.\"	$NetBSD: OPENSSL_ia32cap.3,v 1.16 2017/01/27 23:00:47 spz Exp $
.\"
.\" Automatically generated by Pod::Man 4.07 (Pod::Simple 3.32)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.if !\nF .nr F 0
.if \nF>0 \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    if !\nF==2 \{\
.        nr % 0
.        nr F 2
.    \}
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "OPENSSL_ia32cap 3"
.TH OPENSSL_ia32cap 3 "2016-10-14" "1.0.2k" "OpenSSL"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
OPENSSL_ia32cap, OPENSSL_ia32cap_loc \- the IA\-32 processor capabilities vector
.SH "LIBRARY"
libcrypto, -lcrypto
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 2
\& unsigned long *OPENSSL_ia32cap_loc(void);
\& #define OPENSSL_ia32cap ((OPENSSL_ia32cap_loc())[0])
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Value returned by \fIOPENSSL_ia32cap_loc()\fR is address of a variable
containing \s-1IA\-32\s0 processor capabilities bit vector as it appears in
\&\s-1EDX:ECX\s0 register pair after executing \s-1CPUID\s0 instruction with EAX=1
input value (see Intel Application Note #241618). Naturally it's
meaningful on x86 and x86_64 platforms only. The variable is normally
set up automatically upon toolkit initialization, but can be
manipulated afterwards to modify crypto library behaviour. For the
moment of this writing following bits are significant:
.IP "bit #4 denoting presence of Time-Stamp Counter." 4
.IX Item "bit #4 denoting presence of Time-Stamp Counter."
.PD 0
.IP "bit #19 denoting availability of \s-1CLFLUSH\s0 instruction;" 4
.IX Item "bit #19 denoting availability of CLFLUSH instruction;"
.IP "bit #20, reserved by Intel, is used to choose among \s-1RC4\s0 code paths;" 4
.IX Item "bit #20, reserved by Intel, is used to choose among RC4 code paths;"
.IP "bit #23 denoting \s-1MMX\s0 support;" 4
.IX Item "bit #23 denoting MMX support;"
.IP "bit #24, \s-1FXSR\s0 bit, denoting availability of \s-1XMM\s0 registers;" 4
.IX Item "bit #24, FXSR bit, denoting availability of XMM registers;"
.IP "bit #25 denoting \s-1SSE\s0 support;" 4
.IX Item "bit #25 denoting SSE support;"
.IP "bit #26 denoting \s-1SSE2\s0 support;" 4
.IX Item "bit #26 denoting SSE2 support;"
.IP "bit #28 denoting Hyperthreading, which is used to distinguish cores with shared cache;" 4
.IX Item "bit #28 denoting Hyperthreading, which is used to distinguish cores with shared cache;"
.IP "bit #30, reserved by Intel, denotes specifically Intel CPUs;" 4
.IX Item "bit #30, reserved by Intel, denotes specifically Intel CPUs;"
.IP "bit #33 denoting availability of \s-1PCLMULQDQ\s0 instruction;" 4
.IX Item "bit #33 denoting availability of PCLMULQDQ instruction;"
.IP "bit #41 denoting \s-1SSSE3,\s0 Supplemental \s-1SSE3,\s0 support;" 4
.IX Item "bit #41 denoting SSSE3, Supplemental SSE3, support;"
.IP "bit #43 denoting \s-1AMD XOP\s0 support (forced to zero on non-AMD CPUs);" 4
.IX Item "bit #43 denoting AMD XOP support (forced to zero on non-AMD CPUs);"
.IP "bit #57 denoting AES-NI instruction set extension;" 4
.IX Item "bit #57 denoting AES-NI instruction set extension;"
.IP "bit #59, \s-1OSXSAVE\s0 bit, denoting availability of \s-1YMM\s0 registers;" 4
.IX Item "bit #59, OSXSAVE bit, denoting availability of YMM registers;"
.IP "bit #60 denoting \s-1AVX\s0 extension;" 4
.IX Item "bit #60 denoting AVX extension;"
.IP "bit #62 denoting availability of \s-1RDRAND\s0 instruction;" 4
.IX Item "bit #62 denoting availability of RDRAND instruction;"
.PD
.PP
For example, clearing bit #26 at run-time disables high-performance
\&\s-1SSE2\s0 code present in the crypto library, while clearing bit #24
disables \s-1SSE2\s0 code operating on 128\-bit \s-1XMM\s0 register bank. You might
have to do the latter if target OpenSSL application is executed on \s-1SSE2\s0
capable \s-1CPU,\s0 but under control of \s-1OS\s0 that does not enable \s-1XMM\s0
registers. Even though you can manipulate the value programmatically,
you most likely will find it more appropriate to set up an environment
variable with the same name prior starting target application, e.g. on
Intel P4 processor 'env OPENSSL_ia32cap=0x16980010 apps/openssl', or
better yet 'env OPENSSL_ia32cap=~0x1000000 apps/openssl' to achieve same
effect without modifying the application source code. Alternatively you
can reconfigure the toolkit with no\-sse2 option and recompile.
.PP
Less intuitive is clearing bit #28. The truth is that it's not copied
from \s-1CPUID\s0 output verbatim, but is adjusted to reflect whether or not
the data cache is actually shared between logical cores. This in turn
affects the decision on whether or not expensive countermeasures
against cache-timing attacks are applied, most notably in \s-1AES\s0 assembler
module.
.PP
The vector is further extended with \s-1EBX\s0 value returned by \s-1CPUID\s0 with
EAX=7 and ECX=0 as input. Following bits are significant:
.IP "bit #64+3 denoting availability of \s-1BMI1\s0 instructions, e.g. \s-1ANDN\s0;" 4
.IX Item "bit #64+3 denoting availability of BMI1 instructions, e.g. ANDN;"
.PD 0
.IP "bit #64+5 denoting availability of \s-1AVX2\s0 instructions;" 4
.IX Item "bit #64+5 denoting availability of AVX2 instructions;"
.IP "bit #64+8 denoting availability of \s-1BMI2\s0 instructions, e.g. \s-1MUXL\s0 and \s-1RORX\s0;" 4
.IX Item "bit #64+8 denoting availability of BMI2 instructions, e.g. MUXL and RORX;"
.IP "bit #64+18 denoting availability of \s-1RDSEED\s0 instruction;" 4
.IX Item "bit #64+18 denoting availability of RDSEED instruction;"
.IP "bit #64+19 denoting availability of \s-1ADCX\s0 and \s-1ADOX\s0 instructions;" 4
.IX Item "bit #64+19 denoting availability of ADCX and ADOX instructions;"