diff options
Diffstat (limited to 'arch/arm/include')
-rw-r--r-- | arch/arm/include/asm/arch_gicv3.h | 1 | ||||
-rw-r--r-- | arch/arm/include/asm/barrier.h | 35 | ||||
-rw-r--r-- | arch/arm/include/asm/cacheflush.h | 1 | ||||
-rw-r--r-- | arch/arm/include/asm/cputype.h | 22 | ||||
-rw-r--r-- | arch/arm/include/asm/div64.h | 283 | ||||
-rw-r--r-- | arch/arm/include/asm/dma-mapping.h | 7 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_asm.h | 41 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_emulate.h | 20 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_host.h | 80 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_hyp.h | 139 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_mmu.h | 7 | ||||
-rw-r--r-- | arch/arm/include/asm/pci.h | 4 | ||||
-rw-r--r-- | arch/arm/include/asm/pgtable-3level.h | 10 | ||||
-rw-r--r-- | arch/arm/include/asm/psci.h | 2 | ||||
-rw-r--r-- | arch/arm/include/asm/virt.h | 9 | ||||
-rw-r--r-- | arch/arm/include/asm/xen/page-coherent.h | 21 | ||||
-rw-r--r-- | arch/arm/include/debug/dc21285.S | 42 | ||||
-rw-r--r-- | arch/arm/include/uapi/asm/unistd.h | 1 |
18 files changed, 411 insertions, 314 deletions
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 7da5503c0591..e08d15184056 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void) u32 irqstat; asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat)); + dsb(sy); return irqstat; } diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index 3ff5642d9788..112cc1a5d47f 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -60,38 +60,11 @@ extern void arm_heavy_mb(void); #define dma_wmb() barrier() #endif -#ifndef CONFIG_SMP -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#else -#define smp_mb() dmb(ish) -#define smp_rmb() smp_mb() -#define smp_wmb() dmb(ishst) -#endif - -#define smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - smp_mb(); \ - WRITE_ONCE(*p, v); \ -} while (0) - -#define smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - smp_mb(); \ - ___p1; \ -}) - -#define read_barrier_depends() do { } while(0) -#define smp_read_barrier_depends() do { } while(0) - -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) +#define __smp_mb() dmb(ish) +#define __smp_rmb() __smp_mb() +#define __smp_wmb() dmb(ishst) -#define smp_mb__before_atomic() smp_mb() -#define smp_mb__after_atomic() smp_mb() +#include <asm-generic/barrier.h> #endif /* !__ASSEMBLY__ */ #endif /* __ASM_BARRIER_H */ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d5525bfc7e3e..9156fc303afd 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); void set_kernel_text_rw(void); void set_kernel_text_ro(void); #else diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 85e374f873ac..b23c6c81c9ad 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -228,10 +228,26 @@ static inline int cpu_is_xsc3(void) } #endif -#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3) -#define cpu_is_xscale() 0 +#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3) && \ + !defined(CONFIG_CPU_MOHAWK) +#define cpu_is_xscale_family() 0 #else -#define cpu_is_xscale() 1 +static inline int cpu_is_xscale_family(void) +{ + unsigned int id; + id = read_cpuid_id() & 0xffffe000; + + switch (id) { + case 0x69052000: /* Intel XScale 1 */ + case 0x69054000: /* Intel XScale 2 */ + case 0x69056000: /* Intel XScale 3 */ + case 0x56056000: /* Marvell XScale 3 */ + case 0x56158000: /* Marvell Mohawk */ + return 1; + } + + return 0; +} #endif /* diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index 662c7bd06108..e1f07764b0d6 100644 --- a/arch/arm/include/asm/div64.h +++ b/arch/arm/include/asm/div64.h @@ -5,9 +5,9 @@ #include <asm/compiler.h> /* - * The semantics of do_div() are: + * The semantics of __div64_32() are: * - * uint32_t do_div(uint64_t *n, uint32_t base) + * uint32_t __div64_32(uint64_t *n, uint32_t base) * { * uint32_t remainder = *n % base; * *n = *n / base; @@ -16,8 +16,9 @@ * * In other words, a 64-bit dividend with a 32-bit divisor producing * a 64-bit result and a 32-bit remainder. To accomplish this optimally - * we call a special __do_div64 helper with completely non standard - * calling convention for arguments and results (beware). + * we override the generic version in lib/div64.c to call our __do_div64 + * assembly implementation with completely non standard calling convention + * for arguments and results (beware). */ #ifdef __ARMEB__ @@ -28,199 +29,101 @@ #define __xh "r1" #endif -#define __do_div_asm(n, base) \ -({ \ - register unsigned int __base asm("r4") = base; \ - register unsigned long long __n asm("r0") = n; \ - register unsigned long long __res asm("r2"); \ - register unsigned int __rem asm(__xh); \ - asm( __asmeq("%0", __xh) \ - __asmeq("%1", "r2") \ - __asmeq("%2", "r0") \ - __asmeq("%3", "r4") \ - "bl __do_div64" \ - : "=r" (__rem), "=r" (__res) \ - : "r" (__n), "r" (__base) \ - : "ip", "lr", "cc"); \ - n = __res; \ - __rem; \ -}) - -#if __GNUC__ < 4 || !defined(CONFIG_AEABI) +static inline uint32_t __div64_32(uint64_t *n, uint32_t base) +{ + register unsigned int __base asm("r4") = base; + register unsigned long long __n asm("r0") = *n; + register unsigned long long __res asm("r2"); + register unsigned int __rem asm(__xh); + asm( __asmeq("%0", __xh) + __asmeq("%1", "r2") + __asmeq("%2", "r0") + __asmeq("%3", "r4") + "bl __do_div64" + : "=r" (__rem), "=r" (__res) + : "r" (__n), "r" (__base) + : "ip", "lr", "cc"); + *n = __res; + return __rem; +} +#define __div64_32 __div64_32 + +#if !defined(CONFIG_AEABI) /* - * gcc versions earlier than 4.0 are simply too problematic for the - * optimized implementation below. First there is gcc PR 15089 that - * tend to trig on more complex constructs, spurious .global __udivsi3 - * are inserted even if none of those symbols are referenced in the - * generated code, and those gcc versions are not able to do constant - * propagation on long long values anyway. + * In OABI configurations, some uses of the do_div function + * cause gcc to run out of registers. To work around that, + * we can force the use of the out-of-line version for + * configurations that build a OABI kernel. */ -#define do_div(n, base) __do_div_asm(n, base) - -#elif __GNUC__ >= 4 +#define do_div(n, base) __div64_32(&(n), base) -#include <asm/bug.h> +#else /* - * If the divisor happens to be constant, we determine the appropriate - * inverse at compile time to turn the division into a few inline - * multiplications instead which is much faster. And yet only if compiling - * for ARMv4 or higher (we need umull/umlal) and if the gcc version is - * sufficiently recent to perform proper long long constant propagation. - * (It is unfortunate that gcc doesn't perform all this internally.) + * gcc versions earlier than 4.0 are simply too problematic for the + * __div64_const32() code in asm-generic/div64.h. First there is + * gcc PR 15089 that tend to trig on more complex constructs, spurious + * .global __udivsi3 are inserted even if none of those symbols are + * referenced in the generated code, and those gcc versions are not able + * to do constant propagation on long long values anyway. */ -#define do_div(n, base) \ -({ \ - unsigned int __r, __b = (base); \ - if (!__builtin_constant_p(__b) || __b == 0 || \ - (__LINUX_ARM_ARCH__ < 4 && (__b & (__b - 1)) != 0)) { \ - /* non-constant divisor (or zero): slow path */ \ - __r = __do_div_asm(n, __b); \ - } else if ((__b & (__b - 1)) == 0) { \ - /* Trivial: __b is constant and a power of 2 */ \ - /* gcc does the right thing with this code. */ \ - __r = n; \ - __r &= (__b - 1); \ - n /= __b; \ - } else { \ - /* Multiply by inverse of __b: n/b = n*(p/b)/p */ \ - /* We rely on the fact that most of this code gets */ \ - /* optimized away at compile time due to constant */ \ - /* propagation and only a couple inline assembly */ \ - /* instructions should remain. Better avoid any */ \ - /* code construct that might prevent that. */ \ - unsigned long long __res, __x, __t, __m, __n = n; \ - unsigned int __c, __p, __z = 0; \ - /* preserve low part of n for reminder computation */ \ - __r = __n; \ - /* determine number of bits to represent __b */ \ - __p = 1 << __div64_fls(__b); \ - /* compute __m = ((__p << 64) + __b - 1) / __b */ \ - __m = (~0ULL / __b) * __p; \ - __m += (((~0ULL % __b + 1) * __p) + __b - 1) / __b; \ - /* compute __res = __m*(~0ULL/__b*__b-1)/(__p << 64) */ \ - __x = ~0ULL / __b * __b - 1; \ - __res = (__m & 0xffffffff) * (__x & 0xffffffff); \ - __res >>= 32; \ - __res += (__m & 0xffffffff) * (__x >> 32); \ - __t = __res; \ - __res += (__x & 0xffffffff) * (__m >> 32); \ - __t = (__res < __t) ? (1ULL << 32) : 0; \ - __res = (__res >> 32) + __t; \ - __res += (__m >> 32) * (__x >> 32); \ - __res /= __p; \ - /* Now sanitize and optimize what we've got. */ \ - if (~0ULL % (__b / (__b & -__b)) == 0) { \ - /* those cases can be simplified with: */ \ - __n /= (__b & -__b); \ - __m = ~0ULL / (__b / (__b & -__b)); \ - __p = 1; \ - __c = 1; \ - } else if (__res != __x / __b) { \ - /* We can't get away without a correction */ \ - /* to compensate for bit truncation errors. */ \ - /* To avoid it we'd need an additional bit */ \ - /* to represent __m which would overflow it. */ \ - /* Instead we do m=p/b and n/b=(n*m+m)/p. */ \ - __c = 1; \ - /* Compute __m = (__p << 64) / __b */ \ - __m = (~0ULL / __b) * __p; \ - __m += ((~0ULL % __b + 1) * __p) / __b; \ - } else { \ - /* Reduce __m/__p, and try to clear bit 31 */ \ - /* of __m when possible otherwise that'll */ \ - /* need extra overflow handling later. */ \ - unsigned int __bits = -(__m & -__m); \ - __bits |= __m >> 32; \ - __bits = (~__bits) << 1; \ - /* If __bits == 0 then setting bit 31 is */ \ - /* unavoidable. Simply apply the maximum */ \ - /* possible reduction in that case. */ \ - /* Otherwise the MSB of __bits indicates the */ \ - /* best reduction we should apply. */ \ - if (!__bits) { \ - __p /= (__m & -__m); \ - __m /= (__m & -__m); \ - } else { \ - __p >>= __div64_fls(__bits); \ - __m >>= __div64_fls(__bits); \ - } \ - /* No correction needed. */ \ - __c = 0; \ - } \ - /* Now we have a combination of 2 conditions: */ \ - /* 1) whether or not we need a correction (__c), and */ \ - /* 2) whether or not there might be an overflow in */ \ - /* the cross product (__m & ((1<<63) | (1<<31))) */ \ - /* Select the best insn combination to perform the */ \ - /* actual __m * __n / (__p << 64) operation. */ \ - if (!__c) { \ - asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" \ - "mov %Q0, #0" \ - : "=&r" (__res) \ - : "r" (__m), "r" (__n) \ - : "cc" ); \ - } else if (!(__m & ((1ULL << 63) | (1ULL << 31)))) { \ - __res = __m; \ - asm ( "umlal %Q0, %R0, %Q1, %Q2\n\t" \ - "mov %Q0, #0" \ - : "+&r" (__res) \ - : "r" (__m), "r" (__n) \ - : "cc" ); \ - } else { \ - asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" \ - "cmn %Q0, %Q1\n\t" \ - "adcs %R0, %R0, %R1\n\t" \ - "adc %Q0, %3, #0" \ - : "=&r" (__res) \ - : "r" (__m), "r" (__n), "r" (__z) \ - : "cc" ); \ - } \ - if (!(__m & ((1ULL << 63) | (1ULL << 31)))) { \ - asm ( "umlal %R0, %Q0, %R1, %Q2\n\t" \ - "umlal %R0, %Q0, %Q1, %R2\n\t" \ - "mov %R0, #0\n\t" \ - "umlal %Q0, %R0, %R1, %R2" \ - : "+&r" (__res) \ - : "r" (__m), "r" (__n) \ - : "cc" ); \ - } else { \ - asm ( "umlal %R0, %Q0, %R2, %Q3\n\t" \ - "umlal %R0, %1, %Q2, %R3\n\t" \ - "mov %R0, #0\n\t" \ - "adds %Q0, %1, %Q0\n\t" \ - "adc %R0, %R0, #0\n\t" \ - "umlal %Q0, %R0, %R2, %R3" \ - : "+&r" (__res), "+&r" (__z) \ - : "r" (__m), "r" (__n) \ - : "cc" ); \ - } \ - __res /= __p; \ - /* The reminder can be computed with 32-bit regs */ \ - /* only, and gcc is good at that. */ \ - { \ - unsigned int __res0 = __res; \ - unsigned int __b0 = __b; \ - __r -= __res0 * __b0; \ - } \ - /* BUG_ON(__r >= __b || __res * __b + __r != n); */ \ - n = __res; \ - } \ - __r; \ -}) - -/* our own fls implementation to make sure constant propagation is fine */ -#define __div64_fls(bits) \ -({ \ - unsigned int __left = (bits), __nr = 0; \ - if (__left & 0xffff0000) __nr += 16, __left >>= 16; \ - if (__left & 0x0000ff00) __nr += 8, __left >>= 8; \ - if (__left & 0x000000f0) __nr += 4, __left >>= 4; \ - if (__left & 0x0000000c) __nr += 2, __left >>= 2; \ - if (__left & 0x00000002) __nr += 1; \ - __nr; \ -}) + +#define __div64_const32_is_OK (__GNUC__ >= 4) + +static inline uint64_t __arch_xprod_64(uint64_t m, uint64_t n, bool bias) +{ + unsigned long long res; + unsigned int tmp = 0; + + if (!bias) { + asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" + "mov %Q0, #0" + : "=&r" (res) + : "r" (m), "r" (n) + : "cc"); + } else if (!(m & ((1ULL << 63) | (1ULL << 31)))) { + res = m; + asm ( "umlal %Q0, %R0, %Q1, %Q2\n\t" + "mov %Q0, #0" + : "+&r" (res) + : "r" (m), "r" (n) + : "cc"); + } else { + asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" + "cmn %Q0, %Q1\n\t" + "adcs %R0, %R0, %R1\n\t" + "adc %Q0, %3, #0" + : "=&r" (res) + : "r" (m), "r" (n), "r" (tmp) + : "cc"); + } + + if (!(m & ((1ULL << 63) | (1ULL << 31)))) { + asm ( "umlal %R0, %Q0, %R1, %Q2\n\t" + "umlal %R0, %Q0, %Q1, %R2\n\t" + "mov %R0, #0\n\t" + "umlal %Q0, %R0, %R1, %R2" + : "+&r" (res) + : "r" (m), "r" (n) + : "cc"); + } else { + asm ( "umlal %R0, %Q0, %R2, %Q3\n\t" + "umlal %R0, %1, %Q2, %R3\n\t" + "mov %R0, #0\n\t" + "adds %Q0, %1, %Q0\n\t" + "adc %R0, %R0, #0\n\t" + "umlal %Q0, %R0, %R2, %R3" + : "+&r" (res), "+&r" (tmp) + : "r" (m), "r" (n) + : "cc"); + } + + return res; +} +#define __arch_xprod_64 __arch_xprod_64 + +#include <asm-generic/div64.h> #endif diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index ccb3aa64640d..6ad1ceda62a5 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -41,13 +41,6 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) #define HAVE_ARCH_DMA_SUPPORTED 1 extern int dma_supported(struct device *dev, u64 mask); -/* - * Note that while the generic code provides dummy dma_{alloc,free}_noncoherent - * implementations, we don't provide a dma_cache_sync function so drivers using - * this API are highlighted with build warnings. - */ -#include <asm-generic/dma-mapping-common.h> - #ifdef __arch_page_to_dma #error Please update to __arch_pfn_to_dma #endif diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 194c91b610ff..15d58b42d5a1 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -19,38 +19,7 @@ #ifndef __ARM_KVM_ASM_H__ #define __ARM_KVM_ASM_H__ -/* 0 is reserved as an invalid value. */ -#define c0_MPIDR 1 /* MultiProcessor ID Register */ -#define c0_CSSELR 2 /* Cache Size Selection Register */ -#define c1_SCTLR 3 /* System Control Register */ -#define c1_ACTLR 4 /* Auxiliary Control Register */ -#define c1_CPACR 5 /* Coprocessor Access Control */ -#define c2_TTBR0 6 /* Translation Table Base Register 0 */ -#define c2_TTBR0_high 7 /* TTBR0 top 32 bits */ -#define c2_TTBR1 8 /* Translation Table Base Register 1 */ -#define c2_TTBR1_high 9 /* TTBR1 top 32 bits */ -#define c2_TTBCR 10 /* Translation Table Base Control R. */ -#define c3_DACR 11 /* Domain Access Control Register */ -#define c5_DFSR 12 /* Data Fault Status Register */ -#define c5_IFSR 13 /* Instruction Fault Status Register */ -#define c5_ADFSR 14 /* Auxilary Data Fault Status R */ -#define c5_AIFSR 15 /* Auxilary Instrunction Fault Status R */ -#define c6_DFAR 16 /* Data Fault Address Register */ -#define c6_IFAR 17 /* Instruction Fault Address Register */ -#define c7_PAR 18 /* Physical Address Register */ -#define c7_PAR_high 19 /* PAR top 32 bits */ -#define c9_L2CTLR 20 /* Cortex A15/A7 L2 Control Register */ -#define c10_PRRR 21 /* Primary Region Remap Register */ -#define c10_NMRR 22 /* Normal Memory Remap Register */ -#define c12_VBAR 23 /* Vector Base Address Register */ -#define c13_CID 24 /* Context ID Register */ -#define c13_TID_URW 25 /* Thread ID, User R/W */ -#define c13_TID_URO 26 /* Thread ID, User R/O */ -#define c13_TID_PRIV 27 /* Thread ID, Privileged */ -#define c14_CNTKCTL 28 /* Timer Control Register (PL1) */ -#define c10_AMAIR0 29 /* Auxilary Memory Attribute Indirection Reg0 */ -#define c10_AMAIR1 30 /* Auxilary Memory Attribute Indirection Reg1 */ -#define NR_CP15_REGS 31 /* Number of regs (incl. invalid) */ +#include <asm/virt.h> #define ARM_EXCEPTION_RESET 0 #define ARM_EXCEPTION_UNDEFINED 1 @@ -86,19 +55,15 @@ struct kvm_vcpu; extern char __kvm_hyp_init[]; extern char __kvm_hyp_init_end[]; -extern char __kvm_hyp_exit[]; -extern char __kvm_hyp_exit_end[]; - extern char __kvm_hyp_vector[]; -extern char __kvm_hyp_code_start[]; -extern char __kvm_hyp_code_end[]; - extern void __kvm_flush_vm_context(void); extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern void __kvm_tlb_flush_vmid(struct kvm *kvm); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); + +extern void __init_stage2_translation(void); #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 3095df091ff8..ee5328fc4b06 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -68,12 +68,12 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) { - return &vcpu->arch.regs.usr_regs.ARM_pc; + return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc; } static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu) { - return &vcpu->arch.regs.usr_regs.ARM_cpsr; + return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr; } static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) @@ -83,13 +83,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) static inline bool mode_has_spsr(struct kvm_vcpu *vcpu) { - unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK; + unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE); } static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) { - unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK; + unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; return cpsr_mode > USR_MODE;; } @@ -108,11 +108,6 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; } -static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.fault.hyp_pc; -} - static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; @@ -143,6 +138,11 @@ static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; } +static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu) +{ + return !!(kvm_vcpu_get_hsr(vcpu) & HSR_DABT_CM); +} + /* Get Access Size from a data abort */ static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) { @@ -192,7 +192,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) { - return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK; + return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; } static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index f9f27792d8ed..385070180c25 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -85,20 +85,61 @@ struct kvm_vcpu_fault_info { u32 hsr; /* Hyp Syndrome Register */ u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ u32 hpfar; /* Hyp IPA Fault Address Register */ - u32 hyp_pc; /* PC when exception was taken from Hyp mode */ }; -typedef struct vfp_hard_struct kvm_cpu_context_t; +/* + * 0 is reserved as an invalid value. + * Order should be kept in sync with the save/restore code. + */ +enum vcpu_sysreg { + __INVALID_SYSREG__, + c0_MPIDR, /* MultiProcessor ID Register */ + c0_CSSELR, /* Cache Size Selection Register */ + c1_SCTLR, /* System Control Register */ + c1_ACTLR, /* Auxiliary Control Register */ + c1_CPACR, /* Coprocessor Access Control */ + c2_TTBR0, /* Translation Table Base Register 0 */ + c2_TTBR0_high, /* TTBR0 top 32 bits */ + c2_TTBR1, /* Translation Table Base Register 1 */ + c2_TTBR1_high, /* TTBR1 top 32 bits */ + c2_TTBCR, /* Translation Table Base Control R. */ + c3_DACR, /* Domain Access Control Register */ + c5_DFSR, /* Data Fault Status Register */ + c5_IFSR, /* Instruction Fault Status Register */ + c5_ADFSR, /* Auxilary Data Fault Status R */ + c5_AIFSR, /* Auxilary Instrunction Fault Status R */ + c6_DFAR, /* Data Fault Address Register */ + c6_IFAR, /* Instruction Fault Address Register */ + c7_PAR, /* Physical Address Register */ + c7_PAR_high, /* PAR top 32 bits */ + c9_L2CTLR, /* Cortex A15/A7 L2 Control Register */ + c10_PRRR, /* Primary Region Remap Register */ + c10_NMRR, /* Normal Memory Remap Register */ + c12_VBAR, /* Vector Base Address Register */ + c13_CID, /* Context ID Register */ + c13_TID_URW, /* Thread ID, User R/W */ + c13_TID_URO, /* Thread ID, User R/O */ + c13_TID_PRIV, /* Thread ID, Privileged */ + c14_CNTKCTL, /* Timer Control Register (PL1) */ + c10_AMAIR0, /* Auxilary Memory Attribute Indirection Reg0 */ + c10_AMAIR1, /* Auxilary Memory Attribute Indirection Reg1 */ + NR_CP15_REGS /* Number of regs (incl. invalid) */ +}; + +struct kvm_cpu_context { + struct kvm_regs gp_regs; + struct vfp_hard_struct vfp; + u32 cp15[NR_CP15_REGS]; +}; + +typedef struct kvm_cpu_context kvm_cpu_context_t; struct kvm_vcpu_arch { - struct kvm_regs regs; + struct kvm_cpu_context ctxt; int target; /* Processor target */ DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - /* System control coprocessor (cp15) */ - u32 cp15[NR_CP15_REGS]; - /* The CPU type we expose to the VM */ u32 midr; @@ -111,9 +152,6 @@ struct kvm_vcpu_arch { /* Exception Information */ struct kvm_vcpu_fault_info fault; - /* Floating point registers (VFP and Advanced SIMD/NEON) */ - struct vfp_hard_struct vfp_guest; - /* Host FP context */ kvm_cpu_context_t *host_cpu_context; @@ -158,12 +196,14 @@ struct kvm_vcpu_stat { u64 exits; }; +#define vcpu_cp15(v,r) (v)->arch.ctxt.cp15[r] + int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -u64 kvm_call_hyp(void *hypfn, ...); +unsigned long kvm_call_hyp(void *hypfn, ...); void force_vm_exit(const cpumask_t *mask); #define KVM_ARCH_WANT_MMU_NOTIFIER @@ -220,6 +260,11 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr, kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); } +static inline void __cpu_init_stage2(void) +{ + kvm_call_hyp(__init_stage2_translation); +} + static inline int kvm_arch_dev_ioctl_check_extension(long ext) { return 0; @@ -242,5 +287,20 @@ static inline void kvm_arm_init_debug(void) {} static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {} +static inline int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + return -ENXIO; +} +static inline int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + return -ENXIO; +} +static inline int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + return -ENXIO; +} #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h new file mode 100644 index 000000000000..f0e860761380 --- /dev/null +++ b/arch/arm/include/asm/kvm_hyp.h @@ -0,0 +1,139 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __ARM_KVM_HYP_H__ +#define __ARM_KVM_HYP_H__ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> +#include <asm/kvm_mmu.h> +#include <asm/vfp.h> + +#define __hyp_text __section(.hyp.text) notrace + +#define kern_hyp_va(v) (v) +#define hyp_kern_va(v) (v) + +#define __ACCESS_CP15(CRn, Op1, CRm, Op2) \ + "mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32 +#define __ACCESS_CP15_64(Op1, CRm) \ + "mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64 +#define __ACCESS_VFP(CRn) \ + "mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32 + +#define __write_sysreg(v, r, w, c, t) asm volatile(w " " c : : "r" ((t)(v))) +#define write_sysreg(v, ...) __write_sysreg(v, __VA_ARGS__) + +#define __read_sysreg(r, w, c, t) ({ \ + t __val; \ + asm volatile(r " " c : "=r" (__val)); \ + __val; \ +}) +#define read_sysreg(...) __read_sysreg(__VA_ARGS__) + +#define write_special(v, r) \ + asm volatile("msr " __stringify(r) ", %0" : : "r" (v)) +#define read_special(r) ({ \ + u32 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +#define TTBR0 __ACCESS_CP15_64(0, c2) +#define TTBR1 __ACCESS_CP15_64(1, c2) +#define VTTBR __ACCESS_CP15_64(6, c2) +#define PAR __ACCESS_CP15_64(0, c7) +#define CNTV_CVAL __ACCESS_CP15_64(3, c14) +#define CNTVOFF __ACCESS_CP15_64(4, c14) + +#define MIDR __ACCESS_CP15(c0, 0, c0, 0) +#define CSSELR __ACCESS_CP15(c0, 2, c0, 0) +#define VPIDR __ACCESS_CP15(c0, 4, c0, 0) +#define VMPIDR __ACCESS_CP15(c0, 4, c0, 5) +#define SCTLR __ACCESS_CP15(c1, 0, c0, 0) +#define CPACR __ACCESS_CP15(c1, 0, c0, 2) +#define HCR __ACCESS_CP15(c1, 4, c1, 0) +#define HDCR __ACCESS_CP15(c1, 4, c1, 1) +#define HCPTR __ACCESS_CP15(c1, 4, c1, 2) +#define HSTR __ACCESS_CP15(c1, 4, c1, 3) +#define TTBCR __ACCESS_CP15(c2, 0, c0, 2) +#define HTCR __ACCESS_CP15(c2, 4, c0, 2) +#define VTCR __ACCESS_CP15(c2, 4, c1, 2) +#define DACR __ACCESS_CP15(c3, 0, c0, 0) +#define DFSR __ACCESS_CP15(c5, 0, c0, 0) +#define IFSR __ACCESS_CP15(c5, 0, c0, 1) +#define ADFSR __ACCESS_CP15(c5, 0, c1, 0) +#define AIFSR __ACCESS_CP15(c5, 0, c1, 1) +#define HSR __ACCESS_CP15(c5, 4, c2, 0) +#define DFAR __ACCESS_CP15(c6, 0, c0, 0) +#define IFAR __ACCESS_CP15(c6, 0, c0, 2) +#define HDFAR __ACCESS_CP15(c6, 4, c0, 0) +#define HIFAR __ACCESS_CP15(c6, 4, c0, 2) +#define HPFAR __ACCESS_CP15(c6, 4, c0, 4) +#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0) +#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0) +#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0) +#define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4) +#define PRRR __ACCESS_CP15(c10, 0, c2, 0) +#define NMRR __ACCESS_CP15(c10, 0, c2, 1) +#define AMAIR0 __ACCESS_CP15(c10, 0, c3, 0) +#define AMAIR1 __ACCESS_CP15(c10, 0, c3, 1) +#define VBAR __ACCESS_CP15(c12, 0, c0, 0) +#define CID __ACCESS_CP15(c13, 0, c0, 1) +#define TID_URW __ACCESS_CP15(c13, 0, c0, 2) +#define TID_URO __ACCESS_CP15(c13, 0, c0, 3) +#define TID_PRIV __ACCESS_CP15(c13, 0, c0, 4) +#define HTPIDR __ACCESS_CP15(c13, 4, c0, 2) +#define CNTKCTL __ACCESS_CP15(c14, 0, c1, 0) +#define CNTV_CTL __ACCESS_CP15(c14, 0, c3, 1) +#define CNTHCTL __ACCESS_CP15(c14, 4, c1, 0) + +#define VFP_FPEXC __ACCESS_VFP(FPEXC) + +/* AArch64 compatibility macros, only for the timer so far */ +#define read_sysreg_el0(r) read_sysreg(r##_el0) +#define write_sysreg_el0(v, r) write_sysreg(v, r##_el0) + +#define cntv_ctl_el0 CNTV_CTL +#define cntv_cval_el0 CNTV_CVAL +#define cntvoff_el2 CNTVOFF +#define cnthctl_el2 CNTHCTL + +void __timer_save_state(struct kvm_vcpu *vcpu); +void __timer_restore_state(struct kvm_vcpu *vcpu); + +void __vgic_v2_save_state(struct kvm_vcpu *vcpu); +void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); + +void __sysreg_save_state(struct kvm_cpu_context *ctxt); +void __sysreg_restore_state(struct kvm_cpu_context *ctxt); + +void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp); +void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp); +static inline bool __vfp_enabled(void) +{ + return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10))); +} + +void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt); +void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt); + +int asmlinkage __guest_enter(struct kvm_vcpu *vcpu, + struct kvm_cpu_context *host); +int asmlinkage __hyp_do_panic(const char *, int, u32); + +#endif /* __ARM_KVM_HYP_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 9203c21b4673..da44be9db4fa 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -179,10 +179,11 @@ struct kvm; static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { - return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; + return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { @@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte) static inline void __kvm_flush_dcache_pmd(pmd_t pmd) { unsigned long size = PMD_SIZE; - pfn_t pfn = pmd_pfn(pmd); + kvm_pfn_t pfn = pmd_pfn(pmd); while (size) { void *va = kmap_atomic_pfn(pfn); diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index a5635444ca41..057d381f4e57 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -2,9 +2,6 @@ #define ASMARM_PCI_H #ifdef __KERNEL__ -#include <asm-generic/pci-dma-compat.h> -#include <asm-generic/pci-bridge.h> - #include <asm/mach/pci.h> /* for pci_sys_data */ extern unsigned long pcibios_min_io; @@ -41,5 +38,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) } #endif /* __KERNEL__ */ - #endif diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a53853..dc46398bc3a5 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -88,7 +88,6 @@ #define L_PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) #define L_PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) -#define L_PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) #define L_PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) #define L_PMD_SECT_RDONLY (_AT(pteval_t, 1) << 58) @@ -232,13 +231,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) -#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING)) - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); -#endif #endif #define PMD_BIT_FUNC(fn,op) \ @@ -246,9 +238,9 @@ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } PMD_BIT_FUNC(wrprotect, |= L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); -PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING); PMD_BIT_FUNC(mkwrite, &= ~L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkdirty, |= L_PMD_SECT_DIRTY); +PMD_BIT_FUNC(mkclean, &= ~L_PMD_SECT_DIRTY); PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index b4c6d99364f1..e1b825dfab23 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -14,7 +14,7 @@ #ifndef __ASM_ARM_PSCI_H #define __ASM_ARM_PSCI_H -extern struct smp_operations psci_smp_ops; +extern const struct smp_operations psci_smp_ops; #if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI) bool psci_smp_available(void); diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h index 4371f45c5784..d4ceaf5f299b 100644 --- a/arch/arm/include/asm/virt.h +++ b/arch/arm/include/asm/virt.h @@ -74,6 +74,15 @@ static inline bool is_hyp_mode_mismatched(void) { return !!(__boot_cpu_mode & BOOT_CPU_MODE_MISMATCH); } + +static inline bool is_kernel_in_hyp_mode(void) +{ + return false; +} + +/* The section containing the hypervisor text */ +extern char __hyp_text_start[]; +extern char __hyp_text_end[]; #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<<compound_order(page)) * XEN_PFN_PER_PAGE; + bool local = (page_pfn <= dev_pfn) && + (dev_pfn - page_pfn < compound_pages); + /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. So if the first xen_pfn == mfn the page is local - * otherwise it's a foreign page grant-mapped in dom0. If the page is - * local we can safely call the native dma_ops function, otherwise we - * call the xen specific function. + * Dom0 is mapped 1:1, while the Linux page can span across + * multiple Xen pages, it's not possible for it to contain a + * mix of local and foreign Xen pages. So if the first xen_pfn + * == mfn the page is local otherwise it's a foreign page + * grant-mapped in dom0. If the page is local we can safely + * call the native dma_ops function, otherwise we call the xen + * specific function. */ if (local) __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); diff --git a/arch/arm/include/debug/dc21285.S b/arch/arm/include/debug/dc21285.S new file mode 100644 index 000000000000..02247f313e94 --- /dev/null +++ b/arch/arm/include/debug/dc21285.S @@ -0,0 +1,42 @@ +/* arch/arm/mach-footbridge/include/mach/debug-macro.S + * + * Debugging macro include header + * + * Copyright (C) 1994-1999 Russell King + * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * +*/ + +#include <asm/hardware/dec21285.h> + +#include <mach/hardware.h> + /* For EBSA285 debugging */ + .equ dc21285_high, ARMCSR_BASE & 0xff000000 + .equ dc21285_low, ARMCSR_BASE & 0x00ffffff + + .macro addruart, rp, rv, tmp + .if dc21285_low + mov \rp, #dc21285_low + .else + mov \rp, #0 + .endif + orr \rv, \rp, #dc21285_high + orr \rp, \rp, #0x42000000 + .endm + + .macro senduart,rd,rx + str \rd, [\rx, #0x160] @ UARTDR + .endm + + .macro busyuart,rd,rx +1001: ldr \rd, [\rx, #0x178] @ UARTFLG + tst \rd, #1 << 3 + bne 1001b + .endm + + .macro waituart,rd,rx + .endm diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index ede692ffa32e..5dd2528e9e45 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -417,6 +417,7 @@ #define __NR_userfaultfd (__NR_SYSCALL_BASE+388) #define __NR_membarrier (__NR_SYSCALL_BASE+389) #define __NR_mlock2 (__NR_SYSCALL_BASE+390) +#define __NR_copy_file_range (__NR_SYSCALL_BASE+391) /* * The following SWIs are ARM private. |