Ok, I have something which looks like it works here, even with the pentium3 qemu CPU. I'll be hammering on it in the coming days but if you wanna give it a try, here's a conglomerate patch:
--- >From 0c6adce02d2e7f3b5bbdc4cbe3eb3dae99448def Mon Sep 17 00:00:00 2001 From: Borislav Petkov <[email protected]> Date: Fri, 7 Dec 2018 18:54:23 +0100 Subject: [PATCH] WIP Signed-off-by: Borislav Petkov <[email protected]> --- arch/x86/include/asm/alternative.h | 26 +++++++++++++++++++++++++- arch/x86/include/asm/msr.h | 16 ++++++++++++++-- arch/x86/kernel/alternative.c | 4 ++-- 3 files changed, 41 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ea9886651c39..db8ebe5dd5be 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -114,6 +114,16 @@ static inline int alternatives_text_reserved(void *start, void *end) "(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \ alt_end_marker ":\n" +#define OLDINSTR_3(oldinsn, n1, n2, n3) \ + "# ALT: oldinstr\n" \ + "661:\n\t" oldinsn "\n662:\n" \ + "# ALT: padding\n" \ + ".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ + " - (" alt_slen ")) > 0) * " \ + "(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ + " - (" alt_slen ")), 0x90\n" \ + alt_end_marker ":\n" + #define ALTINSTR_ENTRY(feature, num) \ " .long 661b - .\n" /* label */ \ " .long " b_replacement(num)"f - .\n" /* new instruction */ \ @@ -122,7 +132,8 @@ static inline int alternatives_text_reserved(void *start, void *end) " .byte " alt_rlen(num) "\n" /* replacement len */ \ " .byte " alt_pad_len "\n" /* pad len */ -#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ +#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ + "# ALT: replacement " #num "\n" \ b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t" /* alternative assembly primitive: */ @@ -146,6 +157,19 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ ".popsection\n" +#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \ + OLDINSTR_3(oldinsn, 1, 2, 3) \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feat1, 1) \ + ALTINSTR_ENTRY(feat2, 2) \ + ALTINSTR_ENTRY(feat3, 3) \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinsn1, feat1, 1) \ + ALTINSTR_REPLACEMENT(newinsn2, feat2, 2) \ + ALTINSTR_REPLACEMENT(newinsn3, feat3, 3) \ + ".popsection\n" + /* * Alternative instructions for different CPU types or capabilities. * diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 91e4cf189914..5cc3930cb465 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -217,6 +217,8 @@ static __always_inline unsigned long long rdtsc(void) */ static __always_inline unsigned long long rdtsc_ordered(void) { + DECLARE_ARGS(val, low, high); + /* * The RDTSC instruction is not ordered relative to memory * access. The Intel SDM and the AMD APM are both vague on this @@ -227,9 +229,19 @@ static __always_inline unsigned long long rdtsc_ordered(void) * ordering guarantees as reading from a global memory location * that some other imaginary CPU is updating continuously with a * time stamp. + * + * Thus, use the preferred barrier on the respective CPU, aiming for + * RDTSCP as the default. */ - barrier_nospec(); - return rdtsc(); + asm volatile(ALTERNATIVE_3("rdtsc", + "mfence; rdtsc", X86_FEATURE_MFENCE_RDTSC, + "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, + "rdtscp", X86_FEATURE_RDTSCP) + : EAX_EDX_RET(val, low, high) + /* RDTSCP clobbers ECX with MSR_TSC_AUX. */ + :: "ecx"); + + return EAX_EDX_VAL(val, low, high); } static inline unsigned long long native_read_pmc(int counter) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ebeac487a20c..d458c7973c56 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -393,10 +393,10 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, - instr, a->instrlen, + instr, instr, a->instrlen, replacement, a->replacementlen, a->padlen); DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); -- 2.19.1 -- Regards/Gruss, Boris. Good mailing practices for 400: avoid top-posting and trim the reply.
