diff options
author | Todd Poynor <toddpoynor@google.com> | 2012-04-19 15:15:48 -0700 |
---|---|---|
committer | Todd Poynor <toddpoynor@google.com> | 2012-04-19 15:20:03 -0700 |
commit | 94225ab0bef6f32108eaa410bb894caa2b4317e2 (patch) | |
tree | 3696c83cc5109c7e439c8228fe6be72a3a4a74fe /arch/x86/include | |
parent | 801cb6260fb5cae3bbc513927b583447c38d9deb (diff) | |
parent | 0527fde0639955203ad48a9fd83bd6fc35e82e07 (diff) | |
download | kernel_samsung_tuna-94225ab0bef6f32108eaa410bb894caa2b4317e2.zip kernel_samsung_tuna-94225ab0bef6f32108eaa410bb894caa2b4317e2.tar.gz kernel_samsung_tuna-94225ab0bef6f32108eaa410bb894caa2b4317e2.tar.bz2 |
Merge linux-stable 3.0.28 into android-3.0
Change-Id: Iee820738e53627f5d0447a87ceff34443aa72786
Signed-off-by: Todd Poynor <toddpoynor@google.com>
Diffstat (limited to 'arch/x86/include')
-rw-r--r-- | arch/x86/include/asm/amd_nb.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/apic.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/i387.h | 284 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_emulate.h | 16 | ||||
-rw-r--r-- | arch/x86/include/asm/processor.h | 1 | ||||
-rw-r--r-- | arch/x86/include/asm/thread_info.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/timer.h | 19 | ||||
-rw-r--r-- | arch/x86/include/asm/uv/uv_bau.h | 1 | ||||
-rw-r--r-- | arch/x86/include/asm/uv/uv_hub.h | 39 |
9 files changed, 303 insertions, 63 deletions
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 67f87f2..78a1eff 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_AMD_NB_H #define _ASM_X86_AMD_NB_H +#include <linux/ioport.h> #include <linux/pci.h> struct amd_nb_bus_dev_range { @@ -13,6 +14,7 @@ extern const struct pci_device_id amd_nb_misc_ids[]; extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; extern bool early_is_amd_nb(u32 value); +extern struct resource *amd_get_mmconfig_range(struct resource *res); extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 4a0b7c7..244ac77 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -495,7 +495,7 @@ static inline void default_wait_for_init_deassert(atomic_t *deassert) return; } -extern struct apic *generic_bigsmp_probe(void); +extern void generic_bigsmp_probe(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index c9e09ea..a850b4d 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -29,8 +29,8 @@ extern unsigned int sig_xstate_size; extern void fpu_init(void); extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); -extern asmlinkage void math_state_restore(void); -extern void __math_state_restore(void); +extern void __math_state_restore(struct task_struct *); +extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern user_regset_active_fn fpregs_active, xfpregs_active; @@ -212,19 +212,11 @@ static inline void fpu_fxsave(struct fpu *fpu) #endif /* CONFIG_X86_64 */ -/* We need a safe address that is cheap to find and that is already - in L1 during context switch. The best choices are unfortunately - different for UP and SMP */ -#ifdef CONFIG_SMP -#define safe_address (__per_cpu_offset[0]) -#else -#define safe_address (kstat_cpu(0).cpustat.user) -#endif - /* - * These must be called with preempt disabled + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. */ -static inline void fpu_save_init(struct fpu *fpu) +static inline int fpu_save_init(struct fpu *fpu) { if (use_xsave()) { fpu_xsave(fpu); @@ -233,33 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu) * xsave header may indicate the init state of the FP. */ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return; + return 1; } else if (use_fxsr()) { fpu_fxsave(fpu); } else { asm volatile("fnsave %[fx]; fwait" : [fx] "=m" (fpu->state->fsave)); - return; + return 0; } - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { asm volatile("fnclex"); - - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. safe_address is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (safe_address)); + return 0; + } + return 1; } -static inline void __save_init_fpu(struct task_struct *tsk) +static inline int __save_init_fpu(struct task_struct *tsk) { - fpu_save_init(&tsk->thread.fpu); - task_thread_info(tsk)->status &= ~TS_USEDFPU; + return fpu_save_init(&tsk->thread.fpu); } static inline int fpu_fxrstor_checking(struct fpu *fpu) @@ -281,39 +273,185 @@ static inline int restore_fpu_checking(struct task_struct *tsk) } /* - * Signal frame handlers... + * Software FPU state helpers. Careful: these need to + * be preemption protection *and* they need to be + * properly paired with the CR0.TS changes! */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +static inline int __thread_has_fpu(struct task_struct *tsk) +{ + return tsk->thread.has_fpu; +} -static inline void __unlazy_fpu(struct task_struct *tsk) +/* Must be paired with an 'stts' after! */ +static inline void __thread_clear_has_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { - __save_init_fpu(tsk); - stts(); - } else - tsk->fpu_counter = 0; + tsk->thread.has_fpu = 0; +} + +/* Must be paired with a 'clts' before! */ +static inline void __thread_set_has_fpu(struct task_struct *tsk) +{ + tsk->thread.has_fpu = 1; } +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void __thread_fpu_end(struct task_struct *tsk) +{ + __thread_clear_has_fpu(tsk); + stts(); +} + +static inline void __thread_fpu_begin(struct task_struct *tsk) +{ + clts(); + __thread_set_has_fpu(tsk); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +#define fpu_lazy_restore(tsk) (0) +#define fpu_lazy_state_intact(tsk) do { } while (0) + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (__save_init_fpu(old)) + fpu_lazy_state_intact(old); + __thread_clear_has_fpu(old); + old->fpu_counter++; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + if (fpu.preload) { + if (fpu_lazy_restore(new)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) +{ + if (fpu.preload) + __math_state_restore(new); +} + +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + static inline void __clear_fpu(struct task_struct *tsk) { - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (__thread_has_fpu(tsk)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + __thread_fpu_end(tsk); } } +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +static inline bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} + static inline void kernel_fpu_begin(void) { - struct thread_info *me = current_thread_info(); + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); preempt_disable(); - if (me->status & TS_USEDFPU) - __save_init_fpu(me->task); - else + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else clts(); } @@ -323,14 +461,6 @@ static inline void kernel_fpu_end(void) preempt_enable(); } -static inline bool irq_fpu_usable(void) -{ - struct pt_regs *regs; - - return !in_interrupt() || !(regs = get_irq_regs()) || \ - user_mode(regs) || (read_cr0() & X86_CR0_TS); -} - /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions @@ -363,20 +493,64 @@ static inline void irq_ts_restore(int TS_state) } /* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + * + * The actual user_fpu_begin/end() functions + * need to be preemption-safe, though. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline int user_has_fpu(void) +{ + return __thread_has_fpu(current); +} + +static inline void user_fpu_end(void) +{ + preempt_disable(); + __thread_fpu_end(current); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) + __thread_fpu_begin(current); + preempt_enable(); +} + +/* * These disable preemption on their own and are safe */ static inline void save_init_fpu(struct task_struct *tsk) { + WARN_ON_ONCE(!__thread_has_fpu(tsk)); preempt_disable(); __save_init_fpu(tsk); - stts(); + __thread_fpu_end(tsk); preempt_enable(); } static inline void unlazy_fpu(struct task_struct *tsk) { preempt_disable(); - __unlazy_fpu(tsk); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; preempt_enable(); } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 0049211..0ab6a4d 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -189,6 +189,9 @@ struct x86_emulate_ops { int (*intercept)(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage); + + bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -298,6 +301,19 @@ struct x86_emulate_ctxt { #define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \ X86EMUL_MODE_PROT64) +/* CPUID vendors */ +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273 + +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547 +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e +#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 + enum x86_intercept_stage { X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ X86_ICPT_PRE_EXCEPT, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 2193715..5d9c61d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -454,6 +454,7 @@ struct thread_struct { unsigned long trap_no; unsigned long error_code; /* floating point and extended processor state */ + unsigned long has_fpu; struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 1f2e61e..278d3d5 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -242,8 +242,6 @@ static inline struct thread_info *current_thread_info(void) * ever touches our thread-synchronous status, so we don't * have to worry about atomic accesses. */ -#define TS_USEDFPU 0x0001 /* FPU was used by this task - this quantum (SMP) */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #define TS_POLLING 0x0004 /* idle task polling need_resched, skip sending interrupt */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index fa7b917..34baa0e 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -32,6 +32,22 @@ extern int no_timer_check; * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" + * + * In: + * + * ns = cycles * cyc2ns_scale / SC + * + * Although we may still have enough bits to store the value of ns, + * in some cases, we may not have enough bits to store cycles * cyc2ns_scale, + * leading to an incorrect result. + * + * To avoid this, we can decompose 'cycles' into quotient and remainder + * of division by SC. Then, + * + * ns = (quot * SC + rem) * cyc2ns_scale / SC + * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC + * + * - sqazi@google.com */ DECLARE_PER_CPU(unsigned long, cyc2ns); @@ -43,7 +59,8 @@ static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR; + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index a291c40..5d62d65 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -55,6 +55,7 @@ #define UV_BAU_TUNABLES_DIR "sgi_uv" #define UV_BAU_TUNABLES_FILE "bau_tunables" #define WHITESPACE " \t\n" +#define uv_mmask ((1UL << uv_hub_info->m_val) - 1) #define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) #define cpubit_isset(cpu, bau_local_cpumask) \ test_bit((cpu), (bau_local_cpumask).bits) diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index f26544a..21f7385 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -46,6 +46,13 @@ * PNODE - the low N bits of the GNODE. The PNODE is the most useful variant * of the nasid for socket usage. * + * GPA - (global physical address) a socket physical address converted + * so that it can be used by the GRU as a global address. Socket + * physical addresses 1) need additional NASID (node) bits added + * to the high end of the address, and 2) unaliased if the + * partition does not have a physical address 0. In addition, on + * UV2 rev 1, GPAs need the gnode left shifted to bits 39 or 40. + * * * NumaLink Global Physical Address Format: * +--------------------------------+---------------------+ @@ -141,6 +148,8 @@ struct uv_hub_info_s { unsigned int gnode_extra; unsigned char hub_revision; unsigned char apic_pnode_shift; + unsigned char m_shift; + unsigned char n_lshift; unsigned long gnode_upper; unsigned long lowmem_remap_top; unsigned long lowmem_remap_base; @@ -177,6 +186,16 @@ static inline int is_uv2_hub(void) return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; } +static inline int is_uv2_1_hub(void) +{ + return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE; +} + +static inline int is_uv2_2_hub(void) +{ + return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE + 1; +} + union uvh_apicid { unsigned long v; struct uvh_apicid_s { @@ -276,7 +295,10 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr) { if (paddr < uv_hub_info->lowmem_remap_top) paddr |= uv_hub_info->lowmem_remap_base; - return paddr | uv_hub_info->gnode_upper; + paddr |= uv_hub_info->gnode_upper; + paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | + ((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift); + return paddr; } @@ -296,20 +318,23 @@ uv_gpa_in_mmr_space(unsigned long gpa) /* UV global physical address --> socket phys RAM */ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) { - unsigned long paddr = gpa & uv_hub_info->gpa_mask; + unsigned long paddr; unsigned long remap_base = uv_hub_info->lowmem_remap_base; unsigned long remap_top = uv_hub_info->lowmem_remap_top; + gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | + ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val); + paddr = gpa & uv_hub_info->gpa_mask; if (paddr >= remap_base && paddr < remap_base + remap_top) paddr -= remap_base; return paddr; } -/* gnode -> pnode */ +/* gpa -> pnode */ static inline unsigned long uv_gpa_to_gnode(unsigned long gpa) { - return gpa >> uv_hub_info->m_val; + return gpa >> uv_hub_info->n_lshift; } /* gpa -> pnode */ @@ -320,6 +345,12 @@ static inline int uv_gpa_to_pnode(unsigned long gpa) return uv_gpa_to_gnode(gpa) & n_mask; } +/* gpa -> node offset*/ +static inline unsigned long uv_gpa_to_offset(unsigned long gpa) +{ + return (gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift; +} + /* pnode, offset --> socket virtual */ static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset) { |