diff options
| author | Jerry Jelinek <jerry.jelinek@joyent.com> | 2020-04-22 11:27:20 +0000 |
|---|---|---|
| committer | Jerry Jelinek <jerry.jelinek@joyent.com> | 2020-04-22 11:27:20 +0000 |
| commit | dabc60f5b9afa61baa5a6a19a03802ad59a5462e (patch) | |
| tree | 2fb2a476f888078066eef01d4748f41d3668c145 | |
| parent | 1f6ef55bbc34d163d8228af4d5c128e1e5a5c4db (diff) | |
| parent | 865498e43471404cd766389d4b8e045ed6ef3be1 (diff) | |
| download | illumos-joyent-dabc60f5b9afa61baa5a6a19a03802ad59a5462e.tar.gz | |
[illumos-gate merge]
commit 865498e43471404cd766389d4b8e045ed6ef3be1
commit 6205b5c44bad9044e168b06aef439c2e7cdc8a89
12508 ndi_devi_alloc() and friends could take const char * names
commit e98dc02a871a9cd0498c8862434b16aa85e772d3
12482 Have /usr/bin/awk point to /usr/bin/nawk
commit 9e717e77bf4b9b5ad279c38a2311c076468e85f5
12496 bge mac address initialization is wrong
12497 bge ape locking left always disabled after 7513
12498 bge ring interrupt masking logic is broken
commit a2876d03ca2556102e024ae4a50bb4db8fe562b0
12450 Add support for BCM57765 family devices to bge
commit 85f496fabdffd32673f6be280a3caa103f7d58a5
12520 Enable IPv6 tso in igb, ixgbe, and i40e
commit 0418219cf21334a9c6712bbb2cec543b2ee4f989
12552 increase get_max_pages
commit ee73640b6a4781aa745f3868c448d1b9dd1c29f6
12469 mlxcx: errors in package metadata
Conflicts:
usr/src/man/man1/nawk.1 [deleted upstream]
37 files changed, 2482 insertions, 2435 deletions
@@ -11905,7 +11905,7 @@ f usr/share/man/man1/at.1 0444 root bin f usr/share/man/man1/atq.1 0444 root bin f usr/share/man/man1/atrm.1 0444 root bin f usr/share/man/man1/auths.1 0444 root bin -s usr/share/man/man1/awk.1=nawk.1 +f usr/share/man/man1/awk.1 0444 root bin f usr/share/man/man1/banner.1 0444 root bin f usr/share/man/man1/basename.1 0444 root bin s usr/share/man/man1/batch.1=at.1 @@ -12122,7 +12122,7 @@ f usr/share/man/man1/mpss.so.1.1 0444 root bin f usr/share/man/man1/msgfmt.1 0444 root bin f usr/share/man/man1/mt.1 0444 root bin f usr/share/man/man1/mv.1 0444 root bin -f usr/share/man/man1/nawk.1 0444 root bin +s usr/share/man/man1/nawk.1=awk.1 f usr/share/man/man1/nc.1 0444 root bin s usr/share/man/man1/neqn.1=eqn.1 f usr/share/man/man1/newform.1 0444 root bin diff --git a/usr/src/cmd/awk/Makefile b/usr/src/cmd/awk/Makefile index 046f0b739e..339f22d821 100644 --- a/usr/src/cmd/awk/Makefile +++ b/usr/src/cmd/awk/Makefile @@ -24,11 +24,12 @@ # Copyright 2005 Sun Microsystems, Inc. All rights reserved. # Use is subject to license terms. # -# Copyright (c) 2018, Joyent, Inc. +# Copyright 2020 Joyent, Inc. -# NOTE: awk is oawk. +# NOTE: awk is now nawk. PROG= nawk +LINKPROG= awk OBJ1= b.o lib.o main.o parse.o proctab.o run.o tran.o lex.o OBJ2= awk.g.o @@ -37,6 +38,8 @@ SRCS= $(OBJ1:%.o=%.c) include ../Makefile.cmd +ROOTLINK = $(LINKPROG:%=$(ROOTBIN)/%) + CERRWARN += -_gcc=-Wno-unused-label CERRWARN += -_gcc=-Wno-parentheses CERRWARN += -_gcc=-Wno-unused-variable @@ -61,12 +64,15 @@ CLEANFILES= maketab proctab.c awk.g.c y.tab.h .KEEP_STATE: -all: $(PROG) +all: $(PROG) $(ROOTLINK) $(PROG): $(OBJS) $(LINK.c) $(OBJS) -o $@ $(LDLIBS) $(POST_PROCESS) +$(ROOTLINK): $(ROOTPROG) + $(RM) $@; $(LN) $(ROOTPROG) $@ + # # message catalog # @@ -87,8 +93,6 @@ install: all $(ROOTPROG) $(ROOTLINK) clean: $(RM) $(OBJS) $(CLEANFILES) -lint: awk.g.c lint_SRCS - awk.g.c + y.tab.h: awk.g.y awk.g.o: awk.g.c diff --git a/usr/src/cmd/oawk/Makefile b/usr/src/cmd/oawk/Makefile index 37a2f60f09..0745ca3cfc 100644 --- a/usr/src/cmd/oawk/Makefile +++ b/usr/src/cmd/oawk/Makefile @@ -28,7 +28,6 @@ include ../Makefile.cmd PROG = oawk -LINKPROG = awk SRCS = b.c lib.c main.c parse.c run.c tran.c @@ -62,8 +61,6 @@ LDLIBS += -lm CPPFLAGS = -I. $(CPPFLAGS.master) CPPFLAGS += -D_FILE_OFFSET_BITS=64 -ROOTLINK = $(LINKPROG:%=$(ROOTBIN)/%) - CERRWARN += -_gcc=-Wno-implicit-function-declaration CERRWARN += -_gcc=-Wno-unused-label CERRWARN += -_gcc=-Wno-unused-variable @@ -105,7 +102,7 @@ proctab.c : $(MAKEPRCTAB) $(MAKEPRCTAB) : $(NATIVEDIR) $(NATIVEOBJS) $(LINK.c) $(NATIVEOBJS) -o $@ $(XLDLIBS5CC) -install : all $(ROOTPROG) $(ROOTLINK) +install : all $(ROOTPROG) $(NATIVEDIR) : -@mkdir -p $(NATIVEDIR) @@ -113,9 +110,6 @@ $(NATIVEDIR) : $(NATIVEDIR)/%.o : %.c $(COMPILE.c) -o $@ $< -$(ROOTLINK) : $(ROOTPROG) - $(RM) $@; $(LN) $(ROOTPROG) $@ - clean: $(RM) $(OBJS) $(CLEANFILES) diff --git a/usr/src/man/man1/Makefile b/usr/src/man/man1/Makefile index c80c00d8ed..237f02e1aa 100644 --- a/usr/src/man/man1/Makefile +++ b/usr/src/man/man1/Makefile @@ -250,7 +250,6 @@ MANFILES= acctcom.1 \ msgget.1 \ mt.1 \ mv.1 \ - nawk.1 \ nc.1 \ nca.1 \ ncab2clf.1 \ @@ -264,6 +263,7 @@ MANFILES= acctcom.1 \ nm.1 \ nohup.1 \ nroff.1 \ + oawk.1 \ od.1 \ optisa.1 \ pack.1 \ @@ -484,6 +484,7 @@ MANLINKS= batch.1 \ ksh.1 \ ldapadd.1 \ mailq.1 \ + nawk.1 \ neqn.1 \ notify.1 \ onintr.1 \ @@ -626,6 +627,8 @@ dmake.1 := LINKSRC = make.1 checkeq.1 := LINKSRC = eqn.1 neqn.1 := LINKSRC = eqn.1 +nawk.1 := LINKSRC = awk.1 + eval.1 := LINKSRC = exec.1 source.1 := LINKSRC = exec.1 diff --git a/usr/src/man/man1/awk.1 b/usr/src/man/man1/awk.1 index c5bf3da770..b2983dada4 100644 --- a/usr/src/man/man1/awk.1 +++ b/usr/src/man/man1/awk.1 @@ -41,221 +41,841 @@ .\" .\" .\" Copyright 1989 AT&T -.\" Portions Copyright (c) 1992, X/Open Company Limited. All Rights Reserved. -.\" Copyright (c) 2005, Sun Microsystems, Inc. All Rights Reserved +.\" Copyright 1992, X/Open Company Limited All Rights Reserved +.\" Portions Copyright (c) 2005, 2006 Sun Microsystems, Inc. All Rights Reserved +.\" Copyright 2020 Joyent, Inc. .\" -.TH AWK 1 "Jun 22, 2005" +.TH AWK 1 "Apr 20, 2020" .SH NAME awk \- pattern scanning and processing language .SH SYNOPSIS +.nf +\fB/usr/bin/awk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR] \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... + [\fIargument\fR]... +.fi + .LP .nf -\fB/usr/bin/awk\fR [\fB-f\fR \fIprogfile\fR] [\fB-F\fIc\fR\fR] [' \fIprog\fR '] [\fIparameters\fR] - [\fIfilename\fR]... +\fB/usr/bin/nawk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR] \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... + [\fIargument\fR]... .fi .LP .nf -\fB/usr/xpg4/bin/awk\fR [\fB-F\fR\fIcERE\fR] [\fB-v\fR \fIassignment\fR]... \fI\&'program'\fR \fB-f\fR \fIprogfile\fR... +\fB/usr/xpg4/bin/awk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR]... \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... [\fIargument\fR]... .fi .SH DESCRIPTION -.sp +NOTE: The \fBnawk\fR command is now the system default awk for illumos. .LP -The \fB/usr/xpg4/bin/awk\fR utility is described on the \fBnawk\fR(1) manual -page. +The \fB/usr/bin/awk\fR and \fB/usr/xpg4/bin/awk\fR utilities execute +\fIprogram\fRs written in the \fBawk\fR programming language, which is +specialized for textual data manipulation. A \fBawk\fR \fIprogram\fR is a +sequence of patterns and corresponding actions. The string specifying +\fIprogram\fR must be enclosed in single quotes (') to protect it from +interpretation by the shell. The sequence of pattern - action statements can be +specified in the command line as \fIprogram\fR or in one, or more, file(s) +specified by the \fB-f\fR\fIprogfile\fR option. When input is read that matches +a pattern, the action associated with the pattern is performed. .sp .LP -The \fB/usr/bin/awk\fR utility scans each input \fIfilename\fR for lines that -match any of a set of patterns specified in \fIprog\fR. The \fIprog\fR string -must be enclosed in single quotes (\fB a\'\fR) to protect it from the shell. -For each pattern in \fIprog\fR there can be an associated action performed when -a line of a \fIfilename\fR matches the pattern. The set of pattern-action -statements can appear literally as \fIprog\fR or in a file specified with the -\fB-f\fR\fI progfile\fR option. Input files are read in order; if there are no -files, the standard input is read. The file name \fB\&'\(mi'\fR means the -standard input. -.SH OPTIONS +Input is interpreted as a sequence of records. By default, a record is a line, +but this can be changed by using the \fBRS\fR built-in variable. Each record of +input is matched to each pattern in the \fIprogram\fR. For each pattern +matched, the associated action is executed. .sp .LP +The \fBawk\fR utility interprets each input record as a sequence of fields +where, by default, a field is a string of non-blank characters. This default +white-space field delimiter (blanks and/or tabs) can be changed by using the +\fBFS\fR built-in variable or the \fB-F\fR\fIERE\fR option. The \fBawk\fR +utility denotes the first field in a record \fB$1\fR, the second \fB$2\fR, and +so forth. The symbol \fB$0\fR refers to the entire record; setting any other +field causes the reevaluation of \fB$0\fR. Assigning to \fB$0\fR resets the +values of all fields and the \fBNF\fR built-in variable. + +.SH OPTIONS The following options are supported: .sp .ne 2 .na -\fB\fB-f\fR\fI progfile\fR \fR +\fB\fB-F\fR \fIERE\fR\fR .ad -.RS 16n -\fBawk\fR uses the set of patterns it reads from \fIprogfile\fR. +.RS 17n +Define the input field separator to be the extended regular expression +\fIERE\fR, before any input is read (can be a character). .RE .sp .ne 2 .na -\fB\fB-F\fR\fIc\fR \fR +\fB\fB-f\fR \fIprogfile\fR\fR .ad -.RS 16n -Uses the character \fIc\fR as the field separator (FS) character. See the -discussion of \fBFS\fR below. +.RS 17n +Specifies the pathname of the file \fIprogfile\fR containing a \fBawk\fR +program. If multiple instances of this option are specified, the concatenation +of the files specified as \fIprogfile\fR in the order specified is the +\fBawk\fR program. The \fBawk\fR program can alternatively be specified in +the command line as a single argument. .RE -.SH USAGE -.SS "Input Lines" +.sp +.ne 2 +.na +\fB\fB-v\fR \fIassignment\fR\fR +.ad +.RS 17n +The \fIassignment\fR argument must be in the same form as an \fIassignment\fR +operand. The assignment is of the form \fIvar=value\fR, where \fIvar\fR is the +name of one of the variables described below. The specified assignment occurs +before executing the \fBawk\fR program, including the actions associated with +\fBBEGIN\fR patterns (if any). Multiple occurrences of this option can be +specified. +.RE + +.sp +.ne 2 +.na +\fB\fB-safe\fR\fR +.ad +.RS 17n +When passed to \fBawk\fR, this flag will prevent the program from opening new +files or running child processes. The \fBENVIRON\fR array will also not be +initialized. +.RE + +.SH OPERANDS +The following operands are supported: +.sp +.ne 2 +.na +\fB\fIprogram\fR\fR +.ad +.RS 12n +If no \fB-f\fR option is specified, the first operand to \fBawk\fR is the text +of the \fBawk\fR program. The application supplies the \fIprogram\fR operand +as a single argument to \fBawk.\fR If the text does not end in a newline +character, \fBawk\fR interprets the text as if it did. +.RE + +.sp +.ne 2 +.na +\fB\fIargument\fR\fR +.ad +.RS 12n +Either of the following two types of \fIargument\fR can be intermixed: +.sp +.ne 2 +.na +\fB\fIfile\fR\fR +.ad +.RS 14n +A pathname of a file that contains the input to be read, which is matched +against the set of patterns in the program. If no \fIfile\fR operands are +specified, or if a \fIfile\fR operand is \fB\(mi\fR, the standard input is +used. +.RE + +.sp +.ne 2 +.na +\fB\fIassignment\fR\fR +.ad +.RS 14n +An operand that begins with an underscore or alphabetic character from the +portable character set, followed by a sequence of underscores, digits and +alphabetics from the portable character set, followed by the \fB=\fR character +specifies a variable assignment rather than a pathname. The characters before +the \fB=\fR represent the name of a \fBawk\fR variable. If that name is a +\fBawk\fR reserved word, the behavior is undefined. The characters following +the equal sign is interpreted as if they appeared in the \fBawk\fR program +preceded and followed by a double-quote (\fB"\fR) character, as a \fBSTRING\fR +token , except that if the last character is an unescaped backslash, it is +interpreted as a literal backslash rather than as the first character of the +sequence \fB\e\fR\&.. The variable is assigned the value of that \fBSTRING\fR +token. If the value is considered a \fInumeric\fRstring\fI,\fR the variable is +assigned its numeric value. Each such variable assignment is performed just +before the processing of the following \fIfile\fR, if any. Thus, an assignment +before the first \fBfile\fR argument is executed after the \fBBEGIN\fR actions +(if any), while an assignment after the last \fIfile\fR argument is executed +before the \fBEND\fR actions (if any). If there are no \fIfile\fR arguments, +assignments are executed before processing the standard input. +.RE + +.RE + +.SH INPUT FILES +Input files to the \fBawk\fR program from any of the following sources: +.RS +4 +.TP +.ie t \(bu +.el o +any \fIfile\fR operands or their equivalents, achieved by modifying the +\fBawk\fR variables \fBARGV\fR and \fBARGC\fR +.RE +.RS +4 +.TP +.ie t \(bu +.el o +standard input in the absence of any \fIfile\fR operands +.RE +.RS +4 +.TP +.ie t \(bu +.el o +arguments to the \fBgetline\fR function +.RE .sp .LP -Each input line is matched against the pattern portion of every pattern-action -statement; the associated action is performed for each matched pattern. Any -\fIfilename\fR of the form \fIvar=value\fR is treated as an assignment, not a -filename, and is executed at the time it would have been opened if it were a -filename. \fIVariables\fR assigned in this manner are not available inside a -\fBBEGIN\fR rule, and are assigned after previously specified files have been -read. +must be text files. Whether the variable \fBRS\fR is set to a value other than +a newline character or not, for these files, implementations support records +terminated with the specified separator up to \fB{LINE_MAX}\fR bytes and can +support longer records. .sp .LP -An input line is normally made up of fields separated by white spaces. (This -default can be changed by using the \fBFS\fR built-in variable or the -\fB-F\fR\fIc\fR option.) The default is to ignore leading blanks and to -separate fields by blanks and/or tab characters. However, if \fBFS\fR is -assigned a value that does not include any of the white spaces, then leading -blanks are not ignored. The fields are denoted \fB$1\fR, \fB$2\fR, -\fB\&.\|.\|.\fR\|; \fB$0\fR refers to the entire line. -.SS "Pattern-action Statements" +If \fB-\fR\fBf\fR \fIprogfile\fR is specified, the files named by each of the +\fIprogfile\fR option-arguments must be text files containing an \fBawk\fR +program. .sp .LP -A pattern-action statement has the form: +The standard input are used only if no \fIfile\fR operands are specified, or if +a \fIfile\fR operand is \fB\(mi\fR\&. + +.SH EXTENDED DESCRIPTION +A \fBawk\fR program is composed of pairs of the form: .sp .in +2 .nf -\fIpattern\fR\fB { \fR\fIaction\fR\fB } \fR +pattern { \fIaction\fR } .fi .in -2 -.sp .sp .LP -Either pattern or action can be omitted. If there is no action, the matching -line is printed. If there is no pattern, the action is performed on every input -line. Pattern-action statements are separated by newlines or semicolons. +Either the pattern or the action (including the enclosing brace characters) can +be omitted. Pattern-action statements are separated by a semicolon or by a +newline. +.sp +.LP +A missing pattern matches any record of input, and a missing action is +equivalent to an action that writes the matched record of input to standard +output. +.sp +.LP +Execution of the \fBawk\fR program starts by first executing the actions +associated with all \fBBEGIN\fR patterns in the order they occur in the +program. Then each \fIfile\fR operand (or standard input if no files were +specified) is processed by reading data from the file until a record separator +is seen (a newline character by default), splitting the current record into +fields using the current value of \fBFS\fR, evaluating each pattern in the +program in the order of occurrence, and executing the action associated with +each pattern that matches the current record. The action for a matching pattern +is executed before evaluating subsequent patterns. Last, the actions associated +with all \fBEND\fR patterns is executed in the order they occur in the program. + +.SS "Expressions in awk" +Expressions describe computations used in \fIpatterns\fR and \fIactions\fR. In +the following table, valid expression operations are given in groups from +highest precedence first to lowest precedence last, with equal-precedence +operators grouped between horizontal lines. In expression evaluation, where the +grammar is formally ambiguous, higher precedence operators are evaluated before +lower precedence operators. In this table \fIexpr,\fR \fIexpr1,\fR +\fIexpr2,\fR and \fIexpr3\fR represent any expression, while \fIlvalue\fR +represents any entity that can be assigned to (that is, on the left side of an +assignment operator). +.sp + +.sp +.TS +c c c c +l l l l . +\fBSyntax\fR \fBName\fR \fBType of Result\fR \fBAssociativity\fR +_ +( \fIexpr\fR ) Grouping type of \fIexpr\fR n/a +_ +$\fIexpr\fR Field reference string n/a +_ +++ \fIlvalue\fR Pre-increment numeric n/a +\(mi\(mi \fIlvalue\fR Pre-decrement numeric n/a +\fIlvalue\fR ++ Post-increment numeric n/a +\fIlvalue\fR \(mi\(mi Post-decrement numeric n/a +_ +\fIexpr\fR ^ \fIexpr\fR Exponentiation numeric right +_ +! \fIexpr\fR Logical not numeric n/a ++ \fIexpr\fR Unary plus numeric n/a +\(mi \fIexpr\fR Unary minus numeric n/a +_ +\fIexpr\fR * \fIexpr\fR Multiplication numeric left +\fIexpr\fR / \fIexpr\fR Division numeric left +\fIexpr\fR % \fIexpr\fR Modulus numeric left +_ +\fIexpr\fR + \fIexpr\fR Addition numeric left +\fIexpr\fR \(mi \fIexpr\fR Subtraction numeric left +_ +\fIexpr\fR \fIexpr\fR String concatenation string left +_ +\fIexpr\fR < \fIexpr\fR Less than numeric none +\fIexpr\fR <= \fIexpr\fR Less than or equal to numeric none +\fIexpr\fR != \fIexpr\fR Not equal to numeric none +\fIexpr\fR == \fIexpr\fR Equal to numeric none +\fIexpr\fR > \fIexpr\fR Greater than numeric none +\fIexpr\fR >= \fIexpr\fR Greater than or equal to numeric none +_ +\fIexpr\fR ~ \fIexpr\fR ERE match numeric none +\fIexpr\fR !~ \fIexpr\fR ERE non-match numeric none +_ +\fIexpr\fR in array Array membership numeric left +( \fIindex\fR ) in Multi-dimension array numeric left + \fIarray\fR membership +_ +\fBexpr\fR && \fIexpr\fR Logical AND numeric left +_ +\fBexpr\fR |\|| \fIexpr\fR Logical OR numeric left +_ +\fIexpr1\fR ? \fIexpr2\fR Conditional expression type of selected right + : \fIexpr3\fR \fIexpr2\fR or \fIexpr3\fR +_ +\fIlvalue\fR ^= \fIexpr\fR Exponentiation numeric right + assignment +\fIlvalue\fR %= \fIexpr\fR Modulus assignment numeric right +\fIlvalue\fR *= \fIexpr\fR Multiplication numeric right + assignment +\fIlvalue\fR /= \fIexpr\fR Division assignment numeric right +\fIlvalue\fR += \fIexpr\fR Addition assignment numeric right +\fIlvalue\fR \(mi= \fIexpr\fR Subtraction assignment numeric right +\fIlvalue\fR = \fIexpr\fR Assignment type of \fIexpr\fR right +.TE + .sp .LP -Patterns are arbitrary Boolean combinations ( \fB!\fR, ||, \fB&&\fR, and -parentheses) of relational expressions and regular expressions. A relational -expression is one of the following: +Each expression has either a string value, a numeric value or both. Except as +stated for specific contexts, the value of an expression is implicitly +converted to the type needed for the context in which it is used. A string +value is converted to a numeric value by the equivalent of the following calls: .sp .in +2 .nf -\fIexpression relop expression -expression matchop regular_expression\fR +setlocale(LC_NUMERIC, ""); +\fInumeric_value\fR = atof(\fIstring_value\fR); .fi .in -2 .sp .LP -where a \fIrelop\fR is any of the six relational operators in C, and a -\fImatchop\fR is either \fB~\fR (contains) or \fB!~\fR (does not contain). An -\fIexpression\fR is an arithmetic expression, a relational expression, the -special expression +A numeric value that is exactly equal to the value of an integer is converted +to a string by the equivalent of a call to the \fBsprintf\fR function with the +string \fB%d\fR as the \fBfmt\fR argument and the numeric value being converted +as the first and only \fIexpr\fR argument. Any other numeric value is +converted to a string by the equivalent of a call to the \fBsprintf\fR function +with the value of the variable \fBCONVFMT\fR as the \fBfmt\fR argument and the +numeric value being converted as the first and only \fIexpr\fR argument. +.sp +.LP +A string value is considered to be a \fInumeric string\fR in the following +case: +.RS +4 +.TP +1. +Any leading and trailing blank characters is ignored. +.RE +.RS +4 +.TP +2. +If the first unignored character is a \fB+\fR or \fB\(mi\fR, it is ignored. +.RE +.RS +4 +.TP +3. +If the remaining unignored characters would be lexically recognized as a +\fBNUMBER\fR token, the string is considered a \fInumeric string\fR. +.RE +.sp +.LP +If a \fB\(mi\fR character is ignored in the above steps, the numeric value of +the \fInumeric string\fR is the negation of the numeric value of the recognized +\fBNUMBER\fR token. Otherwise the numeric value of the \fInumeric string\fR is +the numeric value of the recognized \fBNUMBER\fR token. Whether or not a string +is a \fInumeric string\fR is relevant only in contexts where that term is used +in this section. +.sp +.LP +When an expression is used in a Boolean context, if it has a numeric value, a +value of zero is treated as false and any other value is treated as true. +Otherwise, a string value of the null string is treated as false and any other +value is treated as true. A Boolean context is one of the following: +.RS +4 +.TP +.ie t \(bu +.el o +the first subexpression of a conditional expression. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +an expression operated on by logical NOT, logical \fBAND,\fR or logical OR. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +the second expression of a \fBfor\fR statement. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +the expression of an \fBif\fR statement. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +the expression of the \fBwhile\fR clause in either a \fBwhile\fR or \fBdo\fR +\fB\&.\|.\|.\fR \fBwhile\fR statement. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +an expression used as a pattern (as in Overall Program Structure). +.RE +.sp +.LP +The \fBawk\fR language supplies arrays that are used for storing numbers or +strings. Arrays need not be declared. They are initially empty, and their sizes +changes dynamically. The subscripts, or element identifiers, are strings, +providing a type of associative array capability. An array name followed by a +subscript within square brackets can be used as an \fIlvalue\fR and as an +expression, as described in the grammar. Unsubscripted array names are used in +only the following contexts: +.RS +4 +.TP +.ie t \(bu +.el o +a parameter in a function definition or function call. +.RE +.RS +4 +.TP +.ie t \(bu +.el o +the \fBNAME\fR token following any use of the keyword \fBin\fR. +.RE +.sp +.LP +A valid array \fIindex\fR consists of one or more comma-separated expressions, +similar to the way in which multi-dimensional arrays are indexed in some +programming languages. Because \fBawk\fR arrays are really one-dimensional, +such a comma-separated list is converted to a single string by concatenating +the string values of the separate expressions, each separated from the other by +the value of the \fBSUBSEP\fR variable. +.sp +.LP +Thus, the following two index operations are equivalent: .sp .in +2 .nf -\fIvar \fRin \fIarray\fR +var[expr1, expr2, ... exprn] +var[expr1 SUBSEP expr2 SUBSEP ... SUBSEP exprn] .fi .in -2 .sp .LP -or a Boolean combination of these. +A multi-dimensioned \fIindex\fR used with the \fBin\fR operator must be put in +parentheses. The \fBin\fR operator, which tests for the existence of a +particular array element, does not create the element if it does not exist. +Any other reference to a non-existent array element automatically creates it. + +.SS "Variables and Special Variables" +Variables can be used in an \fBawk\fR program by referencing them. With the +exception of function parameters, they are not explicitly declared. +Uninitialized scalar variables and array elements have both a numeric value of +zero and a string value of the empty string. .sp .LP -Regular expressions are as in \fBegrep\fR(1). In patterns they must be -surrounded by slashes. Isolated regular expressions in a pattern apply to the -entire line. Regular expressions can also occur in relational expressions. A -pattern can consist of two patterns separated by a comma; in this case, the -action is performed for all lines between the occurrence of the first pattern -to the occurrence of the second pattern. +Field variables are designated by a \fB$\fR followed by a number or numerical +expression. The effect of the field number \fIexpression\fR evaluating to +anything other than a non-negative integer is unspecified. Uninitialized +variables or string values need not be converted to numeric values in this +context. New field variables are created by assigning a value to them. +References to non-existent fields (that is, fields after \fB$NF\fR) produce the +null string. However, assigning to a non-existent field (for example, +\fB$(NF+2) = 5\fR) increases the value of \fBNF\fR, create any intervening +fields with the null string as their values and cause the value of \fB$0\fR to +be recomputed, with the fields being separated by the value of \fBOFS\fR. Each +field variable has a string value when created. If the string, with any +occurrence of the decimal-point character from the current locale changed to a +period character, is considered a \fInumeric string\fR (see \fBExpressions in +awk\fR above), the field variable also has the numeric value of the \fInumeric +string\fR. + +.SS "/usr/bin/awk, /usr/xpg4/bin/awk" +\fBawk\fR sets the following special variables that are supported by both +\fB/usr/bin/awk\fR and \fB/usr/xpg4/bin/awk\fR: .sp -.LP -The special patterns \fBBEGIN\fR and \fBEND\fR can be used to capture control -before the first input line has been read and after the last input line has -been read respectively. These keywords do not combine with any other patterns. -.SS "Built-in Variables" +.ne 2 +.na +\fB\fBARGC\fR\fR +.ad +.RS 12n +The number of elements in the \fBARGV\fR array. +.RE + .sp -.LP -Built-in variables include: +.ne 2 +.na +\fB\fBARGV\fR\fR +.ad +.RS 12n +An array of command line arguments, excluding options and the \fIprogram\fR +argument, numbered from zero to \fBARGC\fR\(mi1. +.sp +The arguments in \fBARGV\fR can be modified or added to; \fBARGC\fR can be +altered. As each input file ends, \fBawk\fR treats the next non-null element +of \fBARGV\fR, up to the current value of \fBARGC\fR\(mi1, inclusive, as the +name of the next input file. Setting an element of \fBARGV\fR to null means +that it is not treated as an input file. The name \fB\(mi\fR indicates the +standard input. If an argument matches the format of an \fIassignment\fR +operand, this argument is treated as an assignment rather than a \fIfile\fR +argument. +.RE + +.sp +.ne 2 +.na +\fB\fBCONVFMT\fR\fR +.ad +.RS 12n +The \fBprintf\fR format for converting numbers to strings (except for output +statements, where \fBOFMT\fR is used). The default is \fB%.6g\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBENVIRON\fR\fR +.ad +.RS 12n +The variable \fBENVIRON\fR is an array representing the value of the +environment. The indices of the array are strings consisting of the names of +the environment variables, and the value of each array element is a string +consisting of the value of that variable. If the value of an environment +variable is considered a \fInumeric string\fR, the array element also has its +numeric value. +.sp +In all cases where \fBawk\fR behavior is affected by environment variables +(including the environment of any commands that \fBawk\fR executes via the +\fBsystem\fR function or via pipeline redirections with the \fBprint\fR +statement, the \fBprintf\fR statement, or the \fBgetline\fR function), the +environment used is the environment at the time \fBawk\fR began executing. +.RE + +.sp +.ne 2 +.na +\fB\fBFILENAME\fR\fR +.ad +.RS 12n +A pathname of the current input file. Inside a \fBBEGIN\fR action the value is +undefined. Inside an \fBEND\fR action the value is the name of the last input +file processed. +.RE + +.sp +.ne 2 +.na +\fB\fBFNR\fR\fR +.ad +.RS 12n +The ordinal number of the current record in the current file. Inside a +\fBBEGIN\fR action the value is zero. Inside an \fBEND\fR action the value is +the number of the last record processed in the last file processed. +.RE + .sp .ne 2 .na -\fB\fBFILENAME\fR \fR +\fB\fBFS\fR\fR .ad -.RS 13n -name of the current input file +.RS 12n +Input field separator regular expression; a space character by default. .RE .sp .ne 2 .na -\fB\fBFS\fR \fR +\fB\fBNF\fR\fR .ad -.RS 13n -input field separator regular expression (default blank and tab) +.RS 12n +The number of fields in the current record. Inside a \fBBEGIN\fR action, the +use of \fBNF\fR is undefined unless a \fBgetline\fR function without a +\fIvar\fR argument is executed previously. Inside an \fBEND\fR action, \fBNF\fR +retains the value it had for the last record read, unless a subsequent, +redirected, \fBgetline\fR function without a \fIvar\fR argument is performed +prior to entering the \fBEND\fR action. .RE .sp .ne 2 .na -\fB\fBNF\fR \fR +\fB\fBNR\fR\fR .ad -.RS 13n -number of fields in the current record +.RS 12n +The ordinal number of the current record from the start of input. Inside a +\fBBEGIN\fR action the value is zero. Inside an \fBEND\fR action the value is +the number of the last record processed. .RE .sp .ne 2 .na -\fB\fBNR\fR \fR +\fB\fBOFMT\fR\fR .ad -.RS 13n -ordinal number of the current record +.RS 12n +The \fBprintf\fR format for converting numbers to strings in output statements +\fB"%.6g"\fR by default. The result of the conversion is unspecified if the +value of \fBOFMT\fR is not a floating-point format specification. .RE .sp .ne 2 .na -\fB\fBOFMT\fR \fR +\fB\fBOFS\fR\fR .ad -.RS 13n -output format for numbers (default \fB%.6g\fR) +.RS 12n +The \fBprint\fR statement output field separator; a space character by default. .RE .sp .ne 2 .na -\fB\fBOFS\fR \fR +\fB\fBORS\fR\fR .ad -.RS 13n -output field separator (default blank) +.RS 12n +The \fBprint\fR output record separator; a newline character by default. .RE .sp .ne 2 .na -\fB\fBORS\fR \fR +\fB\fBRLENGTH\fR\fR .ad -.RS 13n -output record separator (default new-line) +.RS 12n +The length of the string matched by the \fBmatch\fR function. .RE .sp .ne 2 .na -\fB\fBRS\fR \fR +\fB\fBRS\fR\fR .ad -.RS 13n -input record separator (default new-line) +.RS 12n +The first character of the string value of \fBRS\fR is the input record +separator; a newline character by default. If \fBRS\fR contains more than one +character, the results are unspecified. If \fBRS\fR is null, then records are +separated by sequences of one or more blank lines. Leading or trailing blank +lines do not produce empty records at the beginning or end of input, and the +field separator is always newline, no matter what the value of \fBFS\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBRSTART\fR\fR +.ad +.RS 12n +The starting position of the string matched by the \fBmatch\fR function, +numbering from 1. This is always equivalent to the return value of the +\fBmatch\fR function. +.RE + +.sp +.ne 2 +.na +\fB\fBSUBSEP\fR\fR +.ad +.RS 12n +The subscript separator string for multi-dimensional arrays. The default value +is \fB\e034\fR\&. +.RE + +.SS "/usr/bin/awk" +The following variable is supported for \fB/usr/bin/awk\fR only: +.sp +.ne 2 +.na +\fB\fBRT\fR\fR +.ad +.RS 12n +The record terminator for the most recent record read. For most records this +will be the same value as \fBRS\fR. At the end of a file with no trailing +separator value, though, this will be set to the empty string (\fB""\fR). +.RE + +.SS "Regular Expressions" +The \fBawk\fR utility makes use of the extended regular expression notation +(see \fBregex\fR(5)) except that it allows the use of C-language conventions to +escape special characters within the EREs, namely \fB\e\e\fR, \fB\ea\fR, +\fB\eb\fR, \fB\ef\fR, \fB\en\fR, \fB\er\fR, \fB\et\fR, \fB\ev\fR, and those +specified in the following table. These escape sequences are recognized both +inside and outside bracket expressions. Note that records need not be +separated by newline characters and string constants can contain newline +characters, so even the \fB\en\fR sequence is valid in \fBawk\fR EREs. Using +a slash character within the regular expression requires escaping as shown in +the table below: +.sp + +.sp +.TS +l l l +l l l . +\fBEscape Sequence\fR \fBDescription\fR \fBMeaning\fR +_ +\fB\e"\fR Backslash quotation-mark Quotation-mark character +_ +\fB\e/\fR Backslash slash Slash character +_ +\fB\e\fR\fIddd\fR T{ +A backslash character followed by the longest sequence of one, two, or three octal-digit characters (01234567). If all of the digits are 0, (that is, representation of the NULL character), the behavior is undefined. +T} T{ +The character encoded by the one-, two- or three-digit octal integer. Multi-byte characters require multiple, concatenated escape sequences, including the leading \e for each byte. +T} +_ +\fB\e\fR\fIc\fR T{ +A backslash character followed by any character not described in this table or special characters (\fB\e\e\fR, \fB\ea\fR, \fB\eb\fR, \fB\ef\fR, \fB\en\fR, \fB\er\fR, \fB\et\fR, \fB\ev\fR). +T} Undefined +.TE + +.sp +.LP +A regular expression can be matched against a specific field or string by using +one of the two regular expression matching operators, \fB~\fR and \fB!\|~\fR. +These operators interpret their right-hand operand as a regular expression and +their left-hand operand as a string. If the regular expression matches the +string, the \fB~\fR expression evaluates to the value \fB1\fR, and the +\fB!\|~\fR expression evaluates to the value \fB0\fR. If the regular expression +does not match the string, the \fB~\fR expression evaluates to the value +\fB0\fR, and the \fB!\|~\fR expression evaluates to the value \fB1\fR. If the +right-hand operand is any expression other than the lexical token \fBERE\fR, +the string value of the expression is interpreted as an extended regular +expression, including the escape conventions described above. Notice that these +same escape conventions also are applied in the determining the value of a +string literal (the lexical token \fBSTRING\fR), and is applied a second time +when a string literal is used in this context. +.sp +.LP +When an \fBERE\fR token appears as an expression in any context other than as +the right-hand of the \fB~\fR or \fB!\|~\fR operator or as one of the built-in +function arguments described below, the value of the resulting expression is +the equivalent of: +.sp +.in +2 +.nf +$0 ~ /\fIere\fR/ +.fi +.in -2 + +.sp +.LP +The \fIere\fR argument to the \fBgsub,\fR \fBmatch,\fR \fBsub\fR functions, and +the \fIfs\fR argument to the \fBsplit\fR function (see \fBString Functions\fR) +is interpreted as extended regular expressions. These can be either \fBERE\fR +tokens or arbitrary expressions, and are interpreted in the same manner as the +right-hand side of the \fB~\fR or \fB!\|~\fR operator. +.sp +.LP +An extended regular expression can be used to separate fields by using the +\fB-F\fR \fIERE\fR option or by assigning a string containing the expression to +the built-in variable \fBFS\fR. The default value of the \fBFS\fR variable is a +single space character. The following describes \fBFS\fR behavior: +.RS +4 +.TP +1. +If \fBFS\fR is a single character: +.RS +4 +.TP +.ie t \(bu +.el o +If \fBFS\fR is the space character, skip leading and trailing blank characters; +fields are delimited by sets of one or more blank characters. .RE +.RS +4 +.TP +.ie t \(bu +.el o +Otherwise, if \fBFS\fR is any other character \fIc\fR, fields are delimited by +each single occurrence of \fIc\fR. +.RE +.RE +.RS +4 +.TP +2. +Otherwise, the string value of \fBFS\fR is considered to be an extended +regular expression. Each occurrence of a sequence matching the extended regular +expression delimits fields. +.RE +.sp +.LP +Except in the \fBgsub\fR, \fBmatch\fR, \fBsplit\fR, and \fBsub\fR built-in +functions, regular expression matching is based on input records. That is, +record separator characters (the first character of the value of the variable +\fBRS\fR, a newline character by default) cannot be embedded in the expression, +and no expression matches the record separator character. If the record +separator is not a newline character, newline characters embedded in the +expression can be matched. In those four built-in functions, regular expression +matching are based on text strings. So, any character (including the newline +character and the record separator) can be embedded in the pattern and an +appropriate pattern matches any character. However, in all \fBawk\fR regular +expression matching, the use of one or more NULL characters in the pattern, +input record or text string produces undefined results. + +.SS "Patterns" +A \fIpattern\fR is any valid \fIexpression,\fR a range specified by two +expressions separated by comma, or one of the two special patterns \fBBEGIN\fR +or \fBEND\fR. +.SS "Special Patterns" +The \fBawk\fR utility recognizes two special patterns, \fBBEGIN\fR and +\fBEND\fR. Each \fBBEGIN\fR pattern is matched once and its associated action +executed before the first record of input is read (except possibly by use of +the \fBgetline\fR function in a prior \fBBEGIN\fR action) and before command +line assignment is done. Each \fBEND\fR pattern is matched once and its +associated action executed after the last record of input has been read. These +two patterns have associated actions. +.sp +.LP +\fBBEGIN\fR and \fBEND\fR do not combine with other patterns. Multiple +\fBBEGIN\fR and \fBEND\fR patterns are allowed. The actions associated with the +\fBBEGIN\fR patterns are executed in the order specified in the program, as are +the \fBEND\fR actions. An \fBEND\fR pattern can precede a \fBBEGIN\fR pattern +in a program. .sp .LP +If an \fBawk\fR program consists of only actions with the pattern \fBBEGIN\fR, +and the \fBBEGIN\fR action contains no \fBgetline\fR function, \fBawk\fR exits +without reading its input when the last statement in the last \fBBEGIN\fR +action is executed. If an \fBawk\fR program consists of only actions with the +pattern \fBEND\fR or only actions with the patterns \fBBEGIN\fR and \fBEND\fR, +the input is read before the statements in the \fBEND\fR actions are executed. + +.SS "Expression Patterns" +An expression pattern is evaluated as if it were an expression in a Boolean +context. If the result is true, the pattern is considered to match, and the +associated action (if any) is executed. If the result is false, the action is +not executed. + +.SS "Pattern Ranges" +A pattern range consists of two expressions separated by a comma. In this case, +the action is performed for all records between a match of the first expression +and the following match of the second expression, inclusive. At this point, the +pattern range can be repeated starting at input records subsequent to the end +of the matched range. + +.SS "Actions" An action is a sequence of statements. A statement can be one of the following: .sp .in +2 @@ -265,50 +885,213 @@ while ( \fIexpression\fR ) \fIstatement\fR do \fIstatement\fR while ( \fIexpression\fR ) for ( \fIexpression\fR ; \fIexpression\fR ; \fIexpression\fR ) \fIstatement\fR for ( \fIvar\fR in \fIarray\fR ) \fIstatement\fR +delete \fIarray\fR[\fIsubscript\fR] #delete an array element +delete \fIarray\fR #delete all elements within an array break continue { [ \fIstatement\fR ] .\|.\|. } -\fIexpression\fR # commonly variable = expression +\fIexpression\fR # commonly variable = expression print [ \fIexpression-list\fR ] [ >\fIexpression\fR ] printf format [ ,\fIexpression-list\fR ] [ >\fIexpression\fR ] -next # skip remaining patterns on this input line -exit [expr] # skip the rest of the input; exit status is expr +next # skip remaining patterns on this input line +nextfile # skip remaining patterns on this input file +exit [expr] # skip the rest of the input; exit status is expr +return [expr] .fi .in -2 .sp .LP -Statements are terminated by semicolons, newlines, or right braces. An empty -expression-list stands for the whole input line. Expressions take on string or -numeric values as appropriate, and are built using the operators \fB+\fR, -\fB\(mi\fR, \fB*\fR, \fB/\fR, \fB%\fR, \fB^\fR and concatenation (indicated by -a blank). The operators \fB++\fR, \fB\(mi\(mi\fR, \fB+=\fR, \fB\(mi=\fR, -\fB*=\fR, \fB/=\fR, \fB%=\fR, \fB^=\fR, \fB>\fR, \fB>=\fR, \fB<\fR, \fB<=\fR, -\fB==\fR, \fB!=\fR, and \fB?:\fR are also available in expressions. Variables -can be scalars, array elements (denoted x[i]), or fields. Variables are -initialized to the null string or zero. Array subscripts can be any string, not -necessarily numeric; this allows for a form of associative memory. String -constants are quoted (\fB""\fR), with the usual C escapes recognized within. +Any single statement can be replaced by a statement list enclosed in braces. +The statements are terminated by newline characters or semicolons, and are +executed sequentially in the order that they appear. +.sp +.LP +The \fBnext\fR statement causes all further processing of the current input +record to be abandoned. The behavior is undefined if a \fBnext\fR statement +appears or is invoked in a \fBBEGIN\fR or \fBEND\fR action. +.sp +.LP +The \fBnextfile\fR statement is similar to \fBnext\fR, but also skips all other +records in the current file, and moves on to processing the next input file if +available (or exits the program if there are none). (Note that this keyword is +not supported by \fB/usr/xpg4/bin/awk\fR.) .sp .LP -The \fBprint\fR statement prints its arguments on the standard output, or on a -file if \fB>\fR\fIexpression\fR is present, or on a pipe if '\fB|\fR\fIcmd\fR' -is present. The output resulted from the print statement is terminated by the -output record separator with each argument separated by the current output -field separator. The \fBprintf\fR statement formats its expression list -according to the format (see \fBprintf\fR(3C)). -.SS "Built-in Functions" +The \fBexit\fR statement invokes all \fBEND\fR actions in the order in which +they occur in the program source and then terminate the program without reading +further input. An \fBexit\fR statement inside an \fBEND\fR action terminates +the program without further execution of \fBEND\fR actions. If an expression +is specified in an \fBexit\fR statement, its numeric value is the exit status +of \fBawk\fR, unless subsequent errors are encountered or a subsequent +\fBexit\fR statement with an expression is executed. + +.SS "Output Statements" +Both \fBprint\fR and \fBprintf\fR statements write to standard output by +default. The output is written to the location specified by +\fIoutput_redirection\fR if one is supplied, as follows: +.sp +.in +2 +.nf +\fB>\fR \fIexpression\fR\fB>>\fR \fIexpression\fR\fB|\fR \fIexpression\fR +.fi +.in -2 + .sp .LP -The arithmetic functions are as follows: +In all cases, the \fIexpression\fR is evaluated to produce a string that is +used as a full pathname to write into (for \fB>\fR or \fB>>\fR) or as a command +to be executed (for \fB|\fR). Using the first two forms, if the file of that +name is not currently open, it is opened, creating it if necessary and using +the first form, truncating the file. The output then is appended to the file. +As long as the file remains open, subsequent calls in which \fIexpression\fR +evaluates to the same string value simply appends output to the file. The file +remains open until the \fBclose\fR function, which is called with an expression +that evaluates to the same string value. +.sp +.LP +The third form writes output onto a stream piped to the input of a command. The +stream is created if no stream is currently open with the value of +\fIexpression\fR as its command name. The stream created is equivalent to one +created by a call to the \fBpopen\fR(3C) function with the value of +\fIexpression\fR as the \fIcommand\fR argument and a value of \fBw\fR as the +\fImode\fR argument. As long as the stream remains open, subsequent calls in +which \fIexpression\fR evaluates to the same string value writes output to the +existing stream. The stream remains open until the \fBclose\fR function is +called with an expression that evaluates to the same string value. At that +time, the stream is closed as if by a call to the \fBpclose\fR function. +.sp +.LP +These output statements take a comma-separated list of \fIexpression\fR \fIs\fR +referred in the grammar by the non-terminal symbols \fBexpr_list,\fR +\fBprint_expr_list\fR or \fBprint_expr_list_opt.\fR This list is referred to +here as the \fIexpression list\fR, and each member is referred to as an +\fIexpression argument\fR. +.sp +.LP +The \fBprint\fR statement writes the value of each expression argument onto the +indicated output stream separated by the current output field separator (see +variable \fBOFS\fR above), and terminated by the output record separator (see +variable \fBORS\fR above). All expression arguments is taken as strings, being +converted if necessary; with the exception that the \fBprintf\fR format in +\fBOFMT\fR is used instead of the value in \fBCONVFMT\fR. An empty expression +list stands for the whole input record \fB(\fR$0\fB)\fR. +.sp +.LP +The \fBprintf\fR statement produces output based on a notation similar to the +File Format Notation used to describe file formats in this document Output is +produced as specified with the first expression argument as the string +\fBformat\fR and subsequent expression arguments as the strings \fBarg1\fR to +\fBargn,\fR inclusive, with the following exceptions: +.RS +4 +.TP +1. +The \fIformat\fR is an actual character string rather than a graphical +representation. Therefore, it cannot contain empty character positions. The +space character in the \fIformat\fR string, in any context other than a +\fIflag\fR of a conversion specification, is treated as an ordinary character +that is copied to the output. +.RE +.RS +4 +.TP +2. +If the character set contains a Delta character and that character appears +in the \fIformat\fR string, it is treated as an ordinary character that is +copied to the output. +.RE +.RS +4 +.TP +3. +The \fIescape sequences\fR beginning with a backslash character is treated +as sequences of ordinary characters that are copied to the output. Note that +these same sequences is interpreted lexically by \fBawk\fR when they appear in +literal strings, but they is not treated specially by the \fBprintf\fR +statement. +.RE +.RS +4 +.TP +4. +A \fIfield width\fR or \fIprecision\fR can be specified as the \fB*\fR +character instead of a digit string. In this case the next argument from the +expression list is fetched and its numeric value taken as the field width or +precision. +.RE +.RS +4 +.TP +5. +The implementation does not precede or follow output from the \fBd\fR or +\fBu\fR conversion specifications with blank characters not specified by the +\fIformat\fR string. +.RE +.RS +4 +.TP +6. +The implementation does not precede output from the \fBo\fR conversion +specification with leading zeros not specified by the \fIformat\fR string. +.RE +.RS +4 +.TP +7. +For the \fBc\fR conversion specification: if the argument has a numeric +value, the character whose encoding is that value is output. If the value is +zero or is not the encoding of any character in the character set, the behavior +is undefined. If the argument does not have a numeric value, the first +character of the string value is output; if the string does not contain any +characters the behavior is undefined. +.RE +.RS +4 +.TP +8. +For each conversion specification that consumes an argument, the next +expression argument is evaluated. With the exception of the \fBc\fR conversion, +the value is converted to the appropriate type for the conversion +specification. +.RE +.RS +4 +.TP +9. +If there are insufficient expression arguments to satisfy all the conversion +specifications in the \fIformat\fR string, the behavior is undefined. +.RE +.RS +4 +.TP +10. +If any character sequence in the \fIformat\fR string begins with a % +character, but does not form a valid conversion specification, the behavior is +unspecified. +.RE +.sp +.LP +Both \fBprint\fR and \fBprintf\fR can output at least \fB{LINE_MAX}\fR bytes. + +.SS "Functions" +The \fBawk\fR language has a variety of built-in functions: arithmetic, +string, input/output and general. + +.SS "Arithmetic Functions" +The arithmetic functions, except for \fBint\fR, are based on the \fBISO\fR +\fBC\fR standard. The behavior is undefined in cases where the \fBISO\fR +\fBC\fR standard specifies that an error be returned or that the behavior is +undefined. Although the grammar permits built-in functions to appear with no +arguments or parentheses, unless the argument or parentheses are indicated as +optional in the following list (by displaying them within the \fB[ ]\fR +brackets), such use is undefined. +.sp +.ne 2 +.na +\fB\fBatan2(\fR\fIy\fR,\fIx\fR\fB)\fR\fR +.ad +.RS 17n +Return arctangent of \fIy\fR/\fIx\fR. +.RE + .sp .ne 2 .na \fB\fBcos\fR(\fIx\fR)\fR .ad -.RS 11n -Return cosine of \fIx\fR, where \fIx\fR is in radians. (In -\fB/usr/xpg4/bin/awk\fR only. See \fBnawk\fR(1).) +.RS 17n +Return cosine of \fIx,\fR where \fIx\fR is in radians. .RE .sp @@ -316,9 +1099,8 @@ Return cosine of \fIx\fR, where \fIx\fR is in radians. (In .na \fB\fBsin\fR(\fIx\fR)\fR .ad -.RS 11n -Return sine of \fIx\fR, where \fIx\fR is in radians. (In -\fB/usr/xpg4/bin/awk\fR only. See \fBnawk\fR(1).) +.RS 17n +Return sine of \fIx,\fR where \fIx\fR is in radians. .RE .sp @@ -326,7 +1108,7 @@ Return sine of \fIx\fR, where \fIx\fR is in radians. (In .na \fB\fBexp\fR(\fIx\fR)\fR .ad -.RS 11n +.RS 17n Return the exponential function of \fIx\fR. .RE @@ -335,7 +1117,7 @@ Return the exponential function of \fIx\fR. .na \fB\fBlog\fR(\fIx\fR)\fR .ad -.RS 11n +.RS 17n Return the natural logarithm of \fIx\fR. .RE @@ -344,7 +1126,7 @@ Return the natural logarithm of \fIx\fR. .na \fB\fBsqrt\fR(\fIx\fR)\fR .ad -.RS 11n +.RS 17n Return the square root of \fIx\fR. .RE @@ -353,191 +1135,558 @@ Return the square root of \fIx\fR. .na \fB\fBint\fR(\fIx\fR)\fR .ad -.RS 11n -Truncate its argument to an integer. It is truncated toward \fB0\fR when -\fIx\fR >\fB 0\fR. +.RS 17n +Truncate its argument to an integer. It is truncated toward 0 when \fIx\fR > 0. .RE .sp -.LP -The string functions are as follows: +.ne 2 +.na +\fB\fBrand()\fR\fR +.ad +.RS 17n +Return a random number \fIn\fR, such that 0 \(<= \fIn\fR < 1. +.RE + +.sp +.ne 2 +.na +\fB\fBsrand\fR([\fBexpr\fR])\fR +.ad +.RS 17n +Set the seed value for \fBrand\fR to \fIexpr\fR or use the time of day if +\fIexpr\fR is omitted. The previous seed value is returned. +.RE + +.SS "String Functions" +The string functions in the following list shall be supported. Although the +grammar permits built-in functions to appear with no arguments or parentheses, +unless the argument or parentheses are indicated as optional in the following +list (by displaying them within the \fB[ ]\fR brackets), such use is undefined. +.sp +.ne 2 +.na +\fB\fBgsub\fR(\fIere\fR,\fIrepl\fR[,\|\fIin\fR])\fR +.ad +.sp .6 +.RS 4n +Behave like \fBsub\fR (see below), except that it replaces all occurrences of +the regular expression (like the \fBed\fR utility global substitute) in +\fB$0\fR or in the \fIin\fR argument, when specified. +.RE + .sp .ne 2 .na -\fB\fBindex(\fR\fIs\fR\fB, \fR\fIt\fR\fB)\fR\fR +\fB\fBindex\fR(\fIs\fR,\fIt\fR)\fR .ad .sp .6 .RS 4n -Return the position in string \fIs\fR where string \fIt\fR first occurs, or -\fB0\fR if it does not occur at all. +Return the position, in characters, numbering from 1, in string \fIs\fR where +string \fIt\fR first occurs, or zero if it does not occur at all. .RE .sp .ne 2 .na -\fB\fBint(\fR\fIs\fR\fB)\fR\fR +\fB\fBlength\fR[([\fIv\fR])]\fR .ad .sp .6 .RS 4n -truncates \fIs\fR to an integer value. If \fIs\fR is not specified, $0 is used. +Given no argument, this function returns the length of the whole record, +\fB$0\fR. If given an array as an argument (and using \fB/usr/bin/awk\fR), +then this returns the number of elements it contains. Otherwise, this function +interprets the argument as a string (performing any needed conversions) and +returns its length in characters. .RE .sp .ne 2 .na -\fB\fBlength(\fR\fIs\fR\fB)\fR\fR +\fB\fBmatch\fR(\fIs\fR,\fIere\fR)\fR .ad .sp .6 .RS 4n -Return the length of its argument taken as a string, or of the whole line if -there is no argument. +Return the position, in characters, numbering from 1, in string \fIs\fR where +the extended regular expression \fIere\fR occurs, or zero if it does not occur +at all. \fBRSTART\fR is set to the starting position (which is the same as the +returned value), zero if no match is found; \fBRLENGTH\fR is set to the length +of the matched string, \(mi1 if no match is found. .RE .sp .ne 2 .na -\fB\fBsplit(\fR\fIs\fR, \fIa\fR, \fIfs\fR\fB)\fR\fR +\fB\fBsplit\fR(\fIs\fR,\fIa\fR[,\|\fIfs\fR])\fR .ad .sp .6 .RS 4n -Split the string \fIs\fR into array elements \fIa\fR[\fI1\fR], -\fIa\fR[\fI2\fR], \|.\|.\|. \fIa\fR[\fIn\fR], and returns \fIn\fR. The -separation is done with the regular expression \fIfs\fR or with the field -separator \fBFS\fR if \fIfs\fR is not given. +Split the string \fIs\fR into array elements \fIa\fR[1], \fIa\fR[2], +\fB\&...,\fR \fIa\fR[\fIn\fR], and return \fIn\fR. The separation is done with +the extended regular expression \fIfs\fR or with the field separator \fBFS\fR +if \fIfs\fR is not given. Each array element has a string value when created. +If the string assigned to any array element, with any occurrence of the +decimal-point character from the current locale changed to a period character, +would be considered a \fInumeric string\fR; the array element also has the +numeric value of the \fInumeric string\fR. The effect of a null string as the +value of \fIfs\fR is unspecified. .RE .sp .ne 2 .na -\fB\fBsprintf(\fR\fIfmt\fR, \fIexpr\fR, \fIexpr\fR,\|.\|.\|.\|\fB)\fR\fR +\fB\fBsprintf\fR(\fBfmt\fR,\fIexpr\fR,\fIexpr\fR,\fB\&...\fR)\fR .ad .sp .6 .RS 4n -Format the expressions according to the \fBprintf\fR(3C) format given by -\fIfmt\fR and returns the resulting string. +Format the expressions according to the \fBprintf\fR format given by \fIfmt\fR +and return the resulting string. .RE .sp .ne 2 .na -\fB\fBsubstr(\fR\fIs\fR, \fIm\fR, \fIn\fR\fB)\fR\fR +\fB\fBsub\fR(\fIere\fR,\fIrepl\fR[,\|\fIin\fR])\fR .ad .sp .6 .RS 4n -returns the \fIn\fR-character substring of \fIs\fR that begins at position -\fIm\fR. +Substitute the string \fIrepl\fR in place of the first instance of the extended +regular expression \fBERE\fR in string in and return the number of +substitutions. An ampersand ( \fB&\fR ) appearing in the string \fIrepl\fR is +replaced by the string from in that matches the regular expression. An +ampersand preceded with a backslash ( \fB\e\fR ) is interpreted as the literal +ampersand character. An occurrence of two consecutive backslashes is +interpreted as just a single literal backslash character. Any other occurrence +of a backslash (for example, preceding any other character) is treated as a +literal backslash character. If \fIrepl\fR is a string literal, the handling of +the ampersand character occurs after any lexical processing, including any +lexical backslash escape sequence processing. If \fBin\fR is specified and it +is not an \fBlvalue\fR the behavior is undefined. If in is omitted, \fBawk\fR +uses the current record (\fB$0\fR) in its place. +.RE + +.sp +.ne 2 +.na +\fB\fBsubstr\fR(\fIs\fR,\fIm\fR[,\|\fIn\fR])\fR +.ad +.sp .6 +.RS 4n +Return the at most \fIn\fR-character substring of \fIs\fR that begins at +position \fIm,\fR numbering from 1. If \fIn\fR is missing, the length of the +substring is limited by the length of the string \fIs\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBtolower\fR(\fIs\fR)\fR +.ad +.sp .6 +.RS 4n +Return a string based on the string \fIs\fR. Each character in \fIs\fR that is +an upper-case letter specified to have a \fBtolower\fR mapping by the +\fBLC_CTYPE\fR category of the current locale is replaced in the returned +string by the lower-case letter specified by the mapping. Other characters in +\fIs\fR are unchanged in the returned string. +.RE + +.sp +.ne 2 +.na +\fB\fBtoupper\fR(\fIs\fR)\fR +.ad +.sp .6 +.RS 4n +Return a string based on the string \fIs\fR. Each character in \fIs\fR that is +a lower-case letter specified to have a \fBtoupper\fR mapping by the +\fBLC_CTYPE\fR category of the current locale is replaced in the returned +string by the upper-case letter specified by the mapping. Other characters in +\fIs\fR are unchanged in the returned string. .RE .sp .LP -The input/output function is as follows: +All of the preceding functions that take \fIERE\fR as a parameter expect a +pattern or a string valued expression that is a regular expression as defined +below. + +.SS "Input/Output and General Functions" +The input/output and general functions are: +.sp +.ne 2 +.na +\fB\fBclose(\fR\fIexpression\fR)\fR +.ad +.RS 27n +Close the file or pipe opened by a \fBprint\fR or \fBprintf\fR statement or a +call to \fBgetline\fR with the same string-valued \fIexpression\fR. If the +close was successful, the function returns \fB0\fR; otherwise, it returns +non-zero. +.RE + +.sp +.ne 2 +.na +\fB\fBfflush(\fR\fIexpression\fR)\fR +.ad +.RS 27n +Flush any buffered output for the file or pipe opened by a \fBprint\fR or +\fBprintf\fR statement or a call to \fBgetline\fR with the same string-valued +\fIexpression\fR. If the flush was successful, the function returns \fB0\fR; +otherwise, it returns \fBEOF\fR. If no arguments or the empty string +(\fB""\fR) are given, then all open files will be flushed. (Note that +\fBfflush\fR is supported in \fB/usr/bin/awk\fR only.) +.RE + +.sp +.ne 2 +.na +\fB\fIexpression\fR|\fBgetline\fR[\fIvar\fR]\fR +.ad +.RS 27n +Read a record of input from a stream piped from the output of a command. The +stream is created if no stream is currently open with the value of +\fIexpression\fR as its command name. The stream created is equivalent to one +created by a call to the \fBpopen\fR function with the value of +\fIexpression\fR as the \fIcommand\fR argument and a value of \fBr\fR as the +\fImode\fR argument. As long as the stream remains open, subsequent calls in +which \fIexpression\fR evaluates to the same string value reads subsequent +records from the file. The stream remains open until the \fBclose\fR function +is called with an expression that evaluates to the same string value. At that +time, the stream is closed as if by a call to the \fBpclose\fR function. If +\fIvar\fR is missing, \fB$0\fR and \fBNF\fR is set. Otherwise, \fIvar\fR is +set. +.sp +The \fBgetline\fR operator can form ambiguous constructs when there are +operators that are not in parentheses (including concatenate) to the left of +the \fB|\fR (to the beginning of the expression containing \fBgetline\fR). In +the context of the \fB$\fR operator, \fB|\fR behaves as if it had a lower +precedence than \fB$\fR. The result of evaluating other operators is +unspecified, and all such uses of portable applications must be put in +parentheses properly. +.RE + .sp .ne 2 .na \fB\fBgetline\fR\fR .ad -.RS 11n -Set \fB$0\fR to the next input record from the current input file. -\fBgetline\fR returns \fB1\fR for successful input, \fB0\fR for end of file, -and \fB\(mi1\fR for an error. +.RS 27n +Set \fB$0\fR to the next input record from the current input file. This form of +\fBgetline\fR sets the \fBNF\fR, \fBNR\fR, and \fBFNR\fR variables. +.RE + +.sp +.ne 2 +.na +\fB\fBgetline\fR \fIvar\fR\fR +.ad +.RS 27n +Set variable \fIvar\fR to the next input record from the current input file. +This form of \fBgetline\fR sets the \fBFNR\fR and \fBNR\fR variables. +.RE + +.sp +.ne 2 +.na +\fB\fBgetline\fR [\fIvar\fR] \fB<\fR \fIexpression\fR\fR +.ad +.RS 27n +Read the next record of input from a named file. The \fIexpression\fR is +evaluated to produce a string that is used as a full pathname. If the file of +that name is not currently open, it is opened. As long as the stream remains +open, subsequent calls in which \fIexpression\fR evaluates to the same string +value reads subsequent records from the file. The file remains open until the +\fBclose\fR function is called with an expression that evaluates to the same +string value. If \fIvar\fR is missing, \fB$0\fR and \fBNF\fR is set. Otherwise, +\fIvar\fR is set. +.sp +The \fBgetline\fR operator can form ambiguous constructs when there are binary +operators that are not in parentheses (including concatenate) to the right of +the \fB<\fR (up to the end of the expression containing the \fBgetline\fR). The +result of evaluating such a construct is unspecified, and all such uses of +portable applications must be put in parentheses properly. .RE -.SS "Large File Behavior" +.sp +.ne 2 +.na +\fB\fBsystem\fR(\fIexpression\fR)\fR +.ad +.RS 27n +Execute the command given by \fIexpression\fR in a manner equivalent to the +\fBsystem\fR(3C) function and return the exit status of the command. +.RE + +.sp +.LP +All forms of \fBgetline\fR return \fB1\fR for successful input, \fB0\fR for end +of file, and \fB\(mi1\fR for an error. +.sp +.LP +Where strings are used as the name of a file or pipeline, the strings must be +textually identical. The terminology ``same string value'' implies that +``equivalent strings'', even those that differ only by space characters, +represent different files. + +.SS "User-defined Functions" +The \fBawk\fR language also provides user-defined functions. Such functions +can be defined as: +.sp +.in +2 +.nf +\fBfunction\fR \fIname\fR(\fIargs\fR,\|.\|.\|.) { \fIstatements\fR } +.fi +.in -2 + +.sp +.LP +A function can be referred to anywhere in an \fBawk\fR program; in particular, +its use can precede its definition. The scope of a function is global. +.sp +.LP +Function arguments can be either scalars or arrays; the behavior is undefined +if an array name is passed as an argument that the function uses as a scalar, +or if a scalar expression is passed as an argument that the function uses as an +array. Function arguments are passed by value if scalar and by reference if +array name. Argument names are local to the function; all other variable names +are global. The same name is not used as both an argument name and as the name +of a function or a special \fBawk\fR variable. The same name must not be used +both as a variable name with global scope and as the name of a function. The +same name must not be used within the same scope both as a scalar variable and +as an array. +.sp +.LP +The number of parameters in the function definition need not match the number +of parameters in the function call. Excess formal parameters can be used as +local variables. If fewer arguments are supplied in a function call than are in +the function definition, the extra parameters that are used in the function +body as scalars are initialized with a string value of the null string and a +numeric value of zero, and the extra parameters that are used in the function +body as arrays are initialized as empty arrays. If more arguments are supplied +in a function call than are in the function definition, the behavior is +undefined. +.sp +.LP +When invoking a function, no white space can be placed between the function +name and the opening parenthesis. Function calls can be nested and recursive +calls can be made upon functions. Upon return from any nested or recursive +function call, the values of all of the calling function's parameters are +unchanged, except for array parameters passed by reference. The \fBreturn\fR +statement can be used to return a value. If a \fBreturn\fR statement appears +outside of a function definition, the behavior is undefined. +.sp +.LP +In the function definition, newline characters are optional before the opening +brace and after the closing brace. Function definitions can appear anywhere in +the program where a \fIpattern-action\fR pair is allowed. + +.SH USAGE +The \fBindex\fR, \fBlength\fR, \fBmatch\fR, and \fBsubstr\fR functions should +not be confused with similar functions in the \fBISO C\fR standard; the +\fBawk\fR versions deal with characters, while the \fBISO C\fR standard deals +with bytes. +.sp +.LP +Because the concatenation operation is represented by adjacent expressions +rather than an explicit operator, it is often necessary to use parentheses to +enforce the proper evaluation precedence. .sp .LP See \fBlargefile\fR(5) for the description of the behavior of \fBawk\fR when -encountering files greater than or equal to 2 Gbyte ( 2^31 bytes). +encountering files greater than or equal to 2 Gbyte (2^31 bytes). + .SH EXAMPLES +The \fBawk\fR program specified in the command line is most easily specified +within single-quotes (for example, \fB\&'\fR\fIprogram\fR\fB\&'\fR) for +applications using \fBsh\fR, because \fBawk\fR programs commonly contain +characters that are special to the shell, including double-quotes. In the cases +where a \fBawk\fR program contains single-quote characters, it is usually +easiest to specify most of the program as strings within single-quotes +concatenated by the shell with quoted single-quote characters. For example: +.sp +.in +2 +.nf +awk '/'\e''/ { print "quote:", $0 }' +.fi +.in -2 + +.sp .LP -\fBExample 1 \fRPrinting Lines Longer Than 72 Characters +prints all lines from the standard input containing a single-quote character, +prefixed with \fBquote:\fR. .sp .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints lines longer than seventy two -characters: +The following are examples of simple \fBawk\fR programs: +.LP +\fBExample 1 \fRWrite to the standard output all input lines for which field 3 +is greater than 5: +.sp +.in +2 +.nf +\fB$3 > 5\fR +.fi +.in -2 +.sp +.LP +\fBExample 2 \fRWrite every tenth line: .sp .in +2 .nf -\fBlength > 72\fR +\fB(NR % 10) == 0\fR .fi .in -2 .sp .LP -\fBExample 2 \fRPrinting Fields in Opposite Order +\fBExample 3 \fRWrite any line with a substring matching the regular +expression: +.sp +.in +2 +.nf +\fB/(G|D)(2[0-9][[:alpha:]]*)/\fR +.fi +.in -2 +.sp + +.LP +\fBExample 4 \fRPrint any line with a substring containing a G or D, followed +by a sequence of digits and characters: .sp .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints the first two fields in opposite -order: +This example uses character classes \fBdigit\fR and \fBalpha\fR to match +language-independent digit and alphabetic characters, respectively. .sp .in +2 .nf -\fB{ print $2, $1 }\fR +\fB/(G|D)([[:digit:][:alpha:]]*)/\fR +.fi +.in -2 +.sp + +.LP +\fBExample 5 \fRWrite any line in which the second field matches the regular +expression and the fourth field does not: +.sp +.in +2 +.nf +\fB$2 ~ /xyz/ && $4 !~ /xyz/\fR .fi .in -2 .sp .LP -\fBExample 3 \fRPrinting Fields in Opposite Order with the Input Fields -Separated +\fBExample 6 \fRWrite any line in which the second field contains a backslash: .sp +.in +2 +.nf +\fB$2 ~ /\e\e/\fR +.fi +.in -2 +.sp + .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints the first two input fields in -opposite order, separated by a comma, blanks or tabs: +\fBExample 7 \fRWrite any line in which the second field contains a backslash +(alternate method): +.sp +.LP +Notice that backslash escapes are interpreted twice, once in lexical processing +of the string and once in processing the regular expression. .sp .in +2 .nf -\fBBEGIN { FS = ",[ \et]*|[ \et]+" } - { print $2, $1 }\fR +\fB$2 ~ "\e\e\e\e"\fR .fi .in -2 .sp .LP -\fBExample 4 \fRAdding Up the First Column, Printing the Sum and Average +\fBExample 8 \fRWrite the second to the last and the last field in each line, +separating the fields by a colon: +.sp +.in +2 +.nf +\fB{OFS=":";print $(NF-1), $NF}\fR +.fi +.in -2 +.sp + +.LP +\fBExample 9 \fRWrite the line number and number of fields in each line: .sp .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It adds up the first column, and prints the -sum and average: +The three strings representing the line number, the colon and the number of +fields are concatenated and that string is written to standard output. .sp .in +2 .nf -\fB{ s += $1 } -END { print "sum is", s, " average is", s/NR }\fR +\fB{print NR ":" NF}\fR .fi .in -2 .sp .LP -\fBExample 5 \fRPrinting Fields in Reverse Order +\fBExample 10 \fRWrite lines longer than 72 characters: .sp +.in +2 +.nf +\fB{length($0) > 72}\fR +.fi +.in -2 +.sp + .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints fields in reverse order: +\fBExample 11 \fRWrite first two fields in opposite order separated by the OFS: +.sp +.in +2 +.nf +\fB{ print $2, $1 }\fR +.fi +.in -2 +.sp +.LP +\fBExample 12 \fRSame, with input fields separated by comma or space and tab +characters, or both: .sp .in +2 .nf -\fB{ for (i = NF; i > 0; \(mi\(mii) print $i }\fR +\fBBEGIN { FS = ",[\et]*|[\et]+" } + { print $2, $1 }\fR .fi .in -2 .sp .LP -\fBExample 6 \fRPrinting All lines Between \fBstart/stop\fR Pairs +\fBExample 13 \fRAdd up first column, print sum and average: .sp +.in +2 +.nf +\fB{s += $1 } +END {print "sum is ", s, " average is", s/NR}\fR +.fi +.in -2 +.sp + .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints all lines between start/stop -pairs. +\fBExample 14 \fRWrite fields in reverse order, one per line (many lines out +for each line in): +.sp +.in +2 +.nf +\fB{ for (i = NF; i > 0; --i) print $i }\fR +.fi +.in -2 +.sp +.LP +\fBExample 15 \fRWrite all lines between occurrences of the strings "start" and +"stop": .sp .in +2 .nf @@ -547,61 +1696,89 @@ pairs. .sp .LP -\fBExample 7 \fRPrinting All Lines Whose First Field is Different from the -Previous One +\fBExample 16 \fRWrite all lines whose first field is different from the +previous one: .sp +.in +2 +.nf +\fB$1 != prev { print; prev = $1 }\fR +.fi +.in -2 +.sp + .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints all lines whose first field is -different from the previous one. +\fBExample 17 \fRSimulate the echo command: +.sp +.in +2 +.nf +\fBBEGIN { + for (i = 1; i < ARGC; ++i) + printf "%s%s", ARGV[i], i==ARGC-1?"\en":"" + }\fR +.fi +.in -2 +.sp +.LP +\fBExample 18 \fRWrite the path prefixes contained in the PATH environment +variable, one per line: .sp .in +2 .nf -\fB$1 != prev { print; prev = $1 }\fR +\fBBEGIN { + n = split (ENVIRON["PATH"], path, ":") + for (i = 1; i <= n; ++i) + print path[i] + }\fR .fi .in -2 .sp .LP -\fBExample 8 \fRPrinting a File and Filling in Page numbers +\fBExample 19 \fRPrint the file "input", filling in page numbers starting at 5: .sp .LP -The following example is an \fBawk\fR script that can be executed by an \fBawk --f examplescript\fR style command. It prints a file and fills in page numbers -starting at 5: +If there is a file named \fBinput\fR containing page headers of the form .sp .in +2 .nf -\fB/Page/ { $2 = n++; } - { print }\fR +Page# .fi .in -2 -.sp +.sp .LP -\fBExample 9 \fRPrinting a File and Numbering Its Pages +and a file named \fBprogram\fR that contains + +.sp +.in +2 +.nf +/Page/{ $2 = n++; } +{ print } +.fi +.in -2 + .sp .LP -Assuming this program is in a file named \fBprog\fR, the following example -prints the file \fBinput\fR numbering its pages starting at \fB5\fR: +then the command line .sp .in +2 .nf -example% \fBawk -f prog n=5 input\fR +\fBawk -f program n=5 input\fR .fi .in -2 .sp -.SH ENVIRONMENT VARIABLES .sp .LP +prints the file \fBinput\fR, filling in page numbers starting at 5. + +.SH ENVIRONMENT VARIABLES See \fBenviron\fR(5) for descriptions of the following environment variables -that affect the execution of \fBawk\fR: \fBLANG\fR, \fBLC_ALL\fR, -\fBLC_COLLATE\fR, \fBLC_CTYPE\fR, \fBLC_MESSAGES\fR, \fBNLSPATH\fR, and -\fBPATH\fR. +that affect execution: \fBLC_COLLATE\fR, \fBLC_CTYPE\fR, \fBLC_MESSAGES\fR, and +\fBNLSPATH\fR. .sp .ne 2 .na @@ -615,49 +1792,55 @@ POSIX locale) is the decimal-point character recognized in processing \fBawk\fR programs (including assignments in command-line arguments). .RE -.SH ATTRIBUTES +.SH EXIT STATUS +The following exit values are returned: .sp -.LP -See \fBattributes\fR(5) for descriptions of the following attributes: -.SS "/usr/bin/awk" -.sp - -.sp -.TS -box; -c | c -l | l . -ATTRIBUTE TYPE ATTRIBUTE VALUE -_ -CSI Not Enabled -.TE +.ne 2 +.na +\fB\fB0\fR\fR +.ad +.RS 6n +All input files were processed successfully. +.RE -.SS "/usr/xpg4/bin/awk" .sp +.ne 2 +.na +\fB\fB>0\fR\fR +.ad +.RS 6n +An error occurred. +.RE .sp -.TS -box; -c | c -l | l . -ATTRIBUTE TYPE ATTRIBUTE VALUE -_ -CSI Enabled -_ -Interface Stability Standard -.TE +.LP +The exit status can be altered within the program by using an \fBexit\fR +expression. .SH SEE ALSO +\fBed\fR(1), \fBegrep\fR(1), \fBgrep\fR(1), \fBlex\fR(1), \fBoawk\fR(1), +\fBsed\fR(1), \fBpopen\fR(3C), \fBprintf\fR(3C), \fBsystem\fR(3C), +\fBattributes\fR(5), \fBenviron\fR(5), \fBlargefile\fR(5), \fBregex\fR(5), +\fBXPG4\fR(5) .sp .LP -\fBegrep\fR(1), \fBgrep\fR(1), \fBnawk\fR(1), \fBsed\fR(1), \fBprintf\fR(3C), -\fBattributes\fR(5), \fBenviron\fR(5), \fBlargefile\fR(5), \fBstandards\fR(5) -.SH NOTES +Aho, A. V., B. W. Kernighan, and P. J. Weinberger, \fIThe AWK Programming +Language\fR, Addison-Wesley, 1988. + +.SH DIAGNOSTICS +If any \fIfile\fR operand is specified and the named file cannot be accessed, +\fBawk\fR writes a diagnostic message to standard error and terminate without +any further action. .sp .LP +If the program specified by either the \fIprogram\fR operand or a +\fIprogfile\fR operand is not a valid \fBawk\fR program (as specified in +\fBEXTENDED DESCRIPTION\fR), the behavior is undefined. + +.SH NOTES Input white space is not preserved on output if fields are involved. .sp .LP There are no explicit conversions between numbers and strings. To force an -expression to be treated as a number, add \fB0\fR to it. To force an expression -to be treated as a string, concatenate the null string (\fB""\fR) to it. +expression to be treated as a number add 0 to it; to force it to be treated as +a string concatenate the null string (\fB""\fR) to it. diff --git a/usr/src/man/man1/nawk.1 b/usr/src/man/man1/nawk.1 deleted file mode 100644 index 5fec573a52..0000000000 --- a/usr/src/man/man1/nawk.1 +++ /dev/null @@ -1,1874 +0,0 @@ -.\" -.\" Sun Microsystems, Inc. gratefully acknowledges The Open Group for -.\" permission to reproduce portions of its copyrighted documentation. -.\" Original documentation from The Open Group can be obtained online at -.\" http://www.opengroup.org/bookstore/. -.\" -.\" The Institute of Electrical and Electronics Engineers and The Open -.\" Group, have given us permission to reprint portions of their -.\" documentation. -.\" -.\" In the following statement, the phrase ``this text'' refers to portions -.\" of the system documentation. -.\" -.\" Portions of this text are reprinted and reproduced in electronic form -.\" in the SunOS Reference Manual, from IEEE Std 1003.1, 2004 Edition, -.\" Standard for Information Technology -- Portable Operating System -.\" Interface (POSIX), The Open Group Base Specifications Issue 6, -.\" Copyright (C) 2001-2004 by the Institute of Electrical and Electronics -.\" Engineers, Inc and The Open Group. In the event of any discrepancy -.\" between these versions and the original IEEE and The Open Group -.\" Standard, the original IEEE and The Open Group Standard is the referee -.\" document. The original Standard can be obtained online at -.\" http://www.opengroup.org/unix/online.html. -.\" -.\" This notice shall appear on any product containing this material. -.\" -.\" The contents of this file are subject to the terms of the -.\" Common Development and Distribution License (the "License"). -.\" You may not use this file except in compliance with the License. -.\" -.\" You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE -.\" or http://www.opensolaris.org/os/licensing. -.\" See the License for the specific language governing permissions -.\" and limitations under the License. -.\" -.\" When distributing Covered Code, include this CDDL HEADER in each -.\" file and include the License file at usr/src/OPENSOLARIS.LICENSE. -.\" If applicable, add the following below this CDDL HEADER, with the -.\" fields enclosed by brackets "[]" replaced with your own identifying -.\" information: Portions Copyright [yyyy] [name of copyright owner] -.\" -.\" -.\" Copyright 1989 AT&T -.\" Copyright 1992, X/Open Company Limited All Rights Reserved -.\" Portions Copyright (c) 2005, 2006 Sun Microsystems, Inc. All Rights Reserved -.\" Copyright 2018, Joyent, Inc. -.\" -.TH NAWK 1 "Nov 9, 2018" -.SH NAME -nawk \- pattern scanning and processing language -.SH SYNOPSIS -.LP -.nf -\fB/usr/bin/awk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR] \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... - [\fIargument\fR]... -.fi - -.LP -.nf -\fB/usr/bin/nawk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR] \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... - [\fIargument\fR]... -.fi - -.LP -.nf -\fB/usr/xpg4/bin/awk\fR [\fB-F\fR \fIERE\fR] [\fB-v\fR \fIassignment\fR]... \fI\&'program'\fR | \fB-f\fR \fIprogfile\fR... - [\fIargument\fR]... -.fi - -.SH DESCRIPTION -.LP -The \fB/usr/bin/awk\fR, \fB/usr/bin/nawk\fR and \fB/usr/xpg4/bin/awk\fR -utilities execute -\fIprogram\fRs written in the \fBnawk\fR programming language, which is -specialized for textual data manipulation. A \fBnawk\fR \fIprogram\fR is a -sequence of patterns and corresponding actions. The string specifying -\fIprogram\fR must be enclosed in single quotes (') to protect it from -interpretation by the shell. The sequence of pattern - action statements can be -specified in the command line as \fIprogram\fR or in one, or more, file(s) -specified by the \fB-f\fR\fIprogfile\fR option. When input is read that matches -a pattern, the action associated with the pattern is performed. -.sp -.LP -Input is interpreted as a sequence of records. By default, a record is a line, -but this can be changed by using the \fBRS\fR built-in variable. Each record of -input is matched to each pattern in the \fIprogram\fR. For each pattern -matched, the associated action is executed. -.sp -.LP -The \fBnawk\fR utility interprets each input record as a sequence of fields -where, by default, a field is a string of non-blank characters. This default -white-space field delimiter (blanks and/or tabs) can be changed by using the -\fBFS\fR built-in variable or the \fB-F\fR\fIERE\fR option. The \fBnawk\fR -utility denotes the first field in a record \fB$1\fR, the second \fB$2\fR, and -so forth. The symbol \fB$0\fR refers to the entire record; setting any other -field causes the reevaluation of \fB$0\fR. Assigning to \fB$0\fR resets the -values of all fields and the \fBNF\fR built-in variable. - -.SH OPTIONS -.LP -The following options are supported: -.sp -.ne 2 -.na -\fB\fB-F\fR \fIERE\fR\fR -.ad -.RS 17n -Define the input field separator to be the extended regular expression -\fIERE\fR, before any input is read (can be a character). -.RE - -.sp -.ne 2 -.na -\fB\fB-f\fR \fIprogfile\fR\fR -.ad -.RS 17n -Specifies the pathname of the file \fIprogfile\fR containing a \fBnawk\fR -program. If multiple instances of this option are specified, the concatenation -of the files specified as \fIprogfile\fR in the order specified is the -\fBnawk\fR program. The \fBnawk\fR program can alternatively be specified in -the command line as a single argument. -.RE - -.sp -.ne 2 -.na -\fB\fB-v\fR \fIassignment\fR\fR -.ad -.RS 17n -The \fIassignment\fR argument must be in the same form as an \fIassignment\fR -operand. The assignment is of the form \fIvar=value\fR, where \fIvar\fR is the -name of one of the variables described below. The specified assignment occurs -before executing the \fBnawk\fR program, including the actions associated with -\fBBEGIN\fR patterns (if any). Multiple occurrences of this option can be -specified. -.RE - -.sp -.ne 2 -.na -\fB\fB-safe\fR\fR -.ad -.RS 17n -When passed to \fBnawk\fR, this flag will prevent the program from opening new -files or running child processes. The \fBENVIRON\fR array will also not be -initialized. -.RE - -.SH OPERANDS -.LP -The following operands are supported: -.sp -.ne 2 -.na -\fB\fIprogram\fR\fR -.ad -.RS 12n -If no \fB-f\fR option is specified, the first operand to \fBnawk\fR is the text -of the \fBnawk\fR program. The application supplies the \fIprogram\fR operand -as a single argument to \fBnawk.\fR If the text does not end in a newline -character, \fBnawk\fR interprets the text as if it did. -.RE - -.sp -.ne 2 -.na -\fB\fIargument\fR\fR -.ad -.RS 12n -Either of the following two types of \fIargument\fR can be intermixed: -.sp -.ne 2 -.na -\fB\fIfile\fR\fR -.ad -.RS 14n -A pathname of a file that contains the input to be read, which is matched -against the set of patterns in the program. If no \fIfile\fR operands are -specified, or if a \fIfile\fR operand is \fB\(mi\fR, the standard input is -used. -.RE - -.sp -.ne 2 -.na -\fB\fIassignment\fR\fR -.ad -.RS 14n -An operand that begins with an underscore or alphabetic character from the -portable character set, followed by a sequence of underscores, digits and -alphabetics from the portable character set, followed by the \fB=\fR character -specifies a variable assignment rather than a pathname. The characters before -the \fB=\fR represent the name of a \fBnawk\fR variable. If that name is a -\fBnawk\fR reserved word, the behavior is undefined. The characters following -the equal sign is interpreted as if they appeared in the \fBnawk\fR program -preceded and followed by a double-quote (\fB"\fR) character, as a \fBSTRING\fR -token , except that if the last character is an unescaped backslash, it is -interpreted as a literal backslash rather than as the first character of the -sequence \fB\e\fR\&.. The variable is assigned the value of that \fBSTRING\fR -token. If the value is considered a \fInumeric\fRstring\fI,\fR the variable is -assigned its numeric value. Each such variable assignment is performed just -before the processing of the following \fIfile\fR, if any. Thus, an assignment -before the first \fBfile\fR argument is executed after the \fBBEGIN\fR actions -(if any), while an assignment after the last \fIfile\fR argument is executed -before the \fBEND\fR actions (if any). If there are no \fIfile\fR arguments, -assignments are executed before processing the standard input. -.RE - -.RE - -.SH INPUT FILES -.LP -Input files to the \fBnawk\fR program from any of the following sources: -.RS +4 -.TP -.ie t \(bu -.el o -any \fIfile\fR operands or their equivalents, achieved by modifying the -\fBnawk\fR variables \fBARGV\fR and \fBARGC\fR -.RE -.RS +4 -.TP -.ie t \(bu -.el o -standard input in the absence of any \fIfile\fR operands -.RE -.RS +4 -.TP -.ie t \(bu -.el o -arguments to the \fBgetline\fR function -.RE -.sp -.LP -must be text files. Whether the variable \fBRS\fR is set to a value other than -a newline character or not, for these files, implementations support records -terminated with the specified separator up to \fB{LINE_MAX}\fR bytes and can -support longer records. -.sp -.LP -If \fB-\fR\fBf\fR \fIprogfile\fR is specified, the files named by each of the -\fIprogfile\fR option-arguments must be text files containing an \fBnawk\fR -program. -.sp -.LP -The standard input are used only if no \fIfile\fR operands are specified, or if -a \fIfile\fR operand is \fB\(mi\fR\&. - -.SH EXTENDED DESCRIPTION -.LP -A \fBnawk\fR program is composed of pairs of the form: -.sp -.in +2 -.nf -pattern { \fIaction\fR } -.fi -.in -2 - -.sp -.LP -Either the pattern or the action (including the enclosing brace characters) can -be omitted. Pattern-action statements are separated by a semicolon or by a -newline. -.sp -.LP -A missing pattern matches any record of input, and a missing action is -equivalent to an action that writes the matched record of input to standard -output. -.sp -.LP -Execution of the \fBnawk\fR program starts by first executing the actions -associated with all \fBBEGIN\fR patterns in the order they occur in the -program. Then each \fIfile\fR operand (or standard input if no files were -specified) is processed by reading data from the file until a record separator -is seen (a newline character by default), splitting the current record into -fields using the current value of \fBFS\fR, evaluating each pattern in the -program in the order of occurrence, and executing the action associated with -each pattern that matches the current record. The action for a matching pattern -is executed before evaluating subsequent patterns. Last, the actions associated -with all \fBEND\fR patterns is executed in the order they occur in the program. - -.SS "Expressions in nawk" -.LP -Expressions describe computations used in \fIpatterns\fR and \fIactions\fR. In -the following table, valid expression operations are given in groups from -highest precedence first to lowest precedence last, with equal-precedence -operators grouped between horizontal lines. In expression evaluation, where the -grammar is formally ambiguous, higher precedence operators are evaluated before -lower precedence operators. In this table \fIexpr,\fR \fIexpr1,\fR -\fIexpr2,\fR and \fIexpr3\fR represent any expression, while \fIlvalue\fR -represents any entity that can be assigned to (that is, on the left side of an -assignment operator). -.sp - -.sp -.TS -c c c c -l l l l . -\fBSyntax\fR \fBName\fR \fBType of Result\fR \fBAssociativity\fR -_ -( \fIexpr\fR ) Grouping type of \fIexpr\fR n/a -_ -$\fIexpr\fR Field reference string n/a -_ -++ \fIlvalue\fR Pre-increment numeric n/a -\(mi\(mi \fIlvalue\fR Pre-decrement numeric n/a -\fIlvalue\fR ++ Post-increment numeric n/a -\fIlvalue\fR \(mi\(mi Post-decrement numeric n/a -_ -\fIexpr\fR ^ \fIexpr\fR Exponentiation numeric right -_ -! \fIexpr\fR Logical not numeric n/a -+ \fIexpr\fR Unary plus numeric n/a -\(mi \fIexpr\fR Unary minus numeric n/a -_ -\fIexpr\fR * \fIexpr\fR Multiplication numeric left -\fIexpr\fR / \fIexpr\fR Division numeric left -\fIexpr\fR % \fIexpr\fR Modulus numeric left -_ -\fIexpr\fR + \fIexpr\fR Addition numeric left -\fIexpr\fR \(mi \fIexpr\fR Subtraction numeric left -_ -\fIexpr\fR \fIexpr\fR String concatenation string left -_ -\fIexpr\fR < \fIexpr\fR Less than numeric none -\fIexpr\fR <= \fIexpr\fR Less than or equal to numeric none -\fIexpr\fR != \fIexpr\fR Not equal to numeric none -\fIexpr\fR == \fIexpr\fR Equal to numeric none -\fIexpr\fR > \fIexpr\fR Greater than numeric none -\fIexpr\fR >= \fIexpr\fR Greater than or equal to numeric none -_ -\fIexpr\fR ~ \fIexpr\fR ERE match numeric none -\fIexpr\fR !~ \fIexpr\fR ERE non-match numeric none -_ -\fIexpr\fR in array Array membership numeric left -( \fIindex\fR ) in Multi-dimension array numeric left - \fIarray\fR membership -_ -\fBexpr\fR && \fIexpr\fR Logical AND numeric left -_ -\fBexpr\fR |\|| \fIexpr\fR Logical OR numeric left -_ -\fIexpr1\fR ? \fIexpr2\fR Conditional expression type of selected right - : \fIexpr3\fR \fIexpr2\fR or \fIexpr3\fR -_ -\fIlvalue\fR ^= \fIexpr\fR Exponentiation numeric right - assignment -\fIlvalue\fR %= \fIexpr\fR Modulus assignment numeric right -\fIlvalue\fR *= \fIexpr\fR Multiplication numeric right - assignment -\fIlvalue\fR /= \fIexpr\fR Division assignment numeric right -\fIlvalue\fR += \fIexpr\fR Addition assignment numeric right -\fIlvalue\fR \(mi= \fIexpr\fR Subtraction assignment numeric right -\fIlvalue\fR = \fIexpr\fR Assignment type of \fIexpr\fR right -.TE - -.sp -.LP -Each expression has either a string value, a numeric value or both. Except as -stated for specific contexts, the value of an expression is implicitly -converted to the type needed for the context in which it is used. A string -value is converted to a numeric value by the equivalent of the following calls: -.sp -.in +2 -.nf -setlocale(LC_NUMERIC, ""); -\fInumeric_value\fR = atof(\fIstring_value\fR); -.fi -.in -2 - -.sp -.LP -A numeric value that is exactly equal to the value of an integer is converted -to a string by the equivalent of a call to the \fBsprintf\fR function with the -string \fB%d\fR as the \fBfmt\fR argument and the numeric value being converted -as the first and only \fIexpr\fR argument. Any other numeric value is -converted to a string by the equivalent of a call to the \fBsprintf\fR function -with the value of the variable \fBCONVFMT\fR as the \fBfmt\fR argument and the -numeric value being converted as the first and only \fIexpr\fR argument. -.sp -.LP -A string value is considered to be a \fInumeric string\fR in the following -case: -.RS +4 -.TP -1. -Any leading and trailing blank characters is ignored. -.RE -.RS +4 -.TP -2. -If the first unignored character is a \fB+\fR or \fB\(mi\fR, it is ignored. -.RE -.RS +4 -.TP -3. -If the remaining unignored characters would be lexically recognized as a -\fBNUMBER\fR token, the string is considered a \fInumeric string\fR. -.RE -.sp -.LP -If a \fB\(mi\fR character is ignored in the above steps, the numeric value of -the \fInumeric string\fR is the negation of the numeric value of the recognized -\fBNUMBER\fR token. Otherwise the numeric value of the \fInumeric string\fR is -the numeric value of the recognized \fBNUMBER\fR token. Whether or not a string -is a \fInumeric string\fR is relevant only in contexts where that term is used -in this section. -.sp -.LP -When an expression is used in a Boolean context, if it has a numeric value, a -value of zero is treated as false and any other value is treated as true. -Otherwise, a string value of the null string is treated as false and any other -value is treated as true. A Boolean context is one of the following: -.RS +4 -.TP -.ie t \(bu -.el o -the first subexpression of a conditional expression. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -an expression operated on by logical NOT, logical \fBAND,\fR or logical OR. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -the second expression of a \fBfor\fR statement. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -the expression of an \fBif\fR statement. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -the expression of the \fBwhile\fR clause in either a \fBwhile\fR or \fBdo\fR -\fB\&.\|.\|.\fR \fBwhile\fR statement. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -an expression used as a pattern (as in Overall Program Structure). -.RE -.sp -.LP -The \fBnawk\fR language supplies arrays that are used for storing numbers or -strings. Arrays need not be declared. They are initially empty, and their sizes -changes dynamically. The subscripts, or element identifiers, are strings, -providing a type of associative array capability. An array name followed by a -subscript within square brackets can be used as an \fIlvalue\fR and as an -expression, as described in the grammar. Unsubscripted array names are used in -only the following contexts: -.RS +4 -.TP -.ie t \(bu -.el o -a parameter in a function definition or function call. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -the \fBNAME\fR token following any use of the keyword \fBin\fR. -.RE -.sp -.LP -A valid array \fIindex\fR consists of one or more comma-separated expressions, -similar to the way in which multi-dimensional arrays are indexed in some -programming languages. Because \fBnawk\fR arrays are really one-dimensional, -such a comma-separated list is converted to a single string by concatenating -the string values of the separate expressions, each separated from the other by -the value of the \fBSUBSEP\fR variable. -.sp -.LP -Thus, the following two index operations are equivalent: -.sp -.in +2 -.nf -var[expr1, expr2, ... exprn] -var[expr1 SUBSEP expr2 SUBSEP ... SUBSEP exprn] -.fi -.in -2 - -.sp -.LP -A multi-dimensioned \fIindex\fR used with the \fBin\fR operator must be put in -parentheses. The \fBin\fR operator, which tests for the existence of a -particular array element, does not create the element if it does not exist. -Any other reference to a non-existent array element automatically creates it. - -.SS "Variables and Special Variables" -.LP -Variables can be used in an \fBnawk\fR program by referencing them. With the -exception of function parameters, they are not explicitly declared. -Uninitialized scalar variables and array elements have both a numeric value of -zero and a string value of the empty string. -.sp -.LP -Field variables are designated by a \fB$\fR followed by a number or numerical -expression. The effect of the field number \fIexpression\fR evaluating to -anything other than a non-negative integer is unspecified. Uninitialized -variables or string values need not be converted to numeric values in this -context. New field variables are created by assigning a value to them. -References to non-existent fields (that is, fields after \fB$NF\fR) produce the -null string. However, assigning to a non-existent field (for example, -\fB$(NF+2) = 5\fR) increases the value of \fBNF\fR, create any intervening -fields with the null string as their values and cause the value of \fB$0\fR to -be recomputed, with the fields being separated by the value of \fBOFS\fR. Each -field variable has a string value when created. If the string, with any -occurrence of the decimal-point character from the current locale changed to a -period character, is considered a \fInumeric string\fR (see \fBExpressions in -nawk\fR above), the field variable also has the numeric value of the \fInumeric -string\fR. - -.SS "/usr/bin/nawk, /usr/xpg4/bin/awk" -.LP -\fBnawk\fR sets the following special variables that are supported by both -\fB/usr/bin/nawk\fR and \fB/usr/xpg4/bin/awk\fR: -.sp -.ne 2 -.na -\fB\fBARGC\fR\fR -.ad -.RS 12n -The number of elements in the \fBARGV\fR array. -.RE - -.sp -.ne 2 -.na -\fB\fBARGV\fR\fR -.ad -.RS 12n -An array of command line arguments, excluding options and the \fIprogram\fR -argument, numbered from zero to \fBARGC\fR\(mi1. -.sp -The arguments in \fBARGV\fR can be modified or added to; \fBARGC\fR can be -altered. As each input file ends, \fBnawk\fR treats the next non-null element -of \fBARGV\fR, up to the current value of \fBARGC\fR\(mi1, inclusive, as the -name of the next input file. Setting an element of \fBARGV\fR to null means -that it is not treated as an input file. The name \fB\(mi\fR indicates the -standard input. If an argument matches the format of an \fIassignment\fR -operand, this argument is treated as an assignment rather than a \fIfile\fR -argument. -.RE - -.sp -.ne 2 -.na -\fB\fBCONVFMT\fR\fR -.ad -.RS 12n -The \fBprintf\fR format for converting numbers to strings (except for output -statements, where \fBOFMT\fR is used). The default is \fB%.6g\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBENVIRON\fR\fR -.ad -.RS 12n -The variable \fBENVIRON\fR is an array representing the value of the -environment. The indices of the array are strings consisting of the names of -the environment variables, and the value of each array element is a string -consisting of the value of that variable. If the value of an environment -variable is considered a \fInumeric string\fR, the array element also has its -numeric value. -.sp -In all cases where \fBnawk\fR behavior is affected by environment variables -(including the environment of any commands that \fBnawk\fR executes via the -\fBsystem\fR function or via pipeline redirections with the \fBprint\fR -statement, the \fBprintf\fR statement, or the \fBgetline\fR function), the -environment used is the environment at the time \fBnawk\fR began executing. -.RE - -.sp -.ne 2 -.na -\fB\fBFILENAME\fR\fR -.ad -.RS 12n -A pathname of the current input file. Inside a \fBBEGIN\fR action the value is -undefined. Inside an \fBEND\fR action the value is the name of the last input -file processed. -.RE - -.sp -.ne 2 -.na -\fB\fBFNR\fR\fR -.ad -.RS 12n -The ordinal number of the current record in the current file. Inside a -\fBBEGIN\fR action the value is zero. Inside an \fBEND\fR action the value is -the number of the last record processed in the last file processed. -.RE - -.sp -.ne 2 -.na -\fB\fBFS\fR\fR -.ad -.RS 12n -Input field separator regular expression; a space character by default. -.RE - -.sp -.ne 2 -.na -\fB\fBNF\fR\fR -.ad -.RS 12n -The number of fields in the current record. Inside a \fBBEGIN\fR action, the -use of \fBNF\fR is undefined unless a \fBgetline\fR function without a -\fIvar\fR argument is executed previously. Inside an \fBEND\fR action, \fBNF\fR -retains the value it had for the last record read, unless a subsequent, -redirected, \fBgetline\fR function without a \fIvar\fR argument is performed -prior to entering the \fBEND\fR action. -.RE - -.sp -.ne 2 -.na -\fB\fBNR\fR\fR -.ad -.RS 12n -The ordinal number of the current record from the start of input. Inside a -\fBBEGIN\fR action the value is zero. Inside an \fBEND\fR action the value is -the number of the last record processed. -.RE - -.sp -.ne 2 -.na -\fB\fBOFMT\fR\fR -.ad -.RS 12n -The \fBprintf\fR format for converting numbers to strings in output statements -\fB"%.6g"\fR by default. The result of the conversion is unspecified if the -value of \fBOFMT\fR is not a floating-point format specification. -.RE - -.sp -.ne 2 -.na -\fB\fBOFS\fR\fR -.ad -.RS 12n -The \fBprint\fR statement output field separator; a space character by default. -.RE - -.sp -.ne 2 -.na -\fB\fBORS\fR\fR -.ad -.RS 12n -The \fBprint\fR output record separator; a newline character by default. -.RE - -.sp -.ne 2 -.na -\fB\fBRLENGTH\fR\fR -.ad -.RS 12n -The length of the string matched by the \fBmatch\fR function. -.RE - -.sp -.ne 2 -.na -\fB\fBRS\fR\fR -.ad -.RS 12n -The first character of the string value of \fBRS\fR is the input record -separator; a newline character by default. If \fBRS\fR contains more than one -character, the results are unspecified. If \fBRS\fR is null, then records are -separated by sequences of one or more blank lines. Leading or trailing blank -lines do not produce empty records at the beginning or end of input, and the -field separator is always newline, no matter what the value of \fBFS\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBRSTART\fR\fR -.ad -.RS 12n -The starting position of the string matched by the \fBmatch\fR function, -numbering from 1. This is always equivalent to the return value of the -\fBmatch\fR function. -.RE - -.sp -.ne 2 -.na -\fB\fBSUBSEP\fR\fR -.ad -.RS 12n -The subscript separator string for multi-dimensional arrays. The default value -is \fB\e034\fR\&. -.RE - -.SS "/usr/bin/nawk" -.LP -The following variable is supported for \fB/usr/bin/nawk\fR only: -.sp -.ne 2 -.na -\fB\fBRT\fR\fR -.ad -.RS 12n -The record terminator for the most recent record read. For most records this -will be the same value as \fBRS\fR. At the end of a file with no trailing -separator value, though, this will be set to the empty string (\fB""\fR). -.RE - -.SS "Regular Expressions" -.LP -The \fBnawk\fR utility makes use of the extended regular expression notation -(see \fBregex\fR(5)) except that it allows the use of C-language conventions to -escape special characters within the EREs, namely \fB\e\e\fR, \fB\ea\fR, -\fB\eb\fR, \fB\ef\fR, \fB\en\fR, \fB\er\fR, \fB\et\fR, \fB\ev\fR, and those -specified in the following table. These escape sequences are recognized both -inside and outside bracket expressions. Note that records need not be -separated by newline characters and string constants can contain newline -characters, so even the \fB\en\fR sequence is valid in \fBnawk\fR EREs. Using -a slash character within the regular expression requires escaping as shown in -the table below: -.sp - -.sp -.TS -l l l -l l l . -\fBEscape Sequence\fR \fBDescription\fR \fBMeaning\fR -_ -\fB\e"\fR Backslash quotation-mark Quotation-mark character -_ -\fB\e/\fR Backslash slash Slash character -_ -\fB\e\fR\fIddd\fR T{ -A backslash character followed by the longest sequence of one, two, or three octal-digit characters (01234567). If all of the digits are 0, (that is, representation of the NULL character), the behavior is undefined. -T} T{ -The character encoded by the one-, two- or three-digit octal integer. Multi-byte characters require multiple, concatenated escape sequences, including the leading \e for each byte. -T} -_ -\fB\e\fR\fIc\fR T{ -A backslash character followed by any character not described in this table or special characters (\fB\e\e\fR, \fB\ea\fR, \fB\eb\fR, \fB\ef\fR, \fB\en\fR, \fB\er\fR, \fB\et\fR, \fB\ev\fR). -T} Undefined -.TE - -.sp -.LP -A regular expression can be matched against a specific field or string by using -one of the two regular expression matching operators, \fB~\fR and \fB!\|~\fR. -These operators interpret their right-hand operand as a regular expression and -their left-hand operand as a string. If the regular expression matches the -string, the \fB~\fR expression evaluates to the value \fB1\fR, and the -\fB!\|~\fR expression evaluates to the value \fB0\fR. If the regular expression -does not match the string, the \fB~\fR expression evaluates to the value -\fB0\fR, and the \fB!\|~\fR expression evaluates to the value \fB1\fR. If the -right-hand operand is any expression other than the lexical token \fBERE\fR, -the string value of the expression is interpreted as an extended regular -expression, including the escape conventions described above. Notice that these -same escape conventions also are applied in the determining the value of a -string literal (the lexical token \fBSTRING\fR), and is applied a second time -when a string literal is used in this context. -.sp -.LP -When an \fBERE\fR token appears as an expression in any context other than as -the right-hand of the \fB~\fR or \fB!\|~\fR operator or as one of the built-in -function arguments described below, the value of the resulting expression is -the equivalent of: -.sp -.in +2 -.nf -$0 ~ /\fIere\fR/ -.fi -.in -2 - -.sp -.LP -The \fIere\fR argument to the \fBgsub,\fR \fBmatch,\fR \fBsub\fR functions, and -the \fIfs\fR argument to the \fBsplit\fR function (see \fBString Functions\fR) -is interpreted as extended regular expressions. These can be either \fBERE\fR -tokens or arbitrary expressions, and are interpreted in the same manner as the -right-hand side of the \fB~\fR or \fB!\|~\fR operator. -.sp -.LP -An extended regular expression can be used to separate fields by using the -\fB-F\fR \fIERE\fR option or by assigning a string containing the expression to -the built-in variable \fBFS\fR. The default value of the \fBFS\fR variable is a -single space character. The following describes \fBFS\fR behavior: -.RS +4 -.TP -1. -If \fBFS\fR is a single character: -.RS +4 -.TP -.ie t \(bu -.el o -If \fBFS\fR is the space character, skip leading and trailing blank characters; -fields are delimited by sets of one or more blank characters. -.RE -.RS +4 -.TP -.ie t \(bu -.el o -Otherwise, if \fBFS\fR is any other character \fIc\fR, fields are delimited by -each single occurrence of \fIc\fR. -.RE -.RE -.RS +4 -.TP -2. -Otherwise, the string value of \fBFS\fR is considered to be an extended -regular expression. Each occurrence of a sequence matching the extended regular -expression delimits fields. -.RE -.sp -.LP -Except in the \fBgsub\fR, \fBmatch\fR, \fBsplit\fR, and \fBsub\fR built-in -functions, regular expression matching is based on input records. That is, -record separator characters (the first character of the value of the variable -\fBRS\fR, a newline character by default) cannot be embedded in the expression, -and no expression matches the record separator character. If the record -separator is not a newline character, newline characters embedded in the -expression can be matched. In those four built-in functions, regular expression -matching are based on text strings. So, any character (including the newline -character and the record separator) can be embedded in the pattern and an -appropriate pattern matches any character. However, in all \fBnawk\fR regular -expression matching, the use of one or more NULL characters in the pattern, -input record or text string produces undefined results. - -.SS "Patterns" -.LP -A \fIpattern\fR is any valid \fIexpression,\fR a range specified by two -expressions separated by comma, or one of the two special patterns \fBBEGIN\fR -or \fBEND\fR. - -.SS "Special Patterns" -.LP -The \fBnawk\fR utility recognizes two special patterns, \fBBEGIN\fR and -\fBEND\fR. Each \fBBEGIN\fR pattern is matched once and its associated action -executed before the first record of input is read (except possibly by use of -the \fBgetline\fR function in a prior \fBBEGIN\fR action) and before command -line assignment is done. Each \fBEND\fR pattern is matched once and its -associated action executed after the last record of input has been read. These -two patterns have associated actions. -.sp -.LP -\fBBEGIN\fR and \fBEND\fR do not combine with other patterns. Multiple -\fBBEGIN\fR and \fBEND\fR patterns are allowed. The actions associated with the -\fBBEGIN\fR patterns are executed in the order specified in the program, as are -the \fBEND\fR actions. An \fBEND\fR pattern can precede a \fBBEGIN\fR pattern -in a program. -.sp -.LP -If an \fBnawk\fR program consists of only actions with the pattern \fBBEGIN\fR, -and the \fBBEGIN\fR action contains no \fBgetline\fR function, \fBnawk\fR exits -without reading its input when the last statement in the last \fBBEGIN\fR -action is executed. If an \fBnawk\fR program consists of only actions with the -pattern \fBEND\fR or only actions with the patterns \fBBEGIN\fR and \fBEND\fR, -the input is read before the statements in the \fBEND\fR actions are executed. - -.SS "Expression Patterns" -.LP -An expression pattern is evaluated as if it were an expression in a Boolean -context. If the result is true, the pattern is considered to match, and the -associated action (if any) is executed. If the result is false, the action is -not executed. - -.SS "Pattern Ranges" -.LP -A pattern range consists of two expressions separated by a comma. In this case, -the action is performed for all records between a match of the first expression -and the following match of the second expression, inclusive. At this point, the -pattern range can be repeated starting at input records subsequent to the end -of the matched range. - -.SS "Actions" -.LP -An action is a sequence of statements. A statement can be one of the following: -.sp -.in +2 -.nf -if ( \fIexpression\fR ) \fIstatement\fR [ else \fIstatement\fR ] -while ( \fIexpression\fR ) \fIstatement\fR -do \fIstatement\fR while ( \fIexpression\fR ) -for ( \fIexpression\fR ; \fIexpression\fR ; \fIexpression\fR ) \fIstatement\fR -for ( \fIvar\fR in \fIarray\fR ) \fIstatement\fR -delete \fIarray\fR[\fIsubscript\fR] #delete an array element -delete \fIarray\fR #delete all elements within an array -break -continue -{ [ \fIstatement\fR ] .\|.\|. } -\fIexpression\fR # commonly variable = expression -print [ \fIexpression-list\fR ] [ >\fIexpression\fR ] -printf format [ ,\fIexpression-list\fR ] [ >\fIexpression\fR ] -next # skip remaining patterns on this input line -nextfile # skip remaining patterns on this input file -exit [expr] # skip the rest of the input; exit status is expr -return [expr] -.fi -.in -2 - -.sp -.LP -Any single statement can be replaced by a statement list enclosed in braces. -The statements are terminated by newline characters or semicolons, and are -executed sequentially in the order that they appear. -.sp -.LP -The \fBnext\fR statement causes all further processing of the current input -record to be abandoned. The behavior is undefined if a \fBnext\fR statement -appears or is invoked in a \fBBEGIN\fR or \fBEND\fR action. -.sp -.LP -The \fBnextfile\fR statement is similar to \fBnext\fR, but also skips all other -records in the current file, and moves on to processing the next input file if -available (or exits the program if there are none). (Note that this keyword is -not supported by \fB/usr/xpg4/bin/awk\fR.) -.sp -.LP -The \fBexit\fR statement invokes all \fBEND\fR actions in the order in which -they occur in the program source and then terminate the program without reading -further input. An \fBexit\fR statement inside an \fBEND\fR action terminates -the program without further execution of \fBEND\fR actions. If an expression -is specified in an \fBexit\fR statement, its numeric value is the exit status -of \fBnawk\fR, unless subsequent errors are encountered or a subsequent -\fBexit\fR statement with an expression is executed. - -.SS "Output Statements" -.LP -Both \fBprint\fR and \fBprintf\fR statements write to standard output by -default. The output is written to the location specified by -\fIoutput_redirection\fR if one is supplied, as follows: -.sp -.in +2 -.nf -\fB>\fR \fIexpression\fR\fB>>\fR \fIexpression\fR\fB|\fR \fIexpression\fR -.fi -.in -2 - -.sp -.LP -In all cases, the \fIexpression\fR is evaluated to produce a string that is -used as a full pathname to write into (for \fB>\fR or \fB>>\fR) or as a command -to be executed (for \fB|\fR). Using the first two forms, if the file of that -name is not currently open, it is opened, creating it if necessary and using -the first form, truncating the file. The output then is appended to the file. -As long as the file remains open, subsequent calls in which \fIexpression\fR -evaluates to the same string value simply appends output to the file. The file -remains open until the \fBclose\fR function, which is called with an expression -that evaluates to the same string value. -.sp -.LP -The third form writes output onto a stream piped to the input of a command. The -stream is created if no stream is currently open with the value of -\fIexpression\fR as its command name. The stream created is equivalent to one -created by a call to the \fBpopen\fR(3C) function with the value of -\fIexpression\fR as the \fIcommand\fR argument and a value of \fBw\fR as the -\fImode\fR argument. As long as the stream remains open, subsequent calls in -which \fIexpression\fR evaluates to the same string value writes output to the -existing stream. The stream remains open until the \fBclose\fR function is -called with an expression that evaluates to the same string value. At that -time, the stream is closed as if by a call to the \fBpclose\fR function. -.sp -.LP -These output statements take a comma-separated list of \fIexpression\fR \fIs\fR -referred in the grammar by the non-terminal symbols \fBexpr_list,\fR -\fBprint_expr_list\fR or \fBprint_expr_list_opt.\fR This list is referred to -here as the \fIexpression list\fR, and each member is referred to as an -\fIexpression argument\fR. -.sp -.LP -The \fBprint\fR statement writes the value of each expression argument onto the -indicated output stream separated by the current output field separator (see -variable \fBOFS\fR above), and terminated by the output record separator (see -variable \fBORS\fR above). All expression arguments is taken as strings, being -converted if necessary; with the exception that the \fBprintf\fR format in -\fBOFMT\fR is used instead of the value in \fBCONVFMT\fR. An empty expression -list stands for the whole input record \fB(\fR$0\fB)\fR. -.sp -.LP -The \fBprintf\fR statement produces output based on a notation similar to the -File Format Notation used to describe file formats in this document Output is -produced as specified with the first expression argument as the string -\fBformat\fR and subsequent expression arguments as the strings \fBarg1\fR to -\fBargn,\fR inclusive, with the following exceptions: -.RS +4 -.TP -1. -The \fIformat\fR is an actual character string rather than a graphical -representation. Therefore, it cannot contain empty character positions. The -space character in the \fIformat\fR string, in any context other than a -\fIflag\fR of a conversion specification, is treated as an ordinary character -that is copied to the output. -.RE -.RS +4 -.TP -2. -If the character set contains a Delta character and that character appears -in the \fIformat\fR string, it is treated as an ordinary character that is -copied to the output. -.RE -.RS +4 -.TP -3. -The \fIescape sequences\fR beginning with a backslash character is treated -as sequences of ordinary characters that are copied to the output. Note that -these same sequences is interpreted lexically by \fBnawk\fR when they appear in -literal strings, but they is not treated specially by the \fBprintf\fR -statement. -.RE -.RS +4 -.TP -4. -A \fIfield width\fR or \fIprecision\fR can be specified as the \fB*\fR -character instead of a digit string. In this case the next argument from the -expression list is fetched and its numeric value taken as the field width or -precision. -.RE -.RS +4 -.TP -5. -The implementation does not precede or follow output from the \fBd\fR or -\fBu\fR conversion specifications with blank characters not specified by the -\fIformat\fR string. -.RE -.RS +4 -.TP -6. -The implementation does not precede output from the \fBo\fR conversion -specification with leading zeros not specified by the \fIformat\fR string. -.RE -.RS +4 -.TP -7. -For the \fBc\fR conversion specification: if the argument has a numeric -value, the character whose encoding is that value is output. If the value is -zero or is not the encoding of any character in the character set, the behavior -is undefined. If the argument does not have a numeric value, the first -character of the string value is output; if the string does not contain any -characters the behavior is undefined. -.RE -.RS +4 -.TP -8. -For each conversion specification that consumes an argument, the next -expression argument is evaluated. With the exception of the \fBc\fR conversion, -the value is converted to the appropriate type for the conversion -specification. -.RE -.RS +4 -.TP -9. -If there are insufficient expression arguments to satisfy all the conversion -specifications in the \fIformat\fR string, the behavior is undefined. -.RE -.RS +4 -.TP -10. -If any character sequence in the \fIformat\fR string begins with a % -character, but does not form a valid conversion specification, the behavior is -unspecified. -.RE -.sp -.LP -Both \fBprint\fR and \fBprintf\fR can output at least \fB{LINE_MAX}\fR bytes. - -.SS "Functions" -.LP -The \fBnawk\fR language has a variety of built-in functions: arithmetic, -string, input/output and general. - -.SS "Arithmetic Functions" -.LP -The arithmetic functions, except for \fBint\fR, are based on the \fBISO\fR -\fBC\fR standard. The behavior is undefined in cases where the \fBISO\fR -\fBC\fR standard specifies that an error be returned or that the behavior is -undefined. Although the grammar permits built-in functions to appear with no -arguments or parentheses, unless the argument or parentheses are indicated as -optional in the following list (by displaying them within the \fB[ ]\fR -brackets), such use is undefined. -.sp -.ne 2 -.na -\fB\fBatan2(\fR\fIy\fR,\fIx\fR\fB)\fR\fR -.ad -.RS 17n -Return arctangent of \fIy\fR/\fIx\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBcos\fR(\fIx\fR)\fR -.ad -.RS 17n -Return cosine of \fIx,\fR where \fIx\fR is in radians. -.RE - -.sp -.ne 2 -.na -\fB\fBsin\fR(\fIx\fR)\fR -.ad -.RS 17n -Return sine of \fIx,\fR where \fIx\fR is in radians. -.RE - -.sp -.ne 2 -.na -\fB\fBexp\fR(\fIx\fR)\fR -.ad -.RS 17n -Return the exponential function of \fIx\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBlog\fR(\fIx\fR)\fR -.ad -.RS 17n -Return the natural logarithm of \fIx\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBsqrt\fR(\fIx\fR)\fR -.ad -.RS 17n -Return the square root of \fIx\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBint\fR(\fIx\fR)\fR -.ad -.RS 17n -Truncate its argument to an integer. It is truncated toward 0 when \fIx\fR > 0. -.RE - -.sp -.ne 2 -.na -\fB\fBrand()\fR\fR -.ad -.RS 17n -Return a random number \fIn\fR, such that 0 \(<= \fIn\fR < 1. -.RE - -.sp -.ne 2 -.na -\fB\fBsrand\fR([\fBexpr\fR])\fR -.ad -.RS 17n -Set the seed value for \fBrand\fR to \fIexpr\fR or use the time of day if -\fIexpr\fR is omitted. The previous seed value is returned. -.RE - -.SS "String Functions" -.LP -The string functions in the following list shall be supported. Although the -grammar permits built-in functions to appear with no arguments or parentheses, -unless the argument or parentheses are indicated as optional in the following -list (by displaying them within the \fB[ ]\fR brackets), such use is undefined. -.sp -.ne 2 -.na -\fB\fBgsub\fR(\fIere\fR,\fIrepl\fR[,\|\fIin\fR])\fR -.ad -.sp .6 -.RS 4n -Behave like \fBsub\fR (see below), except that it replaces all occurrences of -the regular expression (like the \fBed\fR utility global substitute) in -\fB$0\fR or in the \fIin\fR argument, when specified. -.RE - -.sp -.ne 2 -.na -\fB\fBindex\fR(\fIs\fR,\fIt\fR)\fR -.ad -.sp .6 -.RS 4n -Return the position, in characters, numbering from 1, in string \fIs\fR where -string \fIt\fR first occurs, or zero if it does not occur at all. -.RE - -.sp -.ne 2 -.na -\fB\fBlength\fR[([\fIv\fR])]\fR -.ad -.sp .6 -.RS 4n -Given no argument, this function returns the length of the whole record, -\fB$0\fR. If given an array as an argument (and using \fB/usr/bin/nawk\fR), -then this returns the number of elements it contains. Otherwise, this function -interprets the argument as a string (performing any needed conversions) and -returns its length in characters. -.RE - -.sp -.ne 2 -.na -\fB\fBmatch\fR(\fIs\fR,\fIere\fR)\fR -.ad -.sp .6 -.RS 4n -Return the position, in characters, numbering from 1, in string \fIs\fR where -the extended regular expression \fIere\fR occurs, or zero if it does not occur -at all. \fBRSTART\fR is set to the starting position (which is the same as the -returned value), zero if no match is found; \fBRLENGTH\fR is set to the length -of the matched string, \(mi1 if no match is found. -.RE - -.sp -.ne 2 -.na -\fB\fBsplit\fR(\fIs\fR,\fIa\fR[,\|\fIfs\fR])\fR -.ad -.sp .6 -.RS 4n -Split the string \fIs\fR into array elements \fIa\fR[1], \fIa\fR[2], -\fB\&...,\fR \fIa\fR[\fIn\fR], and return \fIn\fR. The separation is done with -the extended regular expression \fIfs\fR or with the field separator \fBFS\fR -if \fIfs\fR is not given. Each array element has a string value when created. -If the string assigned to any array element, with any occurrence of the -decimal-point character from the current locale changed to a period character, -would be considered a \fInumeric string\fR; the array element also has the -numeric value of the \fInumeric string\fR. The effect of a null string as the -value of \fIfs\fR is unspecified. -.RE - -.sp -.ne 2 -.na -\fB\fBsprintf\fR(\fBfmt\fR,\fIexpr\fR,\fIexpr\fR,\fB\&...\fR)\fR -.ad -.sp .6 -.RS 4n -Format the expressions according to the \fBprintf\fR format given by \fIfmt\fR -and return the resulting string. -.RE - -.sp -.ne 2 -.na -\fB\fBsub\fR(\fIere\fR,\fIrepl\fR[,\|\fIin\fR])\fR -.ad -.sp .6 -.RS 4n -Substitute the string \fIrepl\fR in place of the first instance of the extended -regular expression \fBERE\fR in string in and return the number of -substitutions. An ampersand ( \fB&\fR ) appearing in the string \fIrepl\fR is -replaced by the string from in that matches the regular expression. An -ampersand preceded with a backslash ( \fB\e\fR ) is interpreted as the literal -ampersand character. An occurrence of two consecutive backslashes is -interpreted as just a single literal backslash character. Any other occurrence -of a backslash (for example, preceding any other character) is treated as a -literal backslash character. If \fIrepl\fR is a string literal, the handling of -the ampersand character occurs after any lexical processing, including any -lexical backslash escape sequence processing. If \fBin\fR is specified and it -is not an \fBlvalue\fR the behavior is undefined. If in is omitted, \fBnawk\fR -uses the current record (\fB$0\fR) in its place. -.RE - -.sp -.ne 2 -.na -\fB\fBsubstr\fR(\fIs\fR,\fIm\fR[,\|\fIn\fR])\fR -.ad -.sp .6 -.RS 4n -Return the at most \fIn\fR-character substring of \fIs\fR that begins at -position \fIm,\fR numbering from 1. If \fIn\fR is missing, the length of the -substring is limited by the length of the string \fIs\fR. -.RE - -.sp -.ne 2 -.na -\fB\fBtolower\fR(\fIs\fR)\fR -.ad -.sp .6 -.RS 4n -Return a string based on the string \fIs\fR. Each character in \fIs\fR that is -an upper-case letter specified to have a \fBtolower\fR mapping by the -\fBLC_CTYPE\fR category of the current locale is replaced in the returned -string by the lower-case letter specified by the mapping. Other characters in -\fIs\fR are unchanged in the returned string. -.RE - -.sp -.ne 2 -.na -\fB\fBtoupper\fR(\fIs\fR)\fR -.ad -.sp .6 -.RS 4n -Return a string based on the string \fIs\fR. Each character in \fIs\fR that is -a lower-case letter specified to have a \fBtoupper\fR mapping by the -\fBLC_CTYPE\fR category of the current locale is replaced in the returned -string by the upper-case letter specified by the mapping. Other characters in -\fIs\fR are unchanged in the returned string. -.RE - -.sp -.LP -All of the preceding functions that take \fIERE\fR as a parameter expect a -pattern or a string valued expression that is a regular expression as defined -below. - -.SS "Input/Output and General Functions" -.LP -The input/output and general functions are: -.sp -.ne 2 -.na -\fB\fBclose(\fR\fIexpression\fR)\fR -.ad -.RS 27n -Close the file or pipe opened by a \fBprint\fR or \fBprintf\fR statement or a -call to \fBgetline\fR with the same string-valued \fIexpression\fR. If the -close was successful, the function returns \fB0\fR; otherwise, it returns -non-zero. -.RE - -.sp -.ne 2 -.na -\fB\fBfflush(\fR\fIexpression\fR)\fR -.ad -.RS 27n -Flush any buffered output for the file or pipe opened by a \fBprint\fR or -\fBprintf\fR statement or a call to \fBgetline\fR with the same string-valued -\fIexpression\fR. If the flush was successful, the function returns \fB0\fR; -otherwise, it returns \fBEOF\fR. If no arguments or the empty string -(\fB""\fR) are given, then all open files will be flushed. (Note that -\fBfflush\fR is supported in \fB/usr/bin/nawk\fR only.) -.RE - -.sp -.ne 2 -.na -\fB\fIexpression\fR|\fBgetline\fR[\fIvar\fR]\fR -.ad -.RS 27n -Read a record of input from a stream piped from the output of a command. The -stream is created if no stream is currently open with the value of -\fIexpression\fR as its command name. The stream created is equivalent to one -created by a call to the \fBpopen\fR function with the value of -\fIexpression\fR as the \fIcommand\fR argument and a value of \fBr\fR as the -\fImode\fR argument. As long as the stream remains open, subsequent calls in -which \fIexpression\fR evaluates to the same string value reads subsequent -records from the file. The stream remains open until the \fBclose\fR function -is called with an expression that evaluates to the same string value. At that -time, the stream is closed as if by a call to the \fBpclose\fR function. If -\fIvar\fR is missing, \fB$0\fR and \fBNF\fR is set. Otherwise, \fIvar\fR is -set. -.sp -The \fBgetline\fR operator can form ambiguous constructs when there are -operators that are not in parentheses (including concatenate) to the left of -the \fB|\fR (to the beginning of the expression containing \fBgetline\fR). In -the context of the \fB$\fR operator, \fB|\fR behaves as if it had a lower -precedence than \fB$\fR. The result of evaluating other operators is -unspecified, and all such uses of portable applications must be put in -parentheses properly. -.RE - -.sp -.ne 2 -.na -\fB\fBgetline\fR\fR -.ad -.RS 27n -Set \fB$0\fR to the next input record from the current input file. This form of -\fBgetline\fR sets the \fBNF\fR, \fBNR\fR, and \fBFNR\fR variables. -.RE - -.sp -.ne 2 -.na -\fB\fBgetline\fR \fIvar\fR\fR -.ad -.RS 27n -Set variable \fIvar\fR to the next input record from the current input file. -This form of \fBgetline\fR sets the \fBFNR\fR and \fBNR\fR variables. -.RE - -.sp -.ne 2 -.na -\fB\fBgetline\fR [\fIvar\fR] \fB<\fR \fIexpression\fR\fR -.ad -.RS 27n -Read the next record of input from a named file. The \fIexpression\fR is -evaluated to produce a string that is used as a full pathname. If the file of -that name is not currently open, it is opened. As long as the stream remains -open, subsequent calls in which \fIexpression\fR evaluates to the same string -value reads subsequent records from the file. The file remains open until the -\fBclose\fR function is called with an expression that evaluates to the same -string value. If \fIvar\fR is missing, \fB$0\fR and \fBNF\fR is set. Otherwise, -\fIvar\fR is set. -.sp -The \fBgetline\fR operator can form ambiguous constructs when there are binary -operators that are not in parentheses (including concatenate) to the right of -the \fB<\fR (up to the end of the expression containing the \fBgetline\fR). The -result of evaluating such a construct is unspecified, and all such uses of -portable applications must be put in parentheses properly. -.RE - -.sp -.ne 2 -.na -\fB\fBsystem\fR(\fIexpression\fR)\fR -.ad -.RS 27n -Execute the command given by \fIexpression\fR in a manner equivalent to the -\fBsystem\fR(3C) function and return the exit status of the command. -.RE - -.sp -.LP -All forms of \fBgetline\fR return \fB1\fR for successful input, \fB0\fR for end -of file, and \fB\(mi1\fR for an error. -.sp -.LP -Where strings are used as the name of a file or pipeline, the strings must be -textually identical. The terminology ``same string value'' implies that -``equivalent strings'', even those that differ only by space characters, -represent different files. - -.SS "User-defined Functions" -.LP -The \fBnawk\fR language also provides user-defined functions. Such functions -can be defined as: -.sp -.in +2 -.nf -\fBfunction\fR \fIname\fR(\fIargs\fR,\|.\|.\|.) { \fIstatements\fR } -.fi -.in -2 - -.sp -.LP -A function can be referred to anywhere in an \fBnawk\fR program; in particular, -its use can precede its definition. The scope of a function is global. -.sp -.LP -Function arguments can be either scalars or arrays; the behavior is undefined -if an array name is passed as an argument that the function uses as a scalar, -or if a scalar expression is passed as an argument that the function uses as an -array. Function arguments are passed by value if scalar and by reference if -array name. Argument names are local to the function; all other variable names -are global. The same name is not used as both an argument name and as the name -of a function or a special \fBnawk\fR variable. The same name must not be used -both as a variable name with global scope and as the name of a function. The -same name must not be used within the same scope both as a scalar variable and -as an array. -.sp -.LP -The number of parameters in the function definition need not match the number -of parameters in the function call. Excess formal parameters can be used as -local variables. If fewer arguments are supplied in a function call than are in -the function definition, the extra parameters that are used in the function -body as scalars are initialized with a string value of the null string and a -numeric value of zero, and the extra parameters that are used in the function -body as arrays are initialized as empty arrays. If more arguments are supplied -in a function call than are in the function definition, the behavior is -undefined. -.sp -.LP -When invoking a function, no white space can be placed between the function -name and the opening parenthesis. Function calls can be nested and recursive -calls can be made upon functions. Upon return from any nested or recursive -function call, the values of all of the calling function's parameters are -unchanged, except for array parameters passed by reference. The \fBreturn\fR -statement can be used to return a value. If a \fBreturn\fR statement appears -outside of a function definition, the behavior is undefined. -.sp -.LP -In the function definition, newline characters are optional before the opening -brace and after the closing brace. Function definitions can appear anywhere in -the program where a \fIpattern-action\fR pair is allowed. - -.SH USAGE -.LP -The \fBindex\fR, \fBlength\fR, \fBmatch\fR, and \fBsubstr\fR functions should -not be confused with similar functions in the \fBISO C\fR standard; the -\fBnawk\fR versions deal with characters, while the \fBISO C\fR standard deals -with bytes. -.sp -.LP -Because the concatenation operation is represented by adjacent expressions -rather than an explicit operator, it is often necessary to use parentheses to -enforce the proper evaluation precedence. -.sp -.LP -See \fBlargefile\fR(5) for the description of the behavior of \fBnawk\fR when -encountering files greater than or equal to 2 Gbyte (2^31 bytes). - -.SH EXAMPLES -.LP -The \fBnawk\fR program specified in the command line is most easily specified -within single-quotes (for example, \fB\&'\fR\fIprogram\fR\fB\&'\fR) for -applications using \fBsh\fR, because \fBnawk\fR programs commonly contain -characters that are special to the shell, including double-quotes. In the cases -where a \fBnawk\fR program contains single-quote characters, it is usually -easiest to specify most of the program as strings within single-quotes -concatenated by the shell with quoted single-quote characters. For example: -.sp -.in +2 -.nf -nawk '/'\e''/ { print "quote:", $0 }' -.fi -.in -2 - -.sp -.LP -prints all lines from the standard input containing a single-quote character, -prefixed with \fBquote:\fR. -.sp -.LP -The following are examples of simple \fBnawk\fR programs: -.LP -\fBExample 1 \fRWrite to the standard output all input lines for which field 3 -is greater than 5: -.sp -.in +2 -.nf -\fB$3 > 5\fR -.fi -.in -2 -.sp - -.LP -\fBExample 2 \fRWrite every tenth line: -.sp -.in +2 -.nf -\fB(NR % 10) == 0\fR -.fi -.in -2 -.sp - -.LP -\fBExample 3 \fRWrite any line with a substring matching the regular -expression: -.sp -.in +2 -.nf -\fB/(G|D)(2[0-9][[:alpha:]]*)/\fR -.fi -.in -2 -.sp - -.LP -\fBExample 4 \fRPrint any line with a substring containing a G or D, followed -by a sequence of digits and characters: -.sp -.LP -This example uses character classes \fBdigit\fR and \fBalpha\fR to match -language-independent digit and alphabetic characters, respectively. - -.sp -.in +2 -.nf -\fB/(G|D)([[:digit:][:alpha:]]*)/\fR -.fi -.in -2 -.sp - -.LP -\fBExample 5 \fRWrite any line in which the second field matches the regular -expression and the fourth field does not: -.sp -.in +2 -.nf -\fB$2 ~ /xyz/ && $4 !~ /xyz/\fR -.fi -.in -2 -.sp - -.LP -\fBExample 6 \fRWrite any line in which the second field contains a backslash: -.sp -.in +2 -.nf -\fB$2 ~ /\e\e/\fR -.fi -.in -2 -.sp - -.LP -\fBExample 7 \fRWrite any line in which the second field contains a backslash -(alternate method): -.sp -.LP -Notice that backslash escapes are interpreted twice, once in lexical processing -of the string and once in processing the regular expression. - -.sp -.in +2 -.nf -\fB$2 ~ "\e\e\e\e"\fR -.fi -.in -2 -.sp - -.LP -\fBExample 8 \fRWrite the second to the last and the last field in each line, -separating the fields by a colon: -.sp -.in +2 -.nf -\fB{OFS=":";print $(NF-1), $NF}\fR -.fi -.in -2 -.sp - -.LP -\fBExample 9 \fRWrite the line number and number of fields in each line: -.sp -.LP -The three strings representing the line number, the colon and the number of -fields are concatenated and that string is written to standard output. - -.sp -.in +2 -.nf -\fB{print NR ":" NF}\fR -.fi -.in -2 -.sp - -.LP -\fBExample 10 \fRWrite lines longer than 72 characters: -.sp -.in +2 -.nf -\fB{length($0) > 72}\fR -.fi -.in -2 -.sp - -.LP -\fBExample 11 \fRWrite first two fields in opposite order separated by the OFS: -.sp -.in +2 -.nf -\fB{ print $2, $1 }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 12 \fRSame, with input fields separated by comma or space and tab -characters, or both: -.sp -.in +2 -.nf -\fBBEGIN { FS = ",[\et]*|[\et]+" } - { print $2, $1 }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 13 \fRAdd up first column, print sum and average: -.sp -.in +2 -.nf -\fB{s += $1 } -END {print "sum is ", s, " average is", s/NR}\fR -.fi -.in -2 -.sp - -.LP -\fBExample 14 \fRWrite fields in reverse order, one per line (many lines out -for each line in): -.sp -.in +2 -.nf -\fB{ for (i = NF; i > 0; --i) print $i }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 15 \fRWrite all lines between occurrences of the strings "start" and -"stop": -.sp -.in +2 -.nf -\fB/start/, /stop/\fR -.fi -.in -2 -.sp - -.LP -\fBExample 16 \fRWrite all lines whose first field is different from the -previous one: -.sp -.in +2 -.nf -\fB$1 != prev { print; prev = $1 }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 17 \fRSimulate the echo command: -.sp -.in +2 -.nf -\fBBEGIN { - for (i = 1; i < ARGC; ++i) - printf "%s%s", ARGV[i], i==ARGC-1?"\en":"" - }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 18 \fRWrite the path prefixes contained in the PATH environment -variable, one per line: -.sp -.in +2 -.nf -\fBBEGIN { - n = split (ENVIRON["PATH"], path, ":") - for (i = 1; i <= n; ++i) - print path[i] - }\fR -.fi -.in -2 -.sp - -.LP -\fBExample 19 \fRPrint the file "input", filling in page numbers starting at 5: -.sp -.LP -If there is a file named \fBinput\fR containing page headers of the form - -.sp -.in +2 -.nf -Page# -.fi -.in -2 - -.sp -.LP -and a file named \fBprogram\fR that contains - -.sp -.in +2 -.nf -/Page/{ $2 = n++; } -{ print } -.fi -.in -2 - -.sp -.LP -then the command line - -.sp -.in +2 -.nf -\fBnawk -f program n=5 input\fR -.fi -.in -2 -.sp - -.sp -.LP -prints the file \fBinput\fR, filling in page numbers starting at 5. - -.SH ENVIRONMENT VARIABLES -.LP -See \fBenviron\fR(5) for descriptions of the following environment variables -that affect execution: \fBLC_COLLATE\fR, \fBLC_CTYPE\fR, \fBLC_MESSAGES\fR, and -\fBNLSPATH\fR. -.sp -.ne 2 -.na -\fB\fBLC_NUMERIC\fR\fR -.ad -.RS 14n -Determine the radix character used when interpreting numeric input, performing -conversions between numeric and string values and formatting numeric output. -Regardless of locale, the period character (the decimal-point character of the -POSIX locale) is the decimal-point character recognized in processing \fBawk\fR -programs (including assignments in command-line arguments). -.RE - -.SH EXIT STATUS -.LP -The following exit values are returned: -.sp -.ne 2 -.na -\fB\fB0\fR\fR -.ad -.RS 6n -All input files were processed successfully. -.RE - -.sp -.ne 2 -.na -\fB\fB>0\fR\fR -.ad -.RS 6n -An error occurred. -.RE - -.sp -.LP -The exit status can be altered within the program by using an \fBexit\fR -expression. - -.SH SEE ALSO -.LP -\fBawk\fR(1), \fBed\fR(1), \fBegrep\fR(1), \fBgrep\fR(1), \fBlex\fR(1), -\fBsed\fR(1), \fBpopen\fR(3C), \fBprintf\fR(3C), \fBsystem\fR(3C), -\fBattributes\fR(5), \fBenviron\fR(5), \fBlargefile\fR(5), \fBregex\fR(5), -\fBXPG4\fR(5) -.sp -.LP -Aho, A. V., B. W. Kernighan, and P. J. Weinberger, \fIThe AWK Programming -Language\fR, Addison-Wesley, 1988. - -.SH DIAGNOSTICS -.LP -If any \fIfile\fR operand is specified and the named file cannot be accessed, -\fBnawk\fR writes a diagnostic message to standard error and terminate without -any further action. -.sp -.LP -If the program specified by either the \fIprogram\fR operand or a -\fIprogfile\fR operand is not a valid \fBnawk\fR program (as specified in -\fBEXTENDED DESCRIPTION\fR), the behavior is undefined. - -.SH NOTES -.LP -Input white space is not preserved on output if fields are involved. -.sp -.LP -There are no explicit conversions between numbers and strings. To force an -expression to be treated as a number add 0 to it; to force it to be treated as -a string concatenate the null string (\fB""\fR) to it. diff --git a/usr/src/man/man1/oawk.1 b/usr/src/man/man1/oawk.1 new file mode 100644 index 0000000000..da7626418c --- /dev/null +++ b/usr/src/man/man1/oawk.1 @@ -0,0 +1,597 @@ +.\" +.\" Sun Microsystems, Inc. gratefully acknowledges The Open Group for +.\" permission to reproduce portions of its copyrighted documentation. +.\" Original documentation from The Open Group can be obtained online at +.\" http://www.opengroup.org/bookstore/. +.\" +.\" The Institute of Electrical and Electronics Engineers and The Open +.\" Group, have given us permission to reprint portions of their +.\" documentation. +.\" +.\" In the following statement, the phrase ``this text'' refers to portions +.\" of the system documentation. +.\" +.\" Portions of this text are reprinted and reproduced in electronic form +.\" in the SunOS Reference Manual, from IEEE Std 1003.1, 2004 Edition, +.\" Standard for Information Technology -- Portable Operating System +.\" Interface (POSIX), The Open Group Base Specifications Issue 6, +.\" Copyright (C) 2001-2004 by the Institute of Electrical and Electronics +.\" Engineers, Inc and The Open Group. In the event of any discrepancy +.\" between these versions and the original IEEE and The Open Group +.\" Standard, the original IEEE and The Open Group Standard is the referee +.\" document. The original Standard can be obtained online at +.\" http://www.opengroup.org/unix/online.html. +.\" +.\" This notice shall appear on any product containing this material. +.\" +.\" The contents of this file are subject to the terms of the +.\" Common Development and Distribution License (the "License"). +.\" You may not use this file except in compliance with the License. +.\" +.\" You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +.\" or http://www.opensolaris.org/os/licensing. +.\" See the License for the specific language governing permissions +.\" and limitations under the License. +.\" +.\" When distributing Covered Code, include this CDDL HEADER in each +.\" file and include the License file at usr/src/OPENSOLARIS.LICENSE. +.\" If applicable, add the following below this CDDL HEADER, with the +.\" fields enclosed by brackets "[]" replaced with your own identifying +.\" information: Portions Copyright [yyyy] [name of copyright owner] +.\" +.\" +.\" Copyright 1989 AT&T +.\" Portions Copyright (c) 1992, X/Open Company Limited. All Rights Reserved. +.\" Copyright (c) 2005, Sun Microsystems, Inc. All Rights Reserved +.\" Copyright 2020 Joyent, Inc. +.\" +.TH OAWK 1 "Apr 20, 2020" +.SH NAME +oawk \- (older) pattern scanning and processing language +.SH SYNOPSIS +.nf +\fB/usr/bin/oawk\fR [\fB-f\fR \fIprogfile\fR] [\fB-F\fIc\fR\fR] [' \fIprog\fR '] [\fIparameters\fR] + [\fIfilename\fR]... +.fi + +.SH DESCRIPTION +This command is now obsolete, and will be removed from illumos at some point. +.sp +.LP +The \fB/usr/bin/oawk\fR utility scans each input \fIfilename\fR for lines that +match any of a set of patterns specified in \fIprog\fR. The \fIprog\fR string +must be enclosed in single quotes (\fB a\'\fR) to protect it from the shell. +For each pattern in \fIprog\fR there can be an associated action performed when +a line of a \fIfilename\fR matches the pattern. The set of pattern-action +statements can appear literally as \fIprog\fR or in a file specified with the +\fB-f\fR\fI progfile\fR option. Input files are read in order; if there are no +files, the standard input is read. The file name \fB\&'\(mi'\fR means the +standard input. +.SH OPTIONS +The following options are supported: +.sp +.ne 2 +.na +\fB\fB-f\fR\fI progfile\fR \fR +.ad +.RS 16n +\fBoawk\fR uses the set of patterns it reads from \fIprogfile\fR. +.RE + +.sp +.ne 2 +.na +\fB\fB-F\fR\fIc\fR \fR +.ad +.RS 16n +Uses the character \fIc\fR as the field separator (FS) character. See the +discussion of \fBFS\fR below. +.RE + +.SH USAGE +.SS "Input Lines" +Each input line is matched against the pattern portion of every pattern-action +statement; the associated action is performed for each matched pattern. Any +\fIfilename\fR of the form \fIvar=value\fR is treated as an assignment, not a +filename, and is executed at the time it would have been opened if it were a +filename. \fIVariables\fR assigned in this manner are not available inside a +\fBBEGIN\fR rule, and are assigned after previously specified files have been +read. +.sp +.LP +An input line is normally made up of fields separated by white spaces. (This +default can be changed by using the \fBFS\fR built-in variable or the +\fB-F\fR\fIc\fR option.) The default is to ignore leading blanks and to +separate fields by blanks and/or tab characters. However, if \fBFS\fR is +assigned a value that does not include any of the white spaces, then leading +blanks are not ignored. The fields are denoted \fB$1\fR, \fB$2\fR, +\fB\&.\|.\|.\fR\|; \fB$0\fR refers to the entire line. +.SS "Pattern-action Statements" +A pattern-action statement has the form: +.sp +.in +2 +.nf +\fIpattern\fR\fB { \fR\fIaction\fR\fB } \fR +.fi +.in -2 +.sp + +.sp +.LP +Either pattern or action can be omitted. If there is no action, the matching +line is printed. If there is no pattern, the action is performed on every input +line. Pattern-action statements are separated by newlines or semicolons. +.sp +.LP +Patterns are arbitrary Boolean combinations ( \fB!\fR, ||, \fB&&\fR, and +parentheses) of relational expressions and regular expressions. A relational +expression is one of the following: +.sp +.in +2 +.nf +\fIexpression relop expression +expression matchop regular_expression\fR +.fi +.in -2 + +.sp +.LP +where a \fIrelop\fR is any of the six relational operators in C, and a +\fImatchop\fR is either \fB~\fR (contains) or \fB!~\fR (does not contain). An +\fIexpression\fR is an arithmetic expression, a relational expression, the +special expression +.sp +.in +2 +.nf +\fIvar \fRin \fIarray\fR +.fi +.in -2 + +.sp +.LP +or a Boolean combination of these. +.sp +.LP +Regular expressions are as in \fBegrep\fR(1). In patterns they must be +surrounded by slashes. Isolated regular expressions in a pattern apply to the +entire line. Regular expressions can also occur in relational expressions. A +pattern can consist of two patterns separated by a comma; in this case, the +action is performed for all lines between the occurrence of the first pattern +to the occurrence of the second pattern. +.sp +.LP +The special patterns \fBBEGIN\fR and \fBEND\fR can be used to capture control +before the first input line has been read and after the last input line has +been read respectively. These keywords do not combine with any other patterns. +.SS "Built-in Variables" +Built-in variables include: +.sp +.ne 2 +.na +\fB\fBFILENAME\fR \fR +.ad +.RS 13n +name of the current input file +.RE + +.sp +.ne 2 +.na +\fB\fBFS\fR \fR +.ad +.RS 13n +input field separator regular expression (default blank and tab) +.RE + +.sp +.ne 2 +.na +\fB\fBNF\fR \fR +.ad +.RS 13n +number of fields in the current record +.RE + +.sp +.ne 2 +.na +\fB\fBNR\fR \fR +.ad +.RS 13n +ordinal number of the current record +.RE + +.sp +.ne 2 +.na +\fB\fBOFMT\fR \fR +.ad +.RS 13n +output format for numbers (default \fB%.6g\fR) +.RE + +.sp +.ne 2 +.na +\fB\fBOFS\fR \fR +.ad +.RS 13n +output field separator (default blank) +.RE + +.sp +.ne 2 +.na +\fB\fBORS\fR \fR +.ad +.RS 13n +output record separator (default new-line) +.RE + +.sp +.ne 2 +.na +\fB\fBRS\fR \fR +.ad +.RS 13n +input record separator (default new-line) +.RE + +.sp +.LP +An action is a sequence of statements. A statement can be one of the following: +.sp +.in +2 +.nf +if ( \fIexpression\fR ) \fIstatement\fR [ else \fIstatement\fR ] +while ( \fIexpression\fR ) \fIstatement\fR +do \fIstatement\fR while ( \fIexpression\fR ) +for ( \fIexpression\fR ; \fIexpression\fR ; \fIexpression\fR ) \fIstatement\fR +for ( \fIvar\fR in \fIarray\fR ) \fIstatement\fR +break +continue +{ [ \fIstatement\fR ] .\|.\|. } +\fIexpression\fR # commonly variable = expression +print [ \fIexpression-list\fR ] [ >\fIexpression\fR ] +printf format [ ,\fIexpression-list\fR ] [ >\fIexpression\fR ] +next # skip remaining patterns on this input line +exit [expr] # skip the rest of the input; exit status is expr +.fi +.in -2 + +.sp +.LP +Statements are terminated by semicolons, newlines, or right braces. An empty +expression-list stands for the whole input line. Expressions take on string or +numeric values as appropriate, and are built using the operators \fB+\fR, +\fB\(mi\fR, \fB*\fR, \fB/\fR, \fB%\fR, \fB^\fR and concatenation (indicated by +a blank). The operators \fB++\fR, \fB\(mi\(mi\fR, \fB+=\fR, \fB\(mi=\fR, +\fB*=\fR, \fB/=\fR, \fB%=\fR, \fB^=\fR, \fB>\fR, \fB>=\fR, \fB<\fR, \fB<=\fR, +\fB==\fR, \fB!=\fR, and \fB?:\fR are also available in expressions. Variables +can be scalars, array elements (denoted x[i]), or fields. Variables are +initialized to the null string or zero. Array subscripts can be any string, not +necessarily numeric; this allows for a form of associative memory. String +constants are quoted (\fB""\fR), with the usual C escapes recognized within. +.sp +.LP +The \fBprint\fR statement prints its arguments on the standard output, or on a +file if \fB>\fR\fIexpression\fR is present, or on a pipe if '\fB|\fR\fIcmd\fR' +is present. The output resulted from the print statement is terminated by the +output record separator with each argument separated by the current output +field separator. The \fBprintf\fR statement formats its expression list +according to the format (see \fBprintf\fR(3C)). +.SS "Built-in Functions" +The arithmetic functions are as follows: +.sp +.ne 2 +.na +\fB\fBexp\fR(\fIx\fR)\fR +.ad +.RS 11n +Return the exponential function of \fIx\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBlog\fR(\fIx\fR)\fR +.ad +.RS 11n +Return the natural logarithm of \fIx\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBsqrt\fR(\fIx\fR)\fR +.ad +.RS 11n +Return the square root of \fIx\fR. +.RE + +.sp +.ne 2 +.na +\fB\fBint\fR(\fIx\fR)\fR +.ad +.RS 11n +Truncate its argument to an integer. It is truncated toward \fB0\fR when +\fIx\fR >\fB 0\fR. +.RE + +.sp +.LP +The string functions are as follows: +.sp +.ne 2 +.na +\fB\fBindex(\fR\fIs\fR\fB, \fR\fIt\fR\fB)\fR\fR +.ad +.sp .6 +.RS 4n +Return the position in string \fIs\fR where string \fIt\fR first occurs, or +\fB0\fR if it does not occur at all. +.RE + +.sp +.ne 2 +.na +\fB\fBint(\fR\fIs\fR\fB)\fR\fR +.ad +.sp .6 +.RS 4n +truncates \fIs\fR to an integer value. If \fIs\fR is not specified, $0 is used. +.RE + +.sp +.ne 2 +.na +\fB\fBlength(\fR\fIs\fR\fB)\fR\fR +.ad +.sp .6 +.RS 4n +Return the length of its argument taken as a string, or of the whole line if +there is no argument. +.RE + +.sp +.ne 2 +.na +\fB\fBsplit(\fR\fIs\fR, \fIa\fR, \fIfs\fR\fB)\fR\fR +.ad +.sp .6 +.RS 4n +Split the string \fIs\fR into array elements \fIa\fR[\fI1\fR], +\fIa\fR[\fI2\fR], \|.\|.\|. \fIa\fR[\fIn\fR], and returns \fIn\fR. The +separation is done with the regular expression \fIfs\fR or with the field +separator \fBFS\fR if \fIfs\fR is not given. +.RE + +.sp +.ne 2 +.na +\fB\fBsprintf(\fR\fIfmt\fR, \fIexpr\fR, \fIexpr\fR,\|.\|.\|.\|\fB)\fR\fR +.ad +.sp .6 +.RS 4n +Format the expressions according to the \fBprintf\fR(3C) format given by +\fIfmt\fR and returns the resulting string. +.RE + +.sp +.ne 2 +.na +\fB\fBsubstr(\fR\fIs\fR, \fIm\fR, \fIn\fR\fB)\fR\fR +.ad +.sp .6 +.RS 4n +returns the \fIn\fR-character substring of \fIs\fR that begins at position +\fIm\fR. +.RE + +.sp +.LP +The input/output function is as follows: +.sp +.ne 2 +.na +\fB\fBgetline\fR\fR +.ad +.RS 11n +Set \fB$0\fR to the next input record from the current input file. +\fBgetline\fR returns \fB1\fR for successful input, \fB0\fR for end of file, +and \fB\(mi1\fR for an error. +.RE + +.SS "Large File Behavior" +See \fBlargefile\fR(5) for the description of the behavior of \fBoawk\fR when +encountering files greater than or equal to 2 Gbyte ( 2^31 bytes). +.SH EXAMPLES +\fBExample 1 \fRPrinting Lines Longer Than 72 Characters +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints lines longer than +seventy two characters: + +.sp +.in +2 +.nf +\fBlength > 72\fR +.fi +.in -2 +.sp + +.LP +\fBExample 2 \fRPrinting Fields in Opposite Order +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints the first two fields in +opposite order: + +.sp +.in +2 +.nf +\fB{ print $2, $1 }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 3 \fRPrinting Fields in Opposite Order with the Input Fields +Separated +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints the first two input +fields in opposite order, separated by a comma, blanks or tabs: + +.sp +.in +2 +.nf +\fBBEGIN { FS = ",[ \et]*|[ \et]+" } + { print $2, $1 }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 4 \fRAdding Up the First Column, Printing the Sum and Average +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It adds up the first column, and +prints the sum and average: + +.sp +.in +2 +.nf +\fB{ s += $1 } +END { print "sum is", s, " average is", s/NR }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 5 \fRPrinting Fields in Reverse Order +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints fields in reverse order: + +.sp +.in +2 +.nf +\fB{ for (i = NF; i > 0; \(mi\(mii) print $i }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 6 \fRPrinting All lines Between \fBstart/stop\fR Pairs +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints all lines between +start/stop pairs. + +.sp +.in +2 +.nf +\fB/start/, /stop/\fR +.fi +.in -2 +.sp + +.LP +\fBExample 7 \fRPrinting All Lines Whose First Field is Different from the +Previous One +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints all lines whose first +field is different from the previous one. + +.sp +.in +2 +.nf +\fB$1 != prev { print; prev = $1 }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 8 \fRPrinting a File and Filling in Page numbers +.sp +.LP +The following example is an \fBoawk\fR script that can be executed by an +\fBoawk -f examplescript\fR style command. It prints a file and fills in page +numbers starting at 5: + +.sp +.in +2 +.nf +\fB/Page/ { $2 = n++; } + { print }\fR +.fi +.in -2 +.sp + +.LP +\fBExample 9 \fRPrinting a File and Numbering Its Pages +.sp +.LP +Assuming this program is in a file named \fBprog\fR, the following example +prints the file \fBinput\fR numbering its pages starting at \fB5\fR: + +.sp +.in +2 +.nf +example% \fBoawk -f prog n=5 input\fR +.fi +.in -2 +.sp + +.SH ENVIRONMENT VARIABLES +See \fBenviron\fR(5) for descriptions of the following environment variables +that affect the execution of \fBoawk\fR: \fBLANG\fR, \fBLC_ALL\fR, +\fBLC_COLLATE\fR, \fBLC_CTYPE\fR, \fBLC_MESSAGES\fR, \fBNLSPATH\fR, and +\fBPATH\fR. +.sp +.ne 2 +.na +\fB\fBLC_NUMERIC\fR\fR +.ad +.RS 14n +Determine the radix character used when interpreting numeric input, +performing conversions between numeric and string values and formatting +numeric output. Regardless of locale, the period character (the +decimal-point character of the POSIX locale) is the decimal-point character +recognized in processing \fBoawk\fR programs (including assignments in +command-line arguments). +.RE + +.SH ATTRIBUTES +See \fBattributes\fR(5) for descriptions of the following attributes: +.SS "/usr/bin/oawk" + +.TS +box; +c | c +l | l . +ATTRIBUTE TYPE ATTRIBUTE VALUE +_ +CSI Not Enabled +.TE + +.SH SEE ALSO +\fBegrep\fR(1), \fBgrep\fR(1), \fBawk\fR(1), \fBsed\fR(1), \fBprintf\fR(3C), +\fBattributes\fR(5), \fBenviron\fR(5), \fBlargefile\fR(5), \fBstandards\fR(5) +.SH NOTES +Input white space is not preserved on output if fields are involved. +.sp +.LP +There are no explicit conversions between numbers and strings. To force an +expression to be treated as a number, add \fB0\fR to it. To force an expression +to be treated as a string, concatenate the null string (\fB""\fR) to it. diff --git a/usr/src/man/man7d/i40e.7d b/usr/src/man/man7d/i40e.7d index 81ab257f6e..c5ba043149 100644 --- a/usr/src/man/man7d/i40e.7d +++ b/usr/src/man/man7d/i40e.7d @@ -11,7 +11,7 @@ .\" .\" Copyright (c) 2018 Joyent, Inc. .\" -.Dd Jan 10, 2020 +.Dd April 15, 2020 .Dt I40E 7D .Os .Sh NAME @@ -44,6 +44,8 @@ Promiscuous access via IPv4 Checksum Offload .It TCP, UDP, and SCTP checksum offload +.It +IPv4 and IPv6 TCP Segmentation offload .El .Pp At this time, the diff --git a/usr/src/pkg/manifests/driver-network-bge.mf b/usr/src/pkg/manifests/driver-network-bge.mf index 6ac1368ea0..0dc0ff7a50 100644 --- a/usr/src/pkg/manifests/driver-network-bge.mf +++ b/usr/src/pkg/manifests/driver-network-bge.mf @@ -48,6 +48,16 @@ $(i386_ONLY)driver name=bge clone_perms="bge 0666 root sys" \ alias=pci108e,1648 \ alias=pci108e,16a7 \ alias=pci108e,16a8 \ + alias=pci14e4,0x1682 \ + alias=pci14e4,0x1686 \ + alias=pci14e4,0x16b0 \ + alias=pci14e4,0x16b1 \ + alias=pci14e4,0x16b2 \ + alias=pci14e4,0x16b3 \ + alias=pci14e4,0x16b4 \ + alias=pci14e4,0x16b5 \ + alias=pci14e4,0x16b6 \ + alias=pci14e4,0x16b7 \ alias=pci14e4,1600 \ alias=pci14e4,1601 \ alias=pci14e4,1644 \ @@ -77,6 +87,16 @@ $(i386_ONLY)driver name=bge clone_perms="bge 0666 root sys" \ alias=pci14e4,16a7 \ alias=pci14e4,16a8 \ alias=pci14e4,16c7 \ + alias=pciex14e4,0x1682 \ + alias=pciex14e4,0x1686 \ + alias=pciex14e4,0x16b0 \ + alias=pciex14e4,0x16b1 \ + alias=pciex14e4,0x16b2 \ + alias=pciex14e4,0x16b3 \ + alias=pciex14e4,0x16b4 \ + alias=pciex14e4,0x16b5 \ + alias=pciex14e4,0x16b6 \ + alias=pciex14e4,0x16b7 \ alias=pciex14e4,1643 \ alias=pciex14e4,1655 \ alias=pciex14e4,1656 \ @@ -106,6 +126,16 @@ $(sparc_ONLY)driver name=bge clone_perms="bge 0666 root sys" \ alias=pci108e,1648 \ alias=pci108e,16a7 \ alias=pci108e,16a8 \ + alias=pci14e4,0x1682 \ + alias=pci14e4,0x1686 \ + alias=pci14e4,0x16b0 \ + alias=pci14e4,0x16b1 \ + alias=pci14e4,0x16b2 \ + alias=pci14e4,0x16b3 \ + alias=pci14e4,0x16b4 \ + alias=pci14e4,0x16b5 \ + alias=pci14e4,0x16b6 \ + alias=pci14e4,0x16b7 \ alias=pci14e4,1645 \ alias=pci14e4,1647 \ alias=pci14e4,1648 \ @@ -118,6 +148,16 @@ $(sparc_ONLY)driver name=bge clone_perms="bge 0666 root sys" \ alias=pci14e4,16a7 \ alias=pci14e4,16a8 \ alias=pci14e4,16c7 \ + alias=pciex14e4,0x1682 \ + alias=pciex14e4,0x1686 \ + alias=pciex14e4,0x16b0 \ + alias=pciex14e4,0x16b1 \ + alias=pciex14e4,0x16b2 \ + alias=pciex14e4,0x16b3 \ + alias=pciex14e4,0x16b4 \ + alias=pciex14e4,0x16b5 \ + alias=pciex14e4,0x16b6 \ + alias=pciex14e4,0x16b7 \ alias=pciex14e4,1655 \ alias=pciex14e4,1656 \ alias=pciex14e4,1659 \ diff --git a/usr/src/pkg/manifests/driver-network-mlxcx.mf b/usr/src/pkg/manifests/driver-network-mlxcx.mf index dec1aa726c..35c6634f0d 100644 --- a/usr/src/pkg/manifests/driver-network-mlxcx.mf +++ b/usr/src/pkg/manifests/driver-network-mlxcx.mf @@ -24,7 +24,7 @@ set name=pkg.fmri value=pkg:/driver/network/mlxcx@$(PKGVERS) set name=pkg.description value="Mellanox ConnectX-4/5/6 Ethernet Driver" set name=pkg.summary value="Mellanox ConnectX-4/5/6 Ethernet Driver" set name=info.classification \ - value=org.opensolaris.category.2008:Drivers/Storage + value=org.opensolaris.category.2008:Drivers/Networking set name=variant.arch value=i386 dir path=kernel group=sys dir path=kernel/drv group=sys @@ -48,7 +48,5 @@ driver name=mlxcx \ file path=kernel/drv/$(ARCH64)/mlxcx group=sys file path=kernel/drv/mlxcx.conf group=sys file path=usr/share/man/man7d/mlxcx.7d -legacy pkg=SUNWmrsas desc="Mellanox ConnectX-4/5/6 Ethernet Driver" \ - name="Mellanox ConnectX-4/5/6 Ethernet Driver" license cr_Sun license=cr_Sun license lic_CDDL license=lic_CDDL diff --git a/usr/src/pkg/manifests/system-extended-system-utilities.mf b/usr/src/pkg/manifests/system-extended-system-utilities.mf index 0a8502a491..ea58ec0d55 100644 --- a/usr/src/pkg/manifests/system-extended-system-utilities.mf +++ b/usr/src/pkg/manifests/system-extended-system-utilities.mf @@ -23,6 +23,7 @@ # Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved. # Copyright 2012 Nexenta Systems, Inc. All rights reserved. # Copyright 2016 RackTop Systems. +# Copyright 2020 Joyent, Inc. # set name=pkg.fmri value=pkg:/system/extended-system-utilities@$(PKGVERS) @@ -117,10 +118,10 @@ file path=usr/bin/lastcomm mode=0555 file path=usr/bin/lgrpinfo mode=0555 file path=usr/bin/look mode=0755 file path=usr/bin/mkfifo mode=0555 -file path=usr/bin/nawk mode=0555 file path=usr/bin/newform mode=0555 file path=usr/bin/news mode=0555 file path=usr/bin/nl mode=0555 +file path=usr/bin/oawk mode=0555 file path=usr/bin/pack mode=0555 file path=usr/bin/pginfo mode=0555 file path=usr/bin/pgstat mode=0555 @@ -185,10 +186,10 @@ file path=usr/share/man/man1/lgrpinfo.1 file path=usr/share/man/man1/look.1 file path=usr/share/man/man1/madv.so.1.1 file path=usr/share/man/man1/mpss.so.1.1 -file path=usr/share/man/man1/nawk.1 file path=usr/share/man/man1/newform.1 file path=usr/share/man/man1/news.1 file path=usr/share/man/man1/nl.1 +file path=usr/share/man/man1/oawk.1 file path=usr/share/man/man1/pack.1 file path=usr/share/man/man1/pargs.1 file path=usr/share/man/man1/plgrp.1 @@ -223,7 +224,7 @@ $(i386_ONLY)hardlink path=usr/bin/$(ARCH32)/penv \ target=../../../usr/bin/$(ARCH32)/pargs hardlink path=usr/bin/$(ARCH64)/pauxv target=../../../usr/bin/$(ARCH64)/pargs hardlink path=usr/bin/$(ARCH64)/penv target=../../../usr/bin/$(ARCH64)/pargs -hardlink path=usr/bin/oawk target=../../usr/bin/awk +hardlink path=usr/bin/nawk target=../../usr/bin/awk hardlink path=usr/bin/pargs target=../../usr/lib/isaexec hardlink path=usr/bin/pauxv target=../../usr/lib/isaexec hardlink path=usr/bin/pcred target=../../usr/lib/isaexec @@ -284,6 +285,7 @@ link path=usr/proc/bin/pwait target=../../bin/pwait link path=usr/proc/bin/pwdx target=../../bin/pwdx link path=usr/share/man/man1/hashcheck.1 target=spell.1 link path=usr/share/man/man1/hashmake.1 target=spell.1 +link path=usr/share/man/man1/nawk.1 target=awk.1 link path=usr/share/man/man1/pauxv.1 target=pargs.1 link path=usr/share/man/man1/pcat.1 target=pack.1 link path=usr/share/man/man1/penv.1 target=pargs.1 diff --git a/usr/src/test/crypto-tests/tests/Makefile.crypto b/usr/src/test/crypto-tests/tests/Makefile.crypto index f53bd7d89b..8d7396fa64 100644 --- a/usr/src/test/crypto-tests/tests/Makefile.crypto +++ b/usr/src/test/crypto-tests/tests/Makefile.crypto @@ -96,8 +96,6 @@ clean: $(CMDS): $(TESTDIR_pkcs) $(TESTDIR_kcf) $(PROGS) -.PARALLEL: $(CMDS) $(PROGS) - $(TESTDIR_pkcs) $(TESTDIR_kcf): $(INS.dir) diff --git a/usr/src/test/crypto-tests/tests/digest/Makefile b/usr/src/test/crypto-tests/tests/digest/Makefile index c381d0c584..a5732aa375 100644 --- a/usr/src/test/crypto-tests/tests/digest/Makefile +++ b/usr/src/test/crypto-tests/tests/digest/Makefile @@ -27,6 +27,4 @@ all clean clobber install: $(ALGS) $(ALGS): FRC $(MAKE) -e -f Makefile.digest BASEPROG=$@ $(TARGET) -.PARALLEL: $(ALGS) - FRC: diff --git a/usr/src/test/util-tests/tests/awk/runtests.sh b/usr/src/test/util-tests/tests/awk/runtests.sh index 28d127dc3c..fd94d3585a 100755 --- a/usr/src/test/util-tests/tests/awk/runtests.sh +++ b/usr/src/test/util-tests/tests/awk/runtests.sh @@ -12,10 +12,10 @@ # # -# Copyright 2018, Joyent, Inc. +# Copyright 2020 Joyent, Inc. # -AWK=/usr/bin/nawk +AWK=/usr/bin/awk WORKDIR=$(mktemp -d /tmp/nawktest.XXXXXX) SUCCESSES=0 diff --git a/usr/src/test/util-tests/tests/awk/tests/T.misc b/usr/src/test/util-tests/tests/awk/tests/T.misc index ee603014e2..04e9794de9 100755 --- a/usr/src/test/util-tests/tests/awk/tests/T.misc +++ b/usr/src/test/util-tests/tests/awk/tests/T.misc @@ -132,7 +132,7 @@ $AWK 'BEGIN { foo() }' 2> $TEMP0 grep "calling undefined function foo" $TEMP0 >/dev/null || fail "BAD: T.misc undefined function" -# gawk arrayparm test; should give error about function +# gawk arrayparm test; should give error about function $AWK ' BEGIN { foo[1]=1; @@ -365,14 +365,14 @@ cmp -s $TEMP1 $TEMP2 || fail 'BAD: T.misc immmediate exit 4' echo 1 > $TEMP1 $AWK ' { n = split($0, x) for (i in x) { - if (i == 1) + if (i == 1) exit } } END { print NR }' /etc/passwd > $TEMP2 cmp -s $TEMP1 $TEMP2 || fail 'BAD: T.misc immmediate exit 5' echo XXXXXXXX > $TEMP1 $AWK 'BEGIN { s = "ab\fc\rd\be" - t = s; gsub("[" s "]", "X", t); print t }' > $TEMP2 + t = s; gsub("[" s "]", "X", t); print t }' > $TEMP2 cmp -s $TEMP1 $TEMP2 || fail 'BAD: T.misc weird escapes in char class' $AWK '{}' /etc/passwd glop/glop > $TEMP0 2> $TEMP2 diff --git a/usr/src/uts/common/io/bge/bge_chip2.c b/usr/src/uts/common/io/bge/bge_chip2.c index 0ceb070556..14797ac90f 100644 --- a/usr/src/uts/common/io/bge/bge_chip2.c +++ b/usr/src/uts/common/io/bge/bge_chip2.c @@ -243,7 +243,8 @@ bge_ind_get32(bge_t *bgep, bge_regno_t regno) #ifdef __sparc if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regno = LE_32(regno); } #endif @@ -270,7 +271,8 @@ bge_ind_put32(bge_t *bgep, bge_regno_t regno, uint32_t val) val = LE_32(val); #ifdef __sparc if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regno = LE_32(regno); } #endif @@ -366,7 +368,8 @@ bge_chip_cfg_init(bge_t *bgep, chip_id_t *cidp, boolean_t enable_dma) */ cidp->device = pci_config_get16(handle, PCI_CONF_DEVID); if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { pci_config_put32(handle, PCI_CONF_BGE_MHCR, 0); } @@ -378,6 +381,8 @@ bge_chip_cfg_init(bge_t *bgep, chip_id_t *cidp, boolean_t enable_dma) if (DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep)) { prodid = CHIP_ASIC_REV_PROD_ID_GEN2_REG; + } else if (DEVICE_57765_SERIES_CHIPSETS(bgep)) { + prodid = CHIP_ASIC_REV_PROD_ID_GEN15_REG; } cidp->asic_rev_prod_id = pci_config_get32(handle, prodid); } @@ -564,7 +569,8 @@ bge_chip_cfg_init(bge_t *bgep, chip_id_t *cidp, boolean_t enable_dma) bge_cfg_clr16(bgep, PCI_CONF_DEV_CTRL_5723, DEV_CTRL_NO_SNOOP | DEV_CTRL_RELAXED); } else if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_cfg_clr16(bgep, PCI_CONF_DEV_CTRL_5717, DEV_CTRL_NO_SNOOP | DEV_CTRL_RELAXED); } else { @@ -667,7 +673,8 @@ bge_reg_get64(bge_t *bgep, bge_regno_t regno) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || bge_get_em64t_type() || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regval = ddi_get32(bgep->io_handle, PIO_ADDR(bgep, regno + 4)); regval <<= 32; regval |= ddi_get32(bgep->io_handle, PIO_ADDR(bgep, regno)); @@ -677,7 +684,8 @@ bge_reg_get64(bge_t *bgep, bge_regno_t regno) #elif defined(__sparc) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regval = ddi_get32(bgep->io_handle, PIO_ADDR(bgep, regno)); regval <<= 32; regval |= ddi_get32(bgep->io_handle, PIO_ADDR(bgep, regno + 4)); @@ -715,7 +723,8 @@ bge_reg_put64(bge_t *bgep, bge_regno_t regno, uint64_t data) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || bge_get_em64t_type() || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, regno), (uint32_t)data); BGE_PCICHK(bgep); @@ -728,7 +737,8 @@ bge_reg_put64(bge_t *bgep, bge_regno_t regno, uint64_t data) #elif defined(__sparc) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, regno + 4), (uint32_t)data); BGE_PCICHK(bgep); @@ -887,7 +897,8 @@ bge_nic_setwin(bge_t *bgep, bge_regno_t base) } #ifdef __sparc if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { base = LE_32(base); } #endif @@ -949,7 +960,8 @@ bge_nic_put32(bge_t *bgep, bge_regno_t addr, uint32_t data) #ifdef __sparc if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { addr = LE_32(addr); } pci_config_put32(bgep->cfg_handle, PCI_CONF_BGE_MWBAR, addr); @@ -981,7 +993,8 @@ bge_nic_get64(bge_t *bgep, bge_regno_t addr) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || bge_get_em64t_type() || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { data = ddi_get32(bgep->io_handle, PIO_ADDR(bgep, addr + 4)); data <<= 32; @@ -992,7 +1005,8 @@ bge_nic_get64(bge_t *bgep, bge_regno_t addr) #elif defined(__sparc) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep || + DEVICE_57765_SERIES_CHIPSETS(bgep))) { data = ddi_get32(bgep->io_handle, PIO_ADDR(bgep, addr)); data <<= 32; data |= ddi_get32(bgep->io_handle, @@ -1027,7 +1041,8 @@ bge_nic_put64(bge_t *bgep, bge_regno_t addr, uint64_t data) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || bge_get_em64t_type() || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr + 4), (uint32_t)data); BGE_PCICHK(bgep); @@ -1039,7 +1054,8 @@ bge_nic_put64(bge_t *bgep, bge_regno_t addr, uint64_t data) #elif defined(__sparc) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr + 4), (uint32_t)data); BGE_PCICHK(bgep); @@ -1082,7 +1098,8 @@ bge_nic_putrcb(bge_t *bgep, bge_regno_t addr, bge_rcb_t *rcbp) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || bge_get_em64t_type() || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr), (uint32_t)(*p)); ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr + 4), @@ -1099,7 +1116,8 @@ bge_nic_putrcb(bge_t *bgep, bge_regno_t addr, bge_rcb_t *rcbp) #elif defined(__sparc) if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr + 4), (uint32_t)(*p)); ddi_put32(bgep->io_handle, PIO_ADDR(bgep, addr), @@ -1801,7 +1819,8 @@ bge_nvmem_rw32(bge_t *bgep, uint32_t cmd, bge_regno_t addr, uint32_t *dp) DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_reg_set32(bgep, NVM_ACCESS_REG, NVM_ACCESS_ENABLE); } @@ -1811,7 +1830,8 @@ bge_nvmem_rw32(bge_t *bgep, uint32_t cmd, bge_regno_t addr, uint32_t *dp) DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_reg_clr32(bgep, NVM_ACCESS_REG, NVM_ACCESS_ENABLE); } @@ -1822,7 +1842,8 @@ bge_nvmem_rw32(bge_t *bgep, uint32_t cmd, bge_regno_t addr, uint32_t *dp) DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_reg_set32(bgep, NVM_ACCESS_REG, NVM_WRITE_ENABLE|NVM_ACCESS_ENABLE); } @@ -1834,7 +1855,8 @@ bge_nvmem_rw32(bge_t *bgep, uint32_t cmd, bge_regno_t addr, uint32_t *dp) DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_reg_clr32(bgep, NVM_ACCESS_REG, NVM_WRITE_ENABLE|NVM_ACCESS_ENABLE); } @@ -2047,6 +2069,16 @@ bge_nvmem_id(bge_t *bgep) case DEVICE_ID_5714S: case DEVICE_ID_5715C: case DEVICE_ID_5715S: + case DEVICE_ID_57761: + case DEVICE_ID_57762: + case DEVICE_ID_57765: + case DEVICE_ID_57766: + case DEVICE_ID_57781: + case DEVICE_ID_57782: + case DEVICE_ID_57785: + case DEVICE_ID_57786: + case DEVICE_ID_57791: + case DEVICE_ID_57795: config1 = bge_reg_get32(bgep, NVM_CONFIG1_REG); if (config1 & NVM_CFG1_FLASH_MODE) if (config1 & NVM_CFG1_BUFFERED_MODE) @@ -2603,6 +2635,16 @@ bge_chip_id_init(bge_t *bgep) case DEVICE_ID_5724: case DEVICE_ID_5725: case DEVICE_ID_5727: + case DEVICE_ID_57761: + case DEVICE_ID_57762: + case DEVICE_ID_57765: + case DEVICE_ID_57766: + case DEVICE_ID_57781: + case DEVICE_ID_57782: + case DEVICE_ID_57785: + case DEVICE_ID_57786: + case DEVICE_ID_57791: + case DEVICE_ID_57795: if (cidp->device == DEVICE_ID_5717) { cidp->chip_label = 5717; } else if (cidp->device == DEVICE_ID_5718) { @@ -2620,9 +2662,30 @@ bge_chip_id_init(bge_t *bgep) cidp->chip_label = 5724; } else if (cidp->device == DEVICE_ID_5725) { cidp->chip_label = 5725; - } else /* (cidp->device == DEVICE_ID_5727) */ { + } else if (cidp->device == DEVICE_ID_5727) { cidp->chip_label = 5727; + } else if (cidp->device == DEVICE_ID_57761) { + cidp->chip_label = 57761; + } else if (cidp->device == DEVICE_ID_57762) { + cidp->chip_label = 57762; + } else if (cidp->device == DEVICE_ID_57765) { + cidp->chip_label = 57765; + } else if (cidp->device == DEVICE_ID_57766) { + cidp->chip_label = 57766; + } else if (cidp->device == DEVICE_ID_57781) { + cidp->chip_label = 57781; + } else if (cidp->device == DEVICE_ID_57782) { + cidp->chip_label = 57782; + } else if (cidp->device == DEVICE_ID_57785) { + cidp->chip_label = 57785; + } else if (cidp->device == DEVICE_ID_57786) { + cidp->chip_label = 57786; + } else if (cidp->device == DEVICE_ID_57791) { + cidp->chip_label = 57791; + } else if (cidp->device == DEVICE_ID_57795) { + cidp->chip_label = 57795; } + cidp->msi_enabled = bge_enable_msi; #ifdef __sparc cidp->mask_pci_int = LE_32(MHCR_MASK_PCI_INT_OUTPUT); @@ -2635,7 +2698,11 @@ bge_chip_id_init(bge_t *bgep) cidp->mbuf_base = bge_mbuf_pool_base_5705; cidp->mbuf_length = bge_mbuf_pool_len_5705; cidp->recv_slots = BGE_RECV_SLOTS_5705; - cidp->bge_mlcr_default = MLCR_DEFAULT_5717; + if (DEVICE_57765_SERIES_CHIPSETS(bgep)) { + cidp->bge_mlcr_default = MLCR_DEFAULT_57765; + } else { + cidp->bge_mlcr_default = MLCR_DEFAULT_5717; + } cidp->rx_rings = BGE_RECV_RINGS_MAX_5705; cidp->tx_rings = BGE_SEND_RINGS_MAX_5705; cidp->statistic_type = BGE_STAT_REG; @@ -3048,7 +3115,8 @@ bge_chip_id_init(bge_t *bgep) (cidp->default_mtu > BGE_DEFAULT_MTU)) { if (DEVICE_5714_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { cidp->mbuf_lo_water_rdma = RDMA_MBUF_LOWAT_5714_JUMBO; cidp->mbuf_lo_water_rmac = @@ -3210,7 +3278,8 @@ bge_chip_reset_engine(bge_t *bgep, bge_regno_t regno) DEVICE_5721_SERIES_CHIPSETS(bgep) || DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5714_SERIES_CHIPSETS(bgep) || - DEVICE_5906_SERIES_CHIPSETS(bgep)) { + DEVICE_5906_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regval |= MISC_CONFIG_GPHY_POWERDOWN_OVERRIDE; if (bgep->chipid.pci_type == BGE_PCI_E) { if (bgep->chipid.asic_rev == @@ -3298,7 +3367,8 @@ bge_chip_reset_engine(bge_t *bgep, bge_regno_t regno) } if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { val16 = pci_config_get16(bgep->cfg_handle, PCI_CONF_DEV_CTRL_5717); val16 &= ~READ_REQ_SIZE_MASK; @@ -3460,7 +3530,8 @@ bge_sync_mac_modes(bge_t *bgep) (bgep->param_loop_mode != BGE_LOOP_INTERNAL_MAC)) { if (DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) macmode |= ETHERNET_MODE_PORTMODE_GMII; else macmode |= ETHERNET_MODE_PORTMODE_TBI; @@ -4023,7 +4094,8 @@ bge_chip_reset(bge_t *bgep, boolean_t enable_dma) #endif if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_reg_set32(bgep, FAST_BOOT_PC, 0); if (!bge_chip_enable_engine(bgep, MEMORY_ARBITER_MODE_REG, 0)) retval = DDI_FAILURE; @@ -4055,6 +4127,18 @@ bge_chip_reset(bge_t *bgep, boolean_t enable_dma) bge_reg_set32(bgep, TLP_CONTROL_REG, TLP_DATA_FIFO_PROTECT); /* + * In the 57765 family of devices we need to work around an apparent + * transmit hang by dorking with the PCIe serdes training clocks. + */ + if (DEVICE_57765_SERIES_CHIPSETS(bgep) && + (CHIP_ASIC_REV_PROD_ID(bgep) >> 8) != CHIP_ASIC_REV_57765_AX) { + tmp = bge_reg_get32(bgep, CPMU_PADRNG_CTL_REG); + tmp |= CPMU_PADRNG_CTL_RDIV2; + bge_reg_set32(bgep, CPMU_PADRNG_CTL_REG, tmp); + } + + + /* * Step 9: enable MAC memory arbiter,bit30 and bit31 of 5714/5715 should * not be changed. */ @@ -4353,7 +4437,8 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) MODE_HOST_STACK_UP); if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { reg = (CHIP_ASIC_REV(bgep) == CHIP_ASIC_REV_5762) ? RDMA_RSRV_CTRL_REG2 : RDMA_RSRV_CTRL_REG; regval = bge_reg_get32(bgep, reg); @@ -4459,7 +4544,8 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) if (bgep->chipid.device == DEVICE_ID_5719) regval |= BUFFER_MANAGER_MODE_NO_TX_UNDERRUN; if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) regval |= BUFFER_MANAGER_MODE_MBLOW_ATTN_ENABLE; if (!bge_chip_enable_engine(bgep, BUFFER_MANAGER_MODE_REG, regval)) retval = DDI_FAILURE; @@ -4471,17 +4557,24 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) * Steps 37-39: initialise Receive Buffer (Producer) RCBs */ if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { buff_ring_t *brp = &bgep->buff[BGE_STD_BUFF_RING]; bge_reg_put64(bgep, STD_RCV_BD_RING_RCB_REG, brp->desc.cookie.dmac_laddress); bge_reg_put32(bgep, STD_RCV_BD_RING_RCB_REG + 8, (brp->desc.nslots) << 16 | brp->buf[0].size << 2); - bge_reg_put32(bgep, STD_RCV_BD_RING_RCB_REG + 0xc, - NIC_MEM_SHADOW_BUFF_STD_5717); - } else + if (DEVICE_57765_SERIES_CHIPSETS(bgep)) { + bge_reg_put32(bgep, STD_RCV_BD_RING_RCB_REG + 0xc, + NIC_MEM_SHADOW_BUFF_STD); + } else { + bge_reg_put32(bgep, STD_RCV_BD_RING_RCB_REG + 0xc, + NIC_MEM_SHADOW_BUFF_STD_5717); + } + } else { bge_reg_putrcb(bgep, STD_RCV_BD_RING_RCB_REG, &bgep->buff[BGE_STD_BUFF_RING].hw_rcb); + } if (DEVICE_5704_SERIES_CHIPSETS(bgep)) { bge_reg_putrcb(bgep, JUMBO_RCV_BD_RING_RCB_REG, @@ -4673,7 +4766,8 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) else coalmode = 0; if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) coalmode = COALESCE_CLR_TICKS_RX; if (!bge_chip_enable_engine(bgep, HOST_COALESCE_MODE_REG, coalmode)) retval = DDI_FAILURE; @@ -4753,6 +4847,10 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) drv_usecwait(40); + /* + * These chipsets no longer use the rdprio logic (bits 31:30 are + * reserved). + */ if (DEVICE_5723_SERIES_CHIPSETS(bgep) || DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep)) @@ -4797,7 +4895,8 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) * Steps 89-90: enable Transmit & Receive MAC Engines */ regval = 0; - if (DEVICE_5717_SERIES_CHIPSETS(bgep)) { + if (DEVICE_5717_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { regval |= TRANSMIT_MODE_MBUF_LOCKUP_FIX; } if (!bge_chip_enable_engine(bgep, TRANSMIT_MAC_MODE_REG, regval)) @@ -4911,7 +5010,8 @@ bge_chip_start(bge_t *bgep, boolean_t reset_phys) #endif if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { bge_cfg_clr16(bgep, PCI_CONF_DEV_CTRL_5717, DEV_CTRL_NO_SNOOP | DEV_CTRL_RELAXED); #if 0 @@ -5076,7 +5176,8 @@ bge_intr(caddr_t arg1, caddr_t arg2) */ regval = bge_reg_get32(bgep, MISC_LOCAL_CONTROL_REG); if (!(DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) && + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) && (regval & MLCR_INTA_STATE)) { if (bge_check_acc_handle(bgep, bgep->io_handle) != DDI_FM_OK) @@ -6413,7 +6514,8 @@ bge_nic_read32(bge_t *bgep, bge_regno_t addr) } #else if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { addr = LE_32(addr); } #endif diff --git a/usr/src/uts/common/io/bge/bge_hw.h b/usr/src/uts/common/io/bge/bge_hw.h index 506b97774e..7dfb86fb0d 100644 --- a/usr/src/uts/common/io/bge/bge_hw.h +++ b/usr/src/uts/common/io/bge/bge_hw.h @@ -109,6 +109,16 @@ extern "C" { #define DEVICE_ID_5906 0x1712 #define DEVICE_ID_5906M 0x1713 #define DEVICE_ID_57780 0x1692 +#define DEVICE_ID_57761 0x16b0 +#define DEVICE_ID_57762 0x1682 +#define DEVICE_ID_57765 0x16b4 +#define DEVICE_ID_57766 0x1686 +#define DEVICE_ID_57781 0x16b1 +#define DEVICE_ID_57782 0x16b7 +#define DEVICE_ID_57785 0x16b5 +#define DEVICE_ID_57786 0x16b3 +#define DEVICE_ID_57791 0x16b2 +#define DEVICE_ID_57795 0x16b6 #define REVISION_ID_5700_B0 0x10 #define REVISION_ID_5700_B2 0x12 @@ -227,6 +237,23 @@ extern "C" { (bgep->chipid.device == DEVICE_ID_5906M)) /* + * Even though the hardware register calls this the 57785 family, all of the + * BSDs call this the 57765 series, so we call it that way to make it more + * similar. + */ +#define DEVICE_57765_SERIES_CHIPSETS(bgep) \ + ((bgep->chipid.device == DEVICE_ID_57761) || \ + (bgep->chipid.device == DEVICE_ID_57762) || \ + (bgep->chipid.device == DEVICE_ID_57765) || \ + (bgep->chipid.device == DEVICE_ID_57766) || \ + (bgep->chipid.device == DEVICE_ID_57781) || \ + (bgep->chipid.device == DEVICE_ID_57782) || \ + (bgep->chipid.device == DEVICE_ID_57785) || \ + (bgep->chipid.device == DEVICE_ID_57786) || \ + (bgep->chipid.device == DEVICE_ID_57791) || \ + (bgep->chipid.device == DEVICE_ID_57795)) + +/* * Second section: * Offsets of important registers & definitions for bits therein */ @@ -334,12 +361,12 @@ extern "C" { #define MHCR_CHIP_ASIC_REV_5704 (0x2 << 28) #define MHCR_CHIP_ASIC_REV_5705 (0x3 << 28) #define MHCR_CHIP_ASIC_REV_5721_5751 (0x4 << 28) -#define MHCR_CHIP_ASIC_REV_5714 (0x5 << 28) +#define MHCR_CHIP_ASIC_REV_5714 (0x5 << 28) #define MHCR_CHIP_ASIC_REV_5752 (0x6 << 28) #define MHCR_CHIP_ASIC_REV_5754 (0xb << 28) #define MHCR_CHIP_ASIC_REV_5787 ((uint32_t)0xb << 28) #define MHCR_CHIP_ASIC_REV_5755 ((uint32_t)0xa << 28) -#define MHCR_CHIP_ASIC_REV_5715 ((uint32_t)0x9 << 28) +#define MHCR_CHIP_ASIC_REV_5715 ((uint32_t)0x9 << 28) #define MHCR_CHIP_ASIC_REV_5906 ((uint32_t)0xc << 28) /* (0xf << 28) touches all 5717 and 5725 series as well (OK) */ #define MHCR_CHIP_ASIC_REV_5723 ((uint32_t)0xf << 28) @@ -348,6 +375,7 @@ extern "C" { #define CHIP_ASIC_REV_5761 0x5761 #define CHIP_ASIC_REV_5785 0x5785 #define CHIP_ASIC_REV_57780 0x57780 +#define CHIP_ASIC_REV_57785 0x57785 #define CHIP_ASIC_REV_5717 0x5717 #define CHIP_ASIC_REV_5719 0x5719 @@ -356,6 +384,7 @@ extern "C" { #define CHIP_ASIC_REV_PROD_ID_REG 0x000000bc #define CHIP_ASIC_REV_PROD_ID_GEN2_REG 0x000000f4 +#define CHIP_ASIC_REV_PROD_ID_GEN15_REG 0x000000fc #define CHIP_ASIC_REV_5717_B0 0x05717100 #define CHIP_ASIC_REV_5717_C0 0x05717200 @@ -367,6 +396,11 @@ extern "C" { #define CHIP_ASIC_REV_5727_B0 0x05762100 /* + * Match any Metal Layer Revision. + */ +#define CHIP_ASIC_REV_57765_AX 0x577850 + +/* * PCI DMA read/write Control Register, in PCI config space * * Note that several fields previously defined here have been deleted @@ -504,7 +538,7 @@ extern "C" { #define PCI_CONF_DEV_CTRL_5717 0xb4 #define READ_REQ_SIZE_MASK 0x7000 #define READ_REQ_SIZE_MAX 0x5000 -#define READ_REQ_SIZE_2K 0x4000 +#define READ_REQ_SIZE_2K 0x4000 #define DEV_CTRL_NO_SNOOP 0x0800 #define DEV_CTRL_RELAXED 0x0010 @@ -1144,15 +1178,17 @@ extern "C" { #define JUMBO_RCV_BD_REPLENISH_DEFAULT 0x00000020 /* 32 */ /* - * CPMU registers (5717/18/19/20 only) + * CPMU registers (5717/18/19/20/57765 only) */ #define CPMU_CLCK_ORIDE_REG 0x3624 #define CPMU_CLCK_ORIDE_MAC_ORIDE_EN 0x80000000 #define CPMU_STATUS_REG 0x362c #define CPMU_STATUS_FUNC_NUM 0x20000000 #define CPMU_STATUS_FUNC_NUM_SHIFT 29 -#define CPMU_STATUS_FUNC_NUM_5719 0xc0000000 +#define CPMU_STATUS_FUNC_NUM_5719 0xc0000000 #define CPMU_STATUS_FUNC_NUM_5719_SHIFT 30 +#define CPMU_PADRNG_CTL_REG 0x3668 +#define CPMU_PADRNG_CTL_RDIV2 0x00040000 /* * EEE registers (5718/19/20 only) @@ -1444,6 +1480,12 @@ extern "C" { #define MLCR_DEFAULT_5717 (MLCR_AUTO_SEEPROM_ACCESS) /* + * MLCR_AUTO_SEEPROM_ACCESS is marked reserved in the 57765 family, so we don't + * try to enable it like on the 5717. + */ +#define MLCR_DEFAULT_57765 0 + +/* * Serial EEPROM Data/Address Registers (auto-access mode) */ #define SERIAL_EEPROM_DATA_REG 0x683c @@ -1544,7 +1586,7 @@ extern "C" { /* * NVM access register - * Applicable to BCM5721,BCM5751,BCM5752,BCM5714 + * Applicable to BCM5721,BCM5751,BCM5752,BCM5714,BCM57725 * and BCM5715 only. */ #define NVM_ACCESS_REG 0x7024 @@ -1731,7 +1773,7 @@ extern "C" { /* * Third section: - * Hardware-defined data structures + * Hardware-defined data structures * * Note that the chip is naturally BIG-endian, so, for a big-endian * host, the structures defined below match those described in the PRM. diff --git a/usr/src/uts/common/io/bge/bge_impl.h b/usr/src/uts/common/io/bge/bge_impl.h index 848f039359..37a927fce5 100644 --- a/usr/src/uts/common/io/bge/bge_impl.h +++ b/usr/src/uts/common/io/bge/bge_impl.h @@ -794,8 +794,8 @@ typedef struct bge { /* * For the BCM5705/5788/5721/5751/5752/5714 and 5715, * the statistic block is not available,the statistic counter must - * be gotten from statistic registers.And bge_statistics_reg_t record - * the statistic registers value + * be gotten from statistic registers. And bge_statistics_reg_t record + * the statistic registers value. */ bge_statistics_reg_t *pstats; diff --git a/usr/src/uts/common/io/bge/bge_lint.c b/usr/src/uts/common/io/bge/bge_lint.c deleted file mode 100644 index 2f51987068..0000000000 --- a/usr/src/uts/common/io/bge/bge_lint.c +++ /dev/null @@ -1,18 +0,0 @@ -/* - * This file and its contents are supplied under the terms of the - * Common Development and Distribution License ("CDDL"), version 1.0. - * You may only use this file in accordance with the terms of version - * 1.0 of the CDDL. - * - * A full copy of the text of the CDDL should have accompanied this - * source. A copy of the CDDL is also available via the Internet at - * http://www.illumos.org/license/CDDL. - */ - -/* - * This is a dummy lint file to pacify lint for bge, which due to its upstream, - * makes it, unfortunately, not realistic to lint. We have a dummy definition to - * ensure that we don't trigger lint's empty translation unit. - */ - -extern int bge_lint; diff --git a/usr/src/uts/common/io/bge/bge_main2.c b/usr/src/uts/common/io/bge/bge_main2.c index dc0174c4a3..ab511c068d 100644 --- a/usr/src/uts/common/io/bge/bge_main2.c +++ b/usr/src/uts/common/io/bge/bge_main2.c @@ -83,8 +83,8 @@ static ddi_dma_attr_t dma_attr = { 0x00000001, /* dma_attr_minxfer */ 0x000000000000FFFFull, /* dma_attr_maxxfer */ 0x00000000FFFFFFFFull, /* dma_attr_seg */ - 1, /* dma_attr_sgllen */ - 0x00000001, /* dma_attr_granular */ + 1, /* dma_attr_sgllen */ + 0x00000001, /* dma_attr_granular */ DDI_DMA_FLAGERR /* dma_attr_flags */ }; @@ -119,9 +119,7 @@ static ddi_device_acc_attr_t bge_data_accattr = { static int bge_m_start(void *); static void bge_m_stop(void *); static int bge_m_promisc(void *, boolean_t); -static int bge_m_unicst(void * pArg, const uint8_t *); static int bge_m_multicst(void *, boolean_t, const uint8_t *); -static void bge_m_resources(void * arg); static void bge_m_ioctl(void *, queue_t *, mblk_t *); static boolean_t bge_m_getcapab(void *, mac_capab_t, void *); static int bge_unicst_set(void *, const uint8_t *, @@ -140,47 +138,19 @@ static void bge_priv_propinfo(const char *, mac_prop_info_handle_t); static mac_callbacks_t bge_m_callbacks = { - MC_IOCTL -#ifdef MC_RESOURCES - | MC_RESOURCES -#endif -#ifdef MC_SETPROP - | MC_SETPROP -#endif -#ifdef MC_GETPROP - | MC_GETPROP -#endif -#ifdef MC_PROPINFO - | MC_PROPINFO -#endif - | MC_GETCAPAB, - bge_m_stat, - bge_m_start, - bge_m_stop, - bge_m_promisc, - bge_m_multicst, - bge_m_unicst, - bge_m_tx, -#ifdef MC_RESOURCES - bge_m_resources, -#else - NULL, -#endif - bge_m_ioctl, - bge_m_getcapab, -#ifdef MC_OPEN - NULL, - NULL, -#endif -#ifdef MC_SETPROP - bge_m_setprop, -#endif -#ifdef MC_GETPROP - bge_m_getprop, -#endif -#ifdef MC_PROPINFO - bge_m_propinfo -#endif + .mc_callbacks = MC_IOCTL | MC_SETPROP | MC_GETPROP | MC_PROPINFO | + MC_GETCAPAB, + .mc_getstat = bge_m_stat, + .mc_start = bge_m_start, + .mc_stop = bge_m_stop, + .mc_setpromisc = bge_m_promisc, + .mc_multicst = bge_m_multicst, + .mc_tx = bge_m_tx, + .mc_ioctl = bge_m_ioctl, + .mc_getcapab = bge_m_getcapab, + .mc_setprop = bge_m_setprop, + .mc_getprop = bge_m_getprop, + .mc_propinfo = bge_m_propinfo }; char *bge_priv_prop[] = { @@ -1288,21 +1258,6 @@ bge_priv_propinfo(const char *pr_name, mac_prop_info_handle_t mph) mac_prop_info_set_default_str(mph, valstr); } - -static int -bge_m_unicst(void * arg, const uint8_t * mac_addr) -{ - bge_t *bgep = arg; - int i; - - /* XXX sets the mac address for all ring slots... OK? */ - for (i = 0; i < MIN(bgep->chipid.rx_rings, MAC_ADDRESS_REGS_MAX); i++) - bge_addmac(&bgep->recv[i], mac_addr); - - return (0); -} - - /* * Compute the index of the required bit in the multicast hash map. * This must mirror the way the hardware actually does it! @@ -1463,37 +1418,6 @@ bge_m_promisc(void *arg, boolean_t on) return (0); } -#ifdef MC_RESOURCES - -static void -bge_blank(void * arg, time_t tick_cnt, uint_t pkt_cnt) -{ - (void)arg; - (void)tick_cnt; - (void)pkt_cnt; -} - -static void -bge_m_resources(void * arg) -{ - bge_t *bgep = arg; - mac_rx_fifo_t mrf; - int i; - - mrf.mrf_type = MAC_RX_FIFO; - mrf.mrf_blank = bge_blank; - mrf.mrf_arg = (void *)bgep; - mrf.mrf_normal_blank_time = 25; - mrf.mrf_normal_pkt_count = 8; - - for (i = 0; i < BGE_RECV_RINGS_MAX; i++) { - bgep->macRxResourceHandles[i] = - mac_resource_add(bgep->mh, (mac_resource_t *)&mrf); - } -} - -#endif /* MC_RESOURCES */ - /* * Find the slot for the specified unicast address */ @@ -1540,7 +1464,10 @@ bge_addmac(void *arg, const uint8_t * mac_addr) * First add the unicast address to a available slot. */ slot = bge_unicst_find(bgep, mac_addr); - ASSERT(slot == -1); + if (slot != -1) { + mutex_exit(bgep->genlock); + return (EEXIST); + } for (slot = 0; slot < bgep->unicst_addr_total; slot++) { if (!bgep->curr_addr[slot].set) { @@ -1549,7 +1476,7 @@ bge_addmac(void *arg, const uint8_t * mac_addr) } } - ASSERT(slot < bgep->unicst_addr_total); + VERIFY3S(slot, <, bgep->unicst_addr_total); bgep->unicst_addr_avail--; mutex_exit(bgep->genlock); @@ -1671,7 +1598,7 @@ bge_remmac(void *arg, const uint8_t *mac_addr) static int -bge_flag_intr_enable(mac_ring_driver_t ih) +bge_flag_intr_enable(mac_intr_handle_t ih) { recv_ring_t *rrp = (recv_ring_t *)ih; bge_t *bgep = rrp->bgep; @@ -1684,7 +1611,7 @@ bge_flag_intr_enable(mac_ring_driver_t ih) } static int -bge_flag_intr_disable(mac_ring_driver_t ih) +bge_flag_intr_disable(mac_intr_handle_t ih) { recv_ring_t *rrp = (recv_ring_t *)ih; bge_t *bgep = rrp->bgep; @@ -1736,8 +1663,9 @@ bge_fill_ring(void *arg, mac_ring_type_t rtype, const int rg_index, infop->mri_stat = bge_rx_ring_stat; mintr = &infop->mri_intr; - mintr->mi_enable = (mac_intr_enable_t)bge_flag_intr_enable; - mintr->mi_disable = (mac_intr_disable_t)bge_flag_intr_disable; + mintr->mi_handle = (mac_intr_handle_t)rx_ring; + mintr->mi_enable = bge_flag_intr_enable; + mintr->mi_disable = bge_flag_intr_disable; break; } @@ -2691,7 +2619,8 @@ bge_alloc_bufs(bge_t *bgep) * Enable PCI relaxed ordering only for RX/TX data buffers */ if (!(DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep))) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep))) { if (bge_relaxed_ordering) dma_attr.dma_attr_flags |= DDI_DMA_RELAXED_ORDERING; } @@ -2727,7 +2656,8 @@ bge_alloc_bufs(bge_t *bgep) txbuffsize)); if (!(DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep))) { + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep))) { /* no relaxed ordering for descriptors rings? */ dma_attr.dma_attr_flags &= ~DDI_DMA_RELAXED_ORDERING; } @@ -3716,6 +3646,8 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) bgep->ape_enabled = B_FALSE; bgep->ape_regs = NULL; + cidp = &bgep->chipid; + cidp->device = pci_config_get16(bgep->cfg_handle, PCI_CONF_DEVID); if (DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep)) { err = ddi_regs_map_setup(devinfo, BGE_PCI_APEREGS_RNUMBER, @@ -3749,8 +3681,6 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) * registers. (This information will be used by bge_ind_put32, * bge_ind_get32 and bge_nic_read32) */ - bgep->chipid.device = pci_config_get16(bgep->cfg_handle, - PCI_CONF_DEVID); value16 = pci_config_get16(bgep->cfg_handle, PCI_CONF_COMM); value16 = value16 | (PCI_COMM_MAE | PCI_COMM_ME); pci_config_put16(bgep->cfg_handle, PCI_CONF_COMM, value16); @@ -3767,7 +3697,8 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) * byte-swapped value to it. So we just write zero first for simplicity. */ if (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) pci_config_put32(bgep->cfg_handle, PCI_CONF_BGE_MHCR, 0); #else mhcrValue = MHCR_ENABLE_INDIRECT_ACCESS | @@ -3792,8 +3723,6 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) goto attach_fail; } bgep->progress |= PROGRESS_CFG; - cidp = &bgep->chipid; - bzero(cidp, sizeof(*cidp)); bge_chip_cfg_init(bgep, cidp, B_FALSE); if (bge_check_acc_handle(bgep, bgep->cfg_handle) != DDI_FM_OK) { ddi_fm_service_impact(bgep->devinfo, DDI_SERVICE_LOST); @@ -4065,14 +3994,6 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) * Determine whether to override the chip's own MAC address */ bge_find_mac_address(bgep, cidp); - { - int slot; - for (slot = 0; slot < MAC_ADDRESS_REGS_MAX; slot++) { - ethaddr_copy(cidp->vendor_addr.addr, - bgep->curr_addr[slot].addr); - bgep->curr_addr[slot].set = 1; - } - } bge_read_fw_ver(bgep); @@ -4090,10 +4011,7 @@ bge_attach(dev_info_t *devinfo, ddi_attach_cmd_t cmd) macp->m_max_sdu = cidp->ethmax_size - sizeof (struct ether_header); macp->m_margin = VLAN_TAGSZ; macp->m_priv_props = bge_priv_prop; - -#if defined(ILLUMOS) - bge_m_unicst(bgep, cidp->vendor_addr.addr); -#endif + macp->m_v12n = MAC_VIRT_LEVEL1; /* * Finally, we're ready to register ourselves with the MAC layer diff --git a/usr/src/uts/common/io/bge/bge_mii.c b/usr/src/uts/common/io/bge/bge_mii.c index 68823b3cba..30cd7c94d9 100644 --- a/usr/src/uts/common/io/bge/bge_mii.c +++ b/usr/src/uts/common/io/bge/bge_mii.c @@ -586,7 +586,7 @@ bge_restart_copper(bge_t *bgep, boolean_t powerdown) case MHCR_CHIP_ASIC_REV_5906: case MHCR_CHIP_ASIC_REV_5700: case MHCR_CHIP_ASIC_REV_5701: - case MHCR_CHIP_ASIC_REV_5723: /* 5717 and 5725 series as well */ + case MHCR_CHIP_ASIC_REV_5723: /* 5717, 5725, 57765 series as well */ case MHCR_CHIP_ASIC_REV_5721_5751: /* * Just a plain reset; the "check" code breaks these chips @@ -1333,7 +1333,8 @@ bge_restart_serdes(bge_t *bgep, boolean_t powerdown) macmode &= ~ETHERNET_MODE_PORTMODE_MASK; if (DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { macmode |= ETHERNET_MODE_PORTMODE_GMII; } else { macmode |= ETHERNET_MODE_PORTMODE_TBI; @@ -1561,11 +1562,12 @@ bge_check_serdes(bge_t *bgep, boolean_t recheck) * Don't call function bge_autoneg_serdes() as * RX_1000BASEX_AUTONEG_REG (0x0448) is not applicable * to BCM5705, BCM5788, BCM5721, BCM5751, BCM5752, - * BCM5714, and BCM5715 devices. + * BCM5714, BCM5715, and BCM57765 family devices. */ if (DEVICE_5717_SERIES_CHIPSETS(bgep) || DEVICE_5725_SERIES_CHIPSETS(bgep) || - DEVICE_5714_SERIES_CHIPSETS(bgep)) { + DEVICE_5714_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) { tx_status = bge_reg_get32(bgep, TRANSMIT_MAC_STATUS_REG); linkup = BIS(tx_status, TRANSMIT_STATUS_LINK_UP); diff --git a/usr/src/uts/common/io/bge/bge_send.c b/usr/src/uts/common/io/bge/bge_send.c index 87e0c0105d..c00f8ac124 100644 --- a/usr/src/uts/common/io/bge/bge_send.c +++ b/usr/src/uts/common/io/bge/bge_send.c @@ -451,7 +451,8 @@ start_tx: hw_sbd_p->flags |= SBD_FLAG_TCP_UDP_CKSUM; if (!(bgep->chipid.flags & CHIP_FLAG_NO_JUMBO) && (DEVICE_5717_SERIES_CHIPSETS(bgep) || - DEVICE_5725_SERIES_CHIPSETS(bgep)) && + DEVICE_5725_SERIES_CHIPSETS(bgep) || + DEVICE_57765_SERIES_CHIPSETS(bgep)) && (txbuf->copy_len > ETHERMAX)) hw_sbd_p->flags |= SBD_FLAG_JMB_PKT; hw_sbd_p->flags |= SBD_FLAG_PACKET_END; diff --git a/usr/src/uts/common/io/i40e/i40e_gld.c b/usr/src/uts/common/io/i40e/i40e_gld.c index ccf814be0b..1bf40bbce3 100644 --- a/usr/src/uts/common/io/i40e/i40e_gld.c +++ b/usr/src/uts/common/io/i40e/i40e_gld.c @@ -733,8 +733,10 @@ i40e_m_getcapab(void *arg, mac_capab_t cap, void *cap_data) mac_capab_lso_t *cap_lso = cap_data; if (i40e->i40e_tx_lso_enable == B_TRUE) { - cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4; + cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4 | + LSO_TX_BASIC_TCP_IPV6; cap_lso->lso_basic_tcp_ipv4.lso_max = I40E_LSO_MAXLEN; + cap_lso->lso_basic_tcp_ipv6.lso_max = I40E_LSO_MAXLEN; } else { return (B_FALSE); } diff --git a/usr/src/uts/common/io/i40e/i40e_transceiver.c b/usr/src/uts/common/io/i40e/i40e_transceiver.c index 9662cb58f5..e324957625 100644 --- a/usr/src/uts/common/io/i40e/i40e_transceiver.c +++ b/usr/src/uts/common/io/i40e/i40e_transceiver.c @@ -1782,7 +1782,8 @@ i40e_tx_context(i40e_t *i40e, i40e_trqpair_t *itrq, mblk_t *mp, * LSO requires that checksum offloads are enabled. If for * some reason they're not we bail out with an error. */ - if ((chkflags & HCK_IPV4_HDRCKSUM) == 0 || + if ((meo->meoi_l3proto == ETHERTYPE_IP && + (chkflags & HCK_IPV4_HDRCKSUM) == 0) || (chkflags & HCK_PARTIALCKSUM) == 0) { txs->itxs_lso_nohck.value.ui64++; return (-1); diff --git a/usr/src/uts/common/io/igb/igb_gld.c b/usr/src/uts/common/io/igb/igb_gld.c index 2bb4f99d6f..f68c4b73e9 100644 --- a/usr/src/uts/common/io/igb/igb_gld.c +++ b/usr/src/uts/common/io/igb/igb_gld.c @@ -965,8 +965,10 @@ igb_m_getcapab(void *arg, mac_capab_t cap, void *cap_data) mac_capab_lso_t *cap_lso = cap_data; if (igb->lso_enable) { - cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4; + cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4 | + LSO_TX_BASIC_TCP_IPV6; cap_lso->lso_basic_tcp_ipv4.lso_max = IGB_LSO_MAXLEN; + cap_lso->lso_basic_tcp_ipv6.lso_max = IGB_LSO_MAXLEN; break; } else { return (B_FALSE); @@ -1645,7 +1647,7 @@ igb_priv_prop_info(igb_t *igb, const char *pr_name, mac_prop_info_handle_t prh) value = DEFAULT_RX_COPY_THRESHOLD; } else if (strcmp(pr_name, "_rx_limit_per_intr") == 0) { value = DEFAULT_RX_LIMIT_PER_INTR; - } else if (strcmp(pr_name, "_intr_throttling") == 0) { + } else if (strcmp(pr_name, "_intr_throttling") == 0) { value = igb->capab->def_intr_throttle; } else { return; diff --git a/usr/src/uts/common/io/igb/igb_sw.h b/usr/src/uts/common/io/igb/igb_sw.h index f689c44b14..2e329d6fdc 100644 --- a/usr/src/uts/common/io/igb/igb_sw.h +++ b/usr/src/uts/common/io/igb/igb_sw.h @@ -227,7 +227,7 @@ extern "C" { enum ioc_reply { IOC_INVAL = -1, /* bad, NAK with EINVAL */ - IOC_DONE, /* OK, reply sent */ + IOC_DONE, /* OK, reply sent */ IOC_ACK, /* OK, just send ACK */ IOC_REPLY /* OK, just send reply */ }; @@ -355,6 +355,7 @@ typedef struct tx_context { uint32_t hcksum_flags; uint32_t ip_hdr_len; uint32_t mac_hdr_len; + uint32_t l3_proto; uint32_t l4_proto; uint32_t mss; uint32_t l4_hdr_len; @@ -558,7 +559,7 @@ typedef struct igb_rx_group { } igb_rx_group_t; typedef struct igb { - int instance; + int instance; mac_handle_t mac_hdl; dev_info_t *dip; struct e1000_hw hw; @@ -606,7 +607,7 @@ typedef struct igb { boolean_t tx_ring_init; boolean_t tx_head_wb_enable; /* Tx head wrtie-back */ boolean_t tx_hcksum_enable; /* Tx h/w cksum offload */ - boolean_t lso_enable; /* Large Segment Offload */ + boolean_t lso_enable; /* Large Segment Offload */ uint32_t tx_copy_thresh; /* Tx copy threshold */ uint32_t tx_recycle_thresh; /* Tx recycle threshold */ uint32_t tx_overload_thresh; /* Tx overload threshold */ diff --git a/usr/src/uts/common/io/igb/igb_tx.c b/usr/src/uts/common/io/igb/igb_tx.c index 0496bf59fe..5245312adc 100644 --- a/usr/src/uts/common/io/igb/igb_tx.c +++ b/usr/src/uts/common/io/igb/igb_tx.c @@ -598,6 +598,7 @@ igb_get_tx_context(mblk_t *mp, tx_context_t *ctx) uint32_t start; uint32_t flags; uint32_t lso_flag; + uint32_t lso_cksum; uint32_t mss; uint32_t len; uint32_t size; @@ -622,19 +623,6 @@ igb_get_tx_context(mblk_t *mp, tx_context_t *ctx) ctx->mss = mss; ctx->lso_flag = (lso_flag == HW_LSO); - /* - * LSO relies on tx h/w checksum, so here the packet will be - * dropped if the h/w checksum flags are not set. - */ - if (ctx->lso_flag) { - if (!((ctx->hcksum_flags & HCK_PARTIALCKSUM) && - (ctx->hcksum_flags & HCK_IPV4_HDRCKSUM))) { - igb_log(NULL, IGB_LOG_INFO, "igb_tx: h/w " - "checksum flags are not set for LSO"); - return (TX_CXT_E_LSO_CSUM); - } - } - etype = 0; mac_hdr_len = 0; l4_proto = 0; @@ -679,6 +667,8 @@ igb_get_tx_context(mblk_t *mp, tx_context_t *ctx) * Here we assume the IP(V6) header is fully included in one * mblk fragment. */ + lso_cksum = HCK_PARTIALCKSUM; + ctx->l3_proto = etype; switch (etype) { case ETHERTYPE_IP: offset = mac_hdr_len; @@ -703,11 +693,27 @@ igb_get_tx_context(mblk_t *mp, tx_context_t *ctx) * with zero. Currently the tcp/ip stack has done * these. */ + lso_cksum |= HCK_IPV4_HDRCKSUM; } l4_proto = *(uint8_t *)(pos + offsetof(ipha_t, ipha_protocol)); break; case ETHERTYPE_IPV6: + /* + * We need to zero out the length in the header. + */ + if (ctx->lso_flag) { + offset = offsetof(ip6_t, ip6_plen) + mac_hdr_len; + while (size <= offset) { + mp = mp->b_cont; + ASSERT(mp != NULL); + len = MBLKL(mp); + size += len; + } + pos = mp->b_rptr + offset + len - size; + *((uint16_t *)(uintptr_t)(pos)) = 0; + } + offset = offsetof(ip6_t, ip6_nxt) + mac_hdr_len; while (size <= offset) { mp = mp->b_cont; @@ -727,6 +733,18 @@ igb_get_tx_context(mblk_t *mp, tx_context_t *ctx) } if (ctx->lso_flag) { + /* + * LSO relies on tx h/w checksum, so here the packet will be + * dropped if the h/w checksum flags are not set. + */ + if ((ctx->hcksum_flags & lso_cksum) != lso_cksum) { + igb_log(NULL, IGB_LOG_INFO, "igb_tx: h/w " + "checksum flags are not set for LSO, found " + "0x%x, needed bits 0x%x", ctx->hcksum_flags, + lso_cksum); + return (TX_CXT_E_LSO_CSUM); + } + offset = mac_hdr_len + start; while (size <= offset) { mp = mp->b_cont; @@ -771,6 +789,7 @@ igb_check_tx_context(igb_tx_ring_t *tx_ring, tx_context_t *ctx) * need to be checked are: * hcksum_flags * l4_proto + * l3_proto * mss (only check for LSO) * l4_hdr_len (only check for LSO) * ip_hdr_len @@ -783,6 +802,7 @@ igb_check_tx_context(igb_tx_ring_t *tx_ring, tx_context_t *ctx) if (ctx->hcksum_flags != 0) { if ((ctx->hcksum_flags != last->hcksum_flags) || (ctx->l4_proto != last->l4_proto) || + (ctx->l3_proto != last->l3_proto) || (ctx->lso_flag && ((ctx->mss != last->mss) || (ctx->l4_hdr_len != last->l4_hdr_len))) || (ctx->ip_hdr_len != last->ip_hdr_len) || @@ -814,10 +834,19 @@ igb_fill_tx_context(struct e1000_adv_tx_context_desc *ctx_tbd, ctx_tbd->type_tucmd_mlhl = E1000_ADVTXD_DCMD_DEXT | E1000_ADVTXD_DTYP_CTXT; - if (ctx->hcksum_flags & HCK_IPV4_HDRCKSUM) - ctx_tbd->type_tucmd_mlhl |= E1000_ADVTXD_TUCMD_IPV4; + /* + * When we have a TX context set up, we enforce that the ethertype is + * either IPv4 or IPv6 in igb_get_tx_context(). + */ + if (ctx->lso_flag || ctx->hcksum_flags & HCK_IPV4_HDRCKSUM) { + if (ctx->l3_proto == ETHERTYPE_IP) { + ctx_tbd->type_tucmd_mlhl |= E1000_ADVTXD_TUCMD_IPV4; + } else { + ctx_tbd->type_tucmd_mlhl |= E1000_ADVTXD_TUCMD_IPV6; + } + } - if (ctx->hcksum_flags & HCK_PARTIALCKSUM) { + if (ctx->lso_flag || ctx->hcksum_flags & HCK_PARTIALCKSUM) { switch (ctx->l4_proto) { case IPPROTO_TCP: ctx_tbd->type_tucmd_mlhl |= E1000_ADVTXD_TUCMD_L4T_TCP; diff --git a/usr/src/uts/common/io/ixgbe/ixgbe_gld.c b/usr/src/uts/common/io/ixgbe/ixgbe_gld.c index ea888220fa..8508e32b82 100644 --- a/usr/src/uts/common/io/ixgbe/ixgbe_gld.c +++ b/usr/src/uts/common/io/ixgbe/ixgbe_gld.c @@ -304,8 +304,10 @@ ixgbe_m_getcapab(void *arg, mac_capab_t cap, void *cap_data) mac_capab_lso_t *cap_lso = cap_data; if (ixgbe->lso_enable) { - cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4; + cap_lso->lso_flags = LSO_TX_BASIC_TCP_IPV4 | + LSO_TX_BASIC_TCP_IPV6; cap_lso->lso_basic_tcp_ipv4.lso_max = IXGBE_LSO_MAXLEN; + cap_lso->lso_basic_tcp_ipv6.lso_max = IXGBE_LSO_MAXLEN; break; } else { return (B_FALSE); diff --git a/usr/src/uts/common/io/ixgbe/ixgbe_sw.h b/usr/src/uts/common/io/ixgbe/ixgbe_sw.h index cfd987787a..8bf93afe9c 100644 --- a/usr/src/uts/common/io/ixgbe/ixgbe_sw.h +++ b/usr/src/uts/common/io/ixgbe/ixgbe_sw.h @@ -408,6 +408,7 @@ typedef struct ixgbe_tx_context { uint32_t hcksum_flags; uint32_t ip_hdr_len; uint32_t mac_hdr_len; + uint32_t l3_proto; uint32_t l4_proto; uint32_t mss; uint32_t l4_hdr_len; diff --git a/usr/src/uts/common/io/ixgbe/ixgbe_tx.c b/usr/src/uts/common/io/ixgbe/ixgbe_tx.c index 9191aad058..b6926fc3b7 100644 --- a/usr/src/uts/common/io/ixgbe/ixgbe_tx.c +++ b/usr/src/uts/common/io/ixgbe/ixgbe_tx.c @@ -697,6 +697,7 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) uint32_t start; uint32_t hckflags; uint32_t lsoflags; + uint32_t lsocksum; uint32_t mss; uint32_t len; uint32_t size; @@ -722,19 +723,6 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) ctx->mss = mss; ctx->lso_flag = (lsoflags == HW_LSO); - /* - * LSO relies on tx h/w checksum, so here will drop the package - * if h/w checksum flag is not declared. - */ - if (ctx->lso_flag) { - if (!((ctx->hcksum_flags & HCK_PARTIALCKSUM) && - (ctx->hcksum_flags & HCK_IPV4_HDRCKSUM))) { - IXGBE_DEBUGLOG_0(NULL, "ixgbe_tx: h/w " - "checksum flags are not specified when doing LSO"); - return (-1); - } - } - etype = 0; mac_hdr_len = 0; l4_proto = 0; @@ -779,6 +767,8 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) * Here we don't assume the IP(V6) header is fully included in * one mblk fragment. */ + lsocksum = HCK_PARTIALCKSUM; + ctx->l3_proto = etype; switch (etype) { case ETHERTYPE_IP: if (ctx->lso_flag) { @@ -810,6 +800,7 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) * (ip_source_addr, ip_destination_addr, l4_proto) * Currently the tcp/ip stack has done it. */ + lsocksum |= HCK_IPV4_HDRCKSUM; } offset = offsetof(ipha_t, ipha_protocol) + mac_hdr_len; @@ -824,6 +815,21 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) l4_proto = *(uint8_t *)pos; break; case ETHERTYPE_IPV6: + /* + * We need to zero out the length in the header. + */ + if (ctx->lso_flag) { + offset = offsetof(ip6_t, ip6_plen) + mac_hdr_len; + while (size <= offset) { + mp = mp->b_cont; + ASSERT(mp != NULL); + len = MBLKL(mp); + size += len; + } + pos = mp->b_rptr + offset + len - size; + *((uint16_t *)(uintptr_t)(pos)) = 0; + } + offset = offsetof(ip6_t, ip6_nxt) + mac_hdr_len; while (size <= offset) { mp = mp->b_cont; @@ -842,6 +848,18 @@ ixgbe_get_context(mblk_t *mp, ixgbe_tx_context_t *ctx) } if (ctx->lso_flag) { + /* + * LSO relies on tx h/w checksum, so here will drop the packet + * if h/w checksum flag is not declared. + */ + if ((ctx->hcksum_flags & lsocksum) != lsocksum) { + IXGBE_DEBUGLOG_2(NULL, "ixgbe_tx: h/w checksum flags " + "are not set for LSO, found 0x%x, needed bits 0x%x", + ctx->hcksum_flags, lsocksum); + return (-1); + } + + offset = mac_hdr_len + start; while (size <= offset) { mp = mp->b_cont; @@ -898,6 +916,7 @@ ixgbe_check_context(ixgbe_tx_ring_t *tx_ring, ixgbe_tx_context_t *ctx) if ((ctx->hcksum_flags != last->hcksum_flags) || (ctx->l4_proto != last->l4_proto) || + (ctx->l3_proto != last->l3_proto) || (ctx->mac_hdr_len != last->mac_hdr_len) || (ctx->ip_hdr_len != last->ip_hdr_len) || (ctx->lso_flag != last->lso_flag) || @@ -928,11 +947,19 @@ ixgbe_fill_context(struct ixgbe_adv_tx_context_desc *ctx_tbd, ctx_tbd->type_tucmd_mlhl = IXGBE_ADVTXD_DCMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; + /* + * When we have a TX context set up, we enforce that the ethertype is + * either IPv4 or IPv6 in ixgbe_get_tx_context(). + */ + if (ctx->lso_flag || ctx->hcksum_flags & HCK_IPV4_HDRCKSUM) { + if (ctx->l3_proto == ETHERTYPE_IP) { + ctx_tbd->type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; + } else { + ctx_tbd->type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV6; + } + } - if (ctx->hcksum_flags & HCK_IPV4_HDRCKSUM) - ctx_tbd->type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; - - if (ctx->hcksum_flags & HCK_PARTIALCKSUM) { + if (ctx->lso_flag || ctx->hcksum_flags & HCK_PARTIALCKSUM) { switch (ctx->l4_proto) { case IPPROTO_TCP: ctx_tbd->type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP; diff --git a/usr/src/uts/common/os/devcfg.c b/usr/src/uts/common/os/devcfg.c index c82a8f86d9..ef2fb9b8a4 100644 --- a/usr/src/uts/common/os/devcfg.c +++ b/usr/src/uts/common/os/devcfg.c @@ -255,7 +255,7 @@ i_ddi_node_cache_init() * The allocated node has a reference count of 0. */ dev_info_t * -i_ddi_alloc_node(dev_info_t *pdip, char *node_name, pnode_t nodeid, +i_ddi_alloc_node(dev_info_t *pdip, const char *node_name, pnode_t nodeid, int instance, ddi_prop_t *sys_prop, int flag) { struct dev_info *devi; @@ -2046,7 +2046,7 @@ ndi_devi_tryenter(dev_info_t *dip, int *circular) * not allowed to sleep. */ int -ndi_devi_alloc(dev_info_t *parent, char *node_name, pnode_t nodeid, +ndi_devi_alloc(dev_info_t *parent, const char *node_name, pnode_t nodeid, dev_info_t **ret_dip) { ASSERT(node_name != NULL); @@ -2066,7 +2066,7 @@ ndi_devi_alloc(dev_info_t *parent, char *node_name, pnode_t nodeid, * This routine may sleep and should not be called at interrupt time */ void -ndi_devi_alloc_sleep(dev_info_t *parent, char *node_name, pnode_t nodeid, +ndi_devi_alloc_sleep(dev_info_t *parent, const char *node_name, pnode_t nodeid, dev_info_t **ret_dip) { ASSERT(node_name != NULL); @@ -2536,7 +2536,7 @@ i_ddi_get_exported_classes(dev_info_t *dip, char ***classes) * Helper functions, returns NULL if no memory. */ char * -i_ddi_strdup(char *str, uint_t flag) +i_ddi_strdup(const char *str, uint_t flag) { char *copy; diff --git a/usr/src/uts/common/sys/autoconf.h b/usr/src/uts/common/sys/autoconf.h index ee97f8d274..5a3ad7df60 100644 --- a/usr/src/uts/common/sys/autoconf.h +++ b/usr/src/uts/common/sys/autoconf.h @@ -274,7 +274,7 @@ extern int exclude_level(int); extern major_t path_to_major(char *); extern void i_ddi_node_cache_init(void); -extern dev_info_t *i_ddi_alloc_node(dev_info_t *, char *, pnode_t, int, +extern dev_info_t *i_ddi_alloc_node(dev_info_t *, const char *, pnode_t, int, ddi_prop_t *, int); extern void i_ddi_forceattach_drivers(void); extern int i_ddi_io_initialized(void); diff --git a/usr/src/uts/common/sys/ddi_implfuncs.h b/usr/src/uts/common/sys/ddi_implfuncs.h index 522366aa23..c5e84e576a 100644 --- a/usr/src/uts/common/sys/ddi_implfuncs.h +++ b/usr/src/uts/common/sys/ddi_implfuncs.h @@ -164,7 +164,7 @@ extern int peekpoke_mem(ddi_ctl_enum_t, peekpoke_ctlops_t *); /* * Helper functions */ -extern char *i_ddi_strdup(char *, uint_t); +extern char *i_ddi_strdup(const char *, uint_t); extern void i_ddi_prop_list_delete(ddi_prop_t *); extern ddi_prop_t *i_ddi_prop_list_dup(ddi_prop_t *, uint_t); extern int i_ddi_load_drvconf(major_t); diff --git a/usr/src/uts/common/sys/sunndi.h b/usr/src/uts/common/sys/sunndi.h index e6a998322d..94313a450e 100644 --- a/usr/src/uts/common/sys/sunndi.h +++ b/usr/src/uts/common/sys/sunndi.h @@ -118,11 +118,11 @@ ndi_prop_remove_all(dev_info_t *dip); * not allowed to sleep. */ int -ndi_devi_alloc(dev_info_t *parent, char *node_name, pnode_t nodeid, +ndi_devi_alloc(dev_info_t *parent, const char *node_name, pnode_t nodeid, dev_info_t **ret_dip); void -ndi_devi_alloc_sleep(dev_info_t *parent, char *node_name, pnode_t nodeid, +ndi_devi_alloc_sleep(dev_info_t *parent, const char *node_name, pnode_t nodeid, dev_info_t **ret_dip); /* @@ -174,7 +174,7 @@ ndi_devi_bind_driver_async(dev_info_t *dip, uint_t flags); */ int ndi_devctl_device_getstate(dev_info_t *parent, struct devctl_iocdata *dcp, - uint_t *state); + uint_t *state); /* * Transition the child addressed by "name@addr" to the online state. @@ -182,7 +182,7 @@ ndi_devctl_device_getstate(dev_info_t *parent, struct devctl_iocdata *dcp, */ int ndi_devctl_device_online(dev_info_t *dip, struct devctl_iocdata *dcp, - uint_t flags); + uint_t flags); /* * Transition the child addressed by "name@addr" to the offline state. @@ -190,7 +190,7 @@ ndi_devctl_device_online(dev_info_t *dip, struct devctl_iocdata *dcp, */ int ndi_devctl_device_offline(dev_info_t *dip, struct devctl_iocdata *dcp, - uint_t flags); + uint_t flags); /* * Remove the child addressed by name@addr. @@ -198,7 +198,7 @@ ndi_devctl_device_offline(dev_info_t *dip, struct devctl_iocdata *dcp, */ int ndi_devctl_device_remove(dev_info_t *dip, struct devctl_iocdata *dcp, - uint_t flags); + uint_t flags); /* * Bus get state @@ -206,7 +206,7 @@ ndi_devctl_device_remove(dev_info_t *dip, struct devctl_iocdata *dcp, */ int ndi_devctl_bus_getstate(dev_info_t *dip, struct devctl_iocdata *dcp, - uint_t *state); + uint_t *state); /* * Place the devinfo in the ONLINE state @@ -219,7 +219,7 @@ ndi_devi_online(dev_info_t *dip, uint_t flags); */ int ndi_devctl_ioctl(dev_info_t *dip, int cmd, intptr_t arg, int mode, - uint_t flags); + uint_t flags); /* * Asynchronous version of ndi_devi_online, callable from interrupt @@ -524,7 +524,7 @@ typedef struct ndi_event_set { */ int ndi_event_alloc_hdl(dev_info_t *dip, ddi_iblock_cookie_t cookie, - ndi_event_hdl_t *ndi_event_hdl, uint_t flag); + ndi_event_hdl_t *ndi_event_hdl, uint_t flag); /* * free the ndi event handle @@ -536,40 +536,28 @@ ndi_event_free_hdl(ndi_event_hdl_t handle); * bind or unbind a set of events to/from the event handle */ int -ndi_event_bind_set(ndi_event_hdl_t handle, - ndi_event_set_t *ndi_event_set, - uint_t flag); +ndi_event_bind_set(ndi_event_hdl_t handle, ndi_event_set_t *ndi_event_set, + uint_t flag); int -ndi_event_unbind_set(ndi_event_hdl_t handle, - ndi_event_set_t *ndi_event_set, - uint_t flag); +ndi_event_unbind_set(ndi_event_hdl_t handle, ndi_event_set_t *ndi_event_set, + uint_t flag); /* * get an event cookie */ int -ndi_event_retrieve_cookie(ndi_event_hdl_t handle, - dev_info_t *child_dip, - char *eventname, - ddi_eventcookie_t *cookiep, - uint_t flag); +ndi_event_retrieve_cookie(ndi_event_hdl_t handle, dev_info_t *child_dip, + char *eventname, ddi_eventcookie_t *cookiep, uint_t flag); /* * add an event callback info to the ndi event handle */ int -ndi_event_add_callback(ndi_event_hdl_t handle, - dev_info_t *child_dip, - ddi_eventcookie_t cookie, - void (*event_callback) - (dev_info_t *, - ddi_eventcookie_t, - void *arg, - void *impldata), - void *arg, - uint_t flag, - ddi_callback_id_t *cb_id); +ndi_event_add_callback(ndi_event_hdl_t handle, dev_info_t *child_dip, + ddi_eventcookie_t cookie, void (*event_callback)(dev_info_t *, + ddi_eventcookie_t, void *arg, void *impldata), void *arg, uint_t flag, + ddi_callback_id_t *cb_id); /* * remove an event callback registration from the ndi event handle @@ -588,7 +576,7 @@ ndi_event_run_callbacks(ndi_event_hdl_t handle, dev_info_t *child_dip, * do callback for just one child_dip, regardless of attributes */ int ndi_event_do_callback(ndi_event_hdl_t handle, dev_info_t *child_dip, - ddi_eventcookie_t cookie, void *bus_impldata); + ddi_eventcookie_t cookie, void *bus_impldata); /* * ndi_event_tag_to_cookie: utility function to find an event cookie @@ -603,7 +591,7 @@ ndi_event_tag_to_cookie(ndi_event_hdl_t handle, int event_tag); */ int ndi_event_cookie_to_tag(ndi_event_hdl_t handle, - ddi_eventcookie_t cookie); + ddi_eventcookie_t cookie); /* * ndi_event_cookie_to_name: utility function to find an event @@ -611,7 +599,7 @@ ndi_event_cookie_to_tag(ndi_event_hdl_t handle, */ char * ndi_event_cookie_to_name(ndi_event_hdl_t handle, - ddi_eventcookie_t cookie); + ddi_eventcookie_t cookie); /* * ndi_event_tag_to_name: utility function to find an event @@ -681,7 +669,7 @@ typedef struct ndi_ra_request { uint64_t ra_boundlen; /* Length of the area, starting */ /* from ra_boundbase, for the */ /* allocated resource to be */ - /* restricted to. */ + /* restricted to. */ uint64_t ra_align_mask; /* Alignment mask used for */ /* allocated base address */ @@ -743,11 +731,11 @@ ndi_ra_map_destroy(dev_info_t *dip, char *type); int ndi_ra_alloc(dev_info_t *dip, ndi_ra_request_t *req, uint64_t *basep, - uint64_t *lenp, char *type, uint_t flag); + uint64_t *lenp, char *type, uint_t flag); int ndi_ra_free(dev_info_t *dip, uint64_t base, uint64_t len, char *type, - uint_t flag); + uint_t flag); /* * ndi_dev_is_prom_node: Return non-zero if the node is a prom node diff --git a/usr/src/uts/intel/bge/Makefile b/usr/src/uts/intel/bge/Makefile index 456cbc9043..95527d4424 100644 --- a/usr/src/uts/intel/bge/Makefile +++ b/usr/src/uts/intel/bge/Makefile @@ -39,7 +39,6 @@ UTSBASE = ../.. # MODULE = bge OBJECTS = $(BGE_OBJS:%=$(OBJS_DIR)/%) -LINTS = $(LINTS_DIR)/bge_lint.ln ROOTMODULE = $(ROOT_DRV_DIR)/$(MODULE) CONF_SRCDIR = $(UTSBASE)/common/io/bge @@ -52,7 +51,6 @@ include $(UTSBASE)/intel/Makefile.intel # Define targets # ALL_TARGET = $(BINARY) -LINT_TARGET = $(MODULE).lint INSTALL_TARGET = $(BINARY) $(ROOTMODULE) $(ROOT_CONFFILE) # @@ -63,7 +61,6 @@ INSTALL_TARGET = $(BINARY) $(ROOTMODULE) $(ROOT_CONFFILE) # to investigate and remove these for maximum lint coverage. # Please do not carry these forward to new Makefiles. # -LINTTAGS += -erroff=E_BAD_PTR_CAST_ALIGN CERRWARN += $(CNOWARN_UNINIT) CERRWARN += -_gcc=-Wno-switch @@ -92,12 +89,6 @@ clean: $(CLEAN_DEPS) clobber: $(CLOBBER_DEPS) -lint: $(LINT_DEPS) - -modlintlib: $(MODLINTLIB_DEPS) - -clean.lint: $(CLEAN_LINT_DEPS) - install: $(INSTALL_DEPS) # diff --git a/usr/src/uts/intel/os/driver_aliases b/usr/src/uts/intel/os/driver_aliases index 8f4c2f1bf2..7e8c801f03 100644 --- a/usr/src/uts/intel/os/driver_aliases +++ b/usr/src/uts/intel/os/driver_aliases @@ -142,6 +142,16 @@ bge "pci108e,1647" bge "pci108e,1648" bge "pci108e,16a7" bge "pci108e,16a8" +bge "pci14e4,0x1682" +bge "pci14e4,0x1686" +bge "pci14e4,0x16b0" +bge "pci14e4,0x16b1" +bge "pci14e4,0x16b2" +bge "pci14e4,0x16b3" +bge "pci14e4,0x16b4" +bge "pci14e4,0x16b5" +bge "pci14e4,0x16b6" +bge "pci14e4,0x16b7" bge "pci14e4,1600" bge "pci14e4,1601" bge "pci14e4,1643" @@ -176,6 +186,16 @@ bge "pci14e4,16a7" bge "pci14e4,16a8" bge "pci14e4,16c7" bge "pci14e4,16f3" +bge "pciex14e4,0x1682" +bge "pciex14e4,0x1686" +bge "pciex14e4,0x16b0" +bge "pciex14e4,0x16b1" +bge "pciex14e4,0x16b2" +bge "pciex14e4,0x16b3" +bge "pciex14e4,0x16b4" +bge "pciex14e4,0x16b5" +bge "pciex14e4,0x16b6" +bge "pciex14e4,0x16b7" bge "pciex14e4,1643" bge "pciex14e4,1655" bge "pciex14e4,1656" diff --git a/usr/src/uts/sparc/bge/Makefile b/usr/src/uts/sparc/bge/Makefile index a0b56a51b0..0a8b2cabc4 100644 --- a/usr/src/uts/sparc/bge/Makefile +++ b/usr/src/uts/sparc/bge/Makefile @@ -39,7 +39,6 @@ UTSBASE = ../.. # MODULE = bge OBJECTS = $(BGE_OBJS:%=$(OBJS_DIR)/%) -LINTS = $(LINTS_DIR)/bge_lint.ln ROOTMODULE = $(ROOT_DRV_DIR)/$(MODULE) CONF_SRCDIR = $(UTSBASE)/common/io/bge @@ -52,7 +51,6 @@ include $(UTSBASE)/sparc/Makefile.sparc # Define targets # ALL_TARGET = $(BINARY) -LINT_TARGET = $(MODULE).lint INSTALL_TARGET = $(BINARY) $(ROOTMODULE) $(ROOT_CONFFILE) # @@ -75,7 +73,6 @@ LDFLAGS += -dy -N misc/mac # to investigate and remove these for maximum lint coverage. # Please do not carry these forward to new Makefiles. # -LINTTAGS += -erroff=E_BAD_PTR_CAST_ALIGN CERRWARN += $(CNOWARN_UNINIT) CERRWARN += -_gcc=-Wno-switch @@ -96,12 +93,6 @@ clean: $(CLEAN_DEPS) clobber: $(CLOBBER_DEPS) -lint: $(LINT_DEPS) - -modlintlib: $(MODLINTLIB_DEPS) - -clean.lint: $(CLEAN_LINT_DEPS) - install: $(INSTALL_DEPS) # |