May 2020 - Linux-stable-mirror

Re: [PATCH] kretprobe: Prevent triggering kretprobe from within kprobe_flush_task

by Masami Hiramatsu

On Wed, 15 Apr 2020 11:05:07 +0200 Jiri Olsa <jolsa(a)redhat.com> wrote: > Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave. > My test was also able to trigger lockdep output: > > ============================================ > WARNING: possible recursive locking detected > 5.6.0-rc6+ #6 Not tainted > -------------------------------------------- > sched-messaging/2767 is trying to acquire lock: > ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0 > > but task is already holding lock: > ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(&(kretprobe_table_locks[i].lock)); > lock(&(kretprobe_table_locks[i].lock)); > > *** DEADLOCK *** > > May be due to missing lock nesting notation > > 1 lock held by sched-messaging/2767: > #0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 > > stack backtrace: > CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6 > Call Trace: > dump_stack+0x96/0xe0 > __lock_acquire.cold.57+0x173/0x2b7 > ? native_queued_spin_lock_slowpath+0x42b/0x9e0 > ? lockdep_hardirqs_on+0x590/0x590 > ? __lock_acquire+0xf63/0x4030 > lock_acquire+0x15a/0x3d0 > ? kretprobe_hash_lock+0x52/0xa0 > _raw_spin_lock_irqsave+0x36/0x70 > ? kretprobe_hash_lock+0x52/0xa0 > kretprobe_hash_lock+0x52/0xa0 > trampoline_handler+0xf8/0x940 > ? kprobe_fault_handler+0x380/0x380 > ? find_held_lock+0x3a/0x1c0 > kretprobe_trampoline+0x25/0x50 > ? lock_acquired+0x392/0xbc0 > ? _raw_spin_lock_irqsave+0x50/0x70 > ? __get_valid_kprobe+0x1f0/0x1f0 > ? _raw_spin_unlock_irqrestore+0x3b/0x40 > ? finish_task_switch+0x4b9/0x6d0 > ? __switch_to_asm+0x34/0x70 > ? __switch_to_asm+0x40/0x70 > > The code within the kretprobe handler checks for probe reentrancy, > so we won't trigger any _raw_spin_lock_irqsave probe in there. > > The problem is in outside kprobe_flush_task, where we call: > > kprobe_flush_task > kretprobe_table_lock > raw_spin_lock_irqsave > _raw_spin_lock_irqsave > > where _raw_spin_lock_irqsave triggers the kretprobe and installs > kretprobe_trampoline handler on _raw_spin_lock_irqsave return. > > The kretprobe_trampoline handler is then executed with already > locked kretprobe_table_locks, and first thing it does is to > lock kretprobe_table_locks ;-) the whole lockup path like: > > kprobe_flush_task > kretprobe_table_lock > raw_spin_lock_irqsave > _raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed > > ---> kretprobe_table_locks locked > > kretprobe_trampoline > trampoline_handler > kretprobe_hash_lock(current, &head, &flags); <--- deadlock > > Adding kprobe_busy_begin/end helpers that mark code with fake > probe installed to prevent triggering of another kprobe within > this code. > > Using these helpers in kprobe_flush_task, so the probe recursion > protection check is hit and the probe is never set to prevent > above lockup. > > Reported-by: "Ziqian SUN (Zamir)" <zsun(a)redhat.com> > Signed-off-by: Jiri Olsa <jolsa(a)kernel.org> Thanks Jiri and Ziqian! Looks good to me. Acked-by: Masami Hiramatsu <mhiramat(a)kernel.org> BTW, this is a kind of bugfix. So should it add a Fixes tag? Fixes: ef53d9c5e4da ('kprobes: improve kretprobe scalability with hashed locking') Cc: stable(a)vger.kernel.org Thank you, > --- > arch/x86/kernel/kprobes/core.c | 16 +++------------- > include/linux/kprobes.h | 4 ++++ > kernel/kprobes.c | 24 ++++++++++++++++++++++++ > 3 files changed, 31 insertions(+), 13 deletions(-) > > diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c > index 4d7022a740ab..a12adbe1559d 100644 > --- a/arch/x86/kernel/kprobes/core.c > +++ b/arch/x86/kernel/kprobes/core.c > @@ -753,16 +753,11 @@ asm( > NOKPROBE_SYMBOL(kretprobe_trampoline); > STACK_FRAME_NON_STANDARD(kretprobe_trampoline); > > -static struct kprobe kretprobe_kprobe = { > - .addr = (void *)kretprobe_trampoline, > -}; > - > /* > * Called from kretprobe_trampoline > */ > __used __visible void *trampoline_handler(struct pt_regs *regs) > { > - struct kprobe_ctlblk *kcb; > struct kretprobe_instance *ri = NULL; > struct hlist_head *head, empty_rp; > struct hlist_node *tmp; > @@ -772,16 +767,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) > void *frame_pointer; > bool skipped = false; > > - preempt_disable(); > - > /* > * Set a dummy kprobe for avoiding kretprobe recursion. > * Since kretprobe never run in kprobe handler, kprobe must not > * be running at this point. > */ > - kcb = get_kprobe_ctlblk(); > - __this_cpu_write(current_kprobe, &kretprobe_kprobe); > - kcb->kprobe_status = KPROBE_HIT_ACTIVE; > + kprobe_busy_begin(); > > INIT_HLIST_HEAD(&empty_rp); > kretprobe_hash_lock(current, &head, &flags); > @@ -857,7 +848,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) > __this_cpu_write(current_kprobe, &ri->rp->kp); > ri->ret_addr = correct_ret_addr; > ri->rp->handler(ri, regs); > - __this_cpu_write(current_kprobe, &kretprobe_kprobe); > + __this_cpu_write(current_kprobe, &kprobe_busy); > } > > recycle_rp_inst(ri, &empty_rp); > @@ -873,8 +864,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) > > kretprobe_hash_unlock(current, &flags); > > - __this_cpu_write(current_kprobe, NULL); > - preempt_enable(); > + kprobe_busy_end(); > > hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { > hlist_del(&ri->hlist); > diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h > index 04bdaf01112c..645fd401c856 100644 > --- a/include/linux/kprobes.h > +++ b/include/linux/kprobes.h > @@ -350,6 +350,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) > return this_cpu_ptr(&kprobe_ctlblk); > } > > +extern struct kprobe kprobe_busy; > +void kprobe_busy_begin(void); > +void kprobe_busy_end(void); > + > kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); > int register_kprobe(struct kprobe *p); > void unregister_kprobe(struct kprobe *p); > diff --git a/kernel/kprobes.c b/kernel/kprobes.c > index 2625c241ac00..75bb4a8458e7 100644 > --- a/kernel/kprobes.c > +++ b/kernel/kprobes.c > @@ -1236,6 +1236,26 @@ __releases(hlist_lock) > } > NOKPROBE_SYMBOL(kretprobe_table_unlock); > > +struct kprobe kprobe_busy = { > + .addr = (void *) get_kprobe, > +}; > + > +void kprobe_busy_begin(void) > +{ > + struct kprobe_ctlblk *kcb; > + > + preempt_disable(); > + __this_cpu_write(current_kprobe, &kprobe_busy); > + kcb = get_kprobe_ctlblk(); > + kcb->kprobe_status = KPROBE_HIT_ACTIVE; > +} > + > +void kprobe_busy_end(void) > +{ > + __this_cpu_write(current_kprobe, NULL); > + preempt_enable(); > +} > + > /* > * This function is called from finish_task_switch when task tk becomes dead, > * so that we can recycle any function-return probe instances associated > @@ -1253,6 +1273,8 @@ void kprobe_flush_task(struct task_struct *tk) > /* Early boot. kretprobe_table_locks not yet initialized. */ > return; > > + kprobe_busy_begin(); > + > INIT_HLIST_HEAD(&empty_rp); > hash = hash_ptr(tk, KPROBE_HASH_BITS); > head = &kretprobe_inst_table[hash]; > @@ -1266,6 +1288,8 @@ void kprobe_flush_task(struct task_struct *tk) > hlist_del(&ri->hlist); > kfree(ri); > } > + > + kprobe_busy_end(); > } > NOKPROBE_SYMBOL(kprobe_flush_task); > > -- > 2.18.2 > -- Masami Hiramatsu <mhiramat(a)kernel.org>

4 years, 8 months

2
7
0 0

[PATCH] arm64: tegra: Fix ethernet phy-mode for Jetson Xavier

by Jon Hunter

The 'phy-mode' property is currently defined as 'rgmii' for Jetson Xavier. This indicates that the RGMII RX and TX delays are set by the MAC and the internal delays set by the PHY are not used. If the Marvell PHY driver is enabled, such that it is used and not the generic PHY, ethernet failures are seen (DHCP is failing to obtain an IP address) and this is caused because the Marvell PHY driver is disabling the internal RX and TX delays. For Jetson Xavier the internal PHY RX and TX delay should be used and so fix this by setting the 'phy-mode' to 'rgmii-id' and not 'rgmii'. Cc: stable(a)vger.kernel.org Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi index 623f7d7d216b..8e3136dfdd62 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi @@ -33,7 +33,7 @@ phy-reset-gpios = <&gpio TEGRA194_MAIN_GPIO(G, 5) GPIO_ACTIVE_LOW>; phy-handle = <&phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; mdio { #address-cells = <1>; -- 2.17.1

4 years, 8 months

3
3
0 0

[PATCH 4/9] lpfc: Fix negation of else clause in lpfc_prep_node_fc4type

by James Smart

Implementation of a previous patch added a condition to an if check that always end up with the if test being true. Execution of the else clause was inadvertantly negated. The additional condition check was incorrect and unnecessary after the other modifications had been done in that patch. Remove the check from the if series. Fixes: b95b21193c85 ("scsi: lpfc: Fix loss of remote port after devloss due to lack of RPIs") Cc: <stable(a)vger.kernel.org> # v5.4+ Signed-off-by: Dick Kennedy <dick.kennedy(a)broadcom.com> Signed-off-by: James Smart <jsmart2021(a)gmail.com> --- drivers/scsi/lpfc/lpfc_ct.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 2aa578d20f8c..7fce73c39c1c 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -462,7 +462,6 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type) struct lpfc_nodelist *ndlp; if ((vport->port_type != LPFC_NPIV_PORT) || - (fc4_type == FC_TYPE_FCP) || !(vport->ct_flags & FC_CT_RFF_ID) || !vport->cfg_restrict_login) { ndlp = lpfc_setup_disc_node(vport, Did); -- 2.26.1

4 years, 8 months

2
1
0 0

patch "usb: chipidea: msm: Ensure proper controller reset using role switch" added to usb-linus

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled usb: chipidea: msm: Ensure proper controller reset using role switch to my usb git tree which can be found at git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git in the usb-linus branch. The patch will show up in the next release of the linux-next tree (usually sometime within the next 24 hours during the week.) The patch will hopefully also be merged in Linus's tree for the next -rc kernel release. If you have any questions about this process, please let me know. >From 91edf63d5022bd0464788ffb4acc3d5febbaf81d Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Date: Thu, 7 May 2020 08:49:18 +0800 Subject: usb: chipidea: msm: Ensure proper controller reset using role switch API Currently we check to make sure there is no error state on the extcon handle for VBUS when writing to the HS_PHY_GENCONFIG_2 register. When using the USB role-switch API we still need to write to this register absent an extcon handle. This patch makes the appropriate update to ensure the write happens if role-switching is true. Fixes: 05559f10ed79 ("usb: chipidea: add role switch class support") Cc: stable <stable(a)vger.kernel.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Philipp Zabel <p.zabel(a)pengutronix.de> Cc: linux-usb(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: Stephen Boyd <swboyd(a)chromium.org> Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Signed-off-by: Peter Chen <peter.chen(a)nxp.com> Link: https://lore.kernel.org/r/20200507004918.25975-2-peter.chen@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/usb/chipidea/ci_hdrc_msm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); -- 2.26.2

4 years, 8 months

1
0
0 0

stable-rc/linux-4.4.y boot: 43 boots: 2 failed, 33 passed with 2 offline, 4 untried/unknown, 2 conflicts (v4.4.222-166-g7ab45cabed0b)

by kernelci.org bot

stable-rc/linux-4.4.y boot: 43 boots: 2 failed, 33 passed with 2 offline, 4 untried/unknown, 2 conflicts (v4.4.222-166-g7ab45cabed0b) Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.4.y/kernel/v4.4.… Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.4.y/kernel/v4.4.222-166… Tree: stable-rc Branch: linux-4.4.y Git Describe: v4.4.222-166-g7ab45cabed0b Git Commit: 7ab45cabed0becc5018c917eb494b860da28dd02 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Tested: 34 unique boards, 10 SoC families, 14 builds out of 190 Boot Regressions Detected: arm: qcom_defconfig: gcc-8: qcom-apq8064-cm-qs600: lab-baylibre-seattle: failing since 88 days (last pass: v4.4.212-56-g758a39807529 - first fail: v4.4.213-28-ga3b43e6eae91) i386: i386_defconfig: gcc-8: qemu_i386: lab-baylibre: new failure (last pass: v4.4.222) x86_64: x86_64_defconfig: gcc-8: qemu_x86_64: lab-baylibre: new failure (last pass: v4.4.222) Boot Failures Detected: arm: multi_v5_defconfig: gcc-8: imx27-phytec-phycard-s-rdk: 1 failed lab imx_v4_v5_defconfig: gcc-8: imx27-phytec-phycard-s-rdk: 1 failed lab Offline Platforms: arm: qcom_defconfig: gcc-8 qcom-apq8064-cm-qs600: 1 offline lab exynos_defconfig: gcc-8 exynos5800-peach-pi: 1 offline lab Conflicting Boot Failures Detected: (These likely are not failures as other labs are reporting PASS. Needs review.) i386: i386_defconfig: qemu_i386: lab-baylibre: FAIL (gcc-8) lab-collabora: PASS (gcc-8) x86_64: x86_64_defconfig: qemu_x86_64: lab-baylibre: FAIL (gcc-8) lab-collabora: PASS (gcc-8) --- For more info write to <info(a)kernelci.org>

4 years, 8 months

1
0
0 0

✅ PASS: Test report for kernel 5.6.11-07dde60.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: 07dde60791b0 - vhost: vsock: kick send_pkt worker once device is started 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 ✅ stress: stress-ng 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests 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: ⚡ 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 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 ⚡⚡⚡ 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 ⚡⚡⚡ 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 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 ⚡⚡⚡ selinux-policy: serge-testsuite ⚡⚡⚡ stress: stress-ng 🚧 ⚡⚡⚡ Storage blktests Host 4: ⚡ 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 - qedf driver Host 3: ✅ Boot test ✅ Storage SAN device stress - mpt3sas_gen1 Host 4: ⚡ 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 5: ⚡ 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 6: ✅ 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 ⏱.

4 years, 8 months

1
0
0 0

[PATCH v3] drm/msm: Check for powered down HW in the devfreq callbacks

by Jordan Crouse

Writing to the devfreq sysfs nodes while the GPU is powered down can result in a system crash (on a5xx) or a nasty GMU error (on a6xx): $ /sys/class/devfreq/5000000.gpu# echo 500000000 > min_freq [ 104.841625] platform 506a000.gmu: [drm:a6xx_gmu_set_oob] *ERROR* Timeout waiting for GMU OOB set GPU_DCVS: 0x0 Despite the fact that we carefully try to suspend the devfreq device when the hardware is powered down there are lots of holes in the governors that don't check for the suspend state and blindly call into the devfreq callbacks that end up triggering hardware reads in the GPU driver. Call pm_runtime_get_if_in_use() in the gpu_busy() and gpu_set_freq() callbacks to skip the hardware access if it isn't active. v3: Only check pm_runtime_get_if_in_use() for == 0 per Eric Anholt v2: Use pm_runtime_get_if_in_use() per Eric Anholt Cc: stable(a)vger.kernel.org Reviewed-by: Eric Anholt <eric(a)anholt.net> Signed-off-by: Jordan Crouse <jcrouse(a)codeaurora.org> --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 ++++++ drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++++++ drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 7 +++++++ 3 files changed, 21 insertions(+) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 724024a2243a..662d02289533 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1404,6 +1404,10 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu) { u64 busy_cycles, busy_time; + /* Only read the gpu busy if the hardware is already active */ + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0) + return 0; + busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO, REG_A5XX_RBBM_PERFCTR_RBBM_0_HI); @@ -1412,6 +1416,8 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu) gpu->devfreq.busy_cycles = busy_cycles; + pm_runtime_put(&gpu->pdev->dev); + if (WARN_ON(busy_time > ~0LU)) return ~0LU; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index c4e71abbdd53..34607a98cc7c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -108,6 +108,13 @@ static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index) struct msm_gpu *gpu = &adreno_gpu->base; int ret; + /* + * This can get called from devfreq while the hardware is idle. Don't + * bring up the power if it isn't already active + */ + if (pm_runtime_get_if_in_use(gmu->dev) == 0) + return; + gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0); gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING, @@ -134,6 +141,7 @@ static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index) * for now leave it at max so that the performance is nominal. */ icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + pm_runtime_put(gmu->dev); } void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 68af24150de5..2c09d2c21773 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -810,6 +810,11 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); u64 busy_cycles, busy_time; + + /* Only read the gpu busy if the hardware is already active */ + if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0) + return 0; + busy_cycles = gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H); @@ -819,6 +824,8 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) gpu->devfreq.busy_cycles = busy_cycles; + pm_runtime_put(a6xx_gpu->gmu.dev); + if (WARN_ON(busy_time > ~0LU)) return ~0LU; -- 2.17.1

4 years, 8 months

2
1
0 0

[PATCH 1/6] drm/i915: Mark concurrent submissions with a weak-dependency

by Chris Wilson

We recorded the dependencies for WAIT_FOR_SUBMIT in order that we could correctly perform priority inheritance from the parallel branches to the common trunk. However, for the purpose of timeslicing and reset handling, the dependency is weak -- as we the pair of requests are allowed to run in parallel and not in strict succession. So for example we do need to suspend one if the other hangs. The real significance though is that this allows us to rearrange groups of WAIT_FOR_SUBMIT linked requests along the single engine, and so can resolve user level inter-batch scheduling dependencies from user semaphores. Fixes: c81471f5e95c ("drm/i915: Copy across scheduler behaviour flags across submit fences") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.6+ --- drivers/gpu/drm/i915/gt/intel_lrc.c | 9 +++++++++ drivers/gpu/drm/i915/i915_request.c | 8 ++++++-- drivers/gpu/drm/i915/i915_scheduler.c | 4 +++- drivers/gpu/drm/i915/i915_scheduler.h | 3 ++- drivers/gpu/drm/i915/i915_scheduler_types.h | 1 + 5 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index d4ef344657b0..a47e4e15cbaa 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1883,6 +1883,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -2729,6 +2732,9 @@ static void __execlists_hold(struct i915_request *rq) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -2853,6 +2859,9 @@ static void __execlists_unhold(struct i915_request *rq) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Propagate any change in error status */ if (rq->fence.error) i915_request_set_error_once(w, rq->fence.error); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 22635bbabf06..95edc5523a01 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1038,7 +1038,9 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) return 0; if (to->engine->schedule) { - ret = i915_sched_node_add_dependency(&to->sched, &from->sched); + ret = i915_sched_node_add_dependency(&to->sched, + &from->sched, + 0); if (ret < 0) return ret; } @@ -1200,7 +1202,9 @@ __i915_request_await_execution(struct i915_request *to, /* Couple the dependency tree for PI on this exposed to->fence */ if (to->engine->schedule) { - err = i915_sched_node_add_dependency(&to->sched, &from->sched); + err = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_WEAK); if (err < 0) return err; } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 37cfcf5b321b..5f4c1e49e974 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -462,7 +462,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, } int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) + struct i915_sched_node *signal, + unsigned long flags) { struct i915_dependency *dep; @@ -473,6 +474,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, local_bh_disable(); if (!__i915_sched_node_add_dependency(node, signal, dep, + flags | I915_DEPENDENCY_EXTERNAL | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d1dc4efef77b..6f0bf00fc569 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, unsigned long flags); int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal); + struct i915_sched_node *signal, + unsigned long flags); void i915_sched_node_fini(struct i915_sched_node *node); diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index d18e70550054..7186875088a0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -78,6 +78,7 @@ struct i915_dependency { unsigned long flags; #define I915_DEPENDENCY_ALLOC BIT(0) #define I915_DEPENDENCY_EXTERNAL BIT(1) +#define I915_DEPENDENCY_WEAK BIT(2) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ -- 2.20.1

4 years, 8 months

2
1
0 0

[PATCH 4/4] KVM: arm64: Fix 32bit PC wrap-around

by Marc Zyngier

In the unlikely event that a 32bit vcpu traps into the hypervisor on an instruction that is located right at the end of the 32bit range, the emulation of that instruction is going to increment PC past the 32bit range. This isn't great, as userspace can then observe this value and get a bit confused. Conversly, userspace can do things like (in the context of a 64bit guest that is capable of 32bit EL0) setting PSTATE to AArch64-EL0, set PC to a 64bit value, change PSTATE to AArch32-USR, and observe that PC hasn't been truncated. More confusion. Fix both by: - truncating PC increments for 32bit guests - sanitizing all 32bit regs every time a core reg is changed by userspace, and that PSTATE indicates a 32bit mode. Cc: stable(a)vger.kernel.org Acked-by: Will Deacon <will(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> --- arch/arm64/kvm/guest.c | 7 +++++++ virt/kvm/arm/hyp/aarch32.c | 8 ++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 23ebe51410f0..50a279d3ddd7 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } -- 2.26.2

4 years, 8 months

2
1
0 0

[PATCH 1/2] drm/i915: Mark concurrent submissions with a weak-dependency

by Chris Wilson

We recorded the dependencies for WAIT_FOR_SUBMIT in order that we could correctly perform priority inheritance from the parallel branches to the common trunk. However, for the purpose of timeslicing and reset handling, the dependency is weak -- as we the pair of requests are allowed to run in parallel and not in strict succession. So for example we do need to suspend one if the other hangs. The real significance though is that this allows us to rearrange groups of WAIT_FOR_SUBMIT linked requests along the single engine, and so can resolve user level inter-batch scheduling dependencies from user semaphores. Fixes: c81471f5e95c ("drm/i915: Copy across scheduler behaviour flags across submit fences") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.6+ --- drivers/gpu/drm/i915/gt/intel_lrc.c | 9 +++++++++ drivers/gpu/drm/i915/i915_request.c | 8 ++++++-- drivers/gpu/drm/i915/i915_scheduler.c | 4 +++- drivers/gpu/drm/i915/i915_scheduler.h | 3 ++- drivers/gpu/drm/i915/i915_scheduler_types.h | 1 + 5 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index dc3f2ee7136d..10109f661bcb 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1880,6 +1880,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -2726,6 +2729,9 @@ static void __execlists_hold(struct i915_request *rq) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -2850,6 +2856,9 @@ static void __execlists_unhold(struct i915_request *rq) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Propagate any change in error status */ if (rq->fence.error) i915_request_set_error_once(w, rq->fence.error); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 22635bbabf06..95edc5523a01 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1038,7 +1038,9 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) return 0; if (to->engine->schedule) { - ret = i915_sched_node_add_dependency(&to->sched, &from->sched); + ret = i915_sched_node_add_dependency(&to->sched, + &from->sched, + 0); if (ret < 0) return ret; } @@ -1200,7 +1202,9 @@ __i915_request_await_execution(struct i915_request *to, /* Couple the dependency tree for PI on this exposed to->fence */ if (to->engine->schedule) { - err = i915_sched_node_add_dependency(&to->sched, &from->sched); + err = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_WEAK); if (err < 0) return err; } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 37cfcf5b321b..5f4c1e49e974 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -462,7 +462,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, } int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) + struct i915_sched_node *signal, + unsigned long flags) { struct i915_dependency *dep; @@ -473,6 +474,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, local_bh_disable(); if (!__i915_sched_node_add_dependency(node, signal, dep, + flags | I915_DEPENDENCY_EXTERNAL | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d1dc4efef77b..6f0bf00fc569 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, unsigned long flags); int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal); + struct i915_sched_node *signal, + unsigned long flags); void i915_sched_node_fini(struct i915_sched_node *node); diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index d18e70550054..7186875088a0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -78,6 +78,7 @@ struct i915_dependency { unsigned long flags; #define I915_DEPENDENCY_ALLOC BIT(0) #define I915_DEPENDENCY_EXTERNAL BIT(1) +#define I915_DEPENDENCY_WEAK BIT(2) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ -- 2.20.1

4 years, 8 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2020