- Linux-kselftest-mirror - lists.linaro.org

[RFC net-next 6/6] selftests: drv-net: add test for RSS on flow label

by Jakub Kicinski

Add a simple test for checking that RSS on flow label works, and that its rejected for IPv4 flows. # ./tools/testing/selftests/drivers/net/hw/rss_flow_label.py TAP version 13 1..2 ok 1 rss_flow_label.test_rss_flow_label ok 2 rss_flow_label.test_rss_flow_label_6only # Totals: pass:2 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: sdf(a)fomichev.me CC: linux-kselftest(a)vger.kernel.org --- .../testing/selftests/drivers/net/hw/Makefile | 1 + .../drivers/net/hw/rss_flow_label.py | 151 ++++++++++++++++++ 2 files changed, 152 insertions(+) create mode 100755 tools/testing/selftests/drivers/net/hw/rss_flow_label.py diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index df2c047ffa90..56bf1f1b8377 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -17,6 +17,7 @@ TEST_PROGS = \ loopback.sh \ pp_alloc_fail.py \ rss_ctx.py \ + rss_flow_label.py \ rss_input_xfrm.py \ tso.py \ xsk_reconfig.py \ diff --git a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py new file mode 100755 index 000000000000..e471e13160ae --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py @@ -0,0 +1,151 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Tests for RSS hashing on IPv6 Flow Label. +""" + +import glob +import socket +from lib.py import CmdExitFailure +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_in, \ + ksft_not_in, ksft_raises, KsftSkipEx +from lib.py import bkg, cmd, defer, fd_read_timeout, rand_port +from lib.py import NetDrvEpEnv + + +def _ethtool_get_cfg(cfg, fl_type): + descr = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout + + converter = { + "IP SA": "s", + "IP DA": "d", + "L3 proto": "t", + "L4 bytes 0 & 1 [TCP/UDP src port]": "f", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "n", + "IPv6 Flow Label": "l", + } + + ret = "" + for line in descr.split("\n")[1:-2]: + # if this raises we probably need to add more keys to converter above + ret += converter[line] + return ret + + +def _traffic(cfg, one_sock, one_cpu): + local_port = rand_port(socket.SOCK_DGRAM) + remote_port = rand_port(socket.SOCK_DGRAM) + + sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) + sock.bind(("", local_port)) + sock.connect((cfg.remote_addr_v["6"], 0)) + if one_sock: + send = f"exec 5<>/dev/udp/{cfg.addr_v['6']}/{local_port}; " \ + "for i in `seq 20`; do echo a >&5; sleep 0.02; done; exec 5>&-" + else: + send = "for i in `seq 20`; do echo a | socat -t0.02 - UDP6:" \ + f"[{cfg.addr_v['6']}]:{local_port},sourceport={remote_port}; done" + + cpus = set() + with bkg(send, shell=True, host=cfg.remote, exit_wait=True): + for _ in range(20): + fd_read_timeout(sock.fileno(), 1) + cpu = sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU) + cpus.add(cpu) + + if one_cpu: + ksft_eq(len(cpus), 1, + f"{one_sock=} - expected one CPU, got traffic on: {cpus=}") + else: + ksft_ge(len(cpus), 2, + f"{one_sock=} - expected many CPUs, got traffic on: {cpus=}") + + +def test_rss_flow_label(cfg): + """ + Test hashing on IPv6 flow label. Send traffic over a single socket + and over multiple sockets. Depend on the remote having auto-label + enabled so that it randomizes the label per socket. + """ + + cfg.require_ipver("6") + cfg.require_cmd("socat", remote=True) + if not hasattr(socket, "SO_INCOMING_CPU"): + raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") + + # 1 is the default, if someone changed it we probably shouldn"t mess with it + af = cmd("cat /proc/sys/net/ipv6/auto_flowlabels", host=cfg.remote).stdout + if af.strip() != "1": + raise KsftSkipEx("Remote does not have auto_flowlabels enabled") + + qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) + if qcnt < 2: + raise KsftSkipEx(f"Local has only {qcnt} queues") + + # Enable flow label hashing for UDP6 + initial = _ethtool_get_cfg(cfg, "udp6") + no_lbl = initial.replace("l", "") + if "l" not in initial: + try: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}") + except CmdExitFailure as exc: + raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc + + defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}") + + _traffic(cfg, one_sock=True, one_cpu=True) + _traffic(cfg, one_sock=False, one_cpu=False) + + # Disable it, we should see no hashing (reset was already defer()ed) + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}") + + _traffic(cfg, one_sock=False, one_cpu=True) + + +def _check_v4_flow_types(cfg): + for fl_type in ["tcp4", "udp4", "ah4", "esp4", "sctp4"]: + try: + cur = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout + ksft_not_in("Flow Label", cur, + comment=f"{fl_type=} has Flow Label:" + cur) + except CmdExitFailure: + # Probably does not support this flow type + pass + + +def test_rss_flow_label_6only(cfg): + """ + Test interactions with IPv4 flow types. It should not be possible to set + IPv6 Flow Label hashing for an IPv4 flow type. The Flow Label should also + not appear in the IPv4 "current config". + """ + + with ksft_raises(CmdExitFailure) as cm: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash tcp4 sdfnl") + ksft_in("Invalid argument", cm.exception.cmd.stderr) + + _check_v4_flow_types(cfg) + + # Try to enable Flow Labels and check again, in case it leaks thru + initial = _ethtool_get_cfg(cfg, "udp6") + changed = initial.replace("l", "") if "l" in initial else initial + "l" + + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {changed}") + restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}") + + _check_v4_flow_types(cfg) + restore.exec() + _check_v4_flow_types(cfg) + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + ksft_run([test_rss_flow_label, + test_rss_flow_label_6only], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() -- 2.49.0

5 months, 2 weeks

1
0
0 0

[RFC net-next 5/6] selftests: drv-net: import things in lib one by one

by Jakub Kicinski

pylint doesn't understand our path hacks, and it generates a lot of warnings for driver tests. Import what we use one by one, this is hopefully not too tedious and it makes pylint happy. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: mohan.prasad(a)microchip.com CC: sdf(a)fomichev.me CC: dw(a)davidwei.uk CC: linux-kselftest(a)vger.kernel.org --- .../selftests/drivers/net/hw/lib/py/__init__.py | 17 +++++++++++++++++ .../selftests/drivers/net/lib/py/__init__.py | 14 ++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index b582885786f5..56ff11074b55 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -7,8 +7,25 @@ KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * from drivers.net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ + rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true + from net.lib.py import NetNSEnter + from drivers.net.lib.py import GenerateTraffic + from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index 401e70f7f136..9ed1d8f70524 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -7,7 +7,21 @@ KSFT_DIR = (Path(__file__).parent / "../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ + rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) -- 2.49.0

5 months, 2 weeks

1
0
0 0

[PATCH] selftests: ir_decoder: Convert header comment to proper multi-line block

by Abdelrahman Fekry

The test file for the IR decoder used single-line comments at the top to document its purpose and licensing, which is inconsistent with the style used throughout the Linux kernel. in this patch i converted the file header to a proper multi-line comment block (/*) that aligns with standard kernel practices. This improves readability, consistency across selftests, and ensures the license and documentation are clearly visible in a familiar format. No functional changes have been made. Signed-off-by: Abdelrahman Fekry <Abdelrahmanfekry375(a)gmail.com> --- tools/testing/selftests/ir/ir_loopback.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index f4a15cbdd5ea..2de4a6296f35 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -1,14 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 -// test ir decoder -// -// Copyright (C) 2018 Sean Young <sean(a)mess.org> - -// When sending LIRC_MODE_SCANCODE, the IR will be encoded. rc-loopback -// will send this IR to the receiver side, where we try to read the decoded -// IR. Decoding happens in a separate kernel thread, so we will need to -// wait until that is scheduled, hence we use poll to check for read -// readiness. - +/* Copyright (C) 2018 Sean Young <sean(a)mess.org> + * + * Selftest for IR decoder + * + * + * When sending LIRC_MODE_SCANCODE, the IR will be encoded. rc-loopback + * will send this IR to the receiver side, where we try to read the decoded + * IR. Decoding happens in a separate kernel thread, so we will need to + * wait until that is scheduled, hence we use poll to check for read + * readiness. +*/ #include <linux/lirc.h> #include <errno.h> #include <stdio.h> -- 2.25.1

5 months, 2 weeks

3
3
0 0

[PATCH v6 0/2] x86/fred: Prevent immediate repeat of single step trap on return from SIGTRAP handler

by Xin Li (Intel)

IDT event delivery has a debug hole in which it does not generate #DB upon returning to userspace before the first userspace instruction is executed if the Trap Flag (TF) is set. FRED closes this hole by introducing a software event flag, i.e., bit 17 of the augmented SS: if the bit is set and ERETU would result in RFLAGS.TF = 1, a single-step trap will be pending upon completion of ERETU. However I overlooked properly setting and clearing the bit in different situations. Thus when FRED is enabled, if the Trap Flag (TF) is set without an external debugger attached, it can lead to an infinite loop in the SIGTRAP handler. To avoid this, the software event flag in the augmented SS must be cleared, ensuring that no single-step trap remains pending when ERETU completes. This patch set combines the fix [1] and its corresponding selftest [2] (requested by Dave Hansen) into one patch set. [1] https://lore.kernel.org/lkml/20250523050153.3308237-1-xin@zytor.com/ [2] https://lore.kernel.org/lkml/20250530230707.2528916-1-xin@zytor.com/ This patch set is based on tip/x86/urgent branch. Link to v5 of this patch set: https://lore.kernel.org/lkml/20250606174528.1004756-1-xin@zytor.com/ Changes in v6: *) Replace a "sub $128, %rsp" with "add $-128, %rsp" (hpa). *) Declared loop_count_on_same_ip inside sigtrap() (Sohil). *) s/sigtrap/SIGTRAP (Sohil). *) Add TB from Sohil to the first patch. Xin Li (Intel) (2): x86/fred/signal: Prevent immediate repeat of single step trap on return from SIGTRAP handler selftests/x86: Add a test to detect infinite SIGTRAP handler loop arch/x86/include/asm/sighandling.h | 22 +++++ arch/x86/kernel/signal_32.c | 4 + arch/x86/kernel/signal_64.c | 4 + tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/sigtrap_loop.c | 101 +++++++++++++++++++++ 5 files changed, 132 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/sigtrap_loop.c base-commit: dd2922dcfaa3296846265e113309e5f7f138839f -- 2.49.0

5 months, 2 weeks

2
3
0 0

[PATCH 0/2] kselftest/arm64: Add coverage for the interaction of vfork() and GCS

by Mark Brown

I had cause to look at the vfork() support for GCS and realised that we don't have any direct test coverage, this series does so by adding vfork() to nolibc and then using that in basic-gcs to provide some simple vfork() coverage. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (2): tools/nolibc: Provide vfork() kselftest/arm64: Add a test for vfork() with GCS tools/include/nolibc/sys.h | 29 ++++++++++++ tools/testing/selftests/arm64/gcs/basic-gcs.c | 63 +++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250528-arm64-gcs-vfork-exit-4a7daf7652ee Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 2 weeks

2
7
0 0

[PATCH v2] selftests/bpf: Validate UDP length in cls_redirect test

by Suchit Karunakaran

From: Suchit <suchitkarunakaran(a)gmail.com> Add validation step to ensure that the UDP payload is long enough to contain the expected GUE and UNIGUE encapsulation headers Signed-off-by: Suchit <suchitkarunakaran(a)gmail.com> --- Changes since v2: - Rebase tools/testing/selftests/bpf/progs/test_cls_redirect.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index f344c6835e84..c1d2eaee2e77 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -978,7 +978,14 @@ int cls_redirect(struct __sk_buff *skb) return TC_ACT_OK; } - /* TODO Check UDP length? */ + uint16_t udp_len = bpf_ntohs(encap->udp.len); + uint16_t min_encap_len = sizeof(encap->udp) + sizeof(encap->gue) + sizeof(encap->unigue); + + if (udp_len < min_encap_len) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + if (encap->udp.dest != ENCAPSULATION_PORT) { return TC_ACT_OK; } -- 2.49.0

5 months, 2 weeks

3
2
1 0

[PATCH v5 0/2] x86/fred: Prevent immediate repeat of single step trap on return from SIGTRAP handler

by Xin Li (Intel)

IDT event delivery has a debug hole in which it does not generate #DB upon returning to userspace before the first userspace instruction is executed if the Trap Flag (TF) is set. FRED closes this hole by introducing a software event flag, i.e., bit 17 of the augmented SS: if the bit is set and ERETU would result in RFLAGS.TF = 1, a single-step trap will be pending upon completion of ERETU. However I overlooked properly setting and clearing the bit in different situations. Thus when FRED is enabled, if the Trap Flag (TF) is set without an external debugger attached, it can lead to an infinite loop in the SIGTRAP handler. To avoid this, the software event flag in the augmented SS must be cleared, ensuring that no single-step trap remains pending when ERETU completes. This patch set combines the fix [1] and its corresponding selftest [2] (requested by Dave Hansen) into one patch set. [1] https://lore.kernel.org/lkml/20250523050153.3308237-1-xin@zytor.com/ [2] https://lore.kernel.org/lkml/20250530230707.2528916-1-xin@zytor.com/ This patch set is based on tip/x86/urgent branch as of today. Link to v4 of this patch set: https://lore.kernel.org/lkml/20250605181020.590459-1-xin@zytor.com/ Changes in v5: *) Accurately rephrase the shortlog (hpa). *) Do "sub $-128, %rsp" rather than "add $128, %rsp", which is more efficient in code size (hpa). *) Add TB from Sohil. *) Add Cc: stable(a)vger.kernel.org to all patches. Xin Li (Intel) (2): x86/fred/signal: Prevent immediate repeat of single step trap on return from SIGTRAP handler selftests/x86: Add a test to detect infinite sigtrap handler loop arch/x86/include/asm/sighandling.h | 22 +++++ arch/x86/kernel/signal_32.c | 4 + arch/x86/kernel/signal_64.c | 4 + tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/sigtrap_loop.c | 98 ++++++++++++++++++++++ 5 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/sigtrap_loop.c base-commit: dd2922dcfaa3296846265e113309e5f7f138839f -- 2.49.0

5 months, 2 weeks

3
4
0 0

[PATCH RFC bpf-next 0/4] bpf, arm64: support up to 12 arguments

by Alexis Lothoré (eBPF Foundation)

Hello, this series is a revival of Xu Kuhoai's work to enable larger arguments count for BPF programs on ARM64 ([1]). His initial series received some positive feedback, but lacked some specific case handling around arguments alignment (see AAPCS64 C.14 rule in section 6.8.2, [2]). There as been another attempt from Puranjay Mohan, which was unfortunately missing the same thing ([3]). Since there has been some time between those series and this new one, I chose to send it as a new series rather than a new revision of the existing series. To support the increased argument counts and arguments larger than registers size (eg: structures), the trampoline does the following: - for bpf programs: arguments are retrieved from both registers and the function stack, and pushed in the trampoline stack as an array of u64 to generate the programs context. It is then passed by pointer to the bpf programs - when the trampoline is in charge of calling the original function: it restores the registers content, and generates a new stack layout for the additional arguments that do not fit in registers. This new attempt is based on Xu's series and aims to handle the missing alignment concern raised in the reviews discussions. The main novelties are then around arguments alignments: - the first commit is exposing some new info in the BTF function model passed to the JIT compiler to allow it to deduce the needed alignment when configuring the trampoline stack - the second commit is taken from Xu's series, and received the following modifications: - the calc_aux_args computes an expected alignment for each argument - the calc_aux_args computes two different stack space sizes: the one needed to store the bpf programs context, and the original function stacked arguments (which needs alignment). Those stack sizes are in bytes instead of "slots" - when saving/restoring arguments for bpf program or for the original function, make sure to align the load/store accordingly, when relevant - a few typos fixes and some rewording, raised by the review on the original series - the last commit introduces some explicit tests that ensure that the needed alignment is enforced by the trampoline I marked the series as RFC because it appears that the new tests trigger some failures in CI on x86 and s390, despite the series not touching any code related to those architectures. Some very early investigation/gdb debugging on the x86 side seems to hint that it could be related to the same missing alignment too (based on section 3.2.3 in [4], and so the x86 trampoline would need the same alignment handling ?). For s390 it looks less clear, as all values captured from the bpf test program are set to 0 in the CI output, and I don't have the proper setup yet to check the low level details. I am tempted to isolate those new tests (which were actually useful to spot real issues while tuning the ARM64 trampoline) and add them to the relevant DENYLIST files for x86/s390, but I guess this is not the right direction, so I would gladly take a second opinion on this. [1] https://lore.kernel.org/all/20230917150752.69612-1-xukuohai@huaweicloud.com… [2] https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#id82 [3] https://lore.kernel.org/bpf/20240705125336.46820-1-puranjay@kernel.org/ [4] https://refspecs.linuxbase.org/elf/x86_64-abi-0.99.pdf Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- Alexis Lothoré (eBPF Foundation) (3): bpf: add struct largest member size in func model bpf/selftests: add tests to validate proper arguments alignment on ARM64 bpf/selftests: enable tracing tests for ARM64 Xu Kuohai (1): bpf, arm64: Support up to 12 function arguments arch/arm64/net/bpf_jit_comp.c | 235 ++++++++++++++++----- include/linux/bpf.h | 1 + kernel/bpf/btf.c | 25 +++ tools/testing/selftests/bpf/DENYLIST.aarch64 | 3 - .../selftests/bpf/prog_tests/tracing_struct.c | 23 ++ tools/testing/selftests/bpf/progs/tracing_struct.c | 10 +- .../selftests/bpf/progs/tracing_struct_many_args.c | 67 ++++++ .../testing/selftests/bpf/test_kmods/bpf_testmod.c | 50 +++++ 8 files changed, 357 insertions(+), 57 deletions(-) --- base-commit: 91e7eb701b4bc389e7ddfd80ef6e82d1a6d2d368 change-id: 20250220-many_args_arm64-8bd3747e6948 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

5 months, 2 weeks

8
31
0 0

[PATCH v2 00/15] Consolidate iommu page table implementations (AMD)

by Jason Gunthorpe

Currently each of the iommu page table formats duplicates all of the logic to maintain the page table and perform map/unmap/etc operations. There are several different versions of the algorithms between all the different formats. The io-pgtable system provides an interface to help isolate the page table code from the iommu driver, but doesn't provide tools to implement the common algorithms. This makes it very hard to improve the state of the pagetable code under the iommu domains as any proposed improvement needs to alter a large number of different driver code paths. Combined with a lack of software based testing this makes improvement in this area very hard. iommufd wants several new page table operations: - More efficient map/unmap operations, using iommufd's batching logic - unmap that returns the physical addresses into a batch as it progresses - cut that allows splitting areas so large pages can have holes poked in them dynamically (ie guestmemfd hitless shared/private transitions) - More agressive freeing of table memory to avoid waste - Fragmenting large pages so that dirty tracking can be more granular - Reassembling large pages so that VMs can run at full IO performance in migration/dirty tracking error flows - KHO integration for kernel live upgrade Together these are algorithmically complex enough to be a very significant task to go and implement in all the page table formats we support. Just the "server" focused drivers use almost all the formats (ARMv8 S1&S2 / x86 PAE / AMDv1 / VT-D SS / RISCV) Instead of doing the duplicated work, this series takes the first step to consolidate the algorithms into one places. In spirit it is similar to the work Christoph did a few years back to pull the redundant get_user_pages() implementations out of the arch code into core MM. This unlocked a great deal of improvement in that space in the following years. I would like to see the same benefit in iommu as well. My first RFC showed a bigger picture with all most all formats and more algorithms. This series reorganizes that to be narrowly focused on just enough to convert the AMD driver to use the new mechanism. kunit tests are provided that allow good testing of the algorithms and all formats on x86, nothing is arch specific. AMD is one of the simpler options as the HW is quite uniform with few different options/bugs while still requiring the complicated contiguous pages support. The HW also has a very simple range based invalidation approach that is easy to implement. The AMD v1 and AMD v2 page table formats are implemented bit for bit identical to the current code, tested using a compare kunit test that checks against the io-pgtable version (on github, see below). Updating the AMD driver to replace the io-pgtable layer with the new stuff is fairly straightforward now. The layering is fixed up in the new version so that all the invalidation goes through function pointers. Several small fixing patches have come out of this as I've been fixing the problems that the test suite uncovers in the current code, and implementing the fixed version in iommupt. On performance, there is a quite wide variety of implementation designs across all the drivers. Looking at some key performance across the main formats: iommu_map(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 53,66 , 51,63 , 19.19 (AMDV1) 256*2^12, 386,1909 , 367,1795 , 79.79 256*2^21, 362,1633 , 355,1556 , 77.77 2^12, 56,62 , 52,59 , 11.11 (AMDv2) 256*2^12, 405,1355 , 357,1292 , 72.72 256*2^21, 393,1160 , 358,1114 , 67.67 2^12, 55,65 , 53,62 , 14.14 (VTD second stage) 256*2^12, 391,518 , 332,512 , 35.35 256*2^21, 383,635 , 336,624 , 46.46 2^12, 57,65 , 55,63 , 12.12 (ARM 64 bit) 256*2^12, 380,389 , 361,369 , 2.02 256*2^21, 358,419 , 345,400 , 13.13 iommu_unmap(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 69,88 , 65,85 , 23.23 (AMDv1) 256*2^12, 353,6498 , 331,6029 , 94.94 256*2^21, 373,6014 , 360,5706 , 93.93 2^12, 71,72 , 66,69 , 4.04 (AMDv2) 256*2^12, 228,891 , 206,871 , 76.76 256*2^21, 254,721 , 245,711 , 65.65 2^12, 69,87 , 65,82 , 20.20 (VTD second stage) 256*2^12, 210,321 , 200,315 , 36.36 256*2^21, 255,349 , 238,342 , 30.30 2^12, 72,77 , 68,74 , 8.08 (ARM 64 bit) 256*2^12, 521,357 , 447,346 , -29.29 256*2^21, 489,358 , 433,345 , -25.25 * Above numbers include additional patches to remove the iommu_pgsize() overheads. gcc 13.3.0, i7-12700 This version provides fairly consistent performance across formats. ARM unmap performance is quite different because this version supports contiguous pages and uses a very different algorithm for unmapping. Though why it is so worse compared to AMDv1 I haven't figured out yet. The per-format commits include a more detailed chart. There is a second branch: https://github.com/jgunthorpe/linux/commits/iommu_pt_all Containing supporting work and future steps: - ARM short descriptor (32 bit), ARM long descriptor (64 bit) formats - VT-D second stage format - DART v1 & v2 format - Draft of a iommufd 'cut' operation to break down huge pages - Draft of support for a DMA incoherent HW page table walker - A compare test that checks the iommupt formats against the iopgtable interface, including updating AMD to have a working iopgtable and patches to make VT-D have an iopgtable for testing. - A performance test to micro-benchmark map and unmap against iogptable My strategy is to go one by one for the drivers: - AMD driver conversion - RISCV page table and driver - Intel VT-D driver and VTDSS page table - ARM SMMUv3 And concurrently work on the algorithm side: - debugfs content dump, like VT-D has - Cut support - Increase/Decrease page size support - map/unmap batching - KHO As we make more algorithm improvements the value to convert the drivers increases. This is on github: https://github.com/jgunthorpe/linux/commits/iommu_pt v1: - AMD driver only, many code changes RFC: https://lore.kernel.org/all/0-v1-01fa10580981+1d-iommu_pt_jgg@nvidia.com/ Alejandro Jimenez (1): iommu/amd: Use the generic iommu page table Jason Gunthorpe (14): genpt: Generic Page Table base API genpt: Add Documentation/ files iommupt: Add the basic structure of the iommu implementation iommupt: Add the AMD IOMMU v1 page table format iommupt: Add iova_to_phys op iommupt: Add unmap_pages op iommupt: Add map_pages op iommupt: Add read_and_clear_dirty op iommupt: Add a kunit test for Generic Page Table iommupt: Add a mock pagetable format for iommufd selftest to use iommufd: Change the selftest to use iommupt instead of xarray iommupt: Add the x86 64 bit page table format iommu/amd: Remove AMD io_pgtable support iommupt: Add a kunit test for the IOMMU implementation .clang-format | 1 + Documentation/driver-api/generic_pt.rst | 105 ++ Documentation/driver-api/index.rst | 1 + drivers/iommu/Kconfig | 2 + drivers/iommu/Makefile | 1 + drivers/iommu/amd/Kconfig | 5 +- drivers/iommu/amd/Makefile | 2 +- drivers/iommu/amd/amd_iommu.h | 1 - drivers/iommu/amd/amd_iommu_types.h | 109 +- drivers/iommu/amd/io_pgtable.c | 560 -------- drivers/iommu/amd/io_pgtable_v2.c | 370 ------ drivers/iommu/amd/iommu.c | 493 ++++--- drivers/iommu/generic_pt/.kunitconfig | 13 + drivers/iommu/generic_pt/Kconfig | 72 ++ drivers/iommu/generic_pt/fmt/Makefile | 26 + drivers/iommu/generic_pt/fmt/amdv1.h | 407 ++++++ drivers/iommu/generic_pt/fmt/defs_amdv1.h | 21 + drivers/iommu/generic_pt/fmt/defs_x86_64.h | 21 + drivers/iommu/generic_pt/fmt/iommu_amdv1.c | 15 + drivers/iommu/generic_pt/fmt/iommu_mock.c | 10 + drivers/iommu/generic_pt/fmt/iommu_template.h | 48 + drivers/iommu/generic_pt/fmt/iommu_x86_64.c | 12 + drivers/iommu/generic_pt/fmt/x86_64.h | 241 ++++ drivers/iommu/generic_pt/iommu_pt.h | 1146 +++++++++++++++++ drivers/iommu/generic_pt/kunit_generic_pt.h | 721 +++++++++++ drivers/iommu/generic_pt/kunit_iommu.h | 183 +++ drivers/iommu/generic_pt/kunit_iommu_pt.h | 451 +++++++ drivers/iommu/generic_pt/pt_common.h | 351 +++++ drivers/iommu/generic_pt/pt_defs.h | 312 +++++ drivers/iommu/generic_pt/pt_fmt_defaults.h | 193 +++ drivers/iommu/generic_pt/pt_iter.h | 638 +++++++++ drivers/iommu/generic_pt/pt_log2.h | 130 ++ drivers/iommu/io-pgtable.c | 4 - drivers/iommu/iommufd/Kconfig | 1 + drivers/iommu/iommufd/iommufd_test.h | 11 +- drivers/iommu/iommufd/selftest.c | 439 +++---- include/linux/generic_pt/common.h | 166 +++ include/linux/generic_pt/iommu.h | 264 ++++ include/linux/io-pgtable.h | 2 - tools/testing/selftests/iommu/iommufd.c | 60 +- tools/testing/selftests/iommu/iommufd_utils.h | 12 + 41 files changed, 6046 insertions(+), 1574 deletions(-) create mode 100644 Documentation/driver-api/generic_pt.rst delete mode 100644 drivers/iommu/amd/io_pgtable.c delete mode 100644 drivers/iommu/amd/io_pgtable_v2.c create mode 100644 drivers/iommu/generic_pt/.kunitconfig create mode 100644 drivers/iommu/generic_pt/Kconfig create mode 100644 drivers/iommu/generic_pt/fmt/Makefile create mode 100644 drivers/iommu/generic_pt/fmt/amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_x86_64.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_amdv1.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_mock.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_template.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_x86_64.c create mode 100644 drivers/iommu/generic_pt/fmt/x86_64.h create mode 100644 drivers/iommu/generic_pt/iommu_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_generic_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu_pt.h create mode 100644 drivers/iommu/generic_pt/pt_common.h create mode 100644 drivers/iommu/generic_pt/pt_defs.h create mode 100644 drivers/iommu/generic_pt/pt_fmt_defaults.h create mode 100644 drivers/iommu/generic_pt/pt_iter.h create mode 100644 drivers/iommu/generic_pt/pt_log2.h create mode 100644 include/linux/generic_pt/common.h create mode 100644 include/linux/generic_pt/iommu.h base-commit: db37090502f67e46541e53b91f00bbd565c96bd0 -- 2.43.0

5 months, 2 weeks

8
37
0 0

[PATCH] selftests/mm: Skip failed memfd setups in gup_longterm

by Mark Brown

Unlike the other cases gup_longterm's memfd tests previously skipped the test when failing to set up the file descriptor to test, restore this behaviour. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/mm/gup_longterm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 8a97ac5176a4..29047d2e0c49 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -298,8 +298,11 @@ static void run_with_memfd(test_fn fn, const char *desc) log_test_start("%s ... with memfd", desc); fd = memfd_create("test", 0); - if (fd < 0) + if (fd < 0) { ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); + return; + } fn(fd, pagesize); close(fd); @@ -366,6 +369,8 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc, fd = memfd_create("test", flags); if (fd < 0) { ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); + return; } fn(fd, hugetlbsize); --- base-commit: ec7714e4947909190ffb3041a03311a975350fe0 change-id: 20250603-selftest-mm-gup-longterm-tweaks-e685a8ae9751 Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 2 weeks

4
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror