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - -extern struct timezone sys_tz; - -asmlinkage int -sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage int -sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage int sys32_llseek(unsigned int fd, unsigned int offset_high, unsigned int offset_low, loff_t __user * result, unsigned int origin) diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 324c5499dec2..e266b3aa6560 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -214,7 +214,7 @@ EXPORT(sysn32_call_table) PTR sys_fchown PTR sys_lchown PTR sys_umask - PTR sys32_gettimeofday + PTR compat_sys_gettimeofday PTR compat_sys_getrlimit /* 6095 */ PTR compat_sys_getrusage PTR compat_sys_sysinfo @@ -279,7 +279,7 @@ EXPORT(sysn32_call_table) PTR sys_chroot PTR sys_sync PTR sys_acct - PTR sys32_settimeofday + PTR compat_sys_settimeofday PTR compat_sys_mount /* 6160 */ PTR sys_umount PTR sys_swapon diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 85fedac99a57..6c7ef8313ebd 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -283,8 +283,8 @@ sys_call_table: PTR compat_sys_setrlimit /* 4075 */ PTR compat_sys_getrlimit PTR compat_sys_getrusage - PTR sys32_gettimeofday - PTR sys32_settimeofday + PTR compat_sys_gettimeofday + PTR compat_sys_settimeofday PTR sys_getgroups /* 4080 */ PTR sys_setgroups PTR sys_ni_syscall /* old_select */ diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 2c3af17e049c..0838155b7a88 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -179,64 +179,6 @@ asmlinkage long sys32_sched_rr_get_interval(pid_t pid, return ret; } -static int -put_compat_timeval(struct compat_timeval __user *u, struct timeval *t) -{ - struct compat_timeval t32; - t32.tv_sec = t->tv_sec; - t32.tv_usec = t->tv_usec; - return copy_to_user(u, &t32, sizeof t32); -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage int -sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - extern void do_gettimeofday(struct timeval *tv); - - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_compat_timeval(tv, &ktv)) - return -EFAULT; - } - if (tz) { - extern struct timezone sys_tz; - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage -int sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - /*** copied from mips64 ***/ /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 6b5ac38f5a99..c7e59f548817 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -149,8 +149,8 @@ ENTRY_COMP(getrlimit) ENTRY_COMP(getrusage) /* struct timeval and timezone are maybe?? consistent wide and narrow */ - ENTRY_DIFF(gettimeofday) - ENTRY_DIFF(settimeofday) + ENTRY_COMP(gettimeofday) + ENTRY_COMP(settimeofday) ENTRY_SAME(getgroups) /* 80 */ ENTRY_SAME(setgroups) /* struct socketaddr... */ diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index d00599bb24a1..bb1cfcfdbbbb 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -71,69 +71,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2) return sys_sysfs((int)option, arg1, arg2); } -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - - - - -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ -extern struct timezone sys_tz; - -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - - return 0; -} - - - -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - #ifdef CONFIG_SYSVIPC long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, u32 fifth) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9b471d785ec1..4646382af34f 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -279,22 +279,6 @@ asmlinkage long sys32_getegid16(void) return high2lowgid(current->egid); } -/* 32-bit timeval and related flotsam. */ - -static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, o, sizeof(*o)) || - (__get_user(o->tv_sec, &i->tv_sec) || - __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) || - __put_user(i->tv_usec, &o->tv_usec))); -} - /* * sys32_ipc() is the de-multiplexer for the SysV IPC calls in 32bit emulation. * @@ -522,57 +506,6 @@ sys32_delete_module(const char __user *name_user, unsigned int flags) #endif /* CONFIG_MODULES */ -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo) { diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 05f8516366ab..836a28842900 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -202,10 +202,6 @@ long sys32_execve(void); long sys32_init_module(void __user *umod, unsigned long len, const char __user *uargs); long sys32_delete_module(const char __user *name_user, unsigned int flags); -long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); -long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo); long sys32_pwrite64(unsigned int fd, const char __user *ubuf, diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index ee51ca9e23b5..fc2c97197a53 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -332,17 +332,17 @@ compat_sys_getrusage_wrapper: llgtr %r3,%r3 # struct rusage_emu31 * jg compat_sys_getrusage # branch to system call - .globl sys32_gettimeofday_wrapper -sys32_gettimeofday_wrapper: + .globl compat_sys_gettimeofday_wrapper +compat_sys_gettimeofday_wrapper: llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * - jg sys32_gettimeofday # branch to system call + jg compat_sys_gettimeofday # branch to system call - .globl sys32_settimeofday_wrapper -sys32_settimeofday_wrapper: + .globl compat_sys_settimeofday_wrapper +compat_sys_settimeofday_wrapper: llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * - jg sys32_settimeofday # branch to system call + jg compat_sys_settimeofday # branch to system call .globl sys32_getgroups16_wrapper sys32_getgroups16_wrapper: diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 3ae303914b42..2d61787949d5 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -86,8 +86,8 @@ SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper) SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper) /* 75 */ SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper) SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage_wrapper) -SYSCALL(sys_gettimeofday,sys_gettimeofday,sys32_gettimeofday_wrapper) -SYSCALL(sys_settimeofday,sys_settimeofday,sys32_settimeofday_wrapper) +SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper) +SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper) SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper) /* 80 old getgroups16 syscall */ SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper) /* old setgroups16 syscall */ NI_SYSCALL /* old select syscall */ diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 73a33dc3bcca..e800503879e4 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -58,15 +58,6 @@ #include #include -/* 32-bit timeval and related flotsam. */ - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - #ifdef CONFIG_SYSVIPC asmlinkage long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, u32 fifth) { @@ -487,59 +478,6 @@ asmlinkage long sys32_delete_module(const char __user *name_user) #endif /* CONFIG_MODULES */ -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage compat_ssize_t sys32_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S index 5daee4b04dd5..b2fa4c163638 100644 --- a/arch/sparc64/kernel/systbls.S +++ b/arch/sparc64/kernel/systbls.S @@ -41,8 +41,8 @@ sys_call_table32: /*100*/ .word sys32_getpriority, sys32_rt_sigreturn, sys32_rt_sigaction, sys32_rt_sigprocmask, sys32_rt_sigpending .word compat_sys_rt_sigtimedwait, sys32_rt_sigqueueinfo, compat_sys_rt_sigsuspend, sys_setresuid, sys_getresuid /*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall - .word sys32_getgroups, sys32_gettimeofday, sys32_getrusage, sys_nis_syscall, sys_getcwd -/*120*/ .word compat_sys_readv, compat_sys_writev, sys32_settimeofday, sys_fchown16, sys_fchmod + .word sys32_getgroups, compat_sys_gettimeofday, sys32_getrusage, sys_nis_syscall, sys_getcwd +/*120*/ .word compat_sys_readv, compat_sys_writev, compat_sys_settimeofday, sys_fchown16, sys_fchmod .word sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate /*130*/ .word sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall .word sys_nis_syscall, sys32_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index eb4314768bf7..256b00b61892 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -571,8 +571,8 @@ ia32_sys_call_table: .quad compat_sys_setrlimit /* 75 */ .quad compat_sys_old_getrlimit /* old_getrlimit */ .quad compat_sys_getrusage - .quad sys32_gettimeofday - .quad sys32_settimeofday + .quad compat_sys_gettimeofday + .quad compat_sys_settimeofday .quad sys_getgroups16 /* 80 */ .quad sys_setgroups16 .quad sys32_old_select diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 4d3ad8d78a4d..2e09dcd3c0a6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -367,75 +367,11 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, return 0; } -static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_READ, i, sizeof(*i))) { - err = __get_user(o->tv_sec, &i->tv_sec); - err |= __get_user(o->tv_usec, &i->tv_usec); - } - return err; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_WRITE, o, sizeof(*o))) { - err = __put_user(i->tv_sec, &o->tv_sec); - err |= __put_user(i->tv_usec, &o->tv_usec); - } - return err; -} - asmlinkage long sys32_alarm(unsigned int seconds) { return alarm_setitimer(seconds); } -/* - * Translations due to time_t size differences. Which affects all - * sorts of things, like timeval and itimerval. - */ -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - struct timeval ktv; - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_tv32(&ktv, tv)) - return -EFAULT; - kts.tv_sec = ktv.tv_sec; - kts.tv_nsec = ktv.tv_usec * NSEC_PER_USEC; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - struct sel_arg_struct { unsigned int n; unsigned int inp; diff --git a/include/linux/compat.h b/include/linux/compat.h index 999dddd8d939..f061a1ea1b74 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -234,6 +234,11 @@ extern int get_compat_itimerspec(struct itimerspec *dst, extern int put_compat_itimerspec(struct compat_itimerspec __user *dst, const struct itimerspec *src); +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); + asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int compat_printk(const char *fmt, ...); diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..51e883df0fa5 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -29,6 +29,8 @@ struct timezone { #ifdef __KERNEL__ +extern struct timezone sys_tz; + /* Parameters used to convert the timespec values: */ #define MSEC_PER_SEC 1000L #define USEC_PER_MSEC 1000L diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a8ab9a..143990e48cb9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,6 +26,64 @@ #include +/* + * Note that the native side is already converted to a timespec, because + * that's what we want anyway. + */ +static int compat_get_timeval(struct timespec *o, + struct compat_timeval __user *i) +{ + long usec; + + if (get_user(o->tv_sec, &i->tv_sec) || + get_user(usec, &i->tv_usec)) + return -EFAULT; + o->tv_nsec = usec * 1000; + return 0; +} + +static int compat_put_timeval(struct compat_timeval __user *o, + struct timeval *i) +{ + return (put_user(i->tv_sec, &o->tv_sec) || + put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0; +} + +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz) +{ + if (tv) { + struct timeval ktv; + do_gettimeofday(&ktv); + if (compat_put_timeval(tv, &ktv)) + return -EFAULT; + } + if (tz) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + + return 0; +} + +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz) +{ + struct timespec kts; + struct timezone ktz; + + if (tv) { + if (compat_get_timeval(&kts, tv)) + return -EFAULT; + } + if (tz) { + if (copy_from_user(&ktz, tz, sizeof(ktz))) + return -EFAULT; + } + + return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); +} + int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || -- cgit v1.2.3 From 3400001c531d283068a60e9f884f7de6f22314be Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 15 Oct 2008 22:02:09 -0700 Subject: powerpc: rename iommu_num_pages function to iommu_nr_pages This is a preparation patch for introducing a generic iommu_num_pages function. Signed-off-by: Joerg Roedel Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: FUJITA Tomonori Cc: Muli Ben-Yehuda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/iommu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 550a19399bfa..e2cf6320907e 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -51,7 +51,7 @@ static int protect4gb = 1; static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int); -static inline unsigned long iommu_num_pages(unsigned long vaddr, +static inline unsigned long iommu_nr_pages(unsigned long vaddr, unsigned long slen) { unsigned long npages; @@ -325,7 +325,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen); + npages = iommu_nr_pages(vaddr, slen); align = 0; if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) @@ -418,7 +418,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, unsigned long vaddr, npages; vaddr = s->dma_address & IOMMU_PAGE_MASK; - npages = iommu_num_pages(s->dma_address, s->dma_length); + npages = iommu_nr_pages(s->dma_address, s->dma_length); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -452,7 +452,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; - npages = iommu_num_pages(dma_handle, sg->dma_length); + npages = iommu_nr_pages(dma_handle, sg->dma_length); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -584,7 +584,7 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl, BUG_ON(direction == DMA_NONE); uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size); + npages = iommu_nr_pages(uaddr, size); if (tbl) { align = 0; @@ -617,7 +617,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size); + npages = iommu_nr_pages(dma_handle, size); iommu_free(tbl, dma_handle, npages); } } -- cgit v1.2.3 From 2994a3b2653a3ab04f7b1459ce2442baecb62961 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 15 Oct 2008 22:02:13 -0700 Subject: powerpc: use iommu_num_pages function in IOMMU code Signed-off-by: Joerg Roedel Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: FUJITA Tomonori Cc: Muli Ben-Yehuda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/iommu.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index e2cf6320907e..ea1ba89f9c90 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -51,17 +51,6 @@ static int protect4gb = 1; static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int); -static inline unsigned long iommu_nr_pages(unsigned long vaddr, - unsigned long slen) -{ - unsigned long npages; - - npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK); - npages >>= IOMMU_PAGE_SHIFT; - - return npages; -} - static int __init setup_protect4gb(char *str) { if (strcmp(str, "on") == 0) @@ -325,7 +314,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_nr_pages(vaddr, slen); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE); align = 0; if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) @@ -418,7 +407,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, unsigned long vaddr, npages; vaddr = s->dma_address & IOMMU_PAGE_MASK; - npages = iommu_nr_pages(s->dma_address, s->dma_length); + npages = iommu_num_pages(s->dma_address, s->dma_length, + IOMMU_PAGE_SIZE); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -452,7 +442,8 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; - npages = iommu_nr_pages(dma_handle, sg->dma_length); + npages = iommu_num_pages(dma_handle, sg->dma_length, + IOMMU_PAGE_SIZE); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -584,7 +575,7 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl, BUG_ON(direction == DMA_NONE); uaddr = (unsigned long)vaddr; - npages = iommu_nr_pages(uaddr, size); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE); if (tbl) { align = 0; @@ -617,7 +608,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_nr_pages(dma_handle, size); + npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE); iommu_free(tbl, dma_handle, npages); } } -- cgit v1.2.3 From 756ba83ee370fbf62643777e7ba4a4f05932f6fb Mon Sep 17 00:00:00 2001 From: Masakazu Mokuno Date: Mon, 20 Oct 2008 08:03:33 +0200 Subject: ps3: Add ps3av_audio_mute_analog() Add support for muting the analog output so that it does not play noises while non-PCM data is played. Signed-off-by: Masakazu Mokuno Signed-off-by: Takashi Iwai --- arch/powerpc/include/asm/ps3av.h | 1 + drivers/ps3/ps3av.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h index fda98715cd35..d30bde2b11ef 100644 --- a/arch/powerpc/include/asm/ps3av.h +++ b/arch/powerpc/include/asm/ps3av.h @@ -735,6 +735,7 @@ extern int ps3av_get_mode(void); extern int ps3av_video_mode2res(u32, u32 *, u32 *); extern int ps3av_video_mute(int); extern int ps3av_audio_mute(int); +extern int ps3av_audio_mute_analog(int); extern int ps3av_dev_open(void); extern int ps3av_dev_close(void); extern void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data), diff --git a/drivers/ps3/ps3av.c b/drivers/ps3/ps3av.c index 6f2f90ebb020..06848b254d57 100644 --- a/drivers/ps3/ps3av.c +++ b/drivers/ps3/ps3av.c @@ -915,6 +915,22 @@ int ps3av_video_mute(int mute) EXPORT_SYMBOL_GPL(ps3av_video_mute); +/* mute analog output only */ +int ps3av_audio_mute_analog(int mute) +{ + int i, res; + + for (i = 0; i < ps3av->av_hw_conf.num_of_avmulti; i++) { + res = ps3av_cmd_av_audio_mute(1, + &ps3av->av_port[i + ps3av->av_hw_conf.num_of_hdmi], + mute); + if (res < 0) + return -1; + } + return 0; +} +EXPORT_SYMBOL_GPL(ps3av_audio_mute_analog); + int ps3av_audio_mute(int mute) { return ps3av_set_audio_mute(mute ? PS3AV_CMD_MUTE_ON -- cgit v1.2.3 From 64931a4be03dbc49bd50d10d211592cf98b523bb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 20 Oct 2008 08:05:10 +0200 Subject: ps3: Add passthru support for non-audio streams Add support for the channel status bit setting so that non-PCM data stream can be sent (i.e. pass-through) via SPDIF/HDMI. Signed-off-by: Masakazu Mokuno Acked-by: Geert Uytterhoeven Signed-off-by: Takashi Iwai --- arch/powerpc/include/asm/ps3av.h | 2 ++ drivers/ps3/ps3av_cmd.c | 19 ++++++++++--------- 2 files changed, 12 insertions(+), 9 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h index d30bde2b11ef..5aa22cffdbd6 100644 --- a/arch/powerpc/include/asm/ps3av.h +++ b/arch/powerpc/include/asm/ps3av.h @@ -678,6 +678,8 @@ struct ps3av_pkt_avb_param { u8 buf[PS3AV_PKT_AVB_PARAM_MAX_BUF_SIZE]; }; +/* channel status */ +extern u8 ps3av_mode_cs_info[]; /** command status **/ #define PS3AV_STATUS_SUCCESS 0x0000 /* success */ diff --git a/drivers/ps3/ps3av_cmd.c b/drivers/ps3/ps3av_cmd.c index 7f880c26122f..11eb50318fec 100644 --- a/drivers/ps3/ps3av_cmd.c +++ b/drivers/ps3/ps3av_cmd.c @@ -660,9 +660,10 @@ u32 ps3av_cmd_set_av_audio_param(void *p, u32 port, } /* default cs val */ -static const u8 ps3av_mode_cs_info[] = { +u8 ps3av_mode_cs_info[] = { 0x00, 0x09, 0x00, 0x02, 0x01, 0x00, 0x00, 0x00 }; +EXPORT_SYMBOL_GPL(ps3av_mode_cs_info); #define CS_44 0x00 #define CS_48 0x02 @@ -677,7 +678,7 @@ void ps3av_cmd_set_audio_mode(struct ps3av_pkt_audio_mode *audio, u32 avport, u32 ch, u32 fs, u32 word_bits, u32 format, u32 source) { - int spdif_through, spdif_bitstream; + int spdif_through; int i; if (!(ch | fs | format | word_bits | source)) { @@ -687,7 +688,6 @@ void ps3av_cmd_set_audio_mode(struct ps3av_pkt_audio_mode *audio, u32 avport, format = PS3AV_CMD_AUDIO_FORMAT_PCM; source = PS3AV_CMD_AUDIO_SOURCE_SERIAL; } - spdif_through = spdif_bitstream = 0; /* XXX not supported */ /* audio mode */ memset(audio, 0, sizeof(*audio)); @@ -777,16 +777,17 @@ void ps3av_cmd_set_audio_mode(struct ps3av_pkt_audio_mode *audio, u32 avport, break; } + /* non-audio bit */ + spdif_through = audio->audio_cs_info[0] & 0x02; + /* pass through setting */ if (spdif_through && (avport == PS3AV_CMD_AVPORT_SPDIF_0 || - avport == PS3AV_CMD_AVPORT_SPDIF_1)) { + avport == PS3AV_CMD_AVPORT_SPDIF_1 || + avport == PS3AV_CMD_AVPORT_HDMI_0 || + avport == PS3AV_CMD_AVPORT_HDMI_1)) { audio->audio_word_bits = PS3AV_CMD_AUDIO_WORD_BITS_16; - audio->audio_source = PS3AV_CMD_AUDIO_SOURCE_SPDIF; - if (spdif_bitstream) { - audio->audio_format = PS3AV_CMD_AUDIO_FORMAT_BITSTREAM; - audio->audio_cs_info[0] |= CS_BIT; - } + audio->audio_format = PS3AV_CMD_AUDIO_FORMAT_BITSTREAM; } } -- cgit v1.2.3 From 71088785c6bc68fddb450063d57b1bd1c78e0ea1 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 18 Oct 2008 20:25:58 -0700 Subject: mm: cleanup to make remove_memory() arch-neutral There is nothing architecture specific about remove_memory(). remove_memory() function is common for all architectures which support hotplug memory remove. Instead of duplicating it in every architecture, collapse them into arch neutral function. [akpm@linux-foundation.org: fix the export] Signed-off-by: Badari Pulavarty Cc: Yasunori Goto Cc: Gary Hade Cc: Mel Gorman Cc: Yasunori Goto Cc: "Luck, Tony" Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 17 ----------------- arch/powerpc/mm/mem.c | 17 ----------------- arch/s390/mm/init.c | 11 ----------- mm/memory_hotplug.c | 12 +++++++++++- 4 files changed, 11 insertions(+), 46 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index f482a9098e32..054bcd9439aa 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -700,23 +700,6 @@ int arch_add_memory(int nid, u64 start, u64 size) return ret; } -#ifdef CONFIG_MEMORY_HOTREMOVE -int remove_memory(u64 start, u64 size) -{ - unsigned long start_pfn, end_pfn; - unsigned long timeout = 120 * HZ; - int ret; - start_pfn = start >> PAGE_SHIFT; - end_pfn = start_pfn + (size >> PAGE_SHIFT); - ret = offline_pages(start_pfn, end_pfn, timeout); - if (ret) - goto out; - /* we can free mem_map at this point */ -out: - return ret; -} -EXPORT_SYMBOL_GPL(remove_memory); -#endif /* CONFIG_MEMORY_HOTREMOVE */ #endif /* diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 98d7bf99533a..b9e1a1da6e52 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -134,23 +134,6 @@ int arch_add_memory(int nid, u64 start, u64 size) return __add_pages(zone, start_pfn, nr_pages); } - -#ifdef CONFIG_MEMORY_HOTREMOVE -int remove_memory(u64 start, u64 size) -{ - unsigned long start_pfn, end_pfn; - int ret; - - start_pfn = start >> PAGE_SHIFT; - end_pfn = start_pfn + (size >> PAGE_SHIFT); - ret = offline_pages(start_pfn, end_pfn, 120 * HZ); - if (ret) - goto out; - /* Arch-specific calls go here - next patch */ -out: - return ret; -} -#endif /* CONFIG_MEMORY_HOTREMOVE */ #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 1169130a97ef..158b0d6d7046 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -189,14 +189,3 @@ int arch_add_memory(int nid, u64 start, u64 size) return rc; } #endif /* CONFIG_MEMORY_HOTPLUG */ - -#ifdef CONFIG_MEMORY_HOTREMOVE -int remove_memory(u64 start, u64 size) -{ - unsigned long start_pfn, end_pfn; - - start_pfn = PFN_DOWN(start); - end_pfn = start_pfn + PFN_DOWN(size); - return offline_pages(start_pfn, end_pfn, 120 * HZ); -} -#endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 89fee2dcb039..c299d083d8e2 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -26,6 +26,7 @@ #include #include #include +#include #include @@ -849,10 +850,19 @@ failed_removal: return ret; } + +int remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn, end_pfn; + + start_pfn = PFN_DOWN(start); + end_pfn = start_pfn + PFN_DOWN(size); + return offline_pages(start_pfn, end_pfn, 120 * HZ); +} #else int remove_memory(u64 start, u64 size) { return -EINVAL; } -EXPORT_SYMBOL_GPL(remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ +EXPORT_SYMBOL_GPL(remove_memory); -- cgit v1.2.3 From dc52ddc0e6f45b04780b26fc0813509f8e798c42 Mon Sep 17 00:00:00 2001 From: Matt Helsley Date: Sat, 18 Oct 2008 20:27:21 -0700 Subject: container freezer: implement freezer cgroup subsystem This patch implements a new freezer subsystem in the control groups framework. It provides a way to stop and resume execution of all tasks in a cgroup by writing in the cgroup filesystem. The freezer subsystem in the container filesystem defines a file named freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in the cgroup. Reading will return the current state. * Examples of usage : # mkdir /containers/freezer # mount -t cgroup -ofreezer freezer /containers # mkdir /containers/0 # echo $some_pid > /containers/0/tasks to get status of the freezer subsystem : # cat /containers/0/freezer.state RUNNING to freeze all tasks in the container : # echo FROZEN > /containers/0/freezer.state # cat /containers/0/freezer.state FREEZING # cat /containers/0/freezer.state FROZEN to unfreeze all tasks in the container : # echo RUNNING > /containers/0/freezer.state # cat /containers/0/freezer.state RUNNING This is the basic mechanism which should do the right thing for user space task in a simple scenario. It's important to note that freezing can be incomplete. In that case we return EBUSY. This means that some tasks in the cgroup are busy doing something that prevents us from completely freezing the cgroup at this time. After EBUSY, the cgroup will remain partially frozen -- reflected by freezer.state reporting "FREEZING" when read. The state will remain "FREEZING" until one of these things happens: 1) Userspace cancels the freezing operation by writing "RUNNING" to the freezer.state file 2) Userspace retries the freezing operation by writing "FROZEN" to the freezer.state file (writing "FREEZING" is not legal and returns EIO) 3) The tasks that blocked the cgroup from entering the "FROZEN" state disappear from the cgroup's set of tasks. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: export thaw_process] Signed-off-by: Cedric Le Goater Signed-off-by: Matt Helsley Acked-by: Serge E. Hallyn Tested-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 + arch/arm/Kconfig | 2 + arch/avr32/Kconfig | 2 + arch/blackfin/Kconfig | 3 + arch/cris/Kconfig | 2 + arch/frv/Kconfig | 2 + arch/h8300/Kconfig | 2 + arch/ia64/Kconfig | 2 + arch/m32r/Kconfig | 2 + arch/m68k/Kconfig | 2 + arch/m68knommu/Kconfig | 2 + arch/mips/Kconfig | 2 + arch/mn10300/Kconfig | 2 + arch/parisc/Kconfig | 2 + arch/powerpc/Kconfig | 2 + arch/s390/Kconfig | 2 + arch/sh/Kconfig | 2 + arch/sparc/Kconfig | 2 + arch/sparc64/Kconfig | 1 + arch/um/Kconfig | 2 + arch/x86/Kconfig | 1 + arch/xtensa/Kconfig | 1 + include/linux/cgroup_subsys.h | 6 + include/linux/freezer.h | 29 ++-- init/Kconfig | 7 + kernel/Kconfig.freezer | 2 + kernel/Makefile | 1 + kernel/cgroup_freezer.c | 366 ++++++++++++++++++++++++++++++++++++++++++ kernel/freezer.c | 32 ++++ kernel/power/Kconfig | 3 - 30 files changed, 465 insertions(+), 22 deletions(-) create mode 100644 kernel/Kconfig.freezer create mode 100644 kernel/cgroup_freezer.c (limited to 'arch/powerpc') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index a0f642b6a4b9..6110197757a3 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -70,6 +70,7 @@ config AUTO_IRQ_AFFINITY default y source "init/Kconfig" +source "kernel/Kconfig.freezer" menu "System setup" diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4853f9df37bd..df39d20f7425 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -192,6 +192,8 @@ config VECTORS_BASE source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "System Type" choice diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index 7c239a916275..33a5b2969eb4 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -72,6 +72,8 @@ config GENERIC_BUG source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "System Type and features" source "kernel/time/Kconfig" diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 8102c79aaa94..29e71ed6b8a7 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -64,8 +64,11 @@ config HARDWARE_PM depends on OPROFILE source "init/Kconfig" + source "kernel/Kconfig.preempt" +source "kernel/Kconfig.freezer" + menu "Blackfin Processor Options" comment "Processor and Board Settings" diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 9389d38f222f..07335e719bf8 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -62,6 +62,8 @@ config HZ source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "General setup" source "fs/Kconfig.binfmt" diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index a5aac1b07562..9d1552a9ee2c 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -66,6 +66,8 @@ mainmenu "Fujitsu FR-V Kernel Configuration" source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Fujitsu FR-V system setup" diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index c7966746fbfe..bd1995403c67 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -90,6 +90,8 @@ config HZ source "init/Kconfig" +source "kernel/Kconfig.freezer" + source "arch/h8300/Kconfig.cpu" menu "Executable file formats" diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 3b7aa38254a8..912c57db2d21 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -7,6 +7,8 @@ mainmenu "IA-64 Linux Kernel Configuration" source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Processor type and features" config IA64 diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 00289c178f89..dbaed4a63815 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -42,6 +42,8 @@ config HZ source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Processor type and features" diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 677c93a490f6..836fb66f080d 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -62,6 +62,8 @@ mainmenu "Linux/68k Kernel Configuration" source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Platform dependent setup" config EISA diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig index 0a8998315e5e..76b66feb74df 100644 --- a/arch/m68knommu/Kconfig +++ b/arch/m68knommu/Kconfig @@ -75,6 +75,8 @@ config NO_IOPORT source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Processor type and features" choice diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b905744d7915..5f149b030c0f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1885,6 +1885,8 @@ config PROBE_INITRD_HEADER add initrd or initramfs image to the kernel image. Otherwise, say N. +source "kernel/Kconfig.freezer" + menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)" config HW_HAS_EISA diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index dd557c9cf001..9a9f43358879 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -68,6 +68,8 @@ mainmenu "Matsushita MN10300/AM33 Kernel Configuration" source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Matsushita MN10300 system setup" diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 8313fccced5e..2bd1f6ef5db0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -90,6 +90,8 @@ config ARCH_MAY_HAVE_PC_FDC source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Processor type and features" diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 380baa1780e9..9391199d9e77 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -230,6 +230,8 @@ config PPC_OF_PLATFORM_PCI source "init/Kconfig" +source "kernel/Kconfig.freezer" + source "arch/powerpc/sysdev/Kconfig" source "arch/powerpc/platforms/Kconfig" diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bc581d8a7cd9..70b7645ce745 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -78,6 +78,8 @@ config S390 source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Base setup" comment "Processor type and features" diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5131d50f851a..2ed5713b7540 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -106,6 +106,8 @@ config IO_TRAPPED source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "System type" # diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 97671dac12a6..e594559c8dba 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -37,6 +37,8 @@ config HZ source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "General machine setup" config SMP diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index 5446e2a499b1..035b15af90d8 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -96,6 +96,7 @@ config GENERIC_HARDIRQS_NO__DO_IRQ def_bool y source "init/Kconfig" +source "kernel/Kconfig.freezer" menu "Processor type and features" diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 6976812cfb18..393bccfe1785 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -229,6 +229,8 @@ endmenu source "init/Kconfig" +source "kernel/Kconfig.freezer" + source "drivers/block/Kconfig" source "arch/um/Kconfig.char" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bd3c2c53873e..49349ba77d80 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -193,6 +193,7 @@ config X86_TRAMPOLINE config KTIME_SCALAR def_bool X86_32 source "init/Kconfig" +source "kernel/Kconfig.freezer" menu "Processor type and features" diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 02e417d3d8e9..a213260b51e5 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -55,6 +55,7 @@ config HZ default 100 source "init/Kconfig" +source "kernel/Kconfig.freezer" menu "Processor type and features" diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index e2877454ec82..9c22396e8b50 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -48,3 +48,9 @@ SUBSYS(devices) #endif /* */ + +#ifdef CONFIG_CGROUP_FREEZER +SUBSYS(freezer) +#endif + +/* */ diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 17e3bb42dd3c..8f225339eee9 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -46,26 +46,11 @@ static inline bool should_send_signal(struct task_struct *p) /* * Wake up a frozen process - * - * task_lock() is taken to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. */ -static inline int thaw_process(struct task_struct *p) -{ - task_lock(p); - if (frozen(p)) { - p->flags &= ~PF_FROZEN; - task_unlock(p); - wake_up_process(p); - return 1; - } - clear_freeze_flag(p); - task_unlock(p); - return 0; -} +extern int __thaw_process(struct task_struct *p); + +/* Takes and releases task alloc lock using task_lock() */ +extern int thaw_process(struct task_struct *p); extern void refrigerator(void); extern int freeze_processes(void); @@ -83,6 +68,12 @@ static inline int try_to_freeze(void) extern bool freeze_task(struct task_struct *p, bool sig_only); extern void cancel_freezing(struct task_struct *p); +#ifdef CONFIG_CGROUP_FREEZER +extern int cgroup_frozen(struct task_struct *task); +#else /* !CONFIG_CGROUP_FREEZER */ +static inline int cgroup_frozen(struct task_struct *task) { return 0; } +#endif /* !CONFIG_CGROUP_FREEZER */ + /* * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it * calls wait_for_completion(&vfork) and reset right after it returns from this diff --git a/init/Kconfig b/init/Kconfig index 5ceff3249a2d..8828ed0b2051 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -299,6 +299,13 @@ config CGROUP_NS for instance virtual servers and checkpoint/restart jobs. +config CGROUP_FREEZER + bool "control group freezer subsystem" + depends on CGROUPS + help + Provides a way to freeze and unfreeze all tasks in a + cgroup. + config CGROUP_DEVICE bool "Device controller for cgroups" depends on CGROUPS && EXPERIMENTAL diff --git a/kernel/Kconfig.freezer b/kernel/Kconfig.freezer new file mode 100644 index 000000000000..a3bb4cb52539 --- /dev/null +++ b/kernel/Kconfig.freezer @@ -0,0 +1,2 @@ +config FREEZER + def_bool PM_SLEEP || CGROUP_FREEZER diff --git a/kernel/Makefile b/kernel/Makefile index e8194d15d5f4..066550aa61c5 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup.o obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o +obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o obj-$(CONFIG_UTS_NS) += utsname.o diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c new file mode 100644 index 000000000000..b08722de610c --- /dev/null +++ b/kernel/cgroup_freezer.c @@ -0,0 +1,366 @@ +/* + * cgroup_freezer.c - control group freezer subsystem + * + * Copyright IBM Corporation, 2007 + * + * Author : Cedric Le Goater + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + */ + +#include +#include +#include +#include +#include +#include + +enum freezer_state { + STATE_RUNNING = 0, + STATE_FREEZING, + STATE_FROZEN, +}; + +struct freezer { + struct cgroup_subsys_state css; + enum freezer_state state; + spinlock_t lock; /* protects _writes_ to state */ +}; + +static inline struct freezer *cgroup_freezer( + struct cgroup *cgroup) +{ + return container_of( + cgroup_subsys_state(cgroup, freezer_subsys_id), + struct freezer, css); +} + +static inline struct freezer *task_freezer(struct task_struct *task) +{ + return container_of(task_subsys_state(task, freezer_subsys_id), + struct freezer, css); +} + +int cgroup_frozen(struct task_struct *task) +{ + struct freezer *freezer; + enum freezer_state state; + + task_lock(task); + freezer = task_freezer(task); + state = freezer->state; + task_unlock(task); + + return state == STATE_FROZEN; +} + +/* + * cgroups_write_string() limits the size of freezer state strings to + * CGROUP_LOCAL_BUFFER_SIZE + */ +static const char *freezer_state_strs[] = { + "RUNNING", + "FREEZING", + "FROZEN", +}; + +/* + * State diagram + * Transitions are caused by userspace writes to the freezer.state file. + * The values in parenthesis are state labels. The rest are edge labels. + * + * (RUNNING) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN) + * ^ ^ | | + * | \_______RUNNING_______/ | + * \_____________________________RUNNING___________/ + */ + +struct cgroup_subsys freezer_subsys; + +/* Locks taken and their ordering + * ------------------------------ + * css_set_lock + * cgroup_mutex (AKA cgroup_lock) + * task->alloc_lock (AKA task_lock) + * freezer->lock + * task->sighand->siglock + * + * cgroup code forces css_set_lock to be taken before task->alloc_lock + * + * freezer_create(), freezer_destroy(): + * cgroup_mutex [ by cgroup core ] + * + * can_attach(): + * cgroup_mutex + * + * cgroup_frozen(): + * task->alloc_lock (to get task's cgroup) + * + * freezer_fork() (preserving fork() performance means can't take cgroup_mutex): + * task->alloc_lock (to get task's cgroup) + * freezer->lock + * sighand->siglock (if the cgroup is freezing) + * + * freezer_read(): + * cgroup_mutex + * freezer->lock + * read_lock css_set_lock (cgroup iterator start) + * + * freezer_write() (freeze): + * cgroup_mutex + * freezer->lock + * read_lock css_set_lock (cgroup iterator start) + * sighand->siglock + * + * freezer_write() (unfreeze): + * cgroup_mutex + * freezer->lock + * read_lock css_set_lock (cgroup iterator start) + * task->alloc_lock (to prevent races with freeze_task()) + * sighand->siglock + */ +static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, + struct cgroup *cgroup) +{ + struct freezer *freezer; + + freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL); + if (!freezer) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&freezer->lock); + freezer->state = STATE_RUNNING; + return &freezer->css; +} + +static void freezer_destroy(struct cgroup_subsys *ss, + struct cgroup *cgroup) +{ + kfree(cgroup_freezer(cgroup)); +} + + +static int freezer_can_attach(struct cgroup_subsys *ss, + struct cgroup *new_cgroup, + struct task_struct *task) +{ + struct freezer *freezer; + int retval = 0; + + /* + * The call to cgroup_lock() in the freezer.state write method prevents + * a write to that file racing against an attach, and hence the + * can_attach() result will remain valid until the attach completes. + */ + freezer = cgroup_freezer(new_cgroup); + if (freezer->state == STATE_FROZEN) + retval = -EBUSY; + return retval; +} + +static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) +{ + struct freezer *freezer; + + task_lock(task); + freezer = task_freezer(task); + task_unlock(task); + + BUG_ON(freezer->state == STATE_FROZEN); + spin_lock_irq(&freezer->lock); + /* Locking avoids race with FREEZING -> RUNNING transitions. */ + if (freezer->state == STATE_FREEZING) + freeze_task(task, true); + spin_unlock_irq(&freezer->lock); +} + +/* + * caller must hold freezer->lock + */ +static void check_if_frozen(struct cgroup *cgroup, + struct freezer *freezer) +{ + struct cgroup_iter it; + struct task_struct *task; + unsigned int nfrozen = 0, ntotal = 0; + + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + ntotal++; + /* + * Task is frozen or will freeze immediately when next it gets + * woken + */ + if (frozen(task) || + (task_is_stopped_or_traced(task) && freezing(task))) + nfrozen++; + } + + /* + * Transition to FROZEN when no new tasks can be added ensures + * that we never exist in the FROZEN state while there are unfrozen + * tasks. + */ + if (nfrozen == ntotal) + freezer->state = STATE_FROZEN; + cgroup_iter_end(cgroup, &it); +} + +static int freezer_read(struct cgroup *cgroup, struct cftype *cft, + struct seq_file *m) +{ + struct freezer *freezer; + enum freezer_state state; + + if (!cgroup_lock_live_group(cgroup)) + return -ENODEV; + + freezer = cgroup_freezer(cgroup); + spin_lock_irq(&freezer->lock); + state = freezer->state; + if (state == STATE_FREEZING) { + /* We change from FREEZING to FROZEN lazily if the cgroup was + * only partially frozen when we exitted write. */ + check_if_frozen(cgroup, freezer); + state = freezer->state; + } + spin_unlock_irq(&freezer->lock); + cgroup_unlock(); + + seq_puts(m, freezer_state_strs[state]); + seq_putc(m, '\n'); + return 0; +} + +static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) +{ + struct cgroup_iter it; + struct task_struct *task; + unsigned int num_cant_freeze_now = 0; + + freezer->state = STATE_FREEZING; + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + if (!freeze_task(task, true)) + continue; + if (task_is_stopped_or_traced(task) && freezing(task)) + /* + * The freeze flag is set so these tasks will + * immediately go into the fridge upon waking. + */ + continue; + if (!freezing(task) && !freezer_should_skip(task)) + num_cant_freeze_now++; + } + cgroup_iter_end(cgroup, &it); + + return num_cant_freeze_now ? -EBUSY : 0; +} + +static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) +{ + struct cgroup_iter it; + struct task_struct *task; + + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + int do_wake; + + task_lock(task); + do_wake = __thaw_process(task); + task_unlock(task); + if (do_wake) + wake_up_process(task); + } + cgroup_iter_end(cgroup, &it); + freezer->state = STATE_RUNNING; + + return 0; +} + +static int freezer_change_state(struct cgroup *cgroup, + enum freezer_state goal_state) +{ + struct freezer *freezer; + int retval = 0; + + freezer = cgroup_freezer(cgroup); + spin_lock_irq(&freezer->lock); + check_if_frozen(cgroup, freezer); /* may update freezer->state */ + if (goal_state == freezer->state) + goto out; + switch (freezer->state) { + case STATE_RUNNING: + retval = try_to_freeze_cgroup(cgroup, freezer); + break; + case STATE_FREEZING: + if (goal_state == STATE_FROZEN) { + /* Userspace is retrying after + * "/bin/echo FROZEN > freezer.state" returned -EBUSY */ + retval = try_to_freeze_cgroup(cgroup, freezer); + break; + } + /* state == FREEZING and goal_state == RUNNING, so unfreeze */ + case STATE_FROZEN: + retval = unfreeze_cgroup(cgroup, freezer); + break; + default: + break; + } +out: + spin_unlock_irq(&freezer->lock); + + return retval; +} + +static int freezer_write(struct cgroup *cgroup, + struct cftype *cft, + const char *buffer) +{ + int retval; + enum freezer_state goal_state; + + if (strcmp(buffer, freezer_state_strs[STATE_RUNNING]) == 0) + goal_state = STATE_RUNNING; + else if (strcmp(buffer, freezer_state_strs[STATE_FROZEN]) == 0) + goal_state = STATE_FROZEN; + else + return -EIO; + + if (!cgroup_lock_live_group(cgroup)) + return -ENODEV; + retval = freezer_change_state(cgroup, goal_state); + cgroup_unlock(); + return retval; +} + +static struct cftype files[] = { + { + .name = "state", + .read_seq_string = freezer_read, + .write_string = freezer_write, + }, +}; + +static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup) +{ + return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files)); +} + +struct cgroup_subsys freezer_subsys = { + .name = "freezer", + .create = freezer_create, + .destroy = freezer_destroy, + .populate = freezer_populate, + .subsys_id = freezer_subsys_id, + .can_attach = freezer_can_attach, + .attach = NULL, + .fork = freezer_fork, + .exit = NULL, +}; diff --git a/kernel/freezer.c b/kernel/freezer.c index cb0931f89306..ba6248b323ef 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -120,3 +120,35 @@ void cancel_freezing(struct task_struct *p) spin_unlock_irqrestore(&p->sighand->siglock, flags); } } + +/* + * Wake up a frozen process + * + * task_lock() is needed to prevent the race with refrigerator() which may + * occur if the freezing of tasks fails. Namely, without the lock, if the + * freezing of tasks failed, thaw_tasks() might have run before a task in + * refrigerator() could call frozen_process(), in which case the task would be + * frozen and no one would thaw it. + */ +int __thaw_process(struct task_struct *p) +{ + if (frozen(p)) { + p->flags &= ~PF_FROZEN; + return 1; + } + clear_freeze_flag(p); + return 0; +} + +int thaw_process(struct task_struct *p) +{ + task_lock(p); + if (__thaw_process(p) == 1) { + task_unlock(p); + wake_up_process(p); + return 1; + } + task_unlock(p); + return 0; +} +EXPORT_SYMBOL(thaw_process); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index ebdd7f55273d..dcd165f92a88 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -85,9 +85,6 @@ config PM_SLEEP depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE default y -config FREEZER - def_bool PM_SLEEP - config SUSPEND bool "Suspend to RAM and standby" depends on PM && ARCH_SUSPEND_POSSIBLE -- cgit v1.2.3 From 57cac4d1880527e0baf6c2fda529d2ad1d815aec Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Sat, 18 Oct 2008 20:28:25 -0700 Subject: kdump: make elfcorehdr_addr independent of CONFIG_PROC_VMCORE o elfcorehdr_addr is used by not only the code under CONFIG_PROC_VMCORE but also by the code which is not inside CONFIG_PROC_VMCORE. For example, is_kdump_kernel() is used by powerpc code to determine if kernel is booting after a panic then use previous kernel's TCE table. So even if CONFIG_PROC_VMCORE is not set in second kernel, one should be able to correctly determine that we are booting after a panic and setup calgary iommu accordingly. o So remove the assumption that elfcorehdr_addr is under CONFIG_PROC_VMCORE. o Move definition of elfcorehdr_addr to arch dependent crash files. (Unfortunately crash dump does not have an arch independent file otherwise that would have been the best place). o kexec.c is not the right place as one can Have CRASH_DUMP enabled in second kernel without KEXEC being enabled. o I don't see sh setup code parsing the command line for elfcorehdr_addr. I am wondering how does vmcore interface work on sh. Anyway, I am atleast defining elfcoredhr_addr so that compilation is not broken on sh. Signed-off-by: Vivek Goyal Acked-by: "Eric W. Biederman" Acked-by: Simon Horman Acked-by: Paul Mundt Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/crash_dump.c | 4 ++++ arch/ia64/kernel/setup.c | 9 ++++++++- arch/powerpc/kernel/crash_dump.c | 10 ++++++++-- arch/sh/kernel/crash_dump.c | 3 +++ arch/x86/kernel/crash_dump_32.c | 3 +++ arch/x86/kernel/crash_dump_64.c | 3 +++ arch/x86/kernel/setup.c | 8 +++++++- fs/proc/vmcore.c | 3 --- include/linux/crash_dump.h | 14 ++++++++++---- 9 files changed, 46 insertions(+), 11 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/ia64/kernel/crash_dump.c b/arch/ia64/kernel/crash_dump.c index da60e90eeeb1..23e91290e41f 100644 --- a/arch/ia64/kernel/crash_dump.c +++ b/arch/ia64/kernel/crash_dump.c @@ -8,10 +8,14 @@ #include #include +#include #include #include +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index de636b215677..a0286be6c235 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -478,7 +478,12 @@ static __init int setup_nomca(char *s) } early_param("nomca", setup_nomca); -#ifdef CONFIG_PROC_VMCORE +/* + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence + * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ +#ifdef CONFIG_CRASH_DUMP /* elfcorehdr= specifies the location of elf core header * stored by the crashed kernel. */ @@ -491,7 +496,9 @@ static int __init parse_elfcorehdr(char *arg) return 0; } early_param("elfcorehdr", parse_elfcorehdr); +#endif +#ifdef CONFIG_PROC_VMCORE int __init reserve_elfcorehdr(unsigned long *start, unsigned long *end) { unsigned long length; diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index a323c9b32ee1..97e056379728 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -27,6 +27,9 @@ #define DBG(fmt...) #endif +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + void __init reserve_kdump_trampoline(void) { lmb_reserve(0, KDUMP_RESERVE_LIMIT); @@ -66,7 +69,11 @@ void __init setup_kdump_trampoline(void) DBG(" <- setup_kdump_trampoline()\n"); } -#ifdef CONFIG_PROC_VMCORE +/* + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence + * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ static int __init parse_elfcorehdr(char *p) { if (p) @@ -75,7 +82,6 @@ static int __init parse_elfcorehdr(char *p) return 1; } __setup("elfcorehdr=", parse_elfcorehdr); -#endif static int __init parse_savemaxmem(char *p) { diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c index 4a2ecbe27d8e..95d216255565 100644 --- a/arch/sh/kernel/crash_dump.c +++ b/arch/sh/kernel/crash_dump.c @@ -10,6 +10,9 @@ #include #include +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 72d0c56c1b48..f7cdb3b457aa 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -13,6 +13,9 @@ static void *kdump_buf_page; +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index e90a60ef10c2..045b36cada65 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -10,6 +10,9 @@ #include #include +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2255782e8d4b..b2c97874ec0f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -561,7 +561,13 @@ static void __init reserve_standard_io_resources(void) } -#ifdef CONFIG_PROC_VMCORE +/* + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence + * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ + +#ifdef CONFIG_CRASH_DUMP /* elfcorehdr= specifies the location of elf core header * stored by the crashed kernel. This option will be passed * by kexec loader to the capture kernel. diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 841368b87a29..4c65ca432d30 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -32,9 +32,6 @@ static size_t elfcorebuf_sz; /* Total size of vmcore file. */ static u64 vmcore_size; -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; - struct proc_dir_entry *proc_vmcore = NULL; /* Reads a page from the oldmem device from given offset. */ diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 025e4f575103..de027d1db745 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -9,11 +9,7 @@ #define ELFCORE_ADDR_MAX (-1ULL) -#ifdef CONFIG_PROC_VMCORE extern unsigned long long elfcorehdr_addr; -#else -static const unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; -#endif extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); @@ -28,6 +24,16 @@ extern struct proc_dir_entry *proc_vmcore; #define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +/* + * is_kdump_kernel() checks whether this kernel is booting after a panic of + * previous kernel or not. This is determined by checking if previous kernel + * has passed the elf core header address on command line. + * + * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will + * return 1 if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic of + * previous kernel. + */ + static inline int is_kdump_kernel(void) { return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0; -- cgit v1.2.3 From e9f82cb75096ae30658a72d473bf170bf4d3bb2e Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 14 Oct 2008 11:55:31 +1100 Subject: powerpc/PCI: Add legacy PCI access via sysfs This patch adds support for legacy_io and legacy_mem files in bus class directories in sysfs for powerpc Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Jesse Barnes --- arch/powerpc/include/asm/pci-bridge.h | 7 ++ arch/powerpc/include/asm/pci.h | 11 +++ arch/powerpc/kernel/pci-common.c | 136 +++++++++++++++++++++++++++++++++- 3 files changed, 153 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index ae2ea803a0f2..9047af7baa69 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -74,6 +74,13 @@ struct pci_controller { unsigned long pci_io_size; #endif + /* Some machines have a special region to forward the ISA + * "memory" cycles such as VGA memory regions. Left to 0 + * if unsupported + */ + resource_size_t isa_mem_phys; + resource_size_t isa_mem_size; + struct pci_ops *ops; unsigned int __iomem *cfg_addr; void __iomem *cfg_data; diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 0e52c7828ea4..39d547fde956 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -123,6 +123,16 @@ int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma, /* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */ #define HAVE_PCI_MMAP 1 +extern int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, + size_t count); +extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, + size_t count); +extern int pci_mmap_legacy_page_range(struct pci_bus *bus, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state); + +#define HAVE_PCI_LEGACY 1 + #if defined(CONFIG_PPC64) || defined(CONFIG_NOT_COHERENT_CACHE) /* * For 64-bit kernels, pci_unmap_{single,page} is not a nop. @@ -226,5 +236,6 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar, extern void pcibios_do_bus_setup(struct pci_bus *bus); extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus); + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_PCI_H */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 01ce8c38bae6..3815d84a1ef4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -451,7 +451,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, pci_dev_put(pdev); } - DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); + DBG("non-PCI map for %llx, prot: %lx\n", + (unsigned long long)offset, prot); return __pgprot(prot); } @@ -490,6 +491,131 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return ret; } +/* This provides legacy IO read access on a bus */ +int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size) +{ + unsigned long offset; + struct pci_controller *hose = pci_bus_to_host(bus); + struct resource *rp = &hose->io_resource; + void __iomem *addr; + + /* Check if port can be supported by that bus. We only check + * the ranges of the PHB though, not the bus itself as the rules + * for forwarding legacy cycles down bridges are not our problem + * here. So if the host bridge supports it, we do it. + */ + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + offset += port; + + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (offset < rp->start || (offset + size) > rp->end) + return -ENXIO; + addr = hose->io_base_virt + port; + + switch(size) { + case 1: + *((u8 *)val) = in_8(addr); + return 1; + case 2: + if (port & 1) + return -EINVAL; + *((u16 *)val) = in_le16(addr); + return 2; + case 4: + if (port & 3) + return -EINVAL; + *((u32 *)val) = in_le32(addr); + return 4; + } + return -EINVAL; +} + +/* This provides legacy IO write access on a bus */ +int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size) +{ + unsigned long offset; + struct pci_controller *hose = pci_bus_to_host(bus); + struct resource *rp = &hose->io_resource; + void __iomem *addr; + + /* Check if port can be supported by that bus. We only check + * the ranges of the PHB though, not the bus itself as the rules + * for forwarding legacy cycles down bridges are not our problem + * here. So if the host bridge supports it, we do it. + */ + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + offset += port; + + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (offset < rp->start || (offset + size) > rp->end) + return -ENXIO; + addr = hose->io_base_virt + port; + + /* WARNING: The generic code is idiotic. It gets passed a pointer + * to what can be a 1, 2 or 4 byte quantity and always reads that + * as a u32, which means that we have to correct the location of + * the data read within those 32 bits for size 1 and 2 + */ + switch(size) { + case 1: + out_8(addr, val >> 24); + return 1; + case 2: + if (port & 1) + return -EINVAL; + out_le16(addr, val >> 16); + return 2; + case 4: + if (port & 3) + return -EINVAL; + out_le32(addr, val); + return 4; + } + return -EINVAL; +} + +/* This provides legacy IO or memory mmap access on a bus */ +int pci_mmap_legacy_page_range(struct pci_bus *bus, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + resource_size_t offset = + ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT; + resource_size_t size = vma->vm_end - vma->vm_start; + struct resource *rp; + + pr_debug("pci_mmap_legacy_page_range(%04x:%02x, %s @%llx..%llx)\n", + pci_domain_nr(bus), bus->number, + mmap_state == pci_mmap_mem ? "MEM" : "IO", + (unsigned long long)offset, + (unsigned long long)(offset + size - 1)); + + if (mmap_state == pci_mmap_mem) { + if ((offset + size) > hose->isa_mem_size) + return -ENXIO; + offset += hose->isa_mem_phys; + } else { + unsigned long io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; + unsigned long roffset = offset + io_offset; + rp = &hose->io_resource; + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (roffset < rp->start || (roffset + size) > rp->end) + return -ENXIO; + offset += hose->io_base_phys; + } + pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset); + + vma->vm_pgoff = offset >> PAGE_SHIFT; + vma->vm_page_prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; + return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); +} + void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end) @@ -592,6 +718,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, cpu_addr = of_translate_address(dev, ranges + 3); size = of_read_number(ranges + pna + 3, 2); ranges += np; + + /* If we failed translation or got a zero-sized region + * (some FW try to feed us with non sensical zero sized regions + * such as power3 which look like some kind of attempt at exposing + * the VGA memory hole) + */ if (cpu_addr == OF_BAD_ADDR || size == 0) continue; @@ -665,6 +797,8 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, isa_hole = memno; if (primary || isa_mem_base == 0) isa_mem_base = cpu_addr; + hose->isa_mem_phys = cpu_addr; + hose->isa_mem_size = size; } /* We get the PCI/Mem offset from the first range or -- cgit v1.2.3 From 653c03168348ac7aebb969931f87ba281749d7dd Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Mon, 20 Oct 2008 16:00:08 -0700 Subject: misc: replace remaining __FUNCTION__ with __func__ __FUNCTION__ is gcc-specific, use __func__ Signed-off-by: Harvey Harrison Acked-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/DocBook/kernel-hacking.tmpl | 2 +- arch/arm/mach-iop13xx/include/mach/time.h | 4 ++-- arch/arm/mach-pxa/include/mach/zylonite.h | 4 ++-- arch/powerpc/include/asm/ptrace.h | 2 +- drivers/net/usb/pegasus.c | 4 ++-- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch/powerpc') diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index 4c63e5864160..ae15d55350ec 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -1105,7 +1105,7 @@ static struct block_device_operations opt_fops = { - Function names as strings (__FUNCTION__). + Function names as strings (__func__). diff --git a/arch/arm/mach-iop13xx/include/mach/time.h b/arch/arm/mach-iop13xx/include/mach/time.h index 49213d9d7cad..d6d52527589d 100644 --- a/arch/arm/mach-iop13xx/include/mach/time.h +++ b/arch/arm/mach-iop13xx/include/mach/time.h @@ -41,7 +41,7 @@ static inline unsigned long iop13xx_core_freq(void) return 1200000000; default: printk("%s: warning unknown frequency, defaulting to 800Mhz\n", - __FUNCTION__); + __func__); } return 800000000; @@ -60,7 +60,7 @@ static inline unsigned long iop13xx_xsi_bus_ratio(void) return 4; default: printk("%s: warning unknown ratio, defaulting to 2\n", - __FUNCTION__); + __func__); } return 2; diff --git a/arch/arm/mach-pxa/include/mach/zylonite.h b/arch/arm/mach-pxa/include/mach/zylonite.h index 0d35ca04731e..bf6785adccf4 100644 --- a/arch/arm/mach-pxa/include/mach/zylonite.h +++ b/arch/arm/mach-pxa/include/mach/zylonite.h @@ -30,7 +30,7 @@ extern void zylonite_pxa300_init(void); static inline void zylonite_pxa300_init(void) { if (cpu_is_pxa300() || cpu_is_pxa310()) - panic("%s: PXA300/PXA310 not supported\n", __FUNCTION__); + panic("%s: PXA300/PXA310 not supported\n", __func__); } #endif @@ -40,7 +40,7 @@ extern void zylonite_pxa320_init(void); static inline void zylonite_pxa320_init(void) { if (cpu_is_pxa320()) - panic("%s: PXA320 not supported\n", __FUNCTION__); + panic("%s: PXA320 not supported\n", __func__); } #endif diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 734e0754fb9b..280a90cc9894 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -129,7 +129,7 @@ extern int ptrace_put_reg(struct task_struct *task, int regno, #define CHECK_FULL_REGS(regs) \ do { \ if ((regs)->trap & 1) \ - printk(KERN_CRIT "%s: partial register set\n", __FUNCTION__); \ + printk(KERN_CRIT "%s: partial register set\n", __func__); \ } while (0) #endif /* __powerpc64__ */ diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 38b90e7a7ed3..7914867110ed 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -168,7 +168,7 @@ static int get_registers(pegasus_t * pegasus, __u16 indx, __u16 size, netif_device_detach(pegasus->net); if (netif_msg_drv(pegasus) && printk_ratelimit()) dev_err(&pegasus->intf->dev, "%s, status %d\n", - __FUNCTION__, ret); + __func__, ret); goto out; } @@ -192,7 +192,7 @@ static int set_registers(pegasus_t * pegasus, __u16 indx, __u16 size, if (!buffer) { if (netif_msg_drv(pegasus)) dev_warn(&pegasus->intf->dev, "out of memory in %s\n", - __FUNCTION__); + __func__); return -ENOMEM; } memcpy(buffer, data, size); -- cgit v1.2.3