All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alejandro Colomar <alx.manpages@gmail.com>
To: linux-man@vger.kernel.org
Cc: Alejandro Colomar <alx@kernel.org>
Subject: [PATCH 1/3] strcpy.3: Rewrite page to document all string-copying functions
Date: Mon, 12 Dec 2022 15:24:16 +0100	[thread overview]
Message-ID: <20221212142418.27615-1-alx@kernel.org> (raw)
In-Reply-To: <176225b0-4b0e-698b-b79e-f8ed78b4cf8c@gmail.com>

This is an opportunity to use consistent language across the
documentation for all string-copying functions.

It is also easier to show the similarities and differences between all
of the functions, so that a reader can use this page to know which
function is needed for a given task.

Many functions that are inferior to another one, have been marked as
deprecated, notwithstanding the deprecation status in C libraries or
any standards.  Alternatives have been given in the same page, with
reference implementations.

Signed-off-by: Alejandro Colomar <alx@kernel.org>
---
 man3/strcpy.3 | 1053 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 965 insertions(+), 88 deletions(-)

diff --git a/man3/strcpy.3 b/man3/strcpy.3
index 74c3180ae..661319f0d 100644
--- a/man3/strcpy.3
+++ b/man3/strcpy.3
@@ -1,48 +1,764 @@
-.\" Copyright (C) 1993 David Metcalfe (david@prism.demon.co.uk)
+.\" Copyright 2022 Alejandro Colomar <alx@kernel.org>
 .\"
-.\" SPDX-License-Identifier: Linux-man-pages-copyleft
-.\"
-.\" References consulted:
-.\"     Linux libc source code
-.\"     Lewine's _POSIX Programmer's Guide_ (O'Reilly & Associates, 1991)
-.\"     386BSD man pages
-.\" Modified Sat Jul 24 18:06:49 1993 by Rik Faith (faith@cs.unc.edu)
-.\" Modified Fri Aug 25 23:17:51 1995 by Andries Brouwer (aeb@cwi.nl)
-.\" Modified Wed Dec 18 00:47:18 1996 by Andries Brouwer (aeb@cwi.nl)
-.\" 2007-06-15, Marc Boyer <marc.boyer@enseeiht.fr> + mtk
-.\"     Improve discussion of strncpy().
+.\" SPDX-License-Identifier: BSD-3-Clause
 .\"
 .TH strcpy 3 (date) "Linux man-pages (unreleased)"
+.\" ----- NAME :: -----------------------------------------------------/
 .SH NAME
-strcpy \- copy a string
+stpcpy,
+stpecpy, stpecpyx,
+strlcpy, strlcat,
+strscpy,
+strcpy, strcat,
+stpncpy,
+ustr2stp,
+strncpy,
+strncat,
+mempcpy
+\- copy strings
+.\" ----- LIBRARY :: --------------------------------------------------/
 .SH LIBRARY
+.TP
+.BR stpcpy (3)
+.TQ
+.BR stpncpy (3)
+.TQ
+.BR mempcpy (3)
+.TQ
+.BR strcpy "(3), \c"
+.BR strcat (3)
+.TQ
+.BR strncpy (3)
+.TQ
+.BR strncat (3)
 Standard C library
 .RI ( libc ", " \-lc )
+.TP
+.BR stpecpy "(3), \c"
+.BR stpecpyx (3)
+Not provided by any library.
+.TP
+.BR strlcpy "(3), \c"
+.BR strlcat (3)
+Utility functions from BSD systems
+.RI ( libbsd ", " \-lbsd )
+.TP
+.BR strscpy (9)
+Not provided by any library.
+It is a Linux kernel internal function.
+.\" ----- SYNOPSIS :: -------------------------------------------------/
 .SH SYNOPSIS
+.\" ----- SYNOPSIS :: (Null-terminated) strings :: --------------------/
 .nf
 .B #include <string.h>
+.fi
+.SS (Null-terminated) strings
+.nf
+// Chain-copy a string.
+.BI "char *stpcpy(char *restrict " dst ", const char *restrict " src );
 .PP
-.BI "char *strcpy(char *restrict " dest ", const char *restrict " src );
+// Chain-copy a string with truncation.
+// Not defined in libc.
+.BI "char *stpecpy(char *" dst ", char " past_end "[0], \
+const char *restrict " src );
+.PP
+// Chain-copy a string with truncation and SIGSEGV on invalid input.
+// Not defined in libc.
+.BI "char *stpecpyx(char *" dst ", char " past_end "[0], \
+const char *restrict " src );
+.PP
+// Copy a string with truncation and SIGSEGV on invalid input.
+.BR [[deprecated]] "  // Use stpecpyx(3) instead."
+.BI "size_t strlcpy(char " dst "[restrict ." sz "], \
+const char *restrict " src ,
+.BI "               size_t " sz );
+.PP
+// Concatenate a string with truncation.
+.BR [[deprecated]] "  // Use stpecpyx(3) instead."
+.BI "size_t strlcat(char " dst "[restrict ." sz "], \
+const char *restrict " src ,
+.BI "               size_t " sz );
+.PP
+// Copy a string with truncation.
+// Not defined in libc.
+.BR [[deprecated]] "  // Use stpecpy(3) instead."
+.BI "ssize_t strscpy(char " dst "[restrict ." sz "], \
+const char " src "[restrict ." sz ],
+.BI "               size_t " sz );
+.PP
+// Copy a string.
+.BR [[deprecated]] "  // Use stpcpy(3) instead."
+.BI "char *strcpy(char *restrict " dst ", const char *restrict " src );
+.PP
+// Concatenate a string.
+.BR [[deprecated]] "  // Use stpcpy(3) instead."
+.BI "char *strcat(char *restrict " dst ", const char *restrict " src );
+.fi
+.\" ----- SYNOPSIS :: Unterminated strings (null-padded fixed-width buffers)
+.SS Unterminated strings (null-padded fixed-width buffers)
+.nf
+// Zero a fixed-width buffer, and
+// copy a string with truncation into an unterminated string.
+.BI "char *stpncpy(char " dst "[restrict ." sz "], \
+const char *restrict " src ,
+.BI "               size_t " sz );
+.PP
+// Chain-copy an unterminated string into a string.
+// Not defined in libc.
+.BI "char *ustr2stp(char *restrict " dst ", \
+const char " src "[restrict ." sz ],
+.BI "               size_t " sz );
+.PP
+// Zero a fixed-width buffer, and
+// copy a string with truncation into an unterminated string
+.BR [[deprecated]] "  // Use stpncpy(3) instead."
+.BI "char *strncpy(char " dest "[restrict ." sz "], \
+const char *restrict " src ,
+.BI "               size_t " sz );
+.PP
+// Concatenate an unterminated string into a string.
+.BR [[deprecated]] "  // Use ustr2stp(3) instead."
+.BI "char *strncat(char *restrict " dst ", const char " src "[restrict ." sz ],
+.BI "               size_t " sz );
+.fi
+.\" ----- SYNOPSIS :: String structures :: ----------------------------/
+.SS String structures
+.nf
+// (Null-terminated) string structure.
+// Not defined in libc.
+.B struct str_s {
+.B "    size_t  len;"
+.B "    char    *str;"
+.B };
+.PP
+// Unterminated string structure (overlapping strings).
+// Not defined in libc.
+.B struct ustr_s {
+.B "    size_t  len;"
+.B "    char    *ustr;"
+.B };
+.PP
+// Chain-copy a string structure into an unterminated string.
+.BI "void *mempcpy(void *restrict " dst ", \
+const void " src "[restrict ." len ],
+.BI "               size_t " len );
+.fi
+.PP
+.RS -4
+Feature Test Macro Requirements for glibc (see
+.BR feature_test_macros (7)):
+.RE
+.PP
+.BR stpcpy (3),
+.BR stpncpy (3):
+.nf
+    Since glibc 2.10:
+        _POSIX_C_SOURCE >= 200809L
+    Before glibc 2.10:
+        _GNU_SOURCE
+.fi
+.PP
+.BR mempcpy (3):
+.nf
+    _GNU_SOURCE
 .fi
 .SH DESCRIPTION
-The
-.BR strcpy ()
-function copies the string pointed to by
-.IR src ,
-including the terminating null byte (\(aq\e0\(aq),
-to the buffer pointed to by
-.IR dest .
-The strings may not overlap, and the destination string
-.I dest
-must be large enough to receive the copy.
-.I Beware of buffer overruns!
-(See BUGS.)
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: -----------------/
+.SS Terms (and abbreviations)
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: string (str) ----/
+.TP
+.IR "string " ( str )
+is a sequence of zero or more non-null characters, followed by a null byte.
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: unterminated string (ustr)
+.TP
+.IR "unterminated string " ( ustr )
+is a sequence of zero or more non-null characters.
+They are sometimes contained in fixed-width buffers,
+which usually contain padding null bytes after the unterminated string,
+to fill the rest of the buffer
+without affecting the unterminated string;
+however, those padding null bytes are not part of the unterminated string.
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: length (len) ----/
+.TP
+.IR "length " ( len )
+is the number of non-null characters in a string.
+It is the return value of
+.I strlen(str)
+and of
+.IR "strnlen(ustr, sz)" .
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: size (sz) -------/
+.TP
+.IR "size " ( sz )
+refers to the entire buffer where the string is contained.
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: end -------------/
+.TP
+.I end
+is the name of a pointer to the terminating null byte of a string,
+or a pointer to one past the last character of an unterminated string.
+This is the return value of functions that allow chaining.
+It is equivalent to
+.IR &str[len] .
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: past_end --------/
+.TP
+.I past_end
+is the name of a pointer to one past the end of the buffer
+that contains a string.
+It is equivalent to
+.IR &str[sz] .
+It is used as a sentinel value,
+to be able to truncate strings instead of overrunning a buffer.
+.\" ----- DESCRIPTION :: Terms (and abbreviations) :: string structures
+.TP
+.I string structure
+.TQ
+.I unterminated string structure
+Structure that contains the length of a string,
+as well as the string or the unterminated string.
+.\" ----- DESCRIPTION :: Types of functions :: ------------------------/
+.SS Types of functions
+.\" ----- DESCRIPTION :: Types of functions :: Copy, concatenate, and chain-copy
+.TP
+Copy, concatenate, and chain-copy
+Originally,
+there was a distinction between functions that copy and those that concatenate.
+However, newer functions that copy while allowing chaining
+cover both use cases with a single API.
+They are also algorithmically faster,
+since they don't need to search for the end of the existing string.
+.IP
+To chain copy functions,
+they need to return a pointer to the
+.IR end .
+That's a byproduct of the copy operation,
+so it has no performance costs.
+These functions are preferred over copy or concatenation functions.
+Functions that return such a pointer,
+and thus can be chained,
+have names of the form
+.RB * stp *(),
+since it's also common to name the pointer just
+.IR p .
+.IP
+Chain-copying functions that truncate
+should accept a pointer to one past the end of the destination buffer.
+This allows not having to recalculate the remaining size after each call.
+.\" ----- DESCRIPTION :: Types of functions :: Truncate or not? -------/
+.TP
+Truncate or not?
+The first thing to note is that programmers should be careful with buffers,
+so they always have the correct size,
+and truncation is not necessary.
+.IP
+In most cases,
+truncation is not desired,
+and it is simpler to just do the copy.
+Simpler code is safer code.
+Programming against programming mistakes by adding more code
+just adds more points where mistakes can be made.
+.IP
+Nowadays,
+compilers can detect most programmer errors with features like
+compiler warnings,
+static analyzers, and
+.BR \%_FORTIFY_SOURCE
+(see
+.BR ftm (7)).
+Keeping the code simple
+helps these error-detection features be more precise.
+.IP
+When validating user input,
+however,
+it makes sense to truncate.
+Remember to check the return value of such function calls.
+.IP
+Functions that truncate:
+.RS
+.IP \(bu 3
+.BR stpecpy (3)
+is the most efficient string copy function that performs truncation.
+It only requires to check for truncation once after all chained calls.
+.IP \(bu
+.BR stpecpyx (3)
+is a variant of
+.BR stpecpy (3)
+that consumes the entire source string,
+to catch bugs in the program
+by forcing a segmentation fault (as
+.BR strlcpy (3bsd)
+and
+.BR strlcat (3bsd)
+do).
+.IP \(bu
+.BR strlcpy (3bsd)
+and
+.BR strlcat (3bsd)
+are designed to crash if the input string is invalid
+(doesn't contain a null byte).
+.IP \(bu
+.BR strscpy (9)
+reports an error instead of crashing (similar to
+.BR stpecpy (3)).
+.IP \(bu
+.BR stpncpy (3)
+and
+.BR strncpy (3)
+also truncate, but they don't write strings,
+but rather unterminated strings.
+.RE
+.\" ----- DESCRIPTION :: Unterminated strings :: ----------------------/
+.SS Unterminated strings (null-padded fixed-width buffers)
+For historic reasons,
+some standard APIs,
+such as
+.BR utmpx (5),
+use unterminated strings in fixed-width buffers.
+To interface with them,
+specialized functions need to be used.
+.PP
+To copy strings into them, use
+.BR stpncpy (3).
+.PP
+To copy from an unterminated string within a fixed-width buffer into a string,
+ignoring any trailing null bytes in the source fixed-width buffer,
+you should use
+.BR ustr2stp (3).
+.\" ----- DESCRIPTION :: String structures :: -------------------------/
+.SS String structures
+The simplest string copying function is
+.BR mempcpy (3).
+It requires always knowing the length of your strings,
+for which string structures can be used.
+It makes the code simpler,
+since you always know the length of your strings,
+and it's also faster,
+since it doesn't need to repeatedly calculate those lengths.
+.BR mempcpy (3)
+always creates an unterminated string,
+so you need to explicitly set the terminating null byte.
+.PP
+.\" ----- DESCRIPTION :: String structures :: String structure --------/
+.TP
+String structure
+The following code can be used to
+chain-copy from a string structure into a string:
+.IP
+.in +4n
+.EX
+p = mempcpy(p, src\->str, src\->len);
+*p = \(aq\e0\(aq;
+.EE
+.in
+.IP
+The following code can be used to
+chain-copy from a string structure into an unterminated string:
+.IP
+.in +4n
+.EX
+p = mempcpy(p, src\->str, src\->len);
+.EE
+.in
+.\" ----- DESCRIPTION :: String structures :: Unterminated string structure
+.TP
+Unterminated string structure (overlapping strings)
+In programs that make considerable use of strings,
+and need the best performance,
+using overlapping strings can make a big difference.
+It allows holding substrings of a bigger string
+while not duplicating memory
+nor using time to do a copy.
+.IP
+However, this is delicate,
+since it requires using unterminated strings.
+C library APIs use strings,
+so programs that use unterminated strings
+will have to take care to differentiate strings from unterminated strings.
+.IP
+The following code can be used to
+chain-copy from an unterminated string structure to a string:
+.IP
+.in +4n
+.EX
+p = mempcpy(p, src\->ustr, src\->len);
+*p = \(aq\e0\(aq;
+.EE
+.in
+.IP
+The following code can be used to
+chain-copy from an unterminated string structure to an unterminated string:
+.IP
+.in +4n
+.EX
+p = mempcpy(p, src\->ustr, src\->len);
+.EE
+.in
+.\" ----- DESCRIPTION :: Functions :: ---------------------------------/
+.SS Functions
+.\" ----- DESCRIPTION :: Functions :: stpcpy(3) -----------------------/
+.TP
+.BR stpcpy (3)
+This function copies the input string into a destination string.
+The programmer is responsible for allocating a buffer large enough.
+It returns a pointer suitable for chaining.
+.IP
+A simple implementation of
+.BR stpcpy (3)
+might be:
+.IP
+.in +4n
+.EX
+char *
+stpcpy(char *restrict dst, const char *restrict src)
+{
+    return mempcpy(dst, src, strlen(src));
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Functions :: stpecpy(3), stpecpyx(3) ---------/
+.TP
+.BR stpecpy (3)
+.TQ
+.BR stpecpyx (3)
+These functions copy the input string into a destination string.
+If the destination buffer,
+limited by a pointer to one past the end of it,
+isn't large enough to hold the copy,
+the resulting string is truncated
+(but it is guaranteed to be null-terminated).
+They return a pointer suitable for chaining.
+Truncation needs to be detected only once after the last chained call.
+.BR stpecpyx (3)
+has identical semantics to
+.BR stpecpy (3),
+except that it forces a SIGSEGV on Undefined Behavior.
+.IP
+These functions are not provided by any library,
+but you can define them with the following reference implementations:
+.IP
+.in +4n
+.EX
+/* This code is in the public domain. */
+char *
+stpecpy(char *dst, char past_end[0],
+        const char *restrict src)
+{
+    char *p;
+
+    if (dst == past_end)
+        return past_end;
+
+    p = memccpy(dst, src, \(aq\e0\(aq, past_end \- dst);
+    if (p != NULL)
+        return p \- 1;
+
+    /* truncation detected */
+    past_end[\-1] = \(aq\e0\(aq;
+    return past_end;
+}
+
+/* This code is in the public domain. */
+char *
+stpecpyx(char *dst, char past_end[0],
+         const char *restrict src)
+{
+    if (src[strlen(src)] != \(aq\e0\(aq)
+        raise(SIGSEGV);
+
+    return stpecpy(dst, past_end, src);
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Functions :: stpncpy(3) ----------------------/
+.TP
+.BR stpncpy (3)
+This function copies the input string into
+a destination null-padded fixed-width unterminated string.
+If the destination buffer,
+limited by its size,
+isn't large enough to hold the copy,
+the resulting string is truncated.
+Since it creates an unterminated string,
+it doesn't need to write a terminating null byte.
+It returns a pointer suitable for chaining,
+but it's not ideal for that.
+Truncation needs to be detected only once after the last chained call.
+.IP
+If you're going to use this function in chained calls,
+it would be useful to develop a similar function
+that accepts a pointer to one past the end of the buffer instead of a size.
+.IP
+A simple implementation of
+.BR stpncpy (3)
+might be:
+.IP
+.in +4n
+.EX
+char *
+stpncpy(char *restrict dst, const char *restrict src,
+        size_t sz)
+{
+    char  *p;
+
+    bzero(dst, sz);
+    p = memccpy(dst, src, \(aq\e0\(aq, sz);
+    if (p == NULL)
+        return dst + sz;
+
+    return p \- 1;
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Functions :: ustr2stp(3) ---------------------/
+.TP
+.BR ustr2stp (3)
+This function copies the input unterminated string
+contained in a null-padded wixed-width buffer,
+into a destination (null-terminated) string.
+The programmer is responsible for allocating a buffer large enough.
+It returns a pointer suitable for chaining.
+.IP
+A truncating version of this function doesn't exist,
+since the size of the original string is always known,
+so it wouldn't be very useful.
+.IP
+This function is not provided by any library,
+but you can define it with the following reference implementation:
+.IP
+.in +4n
+.EX
+/* This code is in the public domain. */
+char *
+ustr2stp(char *restrict dst, const char *restrict src,
+         size_t sz)
+{
+    char  *end;
+
+    end = memccpy(dst, src, \(aq\e0\(aq, sz)) ?: dst + sz;
+    *end = \(aq\e0\(aq;
+
+    return end;
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Functions :: mempcpy(3) ----------------------/
+.TP
+.BR mempcpy (3)
+This function copies the input string,
+limited by its length,
+into a destination unterminated string.
+The programmer is responsible for allocating a buffer large enough.
+It returns a pointer suitable for chaining.
+.IP
+A simple implementation of
+.BR mempcpy (3)
+might be:
+.IP
+.in +4n
+.EX
+void *
+mempcpy(void *restrict dst, const void *restrict src,
+        size_t len)
+{
+    return memcpy(dst, src, len) + len;
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Deprecated functions :: ----------------------/
+.SS Deprecated functions
+.\" ----- DESCRIPTION :: Deprecated functions :: strlcpy(3bsd), strlcat(3bsd)
+.TP
+.BR strlcpy (3bsd)
+.TQ
+.BR strlcat (3bsd)
+.IR Deprecated .
+These functions copy the input string into a destination string.
+If the destination buffer,
+limited by its size,
+isn't large enough to hold the copy,
+the resulting string is truncated
+(but it is guaranteed to be null-terminated).
+They return the length of the total string they tried to create.
+These functions force a SIGSEGV on Undefined Behavior.
+.IP
+.BR stpecpyx (3)
+is a better replacement for these functions.
+.\" ----- DESCRIPTION :: Deprecated functions :: strscpy(9) -----------/
+.TP
+.BR strscpy (9)
+.IR Deprecated .
+This function copies the input string into a destination string.
+If the destination buffer,
+limited by its size,
+isn't large enough to hold the copy,
+the resulting string is truncated
+(but it is guaranteed to be null-terminated).
+It returns the length of the destination string, or
+.B \-E2BIG
+on truncation.
+.IP
+.BR stpecpy (3)
+is a better replacement for this function.
+.RE
+.\" ----- DESCRIPTION :: Deprecated functions :: strcpy(3), strcat(3) -/
+.TP
+.BR strcpy (3)
+.TQ
+.BR strcat (3)
+.IR Deprecated .
+These functions copy the input string into a destination string.
+The programmer is responsible for allocating a buffer large enough.
+The return value is useless.
+.IP
+.BR stpcpy (3)
+is a better replacement for these functions.
+.IP
+A simple implementation of
+.BR strcpy (3)
+and
+.BR strcat (3)
+might be:
+.IP
+.in +4n
+.EX
+char *
+strcpy(char *restrict dst, const char *restrict src)
+{
+    stpcpy(dst, src);
+    return dst;
+}
+
+char *
+strcat(char *restrict dst, const char *restrict src)
+{
+    stpcpy(dst + strlen(dst), src);
+    return dst;
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Deprecated functions :: strncpy(3) -----------/
+.TP
+.BR strncpy (3)
+.IR Deprecated .
+.BR strncpy (3)
+is identical to
+.BR stpncpy (3)
+except for the useless return value.
+Due to the return value,
+with this function it's hard to correctly check for truncation.
+.IP
+.BR stpncpy (3)
+is a better replacement for this function.
+.IP
+A simple implementation of
+.BR strncpy (3)
+might be:
+.IP
+.in +4n
+.EX
+char *
+strncpy(char *restrict dst, const char *restrict src,
+        size_t sz)
+{
+    stpncpy(dst, src, sz);
+    return dst;
+}
+.EE
+.in
+.\" ----- DESCRIPTION :: Deprecated functions :: strncat(3) -----------/
+.TP
+.BR strncat (3)
+.IR Deprecated .
+Do not confuse this function with
+.BR strncpy (3);
+they are not related at all.
+.IP
+This function concatenates the input unterminated string
+contained in a null-padded wixed-width buffer,
+into a destination (null-terminated) string.
+The programmer is responsible for allocating a buffer large enough.
+The return value is useless.
+.IP
+.BR ustr2stp (3)
+is a better replacement for this function.
+.IP
+A simple implementation of
+.BR strncat (3)
+might be:
+.IP
+.in +4n
+.EX
+char *
+strncat(char *restrict dst, const char *restrict src,
+        size_t sz)
+{
+    ustr2stp(dst + strlen(dst), src, sz);
+    return dst;
+}
+.EE
+.in
+.\" ----- RETURN VALUE :: ---------------------------------------------/
 .SH RETURN VALUE
-The
-.BR strcpy ()
-function returns a pointer to
-the destination string
-.IR dest .
+The following functions return
+a pointer to the terminating null byte in the destination string.
+.PD 0
+.IP \(bu 3
+.BR stpcpy (3)
+.IP \(bu
+.BR ustr2stp (3)
+.PD
+.PP
+The following functions return
+a pointer to the terminating null byte in the destination string,
+except when truncation occurs;
+if truncation occurs,
+they return a pointer to one past the end of the destination buffer.
+.IP \(bu 3
+.BR stpecpy (3),
+.BR stpecpyx (3)
+.PP
+The following function returns
+a pointer to one after the last character
+in the destination unterminated string;
+if truncation occurs,
+that pointer is equivalent to
+a pointer to one past the end of the destination buffer.
+.IP \(bu 3
+.BR stpncpy (3)
+.PP
+The following function returns
+a pointer to one after the last character
+in the destination unterminated string.
+.IP \(bu 3
+.BR mempcpy (3)
+.\" ----- RETURN VALUE :: Deprecated ----------------------------------/
+.SS Deprecated
+The following functions return
+the length of the total string that they tried to create
+(as if truncation didn't occur).
+.IP \(bu 3
+.BR strlcpy (3bsd),
+.BR strlcat (3bsd)
+.PP
+The following function returns
+the length of the destination string, or
+.B \-E2BIG
+on truncation.
+.IP \(bu 3
+.BR strscpy (9)
+.PP
+The following functions return the
+.I dst
+pointer,
+which is useless.
+.PD 0
+.IP \(bu 3
+.BR strcpy (3),
+.BR strcat (3)
+.IP \(bu
+.BR strncpy (3)
+.IP \(bu
+.BR strncat (3)
+.PD
+.\" ----- ATTRIBUTES :: -----------------------------------------------/
 .SH ATTRIBUTES
 For an explanation of the terms used in this section, see
 .BR attributes (7).
@@ -54,73 +770,234 @@ .SH ATTRIBUTES
 l l l.
 Interface	Attribute	Value
 T{
-.BR strcpy ()
+.BR stpcpy (),
+.BR stpecpy (),
+.BR stpecpyx ()
+.BR strlcpy (),
+.BR strlcat (),
+.BR strscpy (),
+.BR strcpy (),
+.BR strcat (),
+.BR stpncpy (),
+.BR ustr2stp (),
+.BR strncpy (),
+.BR strncat (),
+.BR mempcpy ()
 T}	Thread safety	MT-Safe
 .TE
 .hy
 .ad
 .sp 1
+.\" ----- STANDARDS :: ------------------------------------------------/
 .SH STANDARDS
-POSIX.1-2001, POSIX.1-2008, C89, C99, SVr4, 4.3BSD.
-.SH NOTES
-.SS strlcpy()
-Some systems (the BSDs, Solaris, and others) provide the following function:
+.TP
+.BR stpcpy (3)
+.\" This function was added to POSIX.1-2008.
+.\" Before that, it was not part of
+.\" the C or POSIX.1 standards, nor customary on UNIX systems.
+.\" It first appeared at least as early as 1986,
+.\" in the Lattice C AmigaDOS compiler,
+.\" then in the GNU fileutils and GNU textutils in 1989,
+.\" and in the GNU C library by 1992.
+.\" It is also present on the BSDs.
+.TQ
+.BR stpncpy (3)
+.\" This function was added to POSIX.1-2008.
+.\" Before that, it was a GNU extension.
+.\" It first appeared in glibc 1.07 in 1993.
+POSIX.1-2008.
+.TP
+.BR stpecpy "(3), \c"
+.BR stpecpyx (3)
+.TQ
+.BR ustr2stp (3)
+Not defined by any standards nor libraries.
+.TP
+.BR mempcpy (3)
+This function is a GNU extension.
+.TP
+.BR strlcpy "(3bsd), \c"
+.BR strlcat (3bsd)
+Functions originated in OpenBSD and present in some Unix systems.
+.TP
+.BR strscpy (9)
+Linux kernel internal function.
+.TP
+.BR strcpy "(3), \c"
+.BR strcat (3)
+.TQ
+.BR strncpy (3)
+.TQ
+.BR strncat (3)
+POSIX.1‐2001, POSIX.1‐2008, C89, C99, SVr4, 4.3BSD.
+.\" ----- CAVEATS :: --------------------------------------------------/
+.SH CAVEATS
+Don't mix chain calls to truncating and non-truncating functions.
+It is conceptually wrong
+unless you know that the first part of a copy will always fit.
+Anyway, the performance difference will probably be negligible,
+so it will probably be more clear if you use consistent semantics:
+either truncating or non-truncating.
+Calling a non-truncating function after a truncating one is necessarily wrong.
 .PP
+Some of the functions described here are not provided by any library;
+you should write your own copy if you want to use them.
+See STANDARDS.
+.PP
+The deprecation status of these functions varies from system to system.
+This page declares as deprecated
+those functions that have a better replacement documented in this same page.
+.\" ----- EXAMPLES :: -------------------------------------------------/
+.SH EXAMPLES
+The following are examples of correct use of each of these functions.
+.\" ----- EXAMPLES :: stpcpy(3) ---------------------------------------/
+.TP
+.BR stpcpy (3)
 .in +4n
 .EX
-size_t strlcpy(char *dest, const char *src, size_t size);
+p = buf;
+p = stpcpy(p, "Hello ");
+p = stpcpy(p, "world");
+p = stpcpy(p, "!");
+len = p \- buf;
+puts(buf);
 .EE
 .in
-.PP
-.\" http://static.usenix.org/event/usenix99/full_papers/millert/millert_html/index.html
-.\"     "strlcpy and strlcat - consistent, safe, string copy and concatenation"
-.\"     1999 USENIX Annual Technical Conference
-This function is similar to
-.BR strcpy (),
-but it copies at most
-.I size\-1
-bytes to
-.IR dest ,
-truncating the string as necessary.
-It always adds a terminating null byte.
-This function fixes some of the problems of
-.BR strcpy ()
-but the caller must still handle the possibility of data loss if
-.I size
-is too small.
-The return value of the function is the length of
-.IR src ,
-which allows truncation to be easily detected:
-if the return value is greater than or equal to
-.IR size ,
-truncation occurred.
-If loss of data matters, the caller
-.I must
-either check the arguments before the call,
-or test the function return value.
-.BR strlcpy ()
-is not present in glibc and is not standardized by POSIX,
-.\" https://lwn.net/Articles/506530/
-but is available on Linux via the
-.I libbsd
-library.
-.SH BUGS
-If the destination string of a
-.BR strcpy ()
-is not large enough, then anything might happen.
-Overflowing fixed-length string buffers is a favorite cracker technique
-for taking complete control of the machine.
-Any time a program reads or copies data into a buffer,
-the program first needs to check that there's enough space.
-This may be unnecessary if you can show that overflow is impossible,
-but be careful: programs can get changed over time,
-in ways that may make the impossible possible.
+.\" ----- EXAMPLES :: stpecpy(3), stpecpyx(3) -------------------------/
+.TP
+.BR stpecpy (3)
+.TQ
+.BR stpecpyx (3)
+.in +4n
+.EX
+past_end = buf + sizeof(buf);
+p = buf;
+p = stpecpy(p, past_end, "Hello ");
+p = stpecpy(p, past_end, "world");
+p = stpecpy(p, past_end, "!");
+if (p == past_end) {
+    p\-\-;
+    goto toolong;
+}
+len = p \- buf;
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: stpncpy(3) --------------------------------------/
+.TP
+.BR stpncpy (3)
+.in +4n
+.EX
+past_end = buf + sizeof(buf);
+end = stpncpy(buf, "Hello world!", sizeof(buf));
+if (end == past_end)
+    goto toolong;
+len = end \- buf;
+for (size_t i = 0; i < sizeof(buf); i++)
+    putchar(buf[i]);
+.EE
+.in
+.\" ----- EXAMPLES :: ustr2stp(3) -------------------------------------/
+.TP
+.BR ustr2stp (3)
+.in +4n
+.EX
+p = buf;
+p = ustr2stp(p, "Hello ", 6);
+p = ustr2stp(p, "world", 42);  // Padding null bytes ignored.
+p = ustr2stp(p, "!", 1);
+len = p \- buf;
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: mempcpy(3) --------------------------------------/
+.TP
+.BR mempcpy (3)
+.in +4n
+.EX
+p = buf;
+p = mempcpy(p, "Hello ", 6);
+p = mempcpy(p, "world", 5);
+p = mempcpy(p, "!", 1);
+p = \(aq\e0\(aq;
+len = p \- buf;
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: Deprecated :: -----------------------------------/
+.SS Deprecated
+.\" ----- EXAMPLES :: Deprecated :: strlcpy(3bsd), strlcat(3bsd) ------/
+.TP
+.BR strlcpy (3bsd)
+.TQ
+.BR strlcat (3bsd)
+.in +4n
+.EX
+if (strlcpy(buf, "Hello ", sizeof(buf)) >= sizeof(buf))
+    goto toolong;
+if (strlcat(buf, "world", sizeof(buf)) >= sizeof(buf))
+    goto toolong;
+len = strlcat(buf, "!", sizeof(buf));
+if (len >= sizeof(buf))
+    goto toolong;
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: Deprecated :: strscpy(9) ------------------------/
+.TP
+.BR strscpy (9)
+.in +4n
+.EX
+len = strscpy(buf, "Hello world!", sizeof(buf));
+if (len == \-E2BIG)
+    goto toolong;
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: Deprecated :: strcpy(3), strcat(3) --------------/
+.TP
+.BR strcpy (3)
+.TQ
+.BR strcat (3)
+.in +4n
+.EX
+strcpy(buf, "Hello ");
+strcat(buf, "world");
+strcat(buf, "!");
+len = strlen(buf);
+puts(buf);
+.EE
+.in
+.\" ----- EXAMPLES :: Deprecated :: strncpy(3) ------------------------/
+.TP
+.BR strncpy (3)
+.in +4n
+.EX
+strncpy(buf, "Hello world!", sizeof(buf));
+if (buf + sizeof(buf) \- 1 == \(aq\e0\(aq)
+    goto toolong;
+len = strnlen(buf, sizeof(buf));
+for (size_t i = 0; i < sizeof(buf); i++)
+    putchar(buf[i]);
+.EE
+.in
+.\" ----- EXAMPLES :: Deprecated :: strncat(3) ------------------------/
+.TP
+.BR strncat (3)
+.in +4n
+.EX
+buf[0] = \(aq\e0\(aq;  // There's no 'cpy' function to this 'cat'.
+strncat(buf, "Hello ", 6);
+strncat(buf, "world", 42);  // Padding null bytes ignored.
+strncat(buf, "!", 1);
+len = strlen(buf);
+puts(buf);
+.EE
+.in
+.\" ----- SEE ALSO :: -------------------------------------------------/
 .SH SEE ALSO
-.BR bcopy (3),
-.BR memccpy (3),
+.BR bzero (3)
 .BR memcpy (3),
-.BR memmove (3),
-.BR stpcpy (3),
-.BR strdup (3),
-.BR string (3),
-.BR wcscpy (3)
+.BR memccpy (3),
+.BR mempcpy (3),
+.BR string (3)
-- 
2.38.1


  parent reply	other threads:[~2022-12-12 14:24 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-12-11 23:59 string_copy(7): New manual page documenting string copying functions Alejandro Colomar
2022-12-12  0:17 ` Alejandro Colomar
2022-12-12  0:25 ` Alejandro Colomar
2022-12-12  0:32 ` Alejandro Colomar
2022-12-12 14:24 ` Alejandro Colomar [this message]
2022-12-12 17:33   ` [PATCH 1/3] strcpy.3: Rewrite page to document all string-copying functions Alejandro Colomar
2022-12-12 18:38     ` groff man(7) extensions (was: [PATCH 1/3] strcpy.3: Rewrite page to document all string-copying functions) G. Branden Robinson
2022-12-13 15:45       ` a Q quotation macro for man(7) (was: groff man(7) extensions) G. Branden Robinson
2022-12-12 23:00   ` [PATCH v2 0/3] Rewrite strcpy(3) Alejandro Colomar
2022-12-13 20:56     ` Jakub Wilk
2022-12-13 20:57       ` Alejandro Colomar
2022-12-13 22:05       ` Alejandro Colomar
2022-12-13 22:46         ` Alejandro Colomar
2022-12-14  0:03     ` [PATCH v3 0/1] Rewritten page for string-copying functions Alejandro Colomar
2022-12-14  0:14       ` Alejandro Colomar
2022-12-14  0:16         ` Alejandro Colomar
2022-12-14 16:17       ` [PATCH v4 " Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 0/5] Rewrite pages about " Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 0/5] Rewrite documentation for " Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 1/5] string_copy.7: Add page to document all " Alejandro Colomar
2022-12-20 15:00             ` Stefan Puiu
2022-12-20 15:03               ` Alejandro Colomar
2023-01-20  3:43             ` Eric Biggers
2023-01-20 12:55               ` Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 2/5] stpecpy.3, stpecpyx.3, ustpcpy.3, ustr2stp.3, zustr2stp.3, zustr2ustp.3: Add new links to string_copy(7) Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 3/5] stpcpy.3, strcpy.3, strcat.3: Document in a single page Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 4/5] stpncpy.3, strncpy.3: " Alejandro Colomar
2022-12-19 21:02           ` [PATCH v6 5/5] strncat.3: Rewrite to be consistent with string_copy.7 Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 1/5] string_copy.7: Add page to document all string-copying functions Alejandro Colomar
2022-12-15  0:30           ` Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 2/5] stpecpy.3, stpecpyx.3, ustpcpy.3, ustr2stp.3, zustr2stp.3, zustr2ustp.3: Add new links to string_copy(7) Alejandro Colomar
2022-12-15  0:27           ` Alejandro Colomar
2022-12-16 18:47             ` Stefan Puiu
2022-12-16 19:03               ` Alejandro Colomar
2022-12-16 19:09                 ` Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 3/5] stpcpy.3, strcpy.3, strcat.3: Document in a single page Alejandro Colomar
2022-12-16 14:46           ` Alejandro Colomar
2022-12-16 14:47             ` Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 4/5] stpncpy.3, strncpy.3: " Alejandro Colomar
2022-12-15  0:28           ` Alejandro Colomar
2022-12-15  0:26         ` [PATCH v5 5/5] strncat.3: Rewrite to be consistent with string_copy.7 Alejandro Colomar
2022-12-15  0:29           ` Alejandro Colomar
2022-12-14 16:17       ` [PATCH v4 1/1] strcpy.3: Rewrite page to document all string-copying functions Alejandro Colomar
2022-12-14  0:03     ` [PATCH v3 " Alejandro Colomar
2022-12-14 16:22       ` Douglas McIlroy
2022-12-14 16:36         ` Alejandro Colomar
2022-12-14 17:11           ` Alejandro Colomar
2022-12-14 17:19             ` Alejandro Colomar
2022-12-12 23:00   ` [PATCH v2 1/3] " Alejandro Colomar
2022-12-12 23:00   ` [PATCH v2 2/3] stpcpy.3, stpncpy.3, strcat.3, strncat.3, strncpy.3: Transform the old pages into links to strcpy(3) Alejandro Colomar
2022-12-12 23:00   ` [PATCH v2 3/3] stpecpy.3, stpecpyx.3, strlcat.3, strlcpy.3, strscpy.3: Add new " Alejandro Colomar
2022-12-12 14:24 ` [PATCH 2/3] stpcpy.3, stpncpy.3, strcat.3, strncat.3, strncpy.3: Transform the old pages into " Alejandro Colomar
2022-12-12 14:24 ` [PATCH 3/3] stpecpy.3, stpecpyx.3, strlcat.3, strlcpy.3, strscpy.3: Add new " Alejandro Colomar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221212142418.27615-1-alx@kernel.org \
    --to=alx.manpages@gmail.com \
    --cc=alx@kernel.org \
    --cc=linux-man@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.