linux_dsm_epyc7002/arch/powerpc/include/asm/processor.h

447 lines
13 KiB
C
Raw Normal View History

/* 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 <asm/reg.h>
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 11:07:18 +07:00
#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
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 11:07:18 +07:00
#else
#define TS_FPRWIDTH 1
#define TS_FPROFFSET 0
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 11:07:18 +07:00
#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) */
/* Macros for adjusting thread priority (hardware multi-threading) */
#define HMT_very_low() asm volatile("or 31,31,31 # very low priority")
#define HMT_low() asm volatile("or 1,1,1 # low priority")
#define HMT_medium_low() asm volatile("or 6,6,6 # medium low priority")
#define HMT_medium() asm volatile("or 2,2,2 # medium priority")
#define HMT_medium_high() asm volatile("or 5,5,5 # medium high priority")
#define HMT_high() asm volatile("or 3,3,3 # high priority")
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
#include <asm/task_size_64.h>
powerpc/mm: Enable mappings above 128TB Not all user space application is ready to handle wide addresses. It's known that at least some JIT compilers use higher bits in pointers to encode their information. It collides with valid pointers with 512TB addresses and leads to crashes. To mitigate this, we are not going to allocate virtual address space above 128TB by default. But userspace can ask for allocation from full address space by specifying hint address (with or without MAP_FIXED) above 128TB. If hint address set above 128TB, but MAP_FIXED is not specified, we try to look for unmapped area by specified address. If it's already occupied, we look for unmapped area in *full* address space, rather than from 128TB window. This approach helps to easily make application's memory allocator aware about large address space without manually tracking allocated virtual address space. This is going to be a per mmap decision. ie, we can have some mmaps with larger addresses and other that do not. A sample memory layout looks like: 10000000-10010000 r-xp 00000000 fc:00 9057045 /home/max_addr_512TB 10010000-10020000 r--p 00000000 fc:00 9057045 /home/max_addr_512TB 10020000-10030000 rw-p 00010000 fc:00 9057045 /home/max_addr_512TB 10029630000-10029660000 rw-p 00000000 00:00 0 [heap] 7fff834a0000-7fff834b0000 rw-p 00000000 00:00 0 7fff834b0000-7fff83670000 r-xp 00000000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83670000-7fff83680000 r--p 001b0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83680000-7fff83690000 rw-p 001c0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83690000-7fff836a0000 rw-p 00000000 00:00 0 7fff836a0000-7fff836c0000 r-xp 00000000 00:00 0 [vdso] 7fff836c0000-7fff83700000 r-xp 00000000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83700000-7fff83710000 r--p 00030000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83710000-7fff83720000 rw-p 00040000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fffdccf0000-7fffdcd20000 rw-p 00000000 00:00 0 [stack] 1000000000000-1000000010000 rw-p 00000000 00:00 0 1ffff83710000-1ffff83720000 rw-p 00000000 00:00 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-03-30 18:05:21 +07:00
#else
#include <asm/task_size_32.h>
powerpc/mm: Enable mappings above 128TB Not all user space application is ready to handle wide addresses. It's known that at least some JIT compilers use higher bits in pointers to encode their information. It collides with valid pointers with 512TB addresses and leads to crashes. To mitigate this, we are not going to allocate virtual address space above 128TB by default. But userspace can ask for allocation from full address space by specifying hint address (with or without MAP_FIXED) above 128TB. If hint address set above 128TB, but MAP_FIXED is not specified, we try to look for unmapped area by specified address. If it's already occupied, we look for unmapped area in *full* address space, rather than from 128TB window. This approach helps to easily make application's memory allocator aware about large address space without manually tracking allocated virtual address space. This is going to be a per mmap decision. ie, we can have some mmaps with larger addresses and other that do not. A sample memory layout looks like: 10000000-10010000 r-xp 00000000 fc:00 9057045 /home/max_addr_512TB 10010000-10020000 r--p 00000000 fc:00 9057045 /home/max_addr_512TB 10020000-10030000 rw-p 00010000 fc:00 9057045 /home/max_addr_512TB 10029630000-10029660000 rw-p 00000000 00:00 0 [heap] 7fff834a0000-7fff834b0000 rw-p 00000000 00:00 0 7fff834b0000-7fff83670000 r-xp 00000000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83670000-7fff83680000 r--p 001b0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83680000-7fff83690000 rw-p 001c0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83690000-7fff836a0000 rw-p 00000000 00:00 0 7fff836a0000-7fff836c0000 r-xp 00000000 00:00 0 [vdso] 7fff836c0000-7fff83700000 r-xp 00000000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83700000-7fff83710000 r--p 00030000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83710000-7fff83720000 rw-p 00040000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fffdccf0000-7fffdcd20000 rw-p 00000000 00:00 0 [stack] 1000000000000-1000000010000 rw-p 00000000 00:00 0 1ffff83710000-1ffff83720000 rw-p 00000000 00:00 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-03-30 18:05:21 +07:00
#endif
struct task_struct;
void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
void release_thread(struct task_struct *);
typedef struct {
unsigned long seg;
} mm_segment_t;
#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 */
mm_segment_t addr_limit; /* for get_fs() validation */
#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 */
unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */
#ifdef CONFIG_PPC_RTAS
unsigned long rtas_sp; /* stack pointer for when in RTAS */
#endif
#endif
#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
unsigned long kuap; /* opened segments for user access */
#endif
/* Debug Registers */
struct debug_reg debug;
struct thread_fp_state fp_state;
struct thread_fp_state *fp_save_area;
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];
/*
* Helps identify source of single-step exception and subsequent
* hw-breakpoint enablement
*/
struct perf_event *last_hit_ubp;
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
unsigned long trap_nr; /* last trap # on this thread */
u8 load_slb; /* Ages out SLB preload cache entries */
powerpc: Restore FPU/VEC/VSX if previously used Currently the FPU, VEC and VSX facilities are lazily loaded. This is not a problem unless a process is using these facilities. Modern versions of GCC are very good at automatically vectorising code, new and modernised workloads make use of floating point and vector facilities, even the kernel makes use of vectorised memcpy. All this combined greatly increases the cost of a syscall since the kernel uses the facilities sometimes even in syscall fast-path making it increasingly common for a thread to take an *_unavailable exception soon after a syscall, not to mention potentially taking all three. The obvious overcompensation to this problem is to simply always load all the facilities on every exit to userspace. Loading up all FPU, VEC and VSX registers every time can be expensive and if a workload does avoid using them, it should not be forced to incur this penalty. An 8bit counter is used to detect if the registers have been used in the past and the registers are always loaded until the value wraps to back to zero. Several versions of the assembly in entry_64.S were tested: 1. Always calling C. 2. Performing a common case check and then calling C. 3. A complex check in asm. After some benchmarking it was determined that avoiding C in the common case is a performance benefit (option 2). The full check in asm (option 3) greatly complicated that codepath for a negligible performance gain and the trade-off was deemed not worth it. Signed-off-by: Cyril Bur <cyrilbur@gmail.com> [mpe: Move load_vec in the struct to fill an existing hole, reword change log] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> fixup
2016-02-29 13:53:47 +07:00
u8 load_fp;
#ifdef CONFIG_ALTIVEC
powerpc: Restore FPU/VEC/VSX if previously used Currently the FPU, VEC and VSX facilities are lazily loaded. This is not a problem unless a process is using these facilities. Modern versions of GCC are very good at automatically vectorising code, new and modernised workloads make use of floating point and vector facilities, even the kernel makes use of vectorised memcpy. All this combined greatly increases the cost of a syscall since the kernel uses the facilities sometimes even in syscall fast-path making it increasingly common for a thread to take an *_unavailable exception soon after a syscall, not to mention potentially taking all three. The obvious overcompensation to this problem is to simply always load all the facilities on every exit to userspace. Loading up all FPU, VEC and VSX registers every time can be expensive and if a workload does avoid using them, it should not be forced to incur this penalty. An 8bit counter is used to detect if the registers have been used in the past and the registers are always loaded until the value wraps to back to zero. Several versions of the assembly in entry_64.S were tested: 1. Always calling C. 2. Performing a common case check and then calling C. 3. A complex check in asm. After some benchmarking it was determined that avoiding C in the common case is a performance benefit (option 2). The full check in asm (option 3) greatly complicated that codepath for a negligible performance gain and the trade-off was deemed not worth it. Signed-off-by: Cyril Bur <cyrilbur@gmail.com> [mpe: Move load_vec in the struct to fill an existing hole, reword change log] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> fixup
2016-02-29 13:53:47 +07:00
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 */
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 11:07:18 +07:00
#ifdef CONFIG_VSX
/* VSR status */
int used_vsr; /* set if process has used VSX */
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 11:07:18 +07:00
#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 */
powerpc: fix exception clearing in e500 SPE float emulation The e500 SPE floating-point emulation code clears existing exceptions (__FPU_FPSCR &= ~FP_EX_MASK;) before ORing in the exceptions from the emulated operation. However, these exception bits are the "sticky", cumulative exception bits, and should only be cleared by the user program setting SPEFSCR, not implicitly by any floating-point instruction (whether executed purely by the hardware or emulated). The spurious clearing of these bits shows up as missing exceptions in glibc testing. Fixing this, however, is not as simple as just not clearing the bits, because while the bits may be from previous floating-point operations (in which case they should not be cleared), the processor can also set the sticky bits itself before the interrupt for an exception occurs, and this can happen in cases when IEEE 754 semantics are that the sticky bit should not be set. Specifically, the "invalid" sticky bit is set in various cases with non-finite operands, where IEEE 754 semantics do not involve raising such an exception, and the "underflow" sticky bit is set in cases of exact underflow, whereas IEEE 754 semantics are that this flag is set only for inexact underflow. Thus, for correct emulation the kernel needs to know the setting of these two sticky bits before the instruction being emulated. When a floating-point operation raises an exception, the kernel can note the state of the sticky bits immediately afterwards. Some <fenv.h> functions that affect the state of these bits, such as fesetenv and feholdexcept, need to use prctl with PR_GET_FPEXC and PR_SET_FPEXC anyway, and so it is natural to record the state of those bits during that call into the kernel and so avoid any need for a separate call into the kernel to inform it of a change to those bits. Thus, the interface I chose to use (in this patch and the glibc port) is that one of those prctl calls must be made after any userspace change to those sticky bits, other than through a floating-point operation that traps into the kernel anyway. feclearexcept and fesetexceptflag duly make those calls, which would not be required were it not for this issue. The previous EGLIBC port, and the uClibc code copied from it, is fundamentally broken as regards any use of prctl for floating-point exceptions because it didn't use the PR_FP_EXC_SW_ENABLE bit in its prctl calls (and did various worse things, such as passing a pointer when prctl expected an integer). If you avoid anything where prctl is used, the clearing of sticky bits still means it will never give anything approximating correct exception semantics with existing kernels. I don't believe the patch makes things any worse for existing code that doesn't try to inform the kernel of changes to sticky bits - such code may get incorrect exceptions in some cases, but it would have done so anyway in other cases. Signed-off-by: Joseph Myers <joseph@codesourcery.com> Signed-off-by: Scott Wood <scottwood@freescale.com>
2013-12-11 06:07:45 +07:00
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;
/*
powerpc: tm: Always use fp_state and vr_state to store live registers There is currently an inconsistency as to how the entire CPU register state is saved and restored when a thread uses transactional memory (TM). Using transactional memory results in the CPU having duplicated (almost) all of its register state. This duplication results in a set of registers which can be considered 'live', those being currently modified by the instructions being executed and another set that is frozen at a point in time. On context switch, both sets of state have to be saved and (later) restored. These two states are often called a variety of different things. Common terms for the state which only exists after the CPU has entered a transaction (performed a TBEGIN instruction) in hardware are 'transactional' or 'speculative'. Between a TBEGIN and a TEND or TABORT (or an event that causes the hardware to abort), regardless of the use of TSUSPEND the transactional state can be referred to as the live state. The second state is often to referred to as the 'checkpointed' state and is a duplication of the live state when the TBEGIN instruction is executed. This state is kept in the hardware and will be rolled back to on transaction failure. Currently all the registers stored in pt_regs are ALWAYS the live registers, that is, when a thread has transactional registers their values are stored in pt_regs and the checkpointed state is in ckpt_regs. A strange opposite is true for fp_state/vr_state. When a thread is non transactional fp_state/vr_state holds the live registers. When a thread has initiated a transaction fp_state/vr_state holds the checkpointed state and transact_fp/transact_vr become the structure which holds the live state (at this point it is a transactional state). This method creates confusion as to where the live state is, in some circumstances it requires extra work to determine where to put the live state and prevents the use of common functions designed (probably before TM) to save the live state. With this patch pt_regs, fp_state and vr_state all represent the same thing and the other structures [pending rename] are for checkpointed state. Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-23 13:18:24 +07:00
* 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.
*
powerpc: tm: Always use fp_state and vr_state to store live registers There is currently an inconsistency as to how the entire CPU register state is saved and restored when a thread uses transactional memory (TM). Using transactional memory results in the CPU having duplicated (almost) all of its register state. This duplication results in a set of registers which can be considered 'live', those being currently modified by the instructions being executed and another set that is frozen at a point in time. On context switch, both sets of state have to be saved and (later) restored. These two states are often called a variety of different things. Common terms for the state which only exists after the CPU has entered a transaction (performed a TBEGIN instruction) in hardware are 'transactional' or 'speculative'. Between a TBEGIN and a TEND or TABORT (or an event that causes the hardware to abort), regardless of the use of TSUSPEND the transactional state can be referred to as the live state. The second state is often to referred to as the 'checkpointed' state and is a duplication of the live state when the TBEGIN instruction is executed. This state is kept in the hardware and will be rolled back to on transaction failure. Currently all the registers stored in pt_regs are ALWAYS the live registers, that is, when a thread has transactional registers their values are stored in pt_regs and the checkpointed state is in ckpt_regs. A strange opposite is true for fp_state/vr_state. When a thread is non transactional fp_state/vr_state holds the live registers. When a thread has initiated a transaction fp_state/vr_state holds the checkpointed state and transact_fp/transact_vr become the structure which holds the live state (at this point it is a transactional state). This method creates confusion as to where the live state is, in some circumstances it requires extra work to determine where to put the live state and prevents the use of common functions designed (probably before TM) to save the live state. With this patch pt_regs, fp_state and vr_state all represent the same thing and the other structures [pending rename] are for checkpointed state. Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-23 13:18:24 +07:00
* 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_PPC_MEM_KEYS
unsigned long amr;
unsigned long iamr;
unsigned long uamor;
#endif
#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 int used_vas;
#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
powerpc: fix exception clearing in e500 SPE float emulation The e500 SPE floating-point emulation code clears existing exceptions (__FPU_FPSCR &= ~FP_EX_MASK;) before ORing in the exceptions from the emulated operation. However, these exception bits are the "sticky", cumulative exception bits, and should only be cleared by the user program setting SPEFSCR, not implicitly by any floating-point instruction (whether executed purely by the hardware or emulated). The spurious clearing of these bits shows up as missing exceptions in glibc testing. Fixing this, however, is not as simple as just not clearing the bits, because while the bits may be from previous floating-point operations (in which case they should not be cleared), the processor can also set the sticky bits itself before the interrupt for an exception occurs, and this can happen in cases when IEEE 754 semantics are that the sticky bit should not be set. Specifically, the "invalid" sticky bit is set in various cases with non-finite operands, where IEEE 754 semantics do not involve raising such an exception, and the "underflow" sticky bit is set in cases of exact underflow, whereas IEEE 754 semantics are that this flag is set only for inexact underflow. Thus, for correct emulation the kernel needs to know the setting of these two sticky bits before the instruction being emulated. When a floating-point operation raises an exception, the kernel can note the state of the sticky bits immediately afterwards. Some <fenv.h> functions that affect the state of these bits, such as fesetenv and feholdexcept, need to use prctl with PR_GET_FPEXC and PR_SET_FPEXC anyway, and so it is natural to record the state of those bits during that call into the kernel and so avoid any need for a separate call into the kernel to inform it of a change to those bits. Thus, the interface I chose to use (in this patch and the glibc port) is that one of those prctl calls must be made after any userspace change to those sticky bits, other than through a floating-point operation that traps into the kernel anyway. feclearexcept and fesetexceptflag duly make those calls, which would not be required were it not for this issue. The previous EGLIBC port, and the uClibc code copied from it, is fundamentally broken as regards any use of prctl for floating-point exceptions because it didn't use the PR_FP_EXC_SW_ENABLE bit in its prctl calls (and did various worse things, such as passing a pointer when prctl expected an integer). If you avoid anything where prctl is used, the clearing of sticky bits still means it will never give anything approximating correct exception semantics with existing kernels. I don't believe the patch makes things any worse for existing code that doesn't try to inform the kernel of changes to sticky bits - such code may get incorrect exceptions in some cases, but it would have done so anyway in other cases. Signed-off-by: Joseph Myers <joseph@codesourcery.com> Signed-off-by: Scott Wood <scottwood@freescale.com>
2013-12-11 06:07:45 +07:00
#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
#ifdef CONFIG_PPC32
#define INIT_THREAD { \
.ksp = INIT_SP, \
.ksp_limit = INIT_SP_LIMIT, \
.addr_limit = KERNEL_DS, \
.pgdir = swapper_pg_dir, \
.fpexc_mode = MSR_FE0 | MSR_FE1, \
SPEFSCR_INIT \
}
#else
#define INIT_THREAD { \
.ksp = INIT_SP, \
.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
.addr_limit = KERNEL_DS, \
.fpexc_mode = 0, \
.fscr = FSCR_TAR | FSCR_EBB \
}
#endif
#define task_pt_regs(tsk) ((struct pt_regs *)(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 cpu_relax() do { HMT_low(); HMT_medium(); barrier(); } while (0)
#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)
#else
#define cpu_relax() barrier()
#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
#ifdef CONFIG_PPC64
static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
{
if (is_32)
return sp & 0x0ffffffffUL;
return sp;
}
#else
static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
{
return sp;
}
#endif
powerpc/64s: Reimplement book3s idle code in C Reimplement Book3S idle code in C, moving POWER7/8/9 implementation speific HV idle code to the powernv platform code. Book3S assembly stubs are kept in common code and used only to save the stack frame and non-volatile GPRs before executing architected idle instructions, and restoring the stack and reloading GPRs then returning to C after waking from idle. The complex logic dealing with threads and subcores, locking, SPRs, HMIs, timebase resync, etc., is all done in C which makes it more maintainable. This is not a strict translation to C code, there are some significant differences: - Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs, but saves and restores them itself. - The optimisation where EC=ESL=0 idle modes did not have to save GPRs or change MSR is restored, because it's now simple to do. ESL=1 sleeps that do not lose GPRs can use this optimization too. - KVM secondary entry and cede is now more of a call/return style rather than branchy. nap_state_lost is not required because KVM always returns via NVGPR restoring path. - KVM secondary wakeup from offline sequence is moved entirely into the offline wakeup, which avoids a hwsync in the normal idle wakeup path. Performance measured with context switch ping-pong on different threads or cores, is possibly improved a small amount, 1-3% depending on stop state and core vs thread test for shallow states. Deep states it's in the noise compared with other latencies. KVM improvements: - Idle sleepers now always return to caller rather than branch out to KVM first. - This allows optimisations like very fast return to caller when no state has been lost. - KVM no longer requires nap_state_lost because it controls NVGPR save/restore itself on the way in and out. - The heavy idle wakeup KVM request check can be moved out of the normal host idle code and into the not-performance-critical offline code. - KVM nap code now returns from where it is called, which makes the flow a bit easier to follow. Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> [mpe: Squash the KVM changes in] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-12 21:30:52 +07:00
/* 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);
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 */
powerpc/64s: Reimplement book3s idle code in C Reimplement Book3S idle code in C, moving POWER7/8/9 implementation speific HV idle code to the powernv platform code. Book3S assembly stubs are kept in common code and used only to save the stack frame and non-volatile GPRs before executing architected idle instructions, and restoring the stack and reloading GPRs then returning to C after waking from idle. The complex logic dealing with threads and subcores, locking, SPRs, HMIs, timebase resync, etc., is all done in C which makes it more maintainable. This is not a strict translation to C code, there are some significant differences: - Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs, but saves and restores them itself. - The optimisation where EC=ESL=0 idle modes did not have to save GPRs or change MSR is restored, because it's now simple to do. ESL=1 sleeps that do not lose GPRs can use this optimization too. - KVM secondary entry and cede is now more of a call/return style rather than branchy. nap_state_lost is not required because KVM always returns via NVGPR restoring path. - KVM secondary wakeup from offline sequence is moved entirely into the offline wakeup, which avoids a hwsync in the normal idle wakeup path. Performance measured with context switch ping-pong on different threads or cores, is possibly improved a small amount, 1-3% depending on stop state and core vs thread test for shallow states. Deep states it's in the noise compared with other latencies. KVM improvements: - Idle sleepers now always return to caller rather than branch out to KVM first. - This allows optimisations like very fast return to caller when no state has been lost. - KVM no longer requires nap_state_lost because it controls NVGPR save/restore itself on the way in and out. - The heavy idle wakeup KVM request check can be moved out of the normal host idle code and into the not-performance-critical offline code. - KVM nap code now returns from where it is called, which makes the flow a bit easier to follow. Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> [mpe: Squash the KVM changes in] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-12 21:30:52 +07:00
extern void power7_idle_type(unsigned long type);
extern void power9_idle_type(unsigned long stop_psscr_val,
unsigned long stop_psscr_mask);
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
extern void poweroff_now(void);
extern int fix_alignment(struct pt_regs *);
extern void cvt_fd(float *from, double *to);
extern void cvt_df(double *from, float *to);
extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val);
#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
#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PROCESSOR_H */