1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
linux/arch/powerpc/include/asm/processor.h
Christophe Leroy 16132529ce powerpc/32s: Rework Kernel Userspace Access Protection
On book3s/32, KUAP is provided by toggling Ks bit in segment registers.
One segment register addresses 256M of virtual memory.

At the time being, KUAP implements a complex logic to apply the
unlock/lock on the exact number of segments covering the user range
to access, with saving the boundaries of the range of segments in
a member of thread struct.

But most if not all user accesses are within a single segment.

Rework KUAP with a different approach:
- Open only one segment, the one corresponding to the starting
address of the range to be accessed.
- If a second segment is involved, it will generate a page fault. The
segment will then be open by the page fault handler.

The kuap member of thread struct will now contain:
- The start address of the current on going user access, that will be
used to know which segment to lock at the end of the user access.
- ~0 when no user access is open
- ~1 when additionnal segments are opened by a page fault.

Then, at lock time
- When only one segment is open, close it.
- When several segments are open, close all user segments.

Almost 100% of the time, only one segment will be involved.

In interrupts, inline the function that unlock/lock all segments,
because not inlining them implies a lot of register save/restore.

With the patch, writing value 128 in userspace in perf_copy_attr() is
done with 16 instructions:

    3890:	93 82 04 dc 	stw     r28,1244(r2)
    3894:	7d 20 e5 26 	mfsrin  r9,r28
    3898:	55 29 00 80 	rlwinm  r9,r9,0,2,0
    389c:	7d 20 e1 e4 	mtsrin  r9,r28
    38a0:	4c 00 01 2c 	isync

    38a4:	39 20 00 80 	li      r9,128
    38a8:	91 3c 00 00 	stw     r9,0(r28)

    38ac:	81 42 04 dc 	lwz     r10,1244(r2)
    38b0:	39 00 ff ff 	li      r8,-1
    38b4:	91 02 04 dc 	stw     r8,1244(r2)
    38b8:	2c 0a ff fe 	cmpwi   r10,-2
    38bc:	41 82 00 88 	beq     3944 <perf_copy_attr+0x36c>
    38c0:	7d 20 55 26 	mfsrin  r9,r10
    38c4:	65 29 40 00 	oris    r9,r9,16384
    38c8:	7d 20 51 e4 	mtsrin  r9,r10
    38cc:	4c 00 01 2c 	isync
...
    3944:	48 00 00 01 	bl      3944 <perf_copy_attr+0x36c>
			3944: R_PPC_REL24	kuap_lock_all_ool

Before the patch it was 118 instructions. In reality only 42 are
executed in most cases, but GCC is not able to see that a properly
aligned user access cannot involve more than one segment.

    5060:	39 1d 00 04 	addi    r8,r29,4
    5064:	3d 20 b0 00 	lis     r9,-20480
    5068:	7c 08 48 40 	cmplw   r8,r9
    506c:	40 81 00 08 	ble     5074 <perf_copy_attr+0x2cc>
    5070:	3d 00 b0 00 	lis     r8,-20480
    5074:	39 28 ff ff 	addi    r9,r8,-1
    5078:	57 aa 00 06 	rlwinm  r10,r29,0,0,3
    507c:	55 29 27 3e 	rlwinm  r9,r9,4,28,31
    5080:	39 29 00 01 	addi    r9,r9,1
    5084:	7d 29 53 78 	or      r9,r9,r10
    5088:	91 22 04 dc 	stw     r9,1244(r2)
    508c:	7d 20 ed 26 	mfsrin  r9,r29
    5090:	55 29 00 80 	rlwinm  r9,r9,0,2,0
    5094:	7c 08 50 40 	cmplw   r8,r10
    5098:	40 81 00 c0 	ble     5158 <perf_copy_attr+0x3b0>
    509c:	7d 46 50 f8 	not     r6,r10
    50a0:	7c c6 42 14 	add     r6,r6,r8
    50a4:	54 c6 27 be 	rlwinm  r6,r6,4,30,31
    50a8:	7d 20 51 e4 	mtsrin  r9,r10
    50ac:	3c ea 10 00 	addis   r7,r10,4096
    50b0:	39 29 01 11 	addi    r9,r9,273
    50b4:	7f 88 38 40 	cmplw   cr7,r8,r7
    50b8:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    50bc:	40 9d 00 9c 	ble     cr7,5158 <perf_copy_attr+0x3b0>

    50c0:	2f 86 00 00 	cmpwi   cr7,r6,0
    50c4:	41 9e 00 4c 	beq     cr7,5110 <perf_copy_attr+0x368>
    50c8:	2f 86 00 01 	cmpwi   cr7,r6,1
    50cc:	41 9e 00 2c 	beq     cr7,50f8 <perf_copy_attr+0x350>
    50d0:	2f 86 00 02 	cmpwi   cr7,r6,2
    50d4:	41 9e 00 14 	beq     cr7,50e8 <perf_copy_attr+0x340>
    50d8:	7d 20 39 e4 	mtsrin  r9,r7
    50dc:	39 29 01 11 	addi    r9,r9,273
    50e0:	3c e7 10 00 	addis   r7,r7,4096
    50e4:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    50e8:	7d 20 39 e4 	mtsrin  r9,r7
    50ec:	39 29 01 11 	addi    r9,r9,273
    50f0:	3c e7 10 00 	addis   r7,r7,4096
    50f4:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    50f8:	7d 20 39 e4 	mtsrin  r9,r7
    50fc:	3c e7 10 00 	addis   r7,r7,4096
    5100:	39 29 01 11 	addi    r9,r9,273
    5104:	7f 88 38 40 	cmplw   cr7,r8,r7
    5108:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    510c:	40 9d 00 4c 	ble     cr7,5158 <perf_copy_attr+0x3b0>
    5110:	7d 20 39 e4 	mtsrin  r9,r7
    5114:	39 29 01 11 	addi    r9,r9,273
    5118:	3c c7 10 00 	addis   r6,r7,4096
    511c:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5120:	7d 20 31 e4 	mtsrin  r9,r6
    5124:	39 29 01 11 	addi    r9,r9,273
    5128:	3c c6 10 00 	addis   r6,r6,4096
    512c:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5130:	7d 20 31 e4 	mtsrin  r9,r6
    5134:	39 29 01 11 	addi    r9,r9,273
    5138:	3c c7 30 00 	addis   r6,r7,12288
    513c:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5140:	7d 20 31 e4 	mtsrin  r9,r6
    5144:	3c e7 40 00 	addis   r7,r7,16384
    5148:	39 29 01 11 	addi    r9,r9,273
    514c:	7f 88 38 40 	cmplw   cr7,r8,r7
    5150:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5154:	41 9d ff bc 	bgt     cr7,5110 <perf_copy_attr+0x368>

    5158:	4c 00 01 2c 	isync
    515c:	39 20 00 80 	li      r9,128
    5160:	91 3d 00 00 	stw     r9,0(r29)

    5164:	38 e0 00 00 	li      r7,0
    5168:	90 e2 04 dc 	stw     r7,1244(r2)
    516c:	7d 20 ed 26 	mfsrin  r9,r29
    5170:	65 29 40 00 	oris    r9,r9,16384
    5174:	40 81 00 c0 	ble     5234 <perf_copy_attr+0x48c>
    5178:	7d 47 50 f8 	not     r7,r10
    517c:	7c e7 42 14 	add     r7,r7,r8
    5180:	54 e7 27 be 	rlwinm  r7,r7,4,30,31
    5184:	7d 20 51 e4 	mtsrin  r9,r10
    5188:	3d 4a 10 00 	addis   r10,r10,4096
    518c:	39 29 01 11 	addi    r9,r9,273
    5190:	7c 08 50 40 	cmplw   r8,r10
    5194:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5198:	40 81 00 9c 	ble     5234 <perf_copy_attr+0x48c>

    519c:	2c 07 00 00 	cmpwi   r7,0
    51a0:	41 82 00 4c 	beq     51ec <perf_copy_attr+0x444>
    51a4:	2c 07 00 01 	cmpwi   r7,1
    51a8:	41 82 00 2c 	beq     51d4 <perf_copy_attr+0x42c>
    51ac:	2c 07 00 02 	cmpwi   r7,2
    51b0:	41 82 00 14 	beq     51c4 <perf_copy_attr+0x41c>
    51b4:	7d 20 51 e4 	mtsrin  r9,r10
    51b8:	39 29 01 11 	addi    r9,r9,273
    51bc:	3d 4a 10 00 	addis   r10,r10,4096
    51c0:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    51c4:	7d 20 51 e4 	mtsrin  r9,r10
    51c8:	39 29 01 11 	addi    r9,r9,273
    51cc:	3d 4a 10 00 	addis   r10,r10,4096
    51d0:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    51d4:	7d 20 51 e4 	mtsrin  r9,r10
    51d8:	3d 4a 10 00 	addis   r10,r10,4096
    51dc:	39 29 01 11 	addi    r9,r9,273
    51e0:	7c 08 50 40 	cmplw   r8,r10
    51e4:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    51e8:	40 81 00 4c 	ble     5234 <perf_copy_attr+0x48c>
    51ec:	7d 20 51 e4 	mtsrin  r9,r10
    51f0:	39 29 01 11 	addi    r9,r9,273
    51f4:	3c ea 10 00 	addis   r7,r10,4096
    51f8:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    51fc:	7d 20 39 e4 	mtsrin  r9,r7
    5200:	39 29 01 11 	addi    r9,r9,273
    5204:	3c e7 10 00 	addis   r7,r7,4096
    5208:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    520c:	7d 20 39 e4 	mtsrin  r9,r7
    5210:	39 29 01 11 	addi    r9,r9,273
    5214:	3c ea 30 00 	addis   r7,r10,12288
    5218:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    521c:	7d 20 39 e4 	mtsrin  r9,r7
    5220:	3d 4a 40 00 	addis   r10,r10,16384
    5224:	39 29 01 11 	addi    r9,r9,273
    5228:	7c 08 50 40 	cmplw   r8,r10
    522c:	55 29 02 06 	rlwinm  r9,r9,0,8,3
    5230:	41 81 ff bc 	bgt     51ec <perf_copy_attr+0x444>

    5234:	4c 00 01 2c 	isync

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mpe: Export the ool handlers to fix build errors]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/d9121f96a7c4302946839a0771f5d1daeeb6968c.1622708530.git.christophe.leroy@csgroup.eu
2021-06-17 00:09:08 +10:00

429 lines
12 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _ASM_POWERPC_PROCESSOR_H
#define _ASM_POWERPC_PROCESSOR_H
/*
* Copyright (C) 2001 PPC 64 Team, IBM Corp
*/
#include <vdso/processor.h>
#include <asm/reg.h>
#ifdef CONFIG_VSX
#define TS_FPRWIDTH 2
#ifdef __BIG_ENDIAN__
#define TS_FPROFFSET 0
#define TS_VSRLOWOFFSET 1
#else
#define TS_FPROFFSET 1
#define TS_VSRLOWOFFSET 0
#endif
#else
#define TS_FPRWIDTH 1
#define TS_FPROFFSET 0
#endif
#ifdef CONFIG_PPC64
/* Default SMT priority is set to 3. Use 11- 13bits to save priority. */
#define PPR_PRIORITY 3
#ifdef __ASSEMBLY__
#define DEFAULT_PPR (PPR_PRIORITY << 50)
#else
#define DEFAULT_PPR ((u64)PPR_PRIORITY << 50)
#endif /* __ASSEMBLY__ */
#endif /* CONFIG_PPC64 */
#ifndef __ASSEMBLY__
#include <linux/types.h>
#include <linux/thread_info.h>
#include <asm/ptrace.h>
#include <asm/hw_breakpoint.h>
/* We do _not_ want to define new machine types at all, those must die
* in favor of using the device-tree
* -- BenH.
*/
/* PREP sub-platform types. Unused */
#define _PREP_Motorola 0x01 /* motorola prep */
#define _PREP_Firm 0x02 /* firmworks prep */
#define _PREP_IBM 0x00 /* ibm prep */
#define _PREP_Bull 0x03 /* bull prep */
/* CHRP sub-platform types. These are arbitrary */
#define _CHRP_Motorola 0x04 /* motorola chrp, the cobra */
#define _CHRP_IBM 0x05 /* IBM chrp, the longtrail and longtrail 2 */
#define _CHRP_Pegasos 0x06 /* Genesi/bplan's Pegasos and Pegasos2 */
#define _CHRP_briq 0x07 /* TotalImpact's briQ */
#if defined(__KERNEL__) && defined(CONFIG_PPC32)
extern int _chrp_type;
#endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
#include <asm/task_size_64.h>
#else
#include <asm/task_size_32.h>
#endif
struct task_struct;
void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
void release_thread(struct task_struct *);
#define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
#define TS_CKFPR(i) ckfp_state.fpr[i][TS_FPROFFSET]
/* FP and VSX 0-31 register set */
struct thread_fp_state {
u64 fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
u64 fpscr; /* Floating point status */
};
/* Complete AltiVec register set including VSCR */
struct thread_vr_state {
vector128 vr[32] __attribute__((aligned(16)));
vector128 vscr __attribute__((aligned(16)));
};
struct debug_reg {
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
/*
* The following help to manage the use of Debug Control Registers
* om the BookE platforms.
*/
uint32_t dbcr0;
uint32_t dbcr1;
#ifdef CONFIG_BOOKE
uint32_t dbcr2;
#endif
/*
* The stored value of the DBSR register will be the value at the
* last debug interrupt. This register can only be read from the
* user (will never be written to) and has value while helping to
* describe the reason for the last debug trap. Torez
*/
uint32_t dbsr;
/*
* The following will contain addresses used by debug applications
* to help trace and trap on particular address locations.
* The bits in the Debug Control Registers above help define which
* of the following registers will contain valid data and/or addresses.
*/
unsigned long iac1;
unsigned long iac2;
#if CONFIG_PPC_ADV_DEBUG_IACS > 2
unsigned long iac3;
unsigned long iac4;
#endif
unsigned long dac1;
unsigned long dac2;
#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
unsigned long dvc1;
unsigned long dvc2;
#endif
#endif
};
struct thread_struct {
unsigned long ksp; /* Kernel stack pointer */
#ifdef CONFIG_PPC64
unsigned long ksp_vsid;
#endif
struct pt_regs *regs; /* Pointer to saved register state */
#ifdef CONFIG_BOOKE
/* BookE base exception scratch space; align on cacheline */
unsigned long normsave[8] ____cacheline_aligned;
#endif
#ifdef CONFIG_PPC32
void *pgdir; /* root of page-table tree */
#ifdef CONFIG_PPC_RTAS
unsigned long rtas_sp; /* stack pointer for when in RTAS */
#endif
#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
unsigned long kuap; /* opened segments for user access */
#endif
unsigned long srr0;
unsigned long srr1;
unsigned long dar;
unsigned long dsisr;
#ifdef CONFIG_PPC_BOOK3S_32
unsigned long r0, r3, r4, r5, r6, r8, r9, r11;
unsigned long lr, ctr;
#endif
#endif /* CONFIG_PPC32 */
/* Debug Registers */
struct debug_reg debug;
#ifdef CONFIG_PPC_FPU_REGS
struct thread_fp_state fp_state;
struct thread_fp_state *fp_save_area;
#endif
int fpexc_mode; /* floating-point exception mode */
unsigned int align_ctl; /* alignment handling control */
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct perf_event *ptrace_bps[HBP_NUM_MAX];
/*
* Helps identify source of single-step exception and subsequent
* hw-breakpoint enablement
*/
struct perf_event *last_hit_ubp[HBP_NUM_MAX];
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
struct arch_hw_breakpoint hw_brk[HBP_NUM_MAX]; /* hardware breakpoint info */
unsigned long trap_nr; /* last trap # on this thread */
u8 load_slb; /* Ages out SLB preload cache entries */
u8 load_fp;
#ifdef CONFIG_ALTIVEC
u8 load_vec;
struct thread_vr_state vr_state;
struct thread_vr_state *vr_save_area;
unsigned long vrsave;
int used_vr; /* set if process has used altivec */
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
/* VSR status */
int used_vsr; /* set if process has used VSX */
#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
unsigned long evr[32]; /* upper 32-bits of SPE regs */
u64 acc; /* Accumulator */
unsigned long spefscr; /* SPE & eFP status */
unsigned long spefscr_last; /* SPEFSCR value on last prctl
call or trap return */
int used_spe; /* set if process has used spe */
#endif /* CONFIG_SPE */
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
u8 load_tm;
u64 tm_tfhar; /* Transaction fail handler addr */
u64 tm_texasr; /* Transaction exception & summary */
u64 tm_tfiar; /* Transaction fail instr address reg */
struct pt_regs ckpt_regs; /* Checkpointed registers */
unsigned long tm_tar;
unsigned long tm_ppr;
unsigned long tm_dscr;
unsigned long tm_amr;
/*
* Checkpointed FP and VSX 0-31 register set.
*
* When a transaction is active/signalled/scheduled etc., *regs is the
* most recent set of/speculated GPRs with ckpt_regs being the older
* checkpointed regs to which we roll back if transaction aborts.
*
* These are analogous to how ckpt_regs and pt_regs work
*/
struct thread_fp_state ckfp_state; /* Checkpointed FP state */
struct thread_vr_state ckvr_state; /* Checkpointed VR state */
unsigned long ckvrsave; /* Checkpointed VRSAVE */
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
void* kvm_shadow_vcpu; /* KVM internal data */
#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
struct kvm_vcpu *kvm_vcpu;
#endif
#ifdef CONFIG_PPC64
unsigned long dscr;
unsigned long fscr;
/*
* This member element dscr_inherit indicates that the process
* has explicitly attempted and changed the DSCR register value
* for itself. Hence kernel wont use the default CPU DSCR value
* contained in the PACA structure anymore during process context
* switch. Once this variable is set, this behaviour will also be
* inherited to all the children of this process from that point
* onwards.
*/
int dscr_inherit;
unsigned long tidr;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
unsigned long tar;
unsigned long ebbrr;
unsigned long ebbhr;
unsigned long bescr;
unsigned long siar;
unsigned long sdar;
unsigned long sier;
unsigned long mmcr2;
unsigned mmcr0;
unsigned used_ebb;
unsigned long mmcr3;
unsigned long sier2;
unsigned long sier3;
#endif
};
#define ARCH_MIN_TASKALIGN 16
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
#define INIT_SP_LIMIT ((unsigned long)&init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
.spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, \
.spefscr_last = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE,
#else
#define SPEFSCR_INIT
#endif
#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
#define INIT_THREAD { \
.ksp = INIT_SP, \
.pgdir = swapper_pg_dir, \
.kuap = ~0UL, /* KUAP_NONE */ \
.fpexc_mode = MSR_FE0 | MSR_FE1, \
SPEFSCR_INIT \
}
#elif defined(CONFIG_PPC32)
#define INIT_THREAD { \
.ksp = INIT_SP, \
.pgdir = swapper_pg_dir, \
.fpexc_mode = MSR_FE0 | MSR_FE1, \
SPEFSCR_INIT \
}
#else
#define INIT_THREAD { \
.ksp = INIT_SP, \
.fpexc_mode = 0, \
}
#endif
#define task_pt_regs(tsk) ((tsk)->thread.regs)
unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0)
#define KSTK_ESP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0)
/* Get/set floating-point exception mode */
#define GET_FPEXC_CTL(tsk, adr) get_fpexc_mode((tsk), (adr))
#define SET_FPEXC_CTL(tsk, val) set_fpexc_mode((tsk), (val))
extern int get_fpexc_mode(struct task_struct *tsk, unsigned long adr);
extern int set_fpexc_mode(struct task_struct *tsk, unsigned int val);
#define GET_ENDIAN(tsk, adr) get_endian((tsk), (adr))
#define SET_ENDIAN(tsk, val) set_endian((tsk), (val))
extern int get_endian(struct task_struct *tsk, unsigned long adr);
extern int set_endian(struct task_struct *tsk, unsigned int val);
#define GET_UNALIGN_CTL(tsk, adr) get_unalign_ctl((tsk), (adr))
#define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val))
extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
extern void load_fp_state(struct thread_fp_state *fp);
extern void store_fp_state(struct thread_fp_state *fp);
extern void load_vr_state(struct thread_vr_state *vr);
extern void store_vr_state(struct thread_vr_state *vr);
static inline unsigned int __unpack_fe01(unsigned long msr_bits)
{
return ((msr_bits & MSR_FE0) >> 10) | ((msr_bits & MSR_FE1) >> 8);
}
static inline unsigned long __pack_fe01(unsigned int fpmode)
{
return ((fpmode << 10) & MSR_FE0) | ((fpmode << 8) & MSR_FE1);
}
#ifdef CONFIG_PPC64
#define spin_begin() HMT_low()
#define spin_cpu_relax() barrier()
#define spin_end() HMT_medium()
#define spin_until_cond(cond) \
do { \
if (unlikely(!(cond))) { \
spin_begin(); \
do { \
spin_cpu_relax(); \
} while (!(cond)); \
spin_end(); \
} \
} while (0)
#endif
/* Check that a certain kernel stack pointer is valid in task_struct p */
int validate_sp(unsigned long sp, struct task_struct *p,
unsigned long nbytes);
/*
* Prefetch macros.
*/
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
#define ARCH_HAS_SPINLOCK_PREFETCH
static inline void prefetch(const void *x)
{
if (unlikely(!x))
return;
__asm__ __volatile__ ("dcbt 0,%0" : : "r" (x));
}
static inline void prefetchw(const void *x)
{
if (unlikely(!x))
return;
__asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x));
}
#define spin_lock_prefetch(x) prefetchw(x)
#define HAVE_ARCH_PICK_MMAP_LAYOUT
/* asm stubs */
extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
#ifdef CONFIG_PPC_970_NAP
extern void power4_idle_nap(void);
void power4_idle_nap_return(void);
#endif
extern unsigned long cpuidle_disable;
enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
extern void power7_idle_type(unsigned long type);
extern void arch300_idle_type(unsigned long stop_psscr_val,
unsigned long stop_psscr_mask);
extern int fix_alignment(struct pt_regs *);
#ifdef CONFIG_PPC64
/*
* We handle most unaligned accesses in hardware. On the other hand
* unaligned DMA can be very expensive on some ppc64 IO chips (it does
* powers of 2 writes until it reaches sufficient alignment).
*
* Based on this we disable the IP header alignment in network drivers.
*/
#define NET_IP_ALIGN 0
#endif
int do_mathemu(struct pt_regs *regs);
#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PROCESSOR_H */