kernel_optimize_test/arch/x86/include/asm/nops.h

119 lines
3.2 KiB
C
Raw Normal View History

#ifndef _ASM_X86_NOPS_H
#define _ASM_X86_NOPS_H
/* Define nops for use with alternative() */
/* generic versions from gas
1: nop
the following instructions are NOT nops in 64-bit mode,
for 64-bit mode use K8 or P6 nops instead
2: movl %esi,%esi
3: leal 0x00(%esi),%esi
4: leal 0x00(,%esi,1),%esi
6: leal 0x00000000(%esi),%esi
7: leal 0x00000000(,%esi,1),%esi
*/
#define GENERIC_NOP1 ".byte 0x90\n"
#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
/* Opteron 64bit nops
1: nop
2: osp nop
3: osp osp nop
4: osp osp osp nop
*/
#define K8_NOP1 GENERIC_NOP1
#define K8_NOP2 ".byte 0x66,0x90\n"
#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
#define K8_NOP5 K8_NOP3 K8_NOP2
#define K8_NOP6 K8_NOP3 K8_NOP3
#define K8_NOP7 K8_NOP4 K8_NOP3
#define K8_NOP8 K8_NOP4 K8_NOP4
/* K7 nops
uses eax dependencies (arbitary choice)
1: nop
2: movl %eax,%eax
3: leal (,%eax,1),%eax
4: leal 0x00(,%eax,1),%eax
6: leal 0x00000000(%eax),%eax
7: leal 0x00000000(,%eax,1),%eax
*/
#define K7_NOP1 GENERIC_NOP1
#define K7_NOP2 ".byte 0x8b,0xc0\n"
#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
#define K7_NOP5 K7_NOP4 ASM_NOP1
#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n"
#define K7_NOP8 K7_NOP7 ASM_NOP1
/* P6 nops
uses eax dependencies (Intel-recommended choice)
1: nop
2: osp nop
3: nopl (%eax)
4: nopl 0x00(%eax)
5: nopl 0x00(%eax,%eax,1)
6: osp nopl 0x00(%eax,%eax,1)
7: nopl 0x00000000(%eax)
8: nopl 0x00000000(%eax,%eax,1)
*/
#define P6_NOP1 GENERIC_NOP1
#define P6_NOP2 ".byte 0x66,0x90\n"
#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
x86: fix 64-bit asm NOPS for CONFIG_GENERIC_CPU ASM_NOP's for 64-bit kernel with CONFIG_GENERIC_CPU is broken with the recent x86 nops merge. They were using GENERIC_NOPS which will truncate the upper 32bits of %rsi, because of the missing 64bit rex prefix. For now, fall back ASM NOPS for generic cpu to K8 NOPS, similar to the code before the wrong x86 nop merge. This should resolve the crash seen by Ingo on a test-system: BUG: unable to handle kernel paging request at 00000000d80d8ee8 IP: [<ffffffff802121af>] save_i387_ia32+0x61/0xd8 PGD b8e0067 PUD 51490067 PMD 0 Oops: 0000 [1] SMP CPU 2 Modules linked in: Pid: 3871, comm: distcc Not tainted 2.6.25-rc7-sched-devel.git-x86-latest.git #359 RIP: 0010:[<ffffffff802121af>] [<ffffffff802121af>] save_i387_ia32+0x61/0xd8 RSP: 0000:ffff81003abd3cb8 EFLAGS: 00010246 RAX: ffff810082e93400 RBX: 00000000ffc37f84 RCX: ffff8100d80d8ee0 RDX: 0000000000000000 RSI: 00000000d80d8ee0 RDI: ffff810082e93400 RBP: 00000000ffc37fdc R08: 00000000ffc37f88 R09: 0000000000000008 R10: ffff81003abd2000 R11: 0000000000000000 R12: ffff810082e93400 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff81011fb12dc0(0063) knlGS:00000000f7f1a6c0 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 00000000d80d8ee8 CR3: 0000000076922000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process distcc (pid: 3871, threadinfo ffff81003abd2000, task ffff8100d80d8ee0) Stack: ffff8100bb670380 ffffffff8026de50 0000000000000118 0000000000000002 0000000000000002 ffff81003abd3e68 ffff81003abd3ed8 ffff81003abd3de8 ffff81003abd3d18 ffffffff80229785 ffff8100d80d8ee0 ffff810001041280 Call Trace: [<ffffffff8026de50>] ? __generic_file_aio_write_nolock+0x343/0x377 [<ffffffff80229785>] ? update_curr+0x54/0x64 [<ffffffff80227cd3>] ? ia32_setup_sigcontext+0x125/0x1d2 [<ffffffff8022839f>] ? ia32_setup_frame+0x73/0x1a5 [<ffffffff8020b2a5>] ? do_notify_resume+0x1aa/0x7db [<ffffffff8024ae8c>] ? getnstimeofday+0x31/0x85 [<ffffffff80249858>] ? ktime_get_ts+0x17/0x48 [<ffffffff80249933>] ? ktime_get+0xc/0x41 [<ffffffff8024973e>] ? hrtimer_nanosleep+0x75/0xd5 [<ffffffff80249261>] ? hrtimer_wakeup+0x0/0x21 [<ffffffff8020bfbc>] ? int_signal+0x12/0x17 [<ffffffff8030e6b3>] ? dummy_file_free_security+0x0/0x1 Code: a6 08 05 00 00 f6 40 14 01 74 34 4c 89 e7 48 0f ae 07 48 8b 86 08 05 00 00 80 78 02 00 79 02 db e2 90 8d b4 26 00 00 00 00 89 f6 <48> 8b 46 08 83 60 14 fe 0f 20 c0 48 83 c8 08 0f 22 c0 eb 07 c6 Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-08 02:56:34 +08:00
#if defined(CONFIG_MK7)
#define ASM_NOP1 K7_NOP1
#define ASM_NOP2 K7_NOP2
#define ASM_NOP3 K7_NOP3
#define ASM_NOP4 K7_NOP4
#define ASM_NOP5 K7_NOP5
#define ASM_NOP6 K7_NOP6
#define ASM_NOP7 K7_NOP7
#define ASM_NOP8 K7_NOP8
#elif defined(CONFIG_X86_P6_NOP)
#define ASM_NOP1 P6_NOP1
#define ASM_NOP2 P6_NOP2
#define ASM_NOP3 P6_NOP3
#define ASM_NOP4 P6_NOP4
#define ASM_NOP5 P6_NOP5
#define ASM_NOP6 P6_NOP6
#define ASM_NOP7 P6_NOP7
#define ASM_NOP8 P6_NOP8
x86: fix 64-bit asm NOPS for CONFIG_GENERIC_CPU ASM_NOP's for 64-bit kernel with CONFIG_GENERIC_CPU is broken with the recent x86 nops merge. They were using GENERIC_NOPS which will truncate the upper 32bits of %rsi, because of the missing 64bit rex prefix. For now, fall back ASM NOPS for generic cpu to K8 NOPS, similar to the code before the wrong x86 nop merge. This should resolve the crash seen by Ingo on a test-system: BUG: unable to handle kernel paging request at 00000000d80d8ee8 IP: [<ffffffff802121af>] save_i387_ia32+0x61/0xd8 PGD b8e0067 PUD 51490067 PMD 0 Oops: 0000 [1] SMP CPU 2 Modules linked in: Pid: 3871, comm: distcc Not tainted 2.6.25-rc7-sched-devel.git-x86-latest.git #359 RIP: 0010:[<ffffffff802121af>] [<ffffffff802121af>] save_i387_ia32+0x61/0xd8 RSP: 0000:ffff81003abd3cb8 EFLAGS: 00010246 RAX: ffff810082e93400 RBX: 00000000ffc37f84 RCX: ffff8100d80d8ee0 RDX: 0000000000000000 RSI: 00000000d80d8ee0 RDI: ffff810082e93400 RBP: 00000000ffc37fdc R08: 00000000ffc37f88 R09: 0000000000000008 R10: ffff81003abd2000 R11: 0000000000000000 R12: ffff810082e93400 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff81011fb12dc0(0063) knlGS:00000000f7f1a6c0 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 00000000d80d8ee8 CR3: 0000000076922000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process distcc (pid: 3871, threadinfo ffff81003abd2000, task ffff8100d80d8ee0) Stack: ffff8100bb670380 ffffffff8026de50 0000000000000118 0000000000000002 0000000000000002 ffff81003abd3e68 ffff81003abd3ed8 ffff81003abd3de8 ffff81003abd3d18 ffffffff80229785 ffff8100d80d8ee0 ffff810001041280 Call Trace: [<ffffffff8026de50>] ? __generic_file_aio_write_nolock+0x343/0x377 [<ffffffff80229785>] ? update_curr+0x54/0x64 [<ffffffff80227cd3>] ? ia32_setup_sigcontext+0x125/0x1d2 [<ffffffff8022839f>] ? ia32_setup_frame+0x73/0x1a5 [<ffffffff8020b2a5>] ? do_notify_resume+0x1aa/0x7db [<ffffffff8024ae8c>] ? getnstimeofday+0x31/0x85 [<ffffffff80249858>] ? ktime_get_ts+0x17/0x48 [<ffffffff80249933>] ? ktime_get+0xc/0x41 [<ffffffff8024973e>] ? hrtimer_nanosleep+0x75/0xd5 [<ffffffff80249261>] ? hrtimer_wakeup+0x0/0x21 [<ffffffff8020bfbc>] ? int_signal+0x12/0x17 [<ffffffff8030e6b3>] ? dummy_file_free_security+0x0/0x1 Code: a6 08 05 00 00 f6 40 14 01 74 34 4c 89 e7 48 0f ae 07 48 8b 86 08 05 00 00 80 78 02 00 79 02 db e2 90 8d b4 26 00 00 00 00 89 f6 <48> 8b 46 08 83 60 14 fe 0f 20 c0 48 83 c8 08 0f 22 c0 eb 07 c6 Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-08 02:56:34 +08:00
#elif defined(CONFIG_X86_64)
#define ASM_NOP1 K8_NOP1
#define ASM_NOP2 K8_NOP2
#define ASM_NOP3 K8_NOP3
#define ASM_NOP4 K8_NOP4
#define ASM_NOP5 K8_NOP5
#define ASM_NOP6 K8_NOP6
#define ASM_NOP7 K8_NOP7
#define ASM_NOP8 K8_NOP8
#else
#define ASM_NOP1 GENERIC_NOP1
#define ASM_NOP2 GENERIC_NOP2
#define ASM_NOP3 GENERIC_NOP3
#define ASM_NOP4 GENERIC_NOP4
#define ASM_NOP5 GENERIC_NOP5
#define ASM_NOP6 GENERIC_NOP6
#define ASM_NOP7 GENERIC_NOP7
#define ASM_NOP8 GENERIC_NOP8
#endif
#define ASM_NOP_MAX 8
#endif /* _ASM_X86_NOPS_H */