Copy stable/9 to releng/9.3 as part of the 9.3-RELEASE cycle.

Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation

MFC r254610, r254611, r254617, r254620:

Implement atomic_swap() and atomic_testandset().
Implement atomic_cmpset_64() and atomic_swap_64() for i386.

The following revisions were merged at the same time, to avoid build
breakage:
o r256118
o r256119
o r256131

MFC: r241374

Add an unified macro to deny ability from the compiler to reorder
instruction loads/stores at its will.
The macro __compiler_membar() is currently supported for both gcc and
clang, but kernel compilation will fail otherwise.

Reviewed by: bde, kib
Discussed with: dim, theraven

MFC r236456:
Use plain store for atomic_store_rel on x86, instead of implicitly
locked xchg instruction. IA32 memory model guarantees that store has
release semantic, since stores cannot pass loads or stores.

Copy head to stable/9 as part of 9.0-RELEASE release cycle.

Approved by: re (implicit)

Implement atomic_load_acq_64(9) and atomic_store_rel_64(9) for i386. These
functions are implemented with CMPXCHG8B instruction where it is available,
i. e., all Pentium-class and later processors. Note this instruction is
also used for atomic_store_rel_64() because a simple XCHG-like instruction
for 64-bit memory access does not exist, unfortunately. If the processor
lacks the instruction, i. e., 80486-class CPUs, two 32-bit load/store are
performed with interrupt temporarily disabled, assuming it does not support
SMP. Although this assumption may be little naive, it is true in reality.
This implementation is inspired by Linux.

Inform a compiler which asm statements in the x86 implementation of
atomics change eflags.

Reviewed by: jhb
MFC after: 2 weeks

Rename an argument from "exp" to "expect" since the former makes FlexeLint
uneasy, in case anybody think it might be exp(3) in libm.

This also makes it consistent with other archs.

atomic_cmpset_barr_* was added in order to cope with compilers willing to
specify their own version of atomic_cmpset_* which could have been
different than the membar version.

Right now, however, FreeBSD is bound mostly to GCC-like compilers and
it is desired to add new support and compat shim mostly when there is
a real necessity, in order to avoid too much compatibility bloats.

In this optic, bring back atomic_cmpset_{acq, rel}_* to be the same as
atomic_cmpset_* and unwind the atomic_cmpset_barr_* introduction.

Requested by: jhb
Reviewed by: jhb
Tested by: Giovanni Trematerra <giovanni dot trematerra at
gmail dot com>

- All the functions in atomic.h needs to be in "physical" form (like
not defined through macros or similar) in order to be later compiled in
the kernel and offer this way the support for modules (and
compatibility among the UP case and SMP case).
Fix this for the newly introduced atomic_cmpset_barr_* cases by defining
and specifying a template. Note that the new DEFINE_CMPSET_GEN()
template save more typing on amd64 than the current code. [1]
- Fix the style for memory barriers on amd64.

[1] Reported by: Paul B. Mahol <onemda at gmail dot com>

Per their definition, atomic instructions used in conjuction with
memory barriers should also ensure that the compiler doesn't reorder paths
where they are used. GCC, however, does that aggressively, even in
presence of volatile operands. The most reliable way GCC offers for avoid
instructions reordering is clobbering "memory" even if that is
theoretically an heavy-weight operation, flushing the content of all
the registers and forcing reload of them (We could rely, however, on
gcc DTRT by just understanding the purpose as this is a well-known
pattern for many modern operating-systems).

Not all our memory barriers, right now, clobber memory for GCC-like
compilers. The most notable cases are IA32 and amd64 where the memory
barrier are treacted the same as normal atomic instructions.
Fix this by offering the possibility to implement atomic instructions
with memory barriers separately from the normal version and implement
the GCC-like specific one using memory clobbering.
Thanks to Chris Lattner (@apple) for his discussion on llvm specifics.

Reported by: jhb
Reviewed by: jhb
Tested by: rdivacky, Giovanni Trematerra
<giovanni dot trematerra at gmail dot com>

Restore memory clobber, to cause mb on the compiler level too.
Use more sane formatting of the assembler.

Pointed out by: bde

Unconditionally use locked addition of zero to tip of the stack for
memory barriers on i386. It works as a serialization instruction on
all IA32 CPUs.

Alternative solution of using {s,l,}fence requires run-time checking
of the presense of the corresponding SSE or SSE2 extensions, and
possible boot-time patching of the kernel text.

Suggested by: many

- bump __FreeBSD version to reflect added buf_ring, memory barriers,
and ifnet functions

- add memory barriers to <machine/atomic.h>
- update drivers to only conditionally define their own

- add lockless producer / consumer ring buffer
- remove ring buffer implementation from cxgb and update its callers

- add if_transmit(struct ifnet *ifp, struct mbuf *m) to ifnet to
allow drivers to efficiently manage multiple hardware queues
(i.e. not serialize all packets through one ifq)
- expose if_qflush to allow drivers to flush any driver managed queues

This work was supported by Bitgravity Inc. and Chelsio Inc.

Implement atomic_fetchadd_long() for all architectures and document it.

Reviewed by: attilio, jhb, jeff, kris (as a part of the uidinfo_waitfree.patch)

Fix oops in previous commit.

Fixed some style bugs (mainly assorted errors in comments, and inconsistent
spelling of `result').

Fixed some style bugs (whitespace only).

Try harder to garbage-collect the "LOCORE" (really asm) version of
MPLOCKED. The cleaning in rev.1.25 was supposed to have been undone
by rev.1.26, but 1.26 could never have actually affected asm files
since atomic.h is full of C declarations so including it in asm files
would just give syntax errors. The asm MPLOCKED is even less needed
than when misplaced definitions of it were first removed, and is now
unused in any asm file in the src tree except in anachronismns in
sys/i386/i386/support.s.

Avoid an instruction in atomic_cmpset_{int_long)() in most cases.
These functions are used a lot for mutexes, so this reduces the text
size of an average kernel by about 0.75%. This wasn't intended to
be a significant optimization, but it somehow increased the maximum
number of packets per second that can be transmitted by my bge hardware
from 320000 to 460000 (this benchmark is CPU-bound and remarkably
sensitive to changes in the text section).

Details: we would prefer to leave the result of the cmpxchg in %al,
but cannot tell gcc that it is there, so we have to convert it to an
integer register. We converted to %al, then to %[re]ax, but the
latter step is usually wasted since gcc usually only wants the condition
code and can recover it from %al just as easily as from %[re]ax. Let
gcc promote %al in the few cases where this is needed.

Nearby style fixes;
- let gcc manage the load of `res', and don't abuse `res' for a copy of `exp'
- don't echo `res's name in comments
- consistently spell the condition code as 'e' after comparison for equality
- don't hard-code %al anywhere except in constraints
- for the version that doesn't use cmpxchg, there is no requirement to use
%al anywhere, so don't hard-code it in the constraints either.

Style non-fix:
- for the versions that use cmpxchg, keep using "a" (was %[re]ax, now %al)
for the main output operand, although this is not required. The input
and output operands that use the "a" constraint are now decoupled, and
this makes things clearer except for the reason that the output register
is hard-coded. It is now just a hack to tell gcc that the input "a" has
been clobbered without increasing the number of operands.

Use wrapper macros for atomic pointer operations in order to perform the
correct casts. This should probably be merged to other architectures.

Add a new atomic_fetchadd() primitive that atomically adds a value to a
variable and returns the previous value of the variable.

Tested on: i386, alpha, sparc64, arm (cognet)
Reviewed by: arch@
Submitted by: cognet (arm)
MFC after: 1 week

Stop using the '+' constraint modifier with inline assembly. The '+'
constraint is actually only allowed for register operands. Instead, use
separate input and output memory constraints.

Education from: alc
Reviewed by: alc
Tested on: i386, alpha
MFC after: 1 week

Convert the atomic_ptr() operations over to operating on uintptr_t
variables rather than void * variables. This makes it easier and simpler
to get asm constraints and volatile keywords correct.

MFC after: 3 days
Tested on: i386, alpha, sparc64
Compiled on: ia64, powerpc, amd64
Kernel toolchain busted on: arm

Some cleanups and tweaks to some of the atomic.h files in preparation for
further changes and fixes in the future:
- Use aliases via macros rather than duplicated inlines wherever possible.
- Move all the aliases to the bottom of these files and the inline
functions to the top.
- Add various comments.
- On alpha, drop atomic_{load_acq,store_rel}_{8,char,16,short}().
- On i386 and amd64, don't duplicate the extern declarations for functions
in the two non-inline cases (KLD_MODULE and compiler doesn't do inlines),
instead, consolidate those two cases.
- Some whitespace fixes.

Approved by: re (scottl)

netchild's mega-patch to isolate compiler dependencies into a central
place.

This moves the dependency on GCC's and other compiler's features into
the central sys/cdefs.h file, while the individual source files can
then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to
refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42.

By now, GCC and ICC (the Intel compiler) have been actively tested on
IA32 platforms by netchild. Extension to other compilers is supposed
to be possible, of course.

Submitted by: netchild
Reviewed by: various developers on arch@, some time ago

Initiate deorbit burn sequence for 80386 support in FreeBSD: Remove
80386 (I386_CPU) support from the kernel.

Spell _KERNEL correctly so that UP kernels are actually optimized again.

Submitted by: pjd

- Use the SMP style ops for atomic_load/store() in userland so that
libraries and binaries will work on both UP and SMP machines.
- Remove unnecessary gcc memory barrier from the UP atomic_store() op.

Submitted by: bde

- Place the gcc memory barrier hint in the right place in the 80386 version
of atomic_store_rel().
- Use the 80386 versions of atomic_load_acq() and atomic_store_rel() that
do not use serializing instructions on all UP kernels since a UP machine
does need to synchronize with other CPUs. This trims lots of cycles from
spin locks on UP kernels among other things.

Benchmarked by: rwatson

These are changes to allow to use the Intel C/C++ compiler (lang/icc)
to build the kernel. It doesn't affect the operation if gcc.

Most of the changes are just adding __INTEL_COMPILER to #ifdef's, as
icc v8 may define __GNUC__ some parts may look strange but are
necessary.

Additional changes:
- in_cksum.[ch]:
* use a generic C version instead of the assembly version in the !gcc
case (ASM code breaks with the optimizations icc does)
-> no bad checksums with an icc compiled kernel
Help from: andre, grehan, das
Stolen from: alpha version via ppc version
The entire checksum code should IMHO be replaced with the DragonFly
version (because it isn't guaranteed future revisions of gcc will
include similar optimizations) as in:
---snip---
Revision Changes Path
1.12 +1 -0 src/sys/conf/files.i386
1.4 +142 -558 src/sys/i386/i386/in_cksum.c
1.5 +33 -69 src/sys/i386/include/in_cksum.h
1.5 +2 -0 src/sys/netinet/igmp.c
1.6 +0 -1 src/sys/netinet/in.h
1.6 +2 -0 src/sys/netinet/ip_icmp.c

1.4 +3 -4 src/contrib/ipfilter/ip_compat.h
1.3 +1 -2 src/sbin/natd/icmp.c
1.4 +0 -1 src/sbin/natd/natd.c
1.48 +1 -0 src/sys/conf/files
1.2 +0 -1 src/sys/conf/files.amd64
1.13 +0 -1 src/sys/conf/files.i386
1.5 +0 -1 src/sys/conf/files.pc98
1.7 +1 -1 src/sys/contrib/ipfilter/netinet/fil.c
1.10 +2 -3 src/sys/contrib/ipfilter/netinet/ip_compat.h
1.10 +1 -1 src/sys/contrib/ipfilter/netinet/ip_fil.c
1.7 +1 -1 src/sys/dev/netif/txp/if_txp.c
1.7 +1 -1 src/sys/net/ip_mroute/ip_mroute.c
1.7 +1 -2 src/sys/net/ipfw/ip_fw2.c
1.6 +1 -2 src/sys/netinet/igmp.c
1.4 +158 -116 src/sys/netinet/in_cksum.c
1.6 +1 -1 src/sys/netinet/ip_gre.c
1.7 +1 -2 src/sys/netinet/ip_icmp.c
1.10 +1 -1 src/sys/netinet/ip_input.c
1.10 +1 -2 src/sys/netinet/ip_output.c
1.13 +1 -2 src/sys/netinet/tcp_input.c
1.9 +1 -2 src/sys/netinet/tcp_output.c
1.10 +1 -1 src/sys/netinet/tcp_subr.c
1.10 +1 -1 src/sys/netinet/tcp_syncache.c
1.9 +1 -2 src/sys/netinet/udp_usrreq.c

1.5 +1 -2 src/sys/netinet6/ipsec.c
1.5 +1 -2 src/sys/netproto/ipsec/ipsec.c
1.5 +1 -1 src/sys/netproto/ipsec/ipsec_input.c
1.4 +1 -2 src/sys/netproto/ipsec/ipsec_output.c

and finally remove
sys/i386/i386 in_cksum.c
sys/i386/include in_cksum.h
---snip---
- endian.h:
* DTRT in C++ mode
- quad.h:
* we don't use gcc v1 anymore, remove support for it
Suggested by: bde (long ago)
- assym.h:
* avoid zero-length arrays (remove dependency on a gcc specific
feature)
This change changes the contents of the object file, but as it's
only used to generate some values for a header, and the generator
knows how to handle this, there's no impact in the gcc case.
Explained by: bde
Submitted by: Marius Strobl <marius@alchemy.franken.de>
- aicasm.c:
* minor change to teach it about the way icc spells "-nostdinc"
Not approved by: gibbs (no reply to my mail)
- bump __FreeBSD_version (lang/icc needs to know about the changes)

Incarnations of this patch survive gcc compiles since a loooong time,
I use it on my desktop. An icc compiled kernel works since Nov. 2003
(exceptions: snd_* if used as modules), it survives a build of the
entire ports collection with icc.

Parts of this commit contains suggestions or submissions from
Marius Strobl <marius@alchemy.franken.de>.

Reviewed by: -arch
Submitted by: netchild

Fixed pedantic syntax errors. Many macros didn't permit a semicolon after
their invocation in the !KLD_MODULE case, but a semicolon is provided after
all invocations and is required in the KLD_MODULE case.

Avoid a warning for compiling with `gcc -Wbad-function cast'. (This
is the warning that points to the bug in `(char *)malloc(...)' where
malloc() is implicitly declared as returning int. We do similar things
here, but they work because u_int is the same as uintptr_t on i386's.)

Add a knob to turn on and off the CMPXCHG instruction on > i386 IA32 systems.
This is most beneficial for vmware client os installs.

Reviewed by: jmallet, iedowse, tlambert2@mindspring.com
MFC After: never, -STABLE does not currently use this instruction

Beautify. This has the side effect of improving portability and
making lint work cleaner.

Inspired to do this by: jhb

Clean up the syntax WRT semicolons at the end of function-like-macros, and protect GCCisms from non-GNU compilers and lint.

Make MPLOCKED work again in asm files and stringify it explicitly
where necessary.

Reviewed by: jake

Garbage-collect the "LOCORE" version of MPLOCKED.

Allow the ATOMIC_ASM() macro to pass in the constraints on the V parameter
since the char versions need to use either ax, bx, cx, or dx.

Submitted by: Peter Jeremy (mostly)
Recommended by: bde

Use newer constraints for atomic_cmpset().

Requested by: bde

Use newer constraints for inline assembly for an operand that is both an
input and an output by using the '+' modifier rather than listing the
operand in both the input and output sections.

Reviwed by: bde

Allow atomic ops to be somewhat safely used in userland. We always use
lock prefixes in the userland case so that the binaries will work on both
SMP and UP systems.

RIP <machine/lock.h>.

Some things needed bits of <i386/include/lock.h> - cy.c now has its
own (only) copy of the COM_(UN)LOCK() macros, and IMASK_(UN)LOCK()
has been moved to <i386/include/apic.h> (AKA <machine/apic.h>).
Reviewed by: jhb

- Sort of lie and say that %eax is an output only and not an input for the
non-386 atomic_load_acq(). %eax is an input since its value is used in
the cmpxchg instruction, but we don't care what value it is, so setting
it to a specific value is just wasteful. Thus, it is being used without
being initialized as the warning stated, but it is ok for it to be used
because its value isn't important. Thus, we are only sort of lying when
we say it is an output only operand.
- Add "cc" to the clobber list for atomic_load_acq() since the cmpxchgl
changes ZF.

- Fix atomic_load_* and atomic_store_* to generate functions for atomic.c
that modules can call.
- Remove the old gcc <= 2.8 versions of the atomic ops.
- Resort the order of some things in the file so that there is only
one #ifdef for KLD_MODULE, and so that all WANT_FUNCTIONS stuff is
moved to the bottom of the file.
- Remove ATOMIC_ACQ_REL() and just use explicit macros instead.

Fix the atomic_load_acq() and atomic_store_rel() functions to properly
implement memory fences for the 486+. The 386 still uses versions w/o
memory fences as all operations on the 386 are not program ordered.
The 386 versions are not MP safe.

The x86 atomic operations are already locked, so they do not need an
additional locked instruction to guarantee a write barrier for the acquire
variants.

Approved by: dfr
Pointy hat to: jhb

- Add atomic_cmpset_{acq_,rel_,}_long
- Add in atomic operations for 8-bit, 16-bit, and 32-bit integers

- Expand the set of atomic operations to optionally include memory barriers
in most of the atomic operations. Now for these operations, you can
use the normal atomic operation, you can use the operation with a read
barrier, or you can use the operation with a write barrier. The function
names follow the same semantics used in the ia64 instruction set. An
atomic operation with a read barrier has the extra suffix 'acq', due to
it having "acquire" semantics. An atomic operation with a write barrier
has the extra suffix 'rel'. These suffixes are inserted between the
name of the operation to perform and the typename. For example, the
atomic_add_int() function now has 3 variants:
- atomic_add_int() - this is the same as the previous function
- atomic_add_acq_int() - this function combines the add operation with a
read memory barrier
- atomic_add_rel_int() - this function combines the add operation with a
write memory barrier
- Add 'ptr' to the list of types that we can perform atomic operations
on. This allows one to do atomic operations on uintptr_t's. This is
useful in the mutex code, for example, because the actual mutex lock is
a pointer.
- Add two new operations for doing loads and stores with memory barriers.
The new load operations use a read barrier before the load, and the
new store operations use a write barrier after the load. For example,
atomic_load_acq_int() will atomically load an integer as well as
enforcing a read barrier.

Add atomic_readandclear_int and atomic_readandclear_long.

Introduce atomic_cmpset_int() and atomic_cmpset_long() from SMPng a
few hours earlier than the rest.

The next DEVFS commit needs these functions.

Alpha versions by: dfr
i386 versions by: jakeb

Approved by: SMPng

Note the syntax for specifying an operand's size is documented in
src/contrib/gcc/config/i386/i386.md.

When using _asm{} in GCC, one must specify the operand's size if one
specifies the instruction's operation size. GCC will default to 32-bit
operands reguardless of the prototype (ie, formal parameters' type)
of an inline function.

Use the rev 1.1.2.1 code from RELENG_3 for atomic operations rather
than the non-atomic C macros.

Typo: s/__GNUC_MINOR_/__GNUC_MINOR__/
(__GNUC_MINOR__ on egcs in -current is "91" and is going to be "95" soon)

Allow compilation with older versions of GCC, in order to make it possible
to bootstrap and work with -current from older versions of FreeBSD.

$Id$ -> $FreeBSD$

Create callable (non-inline) versions of the atomic_OP_TYPE functions
that are linked into the kernel. The KLD compilation options are
changed to call these functions, rather than in-lining the
atomic operations.

This approach makes atomic operations from KLDs significantly
faster on UP systems (though somewhat slower on SMP systems).

PR: i386/13111
Submitted by: peter.jeremy@alcatel.com.au

atomic.h:
Change "void *" to "volatile TYPE *", improving type safety
and eliminating some warnings (e.g., mp_machdep.c rev 1.106).

cpufunc.h:
Eliminate setbits. As defined, it's not precisely correct;
and it's redundant. (Use atomic_set_int instead.)

ipl_funcs.c:
Use atomic_set_int instead of setbits.

systm.h:
Include atomic.h.

Reviewed by: bde

Commit the correct patch, i.e., the one that actually corresponds
to the rev 1.2 log entry.

Changed the implementation of the primitives to guarantee atomicity
with respect to interrupts on UP systems. (The upgrade from gcc 2.7.x
to egcs 1.1.2 produced at least one non-atomic code sequence in
swap_pager_getpages.)

In addition, the primitives are now SMP-safe, but only on SMPs. (For
portability between SMPs and UPs, modules are compiled with the SMP-safe
versions.)

Submitted by: dillon and myself
Reviewed by: bde

Change various syscalls to use size_t arguments instead of u_int.

Add some overflow checks to read/write (from bde).

Change all modifications to vm_page::flags, vm_page::busy, vm_object::flags
and vm_object::paging_in_progress to use operations which are not
interruptable.

Reviewed by: Bruce Evans <bde@zeta.org.au>