passt/Makefile

276 lines
9.4 KiB
Makefile
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
#
# PASST - Plug A Simple Socket Transport
# for qemu/UNIX domain socket mode
#
# PASTA - Pack A Subtle Tap Abstraction
# for network namespace/tap device mode
#
# Copyright (c) 2021 Red Hat GmbH
# Author: Stefano Brivio <sbrivio@redhat.com>
RLIMIT_STACK_VAL := $(shell /bin/sh -c 'ulimit -s')
ifeq ($(RLIMIT_STACK_VAL),unlimited)
RLIMIT_STACK_VAL := 1024
endif
# Get 'uname -m'-like architecture description for target
TARGET_ARCH := $(shell $(CC) -dumpmachine | cut -f1 -d- | tr [a-z] [A-Z])
TARGET_ARCH := $(shell echo $(TARGET_ARCH) | sed 's/POWERPC/PPC/')
AUDIT_ARCH := $(shell echo $(TARGET_ARCH) | sed 's/^ARM.*/ARM/')
AUDIT_ARCH := $(shell echo $(AUDIT_ARCH) | sed 's/I[456]86/I386/')
AUDIT_ARCH := $(shell echo $(AUDIT_ARCH) | sed 's/PPC64/PPC/')
AUDIT_ARCH := $(shell echo $(AUDIT_ARCH) | sed 's/PPCLE/PPC64LE/')
CFLAGS += -Wall -Wextra -pedantic -std=c99 -D_XOPEN_SOURCE=700 -D_GNU_SOURCE
CFLAGS += -D_FORTIFY_SOURCE=2 -O2 -pie -fPIE
CFLAGS += -DPAGE_SIZE=$(shell getconf PAGE_SIZE)
CFLAGS += -DNETNS_RUN_DIR=\"/run/netns\"
CFLAGS += -DPASST_AUDIT_ARCH=AUDIT_ARCH_$(AUDIT_ARCH)
CFLAGS += -DRLIMIT_STACK_VAL=$(RLIMIT_STACK_VAL)
CFLAGS += -DARCH=\"$(TARGET_ARCH)\"
# On gcc 11.2, with -O2 and -flto, tcp_hash() and siphash_20b(), if inlined,
# seem to be hitting something similar to:
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78993
# from the pointer arithmetic used from the tcp_tap_handler() path to get the
# remote connection address.
ifeq ($(shell $(CC) -dumpversion),11)
ifneq (,$(filter -flto%,$(CFLAGS)))
ifneq (,$(filter -O2,$(CFLAGS)))
CFLAGS += -DTCP_HASH_NOINLINE
CFLAGS += -DSIPHASH_20B_NOINLINE
endif
endif
endif
C := \#include <linux/tcp.h>\nstruct tcp_info x = { .tcpi_snd_wnd = 0 };
ifeq ($(shell printf "$(C)" | $(CC) -S -xc - -o - >/dev/null 2>&1; echo $$?),0)
CFLAGS += -DHAS_SND_WND
endif
C := \#include <linux/tcp.h>\nstruct tcp_info x = { .tcpi_bytes_acked = 0 };
ifeq ($(shell printf "$(C)" | $(CC) -S -xc - -o - >/dev/null 2>&1; echo $$?),0)
CFLAGS += -DHAS_BYTES_ACKED
endif
C := \#include <linux/tcp.h>\nstruct tcp_info x = { .tcpi_min_rtt = 0 };
ifeq ($(shell printf "$(C)" | $(CC) -S -xc - -o - >/dev/null 2>&1; echo $$?),0)
CFLAGS += -DHAS_MIN_RTT
endif
C := \#include <sys/random.h>\nint main(){int a=getrandom(0, 0, 0);}
ifeq ($(shell printf "$(C)" | $(CC) -S -xc - -o - >/dev/null 2>&1; echo $$?),0)
CFLAGS += -DHAS_GETRANDOM
endif
ifeq ($(shell :|$(CC) -fstack-protector-strong -S -xc - >/dev/null 2>&1; echo $$?),0)
CFLAGS += -fstack-protector-strong
endif
prefix ?= /usr/local
ifeq ($(TARGET_ARCH),X86_64)
all: passt passt.avx2 pasta pasta.avx2 qrap
BIN := passt passt.avx2 pasta pasta.avx2 qrap
else
all: passt pasta qrap
BIN := passt pasta qrap
endif
static: CFLAGS += -static -DGLIBC_NO_STATIC_NSS
static: clean all
seccomp.h: *.c $(filter-out seccomp.h,$(wildcard *.h))
@ EXTRA_SYSCALLS=$(EXTRA_SYSCALLS) ./seccomp.sh
passt: $(filter-out qrap.c,$(wildcard *.c)) \
$(filter-out qrap.h,$(wildcard *.h)) seccomp.h
$(CC) $(CFLAGS) $(filter-out qrap.c,$(wildcard *.c)) -o passt
passt.avx2: CFLAGS += -Ofast -mavx2 -ftree-vectorize -funroll-loops
passt.avx2: $(filter-out qrap.c,$(wildcard *.c)) \
$(filter-out qrap.h,$(wildcard *.h)) seccomp.h
$(CC) $(filter-out -O2,$(CFLAGS)) $(filter-out qrap.c,$(wildcard *.c)) \
-o passt.avx2
passt.avx2: passt
pasta.avx2: passt.avx2
ln -s passt.avx2 pasta.avx2
passt: Add PASTA mode, major rework PASTA (Pack A Subtle Tap Abstraction) provides quasi-native host connectivity to an otherwise disconnected, unprivileged network and user namespace, similarly to slirp4netns. Given that the implementation is largely overlapping with PASST, no separate binary is built: 'pasta' (and 'passt4netns' for clarity) both link to 'passt', and the mode of operation is selected depending on how the binary is invoked. Usage example: $ unshare -rUn # echo $$ 1871759 $ ./pasta 1871759 # From another terminal # udhcpc -i pasta0 2>/dev/null # ping -c1 pasta.pizza PING pasta.pizza (64.190.62.111) 56(84) bytes of data. 64 bytes from 64.190.62.111 (64.190.62.111): icmp_seq=1 ttl=255 time=34.6 ms --- pasta.pizza ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 34.575/34.575/34.575/0.000 ms # ping -c1 spaghetti.pizza PING spaghetti.pizza(2606:4700:3034::6815:147a (2606:4700:3034::6815:147a)) 56 data bytes 64 bytes from 2606:4700:3034::6815:147a (2606:4700:3034::6815:147a): icmp_seq=1 ttl=255 time=29.0 ms --- spaghetti.pizza ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 28.967/28.967/28.967/0.000 ms This entails a major rework, especially with regard to the storage of tracked connections and to the semantics of epoll(7) references. Indexing TCP and UDP bindings merely by socket proved to be inflexible and unsuitable to handle different connection flows: pasta also provides Layer-2 to Layer-2 socket mapping between init and a separate namespace for local connections, using a pair of splice() system calls for TCP, and a recvmmsg()/sendmmsg() pair for UDP local bindings. For instance, building on the previous example: # ip link set dev lo up # iperf3 -s $ iperf3 -c ::1 -Z -w 32M -l 1024k -P2 | tail -n4 [SUM] 0.00-10.00 sec 52.3 GBytes 44.9 Gbits/sec 283 sender [SUM] 0.00-10.43 sec 52.3 GBytes 43.1 Gbits/sec receiver iperf Done. epoll(7) references now include a generic part in order to demultiplex data to the relevant protocol handler, using 24 bits for the socket number, and an opaque portion reserved for usage by the single protocol handlers, in order to track sockets back to corresponding connections and bindings. A number of fixes pertaining to TCP state machine and congestion window handling are also included here. Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-07-17 08:34:53 +02:00
pasta: passt
ln -s passt pasta
ln -s passt.1 pasta.1
passt: Add PASTA mode, major rework PASTA (Pack A Subtle Tap Abstraction) provides quasi-native host connectivity to an otherwise disconnected, unprivileged network and user namespace, similarly to slirp4netns. Given that the implementation is largely overlapping with PASST, no separate binary is built: 'pasta' (and 'passt4netns' for clarity) both link to 'passt', and the mode of operation is selected depending on how the binary is invoked. Usage example: $ unshare -rUn # echo $$ 1871759 $ ./pasta 1871759 # From another terminal # udhcpc -i pasta0 2>/dev/null # ping -c1 pasta.pizza PING pasta.pizza (64.190.62.111) 56(84) bytes of data. 64 bytes from 64.190.62.111 (64.190.62.111): icmp_seq=1 ttl=255 time=34.6 ms --- pasta.pizza ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 34.575/34.575/34.575/0.000 ms # ping -c1 spaghetti.pizza PING spaghetti.pizza(2606:4700:3034::6815:147a (2606:4700:3034::6815:147a)) 56 data bytes 64 bytes from 2606:4700:3034::6815:147a (2606:4700:3034::6815:147a): icmp_seq=1 ttl=255 time=29.0 ms --- spaghetti.pizza ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 28.967/28.967/28.967/0.000 ms This entails a major rework, especially with regard to the storage of tracked connections and to the semantics of epoll(7) references. Indexing TCP and UDP bindings merely by socket proved to be inflexible and unsuitable to handle different connection flows: pasta also provides Layer-2 to Layer-2 socket mapping between init and a separate namespace for local connections, using a pair of splice() system calls for TCP, and a recvmmsg()/sendmmsg() pair for UDP local bindings. For instance, building on the previous example: # ip link set dev lo up # iperf3 -s $ iperf3 -c ::1 -Z -w 32M -l 1024k -P2 | tail -n4 [SUM] 0.00-10.00 sec 52.3 GBytes 44.9 Gbits/sec 283 sender [SUM] 0.00-10.43 sec 52.3 GBytes 43.1 Gbits/sec receiver iperf Done. epoll(7) references now include a generic part in order to demultiplex data to the relevant protocol handler, using 24 bits for the socket number, and an opaque portion reserved for usage by the single protocol handlers, in order to track sockets back to corresponding connections and bindings. A number of fixes pertaining to TCP state machine and congestion window handling are also included here. Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-07-17 08:34:53 +02:00
qrap: qrap.c passt.h
$(CC) $(CFLAGS) \
qrap.c -o qrap
valgrind: EXTRA_SYSCALLS="rt_sigprocmask rt_sigtimedwait rt_sigaction \
getpid gettid kill clock_gettime mmap munmap open \
unlink exit_group gettimeofday"
valgrind: CFLAGS:=-g -O0 $(filter-out -O%,$(CFLAGS))
valgrind: all
.PHONY: clean
clean:
-${RM} passt passt.avx2 *.o seccomp.h qrap pasta pasta.avx2 pasta.1 \
passt.tar passt.tar.gz *.deb *.rpm
install: $(BIN)
mkdir -p $(DESTDIR)$(prefix)/bin $(DESTDIR)$(prefix)/share/man/man1
cp -d $(BIN) $(DESTDIR)$(prefix)/bin
cp -d passt.1 pasta.1 qrap.1 $(DESTDIR)$(prefix)/share/man/man1
uninstall:
-${RM} $(DESTDIR)$(prefix)/bin/passt
-${RM} $(DESTDIR)$(prefix)/bin/passt.avx2
-${RM} $(DESTDIR)$(prefix)/bin/pasta
-${RM} $(DESTDIR)$(prefix)/bin/pasta.avx2
-${RM} $(DESTDIR)$(prefix)/bin/qrap
-${RM} $(DESTDIR)$(prefix)/share/man/man1/passt.1
-${RM} $(DESTDIR)$(prefix)/share/man/man1/pasta.1
-${RM} $(DESTDIR)$(prefix)/share/man/man1/qrap.1
pkgs: static
tar cf passt.tar -P --xform 's//\/usr\/bin\//' $(BIN)
tar rf passt.tar -P --xform 's//\/usr\/share\/man\/man1\//' \
passt.1 pasta.1 qrap.1
gzip passt.tar
EMAIL="sbrivio@redhat.com" fakeroot alien --to-deb \
--description="User-mode networking for VMs and namespaces" \
-k --version=$(shell git rev-parse --short HEAD) \
passt.tar.gz
fakeroot alien --to-rpm --target=$(shell uname -m) \
--description="User-mode networking for VMs and namespaces" \
-k --version=g$(shell git rev-parse --short HEAD) passt.tar.gz
# Checkers currently disabled for clang-tidy:
# - llvmlibc-restrict-system-libc-headers
# TODO: this is Linux-only for the moment, nice to fix eventually
#
# - bugprone-macro-parentheses
# - google-readability-braces-around-statements
# - hicpp-braces-around-statements
# - readability-braces-around-statements
# Debatable whether that improves readability, right now it would look
# like a mess
#
# - readability-magic-numbers
# - cppcoreguidelines-avoid-magic-numbers
# TODO: in most cases they are justified, but probably not everywhere
#
# - clang-analyzer-valist.Uninitialized
# TODO: enable once https://bugs.llvm.org/show_bug.cgi?id=41311 is fixed
#
# - clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling
# Probably not doable to impement this without plain memcpy(), memset()
#
# - cppcoreguidelines-init-variables
# Dubious value, would kill readability
#
# - hicpp-signed-bitwise
# Those are needed for syscalls, epoll_wait flags, etc.
#
# - llvm-include-order
# TODO: not really important, but nice to fix eventually
#
# - readability-isolate-declaration
# Dubious value, would kill readability
#
# - bugprone-narrowing-conversions
# - cppcoreguidelines-narrowing-conversions
# TODO: nice to fix eventually
#
# - cppcoreguidelines-avoid-non-const-global-variables
# TODO: check, fix, and more in general constify wherever possible
#
# - bugprone-suspicious-string-compare
# Return value of memcmp(), not really suspicious
#
# - altera-unroll-loops
# - altera-id-dependent-backward-branch
# TODO: check paths where it might make sense to improve performance
#
# - bugprone-easily-swappable-parameters
# Not much can be done about them other than being careful
#
# - readability-function-cognitive-complexity
# TODO: split reported functions
#
# - altera-struct-pack-align
# "Poor" alignment needed for structs reflecting message formats/headers
#
# - concurrency-mt-unsafe
# TODO: check again if multithreading is implemented
clang-tidy: $(wildcard *.c) $(wildcard *.h)
clang-tidy -checks=*,-modernize-*,\
-clang-analyzer-valist.Uninitialized,\
-cppcoreguidelines-init-variables,\
-bugprone-macro-parentheses,\
-google-readability-braces-around-statements,\
-hicpp-braces-around-statements,\
-readability-braces-around-statements,\
-readability-magic-numbers,\
-llvmlibc-restrict-system-libc-headers,\
-hicpp-signed-bitwise,\
-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,\
-llvm-include-order,\
-cppcoreguidelines-avoid-magic-numbers,\
-readability-isolate-declaration,\
-bugprone-narrowing-conversions,\
-cppcoreguidelines-narrowing-conversions,\
-cppcoreguidelines-avoid-non-const-global-variables,\
-bugprone-suspicious-string-compare,\
-altera-unroll-loops,-altera-id-dependent-backward-branch,\
-bugprone-easily-swappable-parameters,\
-readability-function-cognitive-complexity,\
-altera-struct-pack-align,\
-concurrency-mt-unsafe \
--warnings-as-errors=* $(wildcard *.c) -- $(filter-out -pie,$(CFLAGS))
ifeq ($(shell $(CC) -v 2>&1 | grep -c "gcc version"),1)
TARGET := $(shell ${CC} -v 2>&1 | sed -n 's/Target: \(.*\)/\1/p')
VER := $(shell $(CC) -dumpversion)
EXTRA_INCLUDES := /usr/lib/gcc/$(TARGET)/$(VER)/include
EXTRA_INCLUDES_OPT := -I$(EXTRA_INCLUDES)
else
EXTRA_INCLUDES_OPT :=
endif
cppcheck: $(wildcard *.c) $(wildcard *.h)
cppcheck --std=c99 --error-exitcode=1 --enable=all --force \
--inconclusive --library=posix \
-I/usr/include $(EXTRA_INCLUDES_OPT) \
\
--suppress=syntaxError:/usr/include/stdlib.h \
--suppress=missingIncludeSystem \
--suppress="*:$(EXTRA_INCLUDES)/avx512fintrin.h" \
--suppress="*:$(EXTRA_INCLUDES)/xmmintrin.h" \
--suppress="*:$(EXTRA_INCLUDES)/emmintrin.h" \
--suppress="*:$(EXTRA_INCLUDES)/avxintrin.h" \
--suppress="*:$(EXTRA_INCLUDES)/bmiintrin.h" \
\
--suppress=objectIndex:tcp.c --suppress=objectIndex:udp.c \
--suppress=va_list_usedBeforeStarted:util.c \
--suppress=unusedFunction \
--suppress=knownConditionTrueFalse:conf.c \
--suppress=strtokCalled:conf.c --suppress=strtokCalled:qrap.c \
--suppress=getpwnamCalled:passt.c \
--suppress=localtimeCalled:pcap.c \
--suppress=unusedStructMember:pcap.c \
--suppress=funcArgNamesDifferent:util.h \
\
--suppress=unmatchedSuppression:conf.c \
--suppress=unmatchedSuppression:passt.c \
--suppress=unmatchedSuppression:pcap.c \
--suppress=unmatchedSuppression:qrap.c \
--suppress=unmatchedSuppression:tcp.c \
--suppress=unmatchedSuppression:udp.c \
--suppress=unmatchedSuppression:util.c \
--suppress=unmatchedSuppression:util.h \
$(filter -D%,$(CFLAGS)) \
.