linux_dsm_epyc7002/arch/mips/include/asm/processor.h
Paul Burton ea7e0480a4
MIPS: VDSO: Always map near top of user memory
When using the legacy mmap layout, for example triggered using ulimit -s
unlimited, get_unmapped_area() fills memory from bottom to top starting
from a fairly low address near TASK_UNMAPPED_BASE.

This placement is suboptimal if the user application wishes to allocate
large amounts of heap memory using the brk syscall. With the VDSO being
located low in the user's virtual address space, the amount of space
available for access using brk is limited much more than it was prior to
the introduction of the VDSO.

For example:

  # ulimit -s unlimited; cat /proc/self/maps
  00400000-004ec000 r-xp 00000000 08:00 71436      /usr/bin/coreutils
  004fc000-004fd000 rwxp 000ec000 08:00 71436      /usr/bin/coreutils
  004fd000-0050f000 rwxp 00000000 00:00 0
  00cc3000-00ce4000 rwxp 00000000 00:00 0          [heap]
  2ab96000-2ab98000 r--p 00000000 00:00 0          [vvar]
  2ab98000-2ab99000 r-xp 00000000 00:00 0          [vdso]
  2ab99000-2ab9d000 rwxp 00000000 00:00 0
  ...

Resolve this by adjusting STACK_TOP to reserve space for the VDSO &
providing an address hint to get_unmapped_area() causing it to use this
space even when using the legacy mmap layout.

We reserve enough space for the VDSO, plus 1MB or 256MB for 32 bit & 64
bit systems respectively within which we randomize the VDSO base
address. Previously this randomization was taken care of by the mmap
base address randomization performed by arch_mmap_rnd(). The 1MB & 256MB
sizes are somewhat arbitrary but chosen such that we have some
randomization without taking up too much of the user's virtual address
space, which is often in short supply for 32 bit systems.

With this the VDSO is always mapped at a high address, leaving lots of
space for statically linked programs to make use of brk:

  # ulimit -s unlimited; cat /proc/self/maps
  00400000-004ec000 r-xp 00000000 08:00 71436      /usr/bin/coreutils
  004fc000-004fd000 rwxp 000ec000 08:00 71436      /usr/bin/coreutils
  004fd000-0050f000 rwxp 00000000 00:00 0
  00c28000-00c49000 rwxp 00000000 00:00 0          [heap]
  ...
  7f67c000-7f69d000 rwxp 00000000 00:00 0          [stack]
  7f7fc000-7f7fd000 rwxp 00000000 00:00 0
  7fcf1000-7fcf3000 r--p 00000000 00:00 0          [vvar]
  7fcf3000-7fcf4000 r-xp 00000000 00:00 0          [vdso]

Signed-off-by: Paul Burton <paul.burton@mips.com>
Reported-by: Huacai Chen <chenhc@lemote.com>
Fixes: ebb5e78cc6 ("MIPS: Initial implementation of a VDSO")
Cc: Huacai Chen <chenhc@lemote.com>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org # v4.4+
2018-09-28 12:09:00 -07:00

440 lines
12 KiB
C

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1994 Waldorf GMBH
* Copyright (C) 1995, 1996, 1997, 1998, 1999, 2001, 2002, 2003 Ralf Baechle
* Copyright (C) 1996 Paul M. Antoine
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
*/
#ifndef _ASM_PROCESSOR_H
#define _ASM_PROCESSOR_H
#include <linux/atomic.h>
#include <linux/cpumask.h>
#include <linux/sizes.h>
#include <linux/threads.h>
#include <asm/cachectl.h>
#include <asm/cpu.h>
#include <asm/cpu-info.h>
#include <asm/dsemul.h>
#include <asm/mipsregs.h>
#include <asm/prefetch.h>
/*
* Return current * instruction pointer ("program counter").
*/
#define current_text_addr() ({ __label__ _l; _l: &&_l;})
/*
* System setup and hardware flags..
*/
extern unsigned int vced_count, vcei_count;
/*
* MIPS does have an arch_pick_mmap_layout()
*/
#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
#ifdef CONFIG_32BIT
#ifdef CONFIG_KVM_GUEST
/* User space process size is limited to 1GB in KVM Guest Mode */
#define TASK_SIZE 0x3fff8000UL
#else
/*
* User space process size: 2GB. This is hardcoded into a few places,
* so don't change it unless you know what you are doing.
*/
#define TASK_SIZE 0x80000000UL
#endif
#define STACK_TOP_MAX TASK_SIZE
#define TASK_IS_32BIT_ADDR 1
#endif
#ifdef CONFIG_64BIT
/*
* User space process size: 1TB. This is hardcoded into a few places,
* so don't change it unless you know what you are doing. TASK_SIZE
* is limited to 1TB by the R4000 architecture; R10000 and better can
* support 16TB; the architectural reserve for future expansion is
* 8192EB ...
*/
#define TASK_SIZE32 0x7fff8000UL
#ifdef CONFIG_MIPS_VA_BITS_48
#define TASK_SIZE64 (0x1UL << ((cpu_data[0].vmbits>48)?48:cpu_data[0].vmbits))
#else
#define TASK_SIZE64 0x10000000000UL
#endif
#define TASK_SIZE (test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE64)
#define STACK_TOP_MAX TASK_SIZE64
#define TASK_SIZE_OF(tsk) \
(test_tsk_thread_flag(tsk, TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE64)
#define TASK_IS_32BIT_ADDR test_thread_flag(TIF_32BIT_ADDR)
#endif
#define VDSO_RANDOMIZE_SIZE (TASK_IS_32BIT_ADDR ? SZ_1M : SZ_256M)
extern unsigned long mips_stack_top(void);
#define STACK_TOP mips_stack_top()
/*
* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3)
#define NUM_FPU_REGS 32
#ifdef CONFIG_CPU_HAS_MSA
# define FPU_REG_WIDTH 128
#else
# define FPU_REG_WIDTH 64
#endif
union fpureg {
__u32 val32[FPU_REG_WIDTH / 32];
__u64 val64[FPU_REG_WIDTH / 64];
};
#ifdef CONFIG_CPU_LITTLE_ENDIAN
# define FPR_IDX(width, idx) (idx)
#else
# define FPR_IDX(width, idx) ((idx) ^ ((64 / (width)) - 1))
#endif
#define BUILD_FPR_ACCESS(width) \
static inline u##width get_fpr##width(union fpureg *fpr, unsigned idx) \
{ \
return fpr->val##width[FPR_IDX(width, idx)]; \
} \
\
static inline void set_fpr##width(union fpureg *fpr, unsigned idx, \
u##width val) \
{ \
fpr->val##width[FPR_IDX(width, idx)] = val; \
}
BUILD_FPR_ACCESS(32)
BUILD_FPR_ACCESS(64)
/*
* It would be nice to add some more fields for emulator statistics,
* the additional information is private to the FPU emulator for now.
* See arch/mips/include/asm/fpu_emulator.h.
*/
struct mips_fpu_struct {
union fpureg fpr[NUM_FPU_REGS];
unsigned int fcr31;
unsigned int msacsr;
};
#define NUM_DSP_REGS 6
typedef unsigned long dspreg_t;
struct mips_dsp_state {
dspreg_t dspr[NUM_DSP_REGS];
unsigned int dspcontrol;
};
#define INIT_CPUMASK { \
{0,} \
}
struct mips3264_watch_reg_state {
/* The width of watchlo is 32 in a 32 bit kernel and 64 in a
64 bit kernel. We use unsigned long as it has the same
property. */
unsigned long watchlo[NUM_WATCH_REGS];
/* Only the mask and IRW bits from watchhi. */
u16 watchhi[NUM_WATCH_REGS];
};
union mips_watch_reg_state {
struct mips3264_watch_reg_state mips3264;
};
#if defined(CONFIG_CPU_CAVIUM_OCTEON)
struct octeon_cop2_state {
/* DMFC2 rt, 0x0201 */
unsigned long cop2_crc_iv;
/* DMFC2 rt, 0x0202 (Set with DMTC2 rt, 0x1202) */
unsigned long cop2_crc_length;
/* DMFC2 rt, 0x0200 (set with DMTC2 rt, 0x4200) */
unsigned long cop2_crc_poly;
/* DMFC2 rt, 0x0402; DMFC2 rt, 0x040A */
unsigned long cop2_llm_dat[2];
/* DMFC2 rt, 0x0084 */
unsigned long cop2_3des_iv;
/* DMFC2 rt, 0x0080; DMFC2 rt, 0x0081; DMFC2 rt, 0x0082 */
unsigned long cop2_3des_key[3];
/* DMFC2 rt, 0x0088 (Set with DMTC2 rt, 0x0098) */
unsigned long cop2_3des_result;
/* DMFC2 rt, 0x0111 (FIXME: Read Pass1 Errata) */
unsigned long cop2_aes_inp0;
/* DMFC2 rt, 0x0102; DMFC2 rt, 0x0103 */
unsigned long cop2_aes_iv[2];
/* DMFC2 rt, 0x0104; DMFC2 rt, 0x0105; DMFC2 rt, 0x0106; DMFC2
* rt, 0x0107 */
unsigned long cop2_aes_key[4];
/* DMFC2 rt, 0x0110 */
unsigned long cop2_aes_keylen;
/* DMFC2 rt, 0x0100; DMFC2 rt, 0x0101 */
unsigned long cop2_aes_result[2];
/* DMFC2 rt, 0x0240; DMFC2 rt, 0x0241; DMFC2 rt, 0x0242; DMFC2
* rt, 0x0243; DMFC2 rt, 0x0244; DMFC2 rt, 0x0245; DMFC2 rt,
* 0x0246; DMFC2 rt, 0x0247; DMFC2 rt, 0x0248; DMFC2 rt,
* 0x0249; DMFC2 rt, 0x024A; DMFC2 rt, 0x024B; DMFC2 rt,
* 0x024C; DMFC2 rt, 0x024D; DMFC2 rt, 0x024E - Pass2 */
unsigned long cop2_hsh_datw[15];
/* DMFC2 rt, 0x0250; DMFC2 rt, 0x0251; DMFC2 rt, 0x0252; DMFC2
* rt, 0x0253; DMFC2 rt, 0x0254; DMFC2 rt, 0x0255; DMFC2 rt,
* 0x0256; DMFC2 rt, 0x0257 - Pass2 */
unsigned long cop2_hsh_ivw[8];
/* DMFC2 rt, 0x0258; DMFC2 rt, 0x0259 - Pass2 */
unsigned long cop2_gfm_mult[2];
/* DMFC2 rt, 0x025E - Pass2 */
unsigned long cop2_gfm_poly;
/* DMFC2 rt, 0x025A; DMFC2 rt, 0x025B - Pass2 */
unsigned long cop2_gfm_result[2];
/* DMFC2 rt, 0x24F, DMFC2 rt, 0x50, OCTEON III */
unsigned long cop2_sha3[2];
};
#define COP2_INIT \
.cp2 = {0,},
struct octeon_cvmseg_state {
unsigned long cvmseg[CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE]
[cpu_dcache_line_size() / sizeof(unsigned long)];
};
#elif defined(CONFIG_CPU_XLP)
struct nlm_cop2_state {
u64 rx[4];
u64 tx[4];
u32 tx_msg_status;
u32 rx_msg_status;
};
#define COP2_INIT \
.cp2 = {{0}, {0}, 0, 0},
#else
#define COP2_INIT
#endif
typedef struct {
unsigned long seg;
} mm_segment_t;
#ifdef CONFIG_CPU_HAS_MSA
# define ARCH_MIN_TASKALIGN 16
# define FPU_ALIGN __aligned(16)
#else
# define ARCH_MIN_TASKALIGN 8
# define FPU_ALIGN
#endif
struct mips_abi;
/*
* If you change thread_struct remember to change the #defines below too!
*/
struct thread_struct {
/* Saved main processor registers. */
unsigned long reg16;
unsigned long reg17, reg18, reg19, reg20, reg21, reg22, reg23;
unsigned long reg29, reg30, reg31;
/* Saved cp0 stuff. */
unsigned long cp0_status;
/* Saved fpu/fpu emulator stuff. */
struct mips_fpu_struct fpu FPU_ALIGN;
/* Assigned branch delay slot 'emulation' frame */
atomic_t bd_emu_frame;
/* PC of the branch from a branch delay slot 'emulation' */
unsigned long bd_emu_branch_pc;
/* PC to continue from following a branch delay slot 'emulation' */
unsigned long bd_emu_cont_pc;
#ifdef CONFIG_MIPS_MT_FPAFF
/* Emulated instruction count */
unsigned long emulated_fp;
/* Saved per-thread scheduler affinity mask */
cpumask_t user_cpus_allowed;
#endif /* CONFIG_MIPS_MT_FPAFF */
/* Saved state of the DSP ASE, if available. */
struct mips_dsp_state dsp;
/* Saved watch register state, if available. */
union mips_watch_reg_state watch;
/* Other stuff associated with the thread. */
unsigned long cp0_badvaddr; /* Last user fault */
unsigned long cp0_baduaddr; /* Last kernel fault accessing USEG */
unsigned long error_code;
unsigned long trap_nr;
#ifdef CONFIG_CPU_CAVIUM_OCTEON
struct octeon_cop2_state cp2 __attribute__ ((__aligned__(128)));
struct octeon_cvmseg_state cvmseg __attribute__ ((__aligned__(128)));
#endif
#ifdef CONFIG_CPU_XLP
struct nlm_cop2_state cp2;
#endif
struct mips_abi *abi;
};
#ifdef CONFIG_MIPS_MT_FPAFF
#define FPAFF_INIT \
.emulated_fp = 0, \
.user_cpus_allowed = INIT_CPUMASK,
#else
#define FPAFF_INIT
#endif /* CONFIG_MIPS_MT_FPAFF */
#define INIT_THREAD { \
/* \
* Saved main processor registers \
*/ \
.reg16 = 0, \
.reg17 = 0, \
.reg18 = 0, \
.reg19 = 0, \
.reg20 = 0, \
.reg21 = 0, \
.reg22 = 0, \
.reg23 = 0, \
.reg29 = 0, \
.reg30 = 0, \
.reg31 = 0, \
/* \
* Saved cp0 stuff \
*/ \
.cp0_status = 0, \
/* \
* Saved FPU/FPU emulator stuff \
*/ \
.fpu = { \
.fpr = {{{0,},},}, \
.fcr31 = 0, \
.msacsr = 0, \
}, \
/* \
* FPU affinity state (null if not FPAFF) \
*/ \
FPAFF_INIT \
/* Delay slot emulation */ \
.bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \
.bd_emu_branch_pc = 0, \
.bd_emu_cont_pc = 0, \
/* \
* Saved DSP stuff \
*/ \
.dsp = { \
.dspr = {0, }, \
.dspcontrol = 0, \
}, \
/* \
* saved watch register stuff \
*/ \
.watch = {{{0,},},}, \
/* \
* Other stuff associated with the process \
*/ \
.cp0_badvaddr = 0, \
.cp0_baduaddr = 0, \
.error_code = 0, \
.trap_nr = 0, \
/* \
* Platform specific cop2 registers(null if no COP2) \
*/ \
COP2_INIT \
}
struct task_struct;
/* Free all resources held by a thread. */
#define release_thread(thread) do { } while(0)
/*
* Do necessary setup to start up a newly executed thread.
*/
extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp);
static inline void flush_thread(void)
{
}
unsigned long get_wchan(struct task_struct *p);
#define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \
THREAD_SIZE - 32 - sizeof(struct pt_regs))
#define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk))
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->cp0_epc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
#define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
#ifdef CONFIG_CPU_LOONGSON3
/*
* Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
* tight read loop is executed, because reads take priority over writes & the
* hardware (incorrectly) doesn't ensure that writes will eventually occur.
*
* Since spin loops of any kind should have a cpu_relax() in them, force an SFB
* flush from cpu_relax() such that any pending writes will become visible as
* expected.
*/
#define cpu_relax() smp_mb()
#else
#define cpu_relax() barrier()
#endif
/*
* Return_address is a replacement for __builtin_return_address(count)
* which on certain architectures cannot reasonably be implemented in GCC
* (MIPS, Alpha) or is unusable with -fomit-frame-pointer (i386).
* Note that __builtin_return_address(x>=1) is forbidden because GCC
* aborts compilation on some CPUs. It's simply not possible to unwind
* some CPU's stackframes.
*
* __builtin_return_address works only for non-leaf functions. We avoid the
* overhead of a function call by forcing the compiler to save the return
* address register on the stack.
*/
#define return_address() ({__asm__ __volatile__("":::"$31");__builtin_return_address(0);})
#ifdef CONFIG_CPU_HAS_PREFETCH
#define ARCH_HAS_PREFETCH
#define prefetch(x) __builtin_prefetch((x), 0, 1)
#define ARCH_HAS_PREFETCHW
#define prefetchw(x) __builtin_prefetch((x), 1, 1)
#endif
/*
* Functions & macros implementing the PR_GET_FP_MODE & PR_SET_FP_MODE options
* to the prctl syscall.
*/
extern int mips_get_process_fp_mode(struct task_struct *task);
extern int mips_set_process_fp_mode(struct task_struct *task,
unsigned int value);
#define GET_FP_MODE(task) mips_get_process_fp_mode(task)
#define SET_FP_MODE(task,value) mips_set_process_fp_mode(task, value)
#endif /* _ASM_PROCESSOR_H */