linux_dsm_epyc7002/arch/x86/include/asm/cpufeature.h

211 lines
7.1 KiB
C
Raw Normal View History

#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
#include <asm/processor.h>
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
#include <asm/asm.h>
#include <linux/bitops.h>
enum cpuid_leafs
{
CPUID_1_EDX = 0,
CPUID_8000_0001_EDX,
CPUID_8086_0001_EDX,
CPUID_LNX_1,
CPUID_1_ECX,
CPUID_C000_0001_EDX,
CPUID_8000_0001_ECX,
CPUID_LNX_2,
CPUID_LNX_3,
CPUID_7_0_EBX,
CPUID_D_1_EAX,
CPUID_F_0_EDX,
CPUID_F_1_EDX,
CPUID_8000_0008_EBX,
CPUID_6_EAX,
CPUID_8000_000A_EDX,
};
#ifdef CONFIG_X86_FEATURE_NAMES
extern const char * const x86_cap_flags[NCAPINTS*32];
extern const char * const x86_power_flags[32];
#define X86_CAP_FMT "%s"
#define x86_cap_flag(flag) x86_cap_flags[flag]
#else
#define X86_CAP_FMT "%d:%d"
#define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31)
#endif
/*
* In order to save room, we index into this array by doing
* X86_BUG_<name> - NCAPINTS*32.
*/
extern const char * const x86_bug_flags[NBUGINTS*32];
#define test_cpu_cap(c, bit) \
test_bit(bit, (unsigned long *)((c)->x86_capability))
#define REQUIRED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) || \
(((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) || \
(((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) || \
(((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) || \
(((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \
(((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \
(((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \
(((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \
(((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \
(((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
x86: Introduce disabled-features I believe the REQUIRED_MASK aproach was taken so that it was easier to consult in assembly (arch/x86/kernel/verify_cpu.S). DISABLED_MASK does not have the same restriction, but I implemented it the same way for consistency. We have a REQUIRED_MASK... which does two things: 1. Keeps a list of cpuid bits to check in very early boot and refuse to boot if those are not present. 2. Consulted during cpu_has() checks, which allows us to optimize out things at compile-time. In other words, if we *KNOW* we will not boot with the feature off, then we can safely assume that it will be present forever. But, we don't have a similar mechanism for CPU features which may be present but that we know we will not use. We simply use our existing mechanisms to repeatedly check the status of the bit at runtime (well, the alternatives patching helps here but it does not provide compile-time optimization). Adding a feature to disabled-features.h allows the bit to be checked via a new macro: cpu_feature_enabled(). Note that for features in DISABLED_MASK, checks with this macro have all of the benefits of an #ifdef. Before, we would have done this in a header: #ifdef CONFIG_X86_INTEL_MPX #define cpu_has_mpx cpu_has(X86_FEATURE_MPX) #else #define cpu_has_mpx 0 #endif and this in the code: if (cpu_has_mpx) do_some_mpx_thing(); Now, just add your feature to DISABLED_MASK and you can do this everywhere, and get the same benefits you would have from #ifdefs: if (cpu_feature_enabled(X86_FEATURE_MPX)) do_some_mpx_thing(); We need a new function and *not* a modification to cpu_has() because there are cases where we actually need to check the CPU itself, despite what features the kernel supports. The best example of this is a hypervisor which has no control over what features its guests are using and where the guest does not depend on the host for support. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Link: http://lkml.kernel.org/r/20140911211513.9E35E931@viggo.jf.intel.com Acked-by: Borislav Petkov <bp@suse.de> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-09-12 04:15:13 +07:00
#define DISABLED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) || \
(((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) || \
(((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) || \
(((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) || \
(((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) || \
(((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) || \
(((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) || \
(((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) || \
(((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) || \
(((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) )
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
test_cpu_cap(c, bit))
#define this_cpu_has(bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
x86: Introduce disabled-features I believe the REQUIRED_MASK aproach was taken so that it was easier to consult in assembly (arch/x86/kernel/verify_cpu.S). DISABLED_MASK does not have the same restriction, but I implemented it the same way for consistency. We have a REQUIRED_MASK... which does two things: 1. Keeps a list of cpuid bits to check in very early boot and refuse to boot if those are not present. 2. Consulted during cpu_has() checks, which allows us to optimize out things at compile-time. In other words, if we *KNOW* we will not boot with the feature off, then we can safely assume that it will be present forever. But, we don't have a similar mechanism for CPU features which may be present but that we know we will not use. We simply use our existing mechanisms to repeatedly check the status of the bit at runtime (well, the alternatives patching helps here but it does not provide compile-time optimization). Adding a feature to disabled-features.h allows the bit to be checked via a new macro: cpu_feature_enabled(). Note that for features in DISABLED_MASK, checks with this macro have all of the benefits of an #ifdef. Before, we would have done this in a header: #ifdef CONFIG_X86_INTEL_MPX #define cpu_has_mpx cpu_has(X86_FEATURE_MPX) #else #define cpu_has_mpx 0 #endif and this in the code: if (cpu_has_mpx) do_some_mpx_thing(); Now, just add your feature to DISABLED_MASK and you can do this everywhere, and get the same benefits you would have from #ifdefs: if (cpu_feature_enabled(X86_FEATURE_MPX)) do_some_mpx_thing(); We need a new function and *not* a modification to cpu_has() because there are cases where we actually need to check the CPU itself, despite what features the kernel supports. The best example of this is a hypervisor which has no control over what features its guests are using and where the guest does not depend on the host for support. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Link: http://lkml.kernel.org/r/20140911211513.9E35E931@viggo.jf.intel.com Acked-by: Borislav Petkov <bp@suse.de> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-09-12 04:15:13 +07:00
/*
* This macro is for detection of features which need kernel
* infrastructure to be used. It may *not* directly test the CPU
* itself. Use the cpu_has() family if you want true runtime
* testing of CPU features, like in hypervisor code where you are
* supporting a possible guest feature where host support for it
* is not relevant.
*/
#define cpu_feature_enabled(bit) \
(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : \
cpu_has(&boot_cpu_data, bit))
#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit)
#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability))
#define clear_cpu_cap(c, bit) clear_bit(bit, (unsigned long *)((c)->x86_capability))
#define setup_clear_cpu_cap(bit) do { \
clear_cpu_cap(&boot_cpu_data, bit); \
set_bit(bit, (unsigned long *)cpu_caps_cleared); \
} while (0)
#define setup_force_cpu_cap(bit) do { \
set_cpu_cap(&boot_cpu_data, bit); \
set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU)
#define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE)
#define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC)
#define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE)
#define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC)
#define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR)
#define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM)
#define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2)
#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES)
crypto: sha1 - SSSE3 based SHA1 implementation for x86-64 This is an assembler implementation of the SHA1 algorithm using the Supplemental SSE3 (SSSE3) instructions or, when available, the Advanced Vector Extensions (AVX). Testing with the tcrypt module shows the raw hash performance is up to 2.3 times faster than the C implementation, using 8k data blocks on a Core 2 Duo T5500. For the smalest data set (16 byte) it is still 25% faster. Since this implementation uses SSE/YMM registers it cannot safely be used in every situation, e.g. while an IRQ interrupts a kernel thread. The implementation falls back to the generic SHA1 variant, if using the SSE/YMM registers is not possible. With this algorithm I was able to increase the throughput of a single IPsec link from 344 Mbit/s to 464 Mbit/s on a Core 2 Quad CPU using the SSSE3 variant -- a speedup of +34.8%. Saving and restoring SSE/YMM state might make the actual throughput fluctuate when there are FPU intensive userland applications running. For example, meassuring the performance using iperf2 directly on the machine under test gives wobbling numbers because iperf2 uses the FPU for each packet to check if the reporting interval has expired (in the above test I got min/max/avg: 402/484/464 MBit/s). Using this algorithm on a IPsec gateway gives much more reasonable and stable numbers, albeit not as high as in the directly connected case. Here is the result from an RFC 2544 test run with a EXFO Packet Blazer FTB-8510: frame size sha1-generic sha1-ssse3 delta 64 byte 37.5 MBit/s 37.5 MBit/s 0.0% 128 byte 56.3 MBit/s 62.5 MBit/s +11.0% 256 byte 87.5 MBit/s 100.0 MBit/s +14.3% 512 byte 131.3 MBit/s 150.0 MBit/s +14.2% 1024 byte 162.5 MBit/s 193.8 MBit/s +19.3% 1280 byte 175.0 MBit/s 212.5 MBit/s +21.4% 1420 byte 175.0 MBit/s 218.7 MBit/s +25.0% 1518 byte 150.0 MBit/s 181.2 MBit/s +20.8% The throughput for the largest frame size is lower than for the previous size because the IP packets need to be fragmented in this case to make there way through the IPsec tunnel. Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Maxim Locktyukhin <maxim.locktyukhin@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-08-05 01:19:25 +07:00
#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX)
#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2)
#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH)
#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES)
#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
#define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT)
#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES)
crypto: sha1 - SSSE3 based SHA1 implementation for x86-64 This is an assembler implementation of the SHA1 algorithm using the Supplemental SSE3 (SSSE3) instructions or, when available, the Advanced Vector Extensions (AVX). Testing with the tcrypt module shows the raw hash performance is up to 2.3 times faster than the C implementation, using 8k data blocks on a Core 2 Duo T5500. For the smalest data set (16 byte) it is still 25% faster. Since this implementation uses SSE/YMM registers it cannot safely be used in every situation, e.g. while an IRQ interrupts a kernel thread. The implementation falls back to the generic SHA1 variant, if using the SSE/YMM registers is not possible. With this algorithm I was able to increase the throughput of a single IPsec link from 344 Mbit/s to 464 Mbit/s on a Core 2 Quad CPU using the SSSE3 variant -- a speedup of +34.8%. Saving and restoring SSE/YMM state might make the actual throughput fluctuate when there are FPU intensive userland applications running. For example, meassuring the performance using iperf2 directly on the machine under test gives wobbling numbers because iperf2 uses the FPU for each packet to check if the reporting interval has expired (in the above test I got min/max/avg: 402/484/464 MBit/s). Using this algorithm on a IPsec gateway gives much more reasonable and stable numbers, albeit not as high as in the directly connected case. Here is the result from an RFC 2544 test run with a EXFO Packet Blazer FTB-8510: frame size sha1-generic sha1-ssse3 delta 64 byte 37.5 MBit/s 37.5 MBit/s 0.0% 128 byte 56.3 MBit/s 62.5 MBit/s +11.0% 256 byte 87.5 MBit/s 100.0 MBit/s +14.3% 512 byte 131.3 MBit/s 150.0 MBit/s +14.2% 1024 byte 162.5 MBit/s 193.8 MBit/s +19.3% 1280 byte 175.0 MBit/s 212.5 MBit/s +21.4% 1420 byte 175.0 MBit/s 218.7 MBit/s +25.0% 1518 byte 150.0 MBit/s 181.2 MBit/s +20.8% The throughput for the largest frame size is lower than for the previous size because the IP packets need to be fragmented in this case to make there way through the IPsec tunnel. Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Maxim Locktyukhin <maxim.locktyukhin@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-08-05 01:19:25 +07:00
#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
/*
* Do not add any more of those clumsy macros - use static_cpu_has() for
* fast paths and boot_cpu_has() otherwise!
*/
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
* performance.
*/
static __always_inline __pure bool _static_cpu_has(u16 bit)
{
asm_volatile_goto("1: jmp 6f\n"
"2:\n"
".skip -(((5f-4f) - (2b-1b)) > 0) * "
"((5f-4f) - (2b-1b)),0x90\n"
"3:\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n" /* src offset */
" .long 4f - .\n" /* repl offset */
" .word %P1\n" /* always replace */
" .byte 3b - 1b\n" /* src len */
" .byte 5f - 4f\n" /* repl len */
" .byte 3b - 2b\n" /* pad len */
".previous\n"
".section .altinstr_replacement,\"ax\"\n"
x86/alternatives: Make JMPs more robust Up until now we had to pay attention to relative JMPs in alternatives about how their relative offset gets computed so that the jump target is still correct. Or, as it is the case for near CALLs (opcode e8), we still have to go and readjust the offset at patching time. What is more, the static_cpu_has_safe() facility had to forcefully generate 5-byte JMPs since we couldn't rely on the compiler to generate properly sized ones so we had to force the longest ones. Worse than that, sometimes it would generate a replacement JMP which is longer than the original one, thus overwriting the beginning of the next instruction at patching time. So, in order to alleviate all that and make using JMPs more straight-forward we go and pad the original instruction in an alternative block with NOPs at build time, should the replacement(s) be longer. This way, alternatives users shouldn't pay special attention so that original and replacement instruction sizes are fine but the assembler would simply add padding where needed and not do anything otherwise. As a second aspect, we go and recompute JMPs at patching time so that we can try to make 5-byte JMPs into two-byte ones if possible. If not, we still have to recompute the offsets as the replacement JMP gets put far away in the .altinstr_replacement section leading to a wrong offset if copied verbatim. For example, on a locally generated kernel image old insn VA: 0xffffffff810014bd, CPU feat: X86_FEATURE_ALWAYS, size: 2 __switch_to: ffffffff810014bd: eb 21 jmp ffffffff810014e0 repl insn: size: 5 ffffffff81d0b23c: e9 b1 62 2f ff jmpq ffffffff810014f2 gets corrected to a 2-byte JMP: apply_alternatives: feat: 3*32+21, old: (ffffffff810014bd, len: 2), repl: (ffffffff81d0b23c, len: 5) alt_insn: e9 b1 62 2f ff recompute_jumps: next_rip: ffffffff81d0b241, tgt_rip: ffffffff810014f2, new_displ: 0x00000033, ret len: 2 converted to: eb 33 90 90 90 and a 5-byte JMP: old insn VA: 0xffffffff81001516, CPU feat: X86_FEATURE_ALWAYS, size: 2 __switch_to: ffffffff81001516: eb 30 jmp ffffffff81001548 repl insn: size: 5 ffffffff81d0b241: e9 10 63 2f ff jmpq ffffffff81001556 gets shortened into a two-byte one: apply_alternatives: feat: 3*32+21, old: (ffffffff81001516, len: 2), repl: (ffffffff81d0b241, len: 5) alt_insn: e9 10 63 2f ff recompute_jumps: next_rip: ffffffff81d0b246, tgt_rip: ffffffff81001556, new_displ: 0x0000003e, ret len: 2 converted to: eb 3e 90 90 90 ... and so on. This leads to a net win of around 40ish replacements * 3 bytes savings =~ 120 bytes of I$ on an AMD guest which means some savings of precious instruction cache bandwidth. The padding to the shorter 2-byte JMPs are single-byte NOPs which on smart microarchitectures means discarding NOPs at decode time and thus freeing up execution bandwidth. Signed-off-by: Borislav Petkov <bp@suse.de>
2015-01-05 19:48:41 +07:00
"4: jmp %l[t_no]\n"
"5:\n"
".previous\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n" /* src offset */
" .long 0\n" /* no replacement */
" .word %P0\n" /* feature bit */
" .byte 3b - 1b\n" /* src len */
" .byte 0\n" /* repl len */
" .byte 0\n" /* pad len */
".previous\n"
".section .altinstr_aux,\"ax\"\n"
"6:\n"
" testb %[bitnum],%[cap_byte]\n"
" jnz %l[t_yes]\n"
" jmp %l[t_no]\n"
".previous\n"
: : "i" (bit), "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
[cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
: : t_yes, t_no);
t_yes:
return true;
t_no:
return false;
}
#define static_cpu_has(bit) \
( \
__builtin_constant_p(boot_cpu_has(bit)) ? \
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
#else
/*
* Fall back to dynamic for gcc versions which don't support asm goto. Should be
* a minority now anyway.
*/
#define static_cpu_has(bit) boot_cpu_has(bit)
#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
#define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit))
#define static_cpu_has_bug(bit) static_cpu_has((bit))
#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit))
#define MAX_CPU_FEATURES (NCAPINTS * 32)
#define cpu_have_feature boot_cpu_has
#define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X"
#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
boot_cpu_data.x86_model
#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
#endif /* _ASM_X86_CPUFEATURE_H */