- Linux-stable-mirror - lists.linaro.org

by Sasha Levin

Hi folks, We're working on trying to figure out a severe performance regression in the 5.4 and older LTS trees. The regression seems to happen only on physical spinning rust disks, which is why it was probably went unnoticed. The regression seems to be introduced in v4.7 with: 1f60fbe72749 ("ext4: allow readdir()'s of large empty directories to be interrupted") The fio test used to reproduce it is: sync; i=0; while [ $i -lt 4 ]; do ( ( time fio --name=disk-burner --readwrite=write --bs=4096 --invalidate=1 --end_fsync=0 --filesize=800M --runtime=120 --ioengine=libaio --thread --numjobs=20 --iodepth=1 --unlink=1 ) 2>&1 | grep '^real' ); ((i++)); done When run with the offending commit, it'll take 3-4x longer to complete. The regression was fixed upstream somewhere in this merge: e5da4c933c50 ("Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4") but it seems to be a combination of commits that fix it rather than a single one. Now, here's the tricky part... reverting these two commits on top of v4.19.118 "fixes" the issue: 06bd3c36a733 ("ext4: fix data exposure after a crash") 1f60fbe72749 ("ext4: allow readdir()'s of large empty directories to be interrupted") but clearly this is not something we want to do in the stable trees, so we're trying to figure out the proper way to fix this. -- Thanks, Sasha

5 years, 7 months

1
0
0 0

[PATCH v3 07/11] PCI: qcom: add support for defining some PARF params

by Ansuel Smith

Add support for Tx De-Emphasis, Tx Swing and Rx equalization definition needed on some ipq8064 based device (Netgear R7800 for example). This cause a total lock of the system on kernel load. Fixes: 82a823833f4e PCI: qcom: Add Qualcomm PCIe controller driver Signed-off-by: Ansuel Smith <ansuelsmth(a)gmail.com> Cc: stable(a)vger.kernel.org # v4.5+ --- drivers/pci/controller/dwc/pcie-qcom.c | 47 ++++++++++++++++++++++++-- 1 file changed, 45 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index a4fd5baada34..da8058fd1925 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -46,6 +46,9 @@ #define PCIE20_PARF_PHY_CTRL 0x40 #define PCIE20_PARF_PHY_REFCLK 0x4C +#define PHY_REFCLK_SSP_EN BIT(16) +#define PHY_REFCLK_USE_PAD BIT(12) + #define PCIE20_PARF_DBI_BASE_ADDR 0x168 #define PCIE20_PARF_SLV_ADDR_SPACE_SIZE 0x16C #define PCIE20_PARF_MHI_CLOCK_RESET_CTRL 0x174 @@ -77,6 +80,18 @@ #define DBI_RO_WR_EN 1 #define PERST_DELAY_US 1000 +/* PARF registers */ +#define PCIE20_PARF_PCS_DEEMPH 0x34 +#define PCS_DEEMPH_TX_DEEMPH_GEN1(x) ((x) << 16) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x) ((x) << 8) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x) ((x) << 0) + +#define PCIE20_PARF_PCS_SWING 0x38 +#define PCS_SWING_TX_SWING_FULL(x) ((x) << 8) +#define PCS_SWING_TX_SWING_LOW(x) ((x) << 0) + +#define PCIE20_PARF_CONFIG_BITS 0x50 +#define PHY_RX0_EQ(x) ((x) << 24) #define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE 0x358 #define SLV_ADDR_SPACE_SZ 0x10000000 @@ -97,6 +112,12 @@ struct qcom_pcie_resources_2_1_0 { struct reset_control *phy_reset; struct reset_control *ext_reset; struct regulator_bulk_data supplies[QCOM_PCIE_2_1_0_MAX_SUPPLY]; + u32 tx_deemph_gen1; + u32 tx_deemph_gen2_3p5db; + u32 tx_deemph_gen2_6db; + u32 tx_swing_full; + u32 tx_swing_low; + u32 rx0_eq; }; struct qcom_pcie_resources_1_0_0 { @@ -234,8 +255,21 @@ static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; + struct device_node *node = dev->of_node; int ret; + of_property_read_u32(node, "qcom,tx-deemph-gen1", + &res->tx_deemph_gen1); + of_property_read_u32(node, "qcom,tx-deemph-gen2-3p5db", + &res->tx_deemph_gen2_3p5db); + of_property_read_u32(node, "qcom,tx-deemph-gen2-6db", + &res->tx_deemph_gen2_6db); + of_property_read_u32(node, "qcom,tx-swing-full", + &res->tx_swing_full); + of_property_read_u32(node, "qcom,tx-swing-low", + &res->tx_swing_low); + of_property_read_u32(node, "qcom,rx0-eq", &res->rx0_eq); + res->supplies[0].supply = "vdda"; res->supplies[1].supply = "vdda_phy"; res->supplies[2].supply = "vdda_refclk"; @@ -368,9 +402,18 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) /* enable PCIe clocks and resets */ qcom_clear_and_set_dword(pcie->parf + PCIE20_PARF_PHY_CTRL, BIT(0), 0); + writel(PCS_DEEMPH_TX_DEEMPH_GEN1(res->tx_deemph_gen1) | + PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(res->tx_deemph_gen2_3p5db) | + PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(res->tx_deemph_gen2_6db), + pcie->parf + PCIE20_PARF_PCS_DEEMPH); + writel(PCS_SWING_TX_SWING_FULL(res->tx_swing_full) | + PCS_SWING_TX_SWING_LOW(res->tx_swing_low), + pcie->parf + PCIE20_PARF_PCS_SWING); + writel(PHY_RX0_EQ(res->rx0_eq), pcie->parf + PCIE20_PARF_CONFIG_BITS); + /* enable external reference clock */ - qcom_clear_and_set_dword(pcie->parf + PCIE20_PARF_PHY_REFCLK, 0, - BIT(16)); + qcom_clear_and_set_dword(pcie->parf + PCIE20_PARF_PHY_REFCLK, + PHY_REFCLK_USE_PAD, PHY_REFCLK_SSP_EN; ret = reset_control_deassert(res->phy_reset); if (ret) { -- 2.25.1

5 years, 7 months

1
0
0 0

+ epoll-atomically-remove-wait-entry-on-wake-up.patch added to -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: epoll: atomically remove wait entry on wake up has been added to the -mm tree. Its filename is epoll-atomically-remove-wait-entry-on-wake-up.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/epoll-atomically-remove-wait-entry… and later at http://ozlabs.org/~akpm/mmotm/broken-out/epoll-atomically-remove-wait-entry… Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Roman Penyaev <rpenyaev(a)suse.de> Subject: epoll: atomically remove wait entry on wake up This patch does two things: 1. fixes lost wakeup introduced by: 339ddb53d373 ("fs/epoll: remove unnecessary wakeups of nested epoll") 2. improves performance for events delivery. The description of the problem is the following: if N (>1) threads are waiting on ep->wq for new events and M (>1) events come, it is quite likely that >1 wakeups hit the same wait queue entry, because there is quite a big window between __add_wait_queue_exclusive() and the following __remove_wait_queue() calls in ep_poll() function. This can lead to lost wakeups, because thread, which was woken up, can handle not all the events in ->rdllist. (in better words the problem is described here: https://lkml.org/lkml/2019/10/7/905) The idea of the current patch is to use init_wait() instead of init_waitqueue_entry(). Internally init_wait() sets autoremove_wake_function as a callback, which removes the wait entry atomically (under the wq locks) from the list, thus the next coming wakeup hits the next wait entry in the wait queue, thus preventing lost wakeups. Problem is very well reproduced by the epoll60 test case [1]. Wait entry removal on wakeup has also performance benefits, because there is no need to take a ep->lock and remove wait entry from the queue after the successful wakeup. Here is the timing output of the epoll60 test case: With explicit wakeup from ep_scan_ready_list() (the state of the code prior 339ddb53d373): real 0m6.970s user 0m49.786s sys 0m0.113s After this patch: real 0m5.220s user 0m36.879s sys 0m0.019s The other testcase is the stress-epoll [2], where one thread consumes all the events and other threads produce many events: With explicit wakeup from ep_scan_ready_list() (the state of the code prior 339ddb53d373): threads events/ms run-time ms 8 5427 1474 16 6163 2596 32 6824 4689 64 7060 9064 128 6991 18309 After this patch: threads events/ms run-time ms 8 5598 1429 16 7073 2262 32 7502 4265 64 7640 8376 128 7634 16767 (number of "events/ms" represents event bandwidth, thus higher is better; number of "run-time ms" represents overall time spent doing the benchmark, thus lower is better) [1] tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c [2] https://github.com/rouming/test-tools/blob/master/stress-epoll.c Link: http://lkml.kernel.org/r/20200430130326.1368509-2-rpenyaev@suse.de Signed-off-by: Roman Penyaev <rpenyaev(a)suse.de> Cc: Khazhismel Kumykov <khazhy(a)google.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Heiher <r(a)hev.cc> Cc: Jason Baron <jbaron(a)akamai.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/eventpoll.c | 43 ++++++++++++++++++++++++------------------- 1 file changed, 24 insertions(+), 19 deletions(-) --- a/fs/eventpoll.c~epoll-atomically-remove-wait-entry-on-wake-up +++ a/fs/eventpoll.c @@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1867,21 +1866,23 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); - + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); - } - for (;;) { /* * We don't want to sleep if the ep_poll_callback() sends us * a wakeup in between. That's why we set the task state @@ -1911,10 +1912,20 @@ fetch_events: timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: /* * Try to transfer events to user space. In case we get 0 events and @@ -1925,12 +1936,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } _ Patches currently in -mm which might be from rpenyaev(a)suse.de are kselftests-introduce-new-epoll60-testcase-for-catching-lost-wakeups.patch epoll-atomically-remove-wait-entry-on-wake-up.patch

5 years, 7 months

1
0
0 0

[PATCH] efi/tpm: fix section mismatch warning

by Arnd Bergmann

Building with gcc-10 causes a harmless warning about a section mismatch: WARNING: modpost: vmlinux.o(.text.unlikely+0x5e191): Section mismatch in reference from the function tpm2_calc_event_log_size() to the function .init.text:early_memunmap() The function tpm2_calc_event_log_size() references the function __init early_memunmap(). This is often because tpm2_calc_event_log_size lacks a __init annotation or the annotation of early_memunmap is wrong. Add the missing annotation. Fixes: e658c82be556 ("efi/tpm: Only set 'efi_tpm_final_log_size' after successful event log parsing") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- drivers/firmware/efi/tpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 31f9f0e369b9..55b031d2c989 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -16,7 +16,7 @@ int efi_tpm_final_log_size; EXPORT_SYMBOL(efi_tpm_final_log_size); -static int tpm2_calc_event_log_size(void *data, int count, void *size_info) +static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info) { struct tcg_pcr_event2_head *header; int event_size, size = 0; -- 2.26.0

5 years, 7 months

5
7
0 0

✅ PASS: Test report for kernel 5.6.8-346f82c.cki (stable-queue)

by CKI Project

Hello, We ran automated tests on a recent commit from this kernel tree: Kernel repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Commit: 346f82c1415d - bpf: Forbid XADD on spilled pointers for unprivileged users The results of these automated tests are provided below. Overall result: PASSED Merge: OK Compile: OK Tests: OK All kernel binaries, config files, and logs are available for download here: https://cki-artifacts.s3.us-east-2.amazonaws.com/index.html?prefix=dataware… Please reply to this email if you have any questions about the tests that we ran or if you have any suggestions on how to make future tests more effective. ,-. ,-. ( C ) ( K ) Continuous `-',-.`-' Kernel ( I ) Integration `-' ______________________________________________________________________________ Compile testing --------------- We compiled the kernel for 4 architectures: aarch64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg ppc64le: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg s390x: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg x86_64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg Hardware testing ---------------- We booted each kernel and ran the following tests: aarch64: Host 1: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing ✅ stress: stress-ng 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests Host 2: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 ✅ storage: SCSI VPD 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ✅ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer ppc64le: Host 1: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ❌ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer Host 2: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ❌ Storage blktests s390x: Host 1: ✅ Boot test ✅ selinux-policy: serge-testsuite ✅ stress: stress-ng 🚧 ❌ Storage blktests Host 2: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking sctp-auth: sockopts test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ❌ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer x86_64: Host 1: ✅ Boot test ✅ Storage SAN device stress - mpt3sas_gen1 Host 2: ✅ Boot test ✅ Storage SAN device stress - qedf driver Host 3: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ pciutils: sanity smoke test ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 ✅ storage: SCSI VPD 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer Host 4: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing ✅ stress: stress-ng 🚧 ✅ IOMMU boot test 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests Test sources: https://github.com/CKI-project/tests-beaker 💚 Pull requests are welcome for new tests or improvements to existing tests! Aborted tests ------------- Tests that didn't complete running successfully are marked with ⚡⚡⚡. If this was caused by an infrastructure issue, we try to mark that explicitly in the report. Waived tests ------------ If the test run included waived tests, they are marked with 🚧. Such tests are executed but their results are not taken into account. Tests are waived when their results are not reliable enough, e.g. when they're just introduced or are being fixed. Testing timeout --------------- We aim to provide a report within reasonable timeframe. Tests that haven't finished running yet are marked with ⏱.

5 years, 7 months

1
0
0 0

✅ PASS: Test report for kernel 5.6.8-b54f6f4.cki (stable-queue)

by CKI Project

Hello, We ran automated tests on a recent commit from this kernel tree: Kernel repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Commit: b54f6f42cf2e - ASoC: stm32: sai: fix sai probe The results of these automated tests are provided below. Overall result: PASSED Merge: OK Compile: OK Tests: OK All kernel binaries, config files, and logs are available for download here: https://cki-artifacts.s3.us-east-2.amazonaws.com/index.html?prefix=dataware… Please reply to this email if you have any questions about the tests that we ran or if you have any suggestions on how to make future tests more effective. ,-. ,-. ( C ) ( K ) Continuous `-',-.`-' Kernel ( I ) Integration `-' ______________________________________________________________________________ Compile testing --------------- We compiled the kernel for 4 architectures: aarch64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg ppc64le: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg s390x: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg x86_64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg Hardware testing ---------------- We booted each kernel and ran the following tests: aarch64: Host 1: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 ✅ storage: SCSI VPD 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ✅ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer Host 2: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing 🚧 ✅ Storage blktests ppc64le: Host 1: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ❌ Storage blktests Host 2: ⚡ Internal infrastructure issues prevented one or more tests (marked with ⚡⚡⚡) from running on this architecture. This is not the fault of the kernel that was tested. ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ❌ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ⚡⚡⚡ iotop: sanity 🚧 ⚡⚡⚡ storage: dm/common 🚧 ⚡⚡⚡ trace: ftrace/tracer s390x: Host 1: ⚡ Internal infrastructure issues prevented one or more tests (marked with ⚡⚡⚡) from running on this architecture. This is not the fault of the kernel that was tested. ✅ Boot test ⚡⚡⚡ Podman system integration test - as root ⚡⚡⚡ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking sctp-auth: sockopts test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ❌ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ❌ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer Host 2: ⚡ Internal infrastructure issues prevented one or more tests (marked with ⚡⚡⚡) from running on this architecture. This is not the fault of the kernel that was tested. ✅ Boot test ✅ selinux-policy: serge-testsuite ⚡⚡⚡ stress: stress-ng 🚧 ❌ Storage blktests x86_64: Host 1: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing ✅ stress: stress-ng 🚧 ✅ IOMMU boot test 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests Host 2: ✅ Boot test ✅ Storage SAN device stress - mpt3sas_gen1 Host 3: ⚡ Internal infrastructure issues prevented one or more tests (marked with ⚡⚡⚡) from running on this architecture. This is not the fault of the kernel that was tested. ⚡⚡⚡ Boot test ⚡⚡⚡ Podman system integration test - as root ⚡⚡⚡ Podman system integration test - as user ⚡⚡⚡ LTP ⚡⚡⚡ Loopdev Sanity ⚡⚡⚡ Memory function: memfd_create ⚡⚡⚡ AMTU (Abstract Machine Test Utility) ⚡⚡⚡ Networking bridge: sanity ⚡⚡⚡ Ethernet drivers sanity ⚡⚡⚡ Networking MACsec: sanity ⚡⚡⚡ Networking socket: fuzz ⚡⚡⚡ Networking sctp-auth: sockopts test ⚡⚡⚡ Networking: igmp conformance test ⚡⚡⚡ Networking route: pmtu ⚡⚡⚡ Networking route_func - local ⚡⚡⚡ Networking route_func - forward ⚡⚡⚡ Networking TCP: keepalive test ⚡⚡⚡ Networking UDP: socket ⚡⚡⚡ Networking tunnel: geneve basic test ⚡⚡⚡ Networking tunnel: gre basic ⚡⚡⚡ L2TP basic test ⚡⚡⚡ Networking tunnel: vxlan basic ⚡⚡⚡ Networking ipsec: basic netns - transport ⚡⚡⚡ Networking ipsec: basic netns - tunnel ⚡⚡⚡ httpd: mod_ssl smoke sanity ⚡⚡⚡ tuned: tune-processes-through-perf ⚡⚡⚡ pciutils: sanity smoke test ⚡⚡⚡ ALSA PCM loopback test ⚡⚡⚡ ALSA Control (mixer) Userspace Element test ⚡⚡⚡ Usex - version 1.9-29 ⚡⚡⚡ storage: SCSI VPD 🚧 ⚡⚡⚡ CIFS Connectathon 🚧 ⚡⚡⚡ POSIX pjd-fstest suites 🚧 ⚡⚡⚡ jvm - DaCapo Benchmark Suite 🚧 ⚡⚡⚡ jvm - jcstress tests 🚧 ⚡⚡⚡ Memory function: kaslr 🚧 ⚡⚡⚡ LTP: openposix test suite 🚧 ⚡⚡⚡ Networking vnic: ipvlan/basic 🚧 ⚡⚡⚡ audit: audit testsuite test 🚧 ⚡⚡⚡ iotop: sanity 🚧 ⚡⚡⚡ storage: dm/common 🚧 ⚡⚡⚡ trace: ftrace/tracer Host 4: ✅ Boot test ✅ Storage SAN device stress - qedf driver Host 5: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ pciutils: sanity smoke test ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ Usex - version 1.9-29 ✅ storage: SCSI VPD 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm - DaCapo Benchmark Suite 🚧 ✅ jvm - jcstress tests 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ❌ audit: audit testsuite test 🚧 ✅ iotop: sanity 🚧 ✅ storage: dm/common 🚧 ✅ trace: ftrace/tracer Test sources: https://github.com/CKI-project/tests-beaker 💚 Pull requests are welcome for new tests or improvements to existing tests! Aborted tests ------------- Tests that didn't complete running successfully are marked with ⚡⚡⚡. If this was caused by an infrastructure issue, we try to mark that explicitly in the report. Waived tests ------------ If the test run included waived tests, they are marked with 🚧. Such tests are executed but their results are not taken into account. Tests are waived when their results are not reliable enough, e.g. when they're just introduced or are being fixed. Testing timeout --------------- We aim to provide a report within reasonable timeframe. Tests that haven't finished running yet are marked with ⏱.

5 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] bpf, x86_32: Fix clobbering of dst for BPF_JSET" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 50fe7ebb6475711c15b3397467e6424e20026d94 Mon Sep 17 00:00:00 2001 From: Luke Nelson <lukenels(a)cs.washington.edu> Date: Wed, 22 Apr 2020 10:36:30 -0700 Subject: [PATCH] bpf, x86_32: Fix clobbering of dst for BPF_JSET The current JIT clobbers the destination register for BPF_JSET BPF_X and BPF_K by using "and" and "or" instructions. This is fine when the destination register is a temporary loaded from a register stored on the stack but not otherwise. This patch fixes the problem (for both BPF_K and BPF_X) by always loading the destination register into temporaries since BPF_JSET should not modify the destination register. This bug may not be currently triggerable as BPF_REG_AX is the only register not stored on the stack and the verifier uses it in a limited way. Fixes: 03f5781be2c7b ("bpf, x86_32: add eBPF JIT compiler for ia32") Signed-off-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Luke Nelson <luke.r.nels(a)gmail.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Acked-by: Wang YanQing <udknight(a)gmail.com> Link: https://lore.kernel.org/bpf/20200422173630.8351-2-luke.r.nels@gmail.com diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index cc9ad3892ea6..ba7d9ccfc662 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2015,8 +2015,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = sstk ? IA32_ECX : src_lo; u8 sreg_hi = sstk ? IA32_EBX : src_hi; @@ -2028,6 +2028,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } if (sstk) { @@ -2052,8 +2059,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = IA32_ECX; u8 sreg_hi = IA32_EBX; u32 hi; @@ -2066,6 +2073,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } /* mov ecx,imm32 */

5 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From aee194b14dd2b2bde6252b3acf57d36dccfc743a Mon Sep 17 00:00:00 2001 From: Luke Nelson <lukenels(a)cs.washington.edu> Date: Sat, 18 Apr 2020 16:26:53 -0700 Subject: [PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX BPF_B This patch fixes an encoding bug in emit_stx for BPF_B when the source register is BPF_REG_FP. The current implementation for BPF_STX BPF_B in emit_stx saves one REX byte when the operands can be encoded using Mod-R/M alone. The lower 8 bits of registers %rax, %rbx, %rcx, and %rdx can be accessed without using a REX prefix via %al, %bl, %cl, and %dl, respectively. Other registers, (e.g., %rsi, %rdi, %rbp, %rsp) require a REX prefix to use their 8-bit equivalents (%sil, %dil, %bpl, %spl). The current code checks if the source for BPF_STX BPF_B is BPF_REG_1 or BPF_REG_2 (which map to %rdi and %rsi), in which case it emits the required REX prefix. However, it misses the case when the source is BPF_REG_FP (mapped to %rbp). The result is that BPF_STX BPF_B with BPF_REG_FP as the source operand will read from register %ch instead of the correct %bpl. This patch fixes the problem by fixing and refactoring the check on which registers need the extra REX byte. Since no BPF registers map to %rsp, there is no need to handle %spl. Fixes: 622582786c9e0 ("net: filter: x86: internal BPF JIT") Signed-off-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Luke Nelson <luke.r.nels(a)gmail.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Link: https://lore.kernel.org/bpf/20200418232655.23870-1-luke.r.nels@gmail.com diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5ea7c2cf7ab4..42b6709e6dc7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -158,6 +158,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88);

5 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From aee194b14dd2b2bde6252b3acf57d36dccfc743a Mon Sep 17 00:00:00 2001 From: Luke Nelson <lukenels(a)cs.washington.edu> Date: Sat, 18 Apr 2020 16:26:53 -0700 Subject: [PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX BPF_B This patch fixes an encoding bug in emit_stx for BPF_B when the source register is BPF_REG_FP. The current implementation for BPF_STX BPF_B in emit_stx saves one REX byte when the operands can be encoded using Mod-R/M alone. The lower 8 bits of registers %rax, %rbx, %rcx, and %rdx can be accessed without using a REX prefix via %al, %bl, %cl, and %dl, respectively. Other registers, (e.g., %rsi, %rdi, %rbp, %rsp) require a REX prefix to use their 8-bit equivalents (%sil, %dil, %bpl, %spl). The current code checks if the source for BPF_STX BPF_B is BPF_REG_1 or BPF_REG_2 (which map to %rdi and %rsi), in which case it emits the required REX prefix. However, it misses the case when the source is BPF_REG_FP (mapped to %rbp). The result is that BPF_STX BPF_B with BPF_REG_FP as the source operand will read from register %ch instead of the correct %bpl. This patch fixes the problem by fixing and refactoring the check on which registers need the extra REX byte. Since no BPF registers map to %rsp, there is no need to handle %spl. Fixes: 622582786c9e0 ("net: filter: x86: internal BPF JIT") Signed-off-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Luke Nelson <luke.r.nels(a)gmail.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Link: https://lore.kernel.org/bpf/20200418232655.23870-1-luke.r.nels@gmail.com diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5ea7c2cf7ab4..42b6709e6dc7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -158,6 +158,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88);

5 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From aee194b14dd2b2bde6252b3acf57d36dccfc743a Mon Sep 17 00:00:00 2001 From: Luke Nelson <lukenels(a)cs.washington.edu> Date: Sat, 18 Apr 2020 16:26:53 -0700 Subject: [PATCH] bpf, x86: Fix encoding for lower 8-bit registers in BPF_STX BPF_B This patch fixes an encoding bug in emit_stx for BPF_B when the source register is BPF_REG_FP. The current implementation for BPF_STX BPF_B in emit_stx saves one REX byte when the operands can be encoded using Mod-R/M alone. The lower 8 bits of registers %rax, %rbx, %rcx, and %rdx can be accessed without using a REX prefix via %al, %bl, %cl, and %dl, respectively. Other registers, (e.g., %rsi, %rdi, %rbp, %rsp) require a REX prefix to use their 8-bit equivalents (%sil, %dil, %bpl, %spl). The current code checks if the source for BPF_STX BPF_B is BPF_REG_1 or BPF_REG_2 (which map to %rdi and %rsi), in which case it emits the required REX prefix. However, it misses the case when the source is BPF_REG_FP (mapped to %rbp). The result is that BPF_STX BPF_B with BPF_REG_FP as the source operand will read from register %ch instead of the correct %bpl. This patch fixes the problem by fixing and refactoring the check on which registers need the extra REX byte. Since no BPF registers map to %rsp, there is no need to handle %spl. Fixes: 622582786c9e0 ("net: filter: x86: internal BPF JIT") Signed-off-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Luke Nelson <luke.r.nels(a)gmail.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Link: https://lore.kernel.org/bpf/20200418232655.23870-1-luke.r.nels@gmail.com diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5ea7c2cf7ab4..42b6709e6dc7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -158,6 +158,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88);

5 years, 7 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror