From: Thomas Weißschuh thomas.weissschuh@linutronix.de

[ Upstream commit 0c7fbae5bc782429c97d68dc40fb126748d7e352 ]

Restricted pointers ("%pK") are only meant to be used when directly printing to a file from task context. Otherwise it can unintentionally expose security sensitive, raw pointer values.

Use regular pointer formatting instead.

Link: https://lore.kernel.org/lkml/20250113171731-dc10e3c1-da64-4af0-b767-7c707046... Signed-off-by: Thomas Weißschuh thomas.weissschuh@linutronix.de Reviewed-by: Michael Mueller mimu@linux.ibm.com Tested-by: Michael Mueller mimu@linux.ibm.com Link: https://lore.kernel.org/r/20250217-restricted-pointers-s390-v1-2-0e4ace75d8a... Signed-off-by: Janosch Frank frankja@linux.ibm.com Message-ID: 20250217-restricted-pointers-s390-v1-2-0e4ace75d8aa@linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kvm/intercept.c | 2 +- arch/s390/kvm/interrupt.c | 8 ++++---- arch/s390/kvm/kvm-s390.c | 10 +++++----- 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index b16352083ff98..f0be263b334ce 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -94,7 +94,7 @@ static int handle_validity(struct kvm_vcpu *vcpu)

vcpu->stat.exit_validity++; trace_kvm_s390_intercept_validity(vcpu, viwhy); - KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy, + KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%p)", viwhy, current->pid, vcpu->kvm);

/* do not warn on invalid runtime instrumentation mode */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index efaebba5ee19c..fe4841104ed92 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3161,7 +3161,7 @@ void kvm_s390_gisa_clear(struct kvm *kvm) if (!gi->origin) return; gisa_clear_ipm(gi->origin); - VM_EVENT(kvm, 3, "gisa 0x%pK cleared", gi->origin); + VM_EVENT(kvm, 3, "gisa 0x%p cleared", gi->origin); }

void kvm_s390_gisa_init(struct kvm *kvm) @@ -3178,7 +3178,7 @@ void kvm_s390_gisa_init(struct kvm *kvm) gi->timer.function = gisa_vcpu_kicker; memset(gi->origin, 0, sizeof(struct kvm_s390_gisa)); gi->origin->next_alert = (u32)virt_to_phys(gi->origin); - VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin); + VM_EVENT(kvm, 3, "gisa 0x%p initialized", gi->origin); }

void kvm_s390_gisa_enable(struct kvm *kvm) @@ -3219,7 +3219,7 @@ void kvm_s390_gisa_destroy(struct kvm *kvm) process_gib_alert_list(); hrtimer_cancel(&gi->timer); gi->origin = NULL; - VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa); + VM_EVENT(kvm, 3, "gisa 0x%p destroyed", gisa); }

void kvm_s390_gisa_disable(struct kvm *kvm) @@ -3468,7 +3468,7 @@ int __init kvm_s390_gib_init(u8 nisc) } }

- KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc); + KVM_EVENT(3, "gib 0x%p (nisc=%d) initialized", gib, gib->nisc); goto out;

out_unreg_gal: diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 348d030d2660c..890d850f51f07 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -990,7 +990,7 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att } mutex_unlock(&kvm->lock); VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit); - VM_EVENT(kvm, 3, "New guest asce: 0x%pK", + VM_EVENT(kvm, 3, "New guest asce: 0x%p", (void *) kvm->arch.gmap->asce); break; } @@ -3418,7 +3418,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_s390_gisa_init(kvm); INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup); kvm->arch.pv.set_aside = NULL; - KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); + KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);

return 0; out_err: @@ -3481,7 +3481,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_s390_destroy_adapters(kvm); kvm_s390_clear_float_irqs(kvm); kvm_s390_vsie_destroy(kvm); - KVM_EVENT(3, "vm 0x%pK destroyed", kvm); + KVM_EVENT(3, "vm 0x%p destroyed", kvm); }

/* Section: vcpu related */ @@ -3602,7 +3602,7 @@ static int sca_switch_to_extended(struct kvm *kvm)

free_page((unsigned long)old_sca);

- VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)", + VM_EVENT(kvm, 2, "Switched to ESCA (0x%p -> 0x%p)", old_sca, kvm->arch.sca); return 0; } @@ -3974,7 +3974,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto out_free_sie_block; }

- VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", + VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p", vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);

From: Ming Lei ming.lei@redhat.com

[ Upstream commit 72070e57b0a518ec8e562a2b68fdfc796ef5c040 ]

Commit 57ed58c13256 ("selftests: ublk: enable zero copy for stripe target") added test entry of test_stripe_04, but forgot to add the test script.

So fix the test by adding the script file.

Reported-by: Uday Shankar ushankar@purestorage.com Signed-off-by: Ming Lei ming.lei@redhat.com Reviewed-by: Uday Shankar ushankar@purestorage.com Link: https://lore.kernel.org/r/20250404001849.1443064-1-ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- .../testing/selftests/ublk/test_stripe_04.sh | 24 +++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100755 tools/testing/selftests/ublk/test_stripe_04.sh

diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh new file mode 100755 index 0000000000000..1f2b642381d17 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stripe_04.sh @@ -0,0 +1,24 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="stripe_04" +ERR_CODE=0 + +_prep_test "stripe" "mkfs & mount & umount on zero copy" + +backfile_0=$(_create_backfile 256M) +backfile_1=$(_create_backfile 256M) +dev_id=$(_add_ublk_dev -t stripe -z -q 2 "$backfile_0" "$backfile_1") +_check_add_dev $TID $? "$backfile_0" "$backfile_1" + +_mkfs_mount_test /dev/ublkb"${dev_id}" +ERR_CODE=$? + +_cleanup_test "stripe" + +_remove_backfile "$backfile_0" +_remove_backfile "$backfile_1" + +_show_result $TID $ERR_CODE

From: Jason Andryuk jason.andryuk@amd.com

[ Upstream commit 0f2946bb172632e122d4033e0b03f85230a29510 ]

xen-acpi-processor functions under a PVH dom0 with only a xen_initial_domain() runtime check. Change the Kconfig dependency from PV dom0 to generic dom0 to reflect that.

Suggested-by: Jan Beulich jbeulich@suse.com Signed-off-by: Jason Andryuk jason.andryuk@amd.com Reviewed-by: Juergen Gross jgross@suse.com Tested-by: Jan Beulich jbeulich@suse.com Signed-off-by: Juergen Gross jgross@suse.com Message-ID: 20250331172913.51240-1-jason.andryuk@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/xen/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index d43153fec18ea..af5c214b22069 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -278,7 +278,7 @@ config XEN_PRIVCMD_IRQFD

config XEN_ACPI_PROCESSOR tristate "Xen ACPI processor" - depends on XEN && XEN_PV_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ + depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ default m help This ACPI processor uploads Power Management information to the Xen

From: Mario Limonciello mario.limonciello@amd.com

[ Upstream commit b988685388effd648150aab272533f833a2a70f0 ]

When AC adapter is unplugged or plugged in EC wakes from HW sleep but APU doesn't enter back into HW sleep.

The reason this happens is that, when the APU exits HW sleep, the power rails controlled by the EC will power up the TCON. The TCON has a GPIO that will be toggled at this time. The GPIO is not marked as a wakeup source, but the GPIO controller still has an unserviced interrupt. Unserviced interrupts will block entering HW sleep again. Clearing the GPIO doesn't help as the TCON continues to assert it until it's been initialized by i2c-hid.

Fixing this would require TCON F/W changes and it's already broken in the wild on production hardware.

To avoid triggering this issue add a quirk to avoid letting EC wake up system at all. The power button still works properly on this system.

Reported-by: Antheas Kapenekakis lkml@antheas.dev Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3929 Link: https://github.com/bazzite-org/patchwork/commit/95b93b2852718ee1e808c72e6b18... Co-developed-by: Antheas Kapenekakis lkml@antheas.dev Signed-off-by: Antheas Kapenekakis lkml@antheas.dev Signed-off-by: Mario Limonciello mario.limonciello@amd.com Link: https://patch.msgid.link/20250401133858.1892077-1-superm1@kernel.org [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/ec.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 115994dfefec1..77d6af6115893 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2301,6 +2301,34 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = { DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"), }, }, + /* + * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC + * https://gitlab.freedesktop.org/drm/amd/-/issues/3929 + */ + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83L3"), + } + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83N6"), + } + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"), + } + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"), + } + }, { }, };

From: Hannes Reinecke hare@kernel.org

[ Upstream commit 62baf70c327444338c34703c71aa8cc8e4189bd6 ]

When scanning for new namespaces we might have missed an ANA AEN.

The NVMe base spec (NVMe Base Specification v2.1, Figure 151 'Asynchonous Event Information - Notice': Asymmetric Namespace Access Change) states:

A controller shall not send this even if an Attached Namespace Attribute Changed asynchronous event [...] is sent for the same event.

so we need to re-read the ANA log page after we rescanned the namespace list to update the ANA states of the new namespaces.

Signed-off-by: Hannes Reinecke hare@kernel.org Reviewed-by: Keith Busch kbusch@kernel.org Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e36c6fcab1eed..8827614ab8c63 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3976,6 +3976,11 @@ static void nvme_scan_work(struct work_struct *work) /* Requeue if we have missed AENs */ if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) nvme_queue_scan(ctrl); +#ifdef CONFIG_NVME_MULTIPATH + else + /* Re-read the ANA log page to not miss updates */ + queue_work(nvme_wq, &ctrl->ana_work); +#endif }

/*

From: Josh Poimboeuf jpoimboe@kernel.org

[ Upstream commit 9f9cc012c2cbac4833746a0182e06a8eec940d19 ]

In preparation for simplifying INSN_SYSCALL, make validate_unret() terminate control flow on UD2 just like validate_branch() already does.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Link: https://lore.kernel.org/r/ce841269e7e28c8b7f32064464a9821034d724ff.174409521... Signed-off-by: Sasha Levin sashal@kernel.org --- tools/objtool/check.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9102ad5985cc0..78f38a74bd398 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3935,6 +3935,9 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) break; }

+ if (insn->dead_end) + return 0; + if (!next) { WARN_INSN(insn, "teh end!"); return -1;

From: Qiuxu Zhuo qiuxu.zhuo@intel.com

[ Upstream commit 197c1eaa7ba633a482ed7588eea6fd4aa57e08d4 ]

When running the mincore_selftest on a system with an XFS file system, it failed the "check_file_mmap" test case due to the read-ahead pages reaching the end of the file. The failure log is as below:

RUN global.check_file_mmap ... mincore_selftest.c:264:check_file_mmap:Expected i (1024) < vec_size (1024) mincore_selftest.c:265:check_file_mmap:Read-ahead pages reached the end of the file check_file_mmap: Test failed FAIL global.check_file_mmap

This is because the read-ahead window size of the XFS file system on this machine is 4 MB, which is larger than the size from the #PF address to the end of the file. As a result, all the pages for this file are populated.

blockdev --getra /dev/nvme0n1p5 8192 blockdev --getbsz /dev/nvme0n1p5 512

This issue can be fixed by extending the current FILE_SIZE 4MB to a larger number, but it will still fail if the read-ahead window size of the file system is larger enough. Additionally, in the real world, read-ahead pages reaching the end of the file can happen and is an expected behavior. Therefore, allowing read-ahead pages to reach the end of the file is a better choice for the "check_file_mmap" test case.

Link: https://lore.kernel.org/r/20250311080940.21413-1-qiuxu.zhuo@intel.com Reported-by: Yi Lai yi1.lai@intel.com Signed-off-by: Qiuxu Zhuo qiuxu.zhuo@intel.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/mincore/mincore_selftest.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index e949a43a61450..efabfcbe0b498 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -261,9 +261,6 @@ TEST(check_file_mmap) TH_LOG("No read-ahead pages found in memory"); }

- EXPECT_LT(i, vec_size) { - TH_LOG("Read-ahead pages reached the end of the file"); - } /* * End of the readahead window. The rest of the pages shouldn't * be in memory.

From: Josh Poimboeuf jpoimboe@kernel.org

[ Upstream commit 18bae0dfec15b24ec14ca17dc18603372f5f254f ]

eIBRS protects against guest->host RSB underflow/poisoning attacks. Adding retpoline to the mix doesn't change that. Retpoline has a balanced CALL/RET anyway.

So the current full RSB filling on VMEXIT with eIBRS+retpoline is overkill. Disable it or do the VMEXIT_LITE mitigation if needed.

Suggested-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Reviewed-by: Amit Shah amit.shah@amd.com Reviewed-by: Nikolay Borisov nik.borisov@suse.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Vitaly Kuznetsov vkuznets@redhat.com Cc: Sean Christopherson seanjc@google.com Cc: David Woodhouse dwmw2@infradead.org Link: https://lore.kernel.org/r/84a1226e5c9e2698eae1b5ade861f1b8bf3677dc.174414825... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/bugs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7df458a6553eb..a8fce2ab0f250 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1600,20 +1600,20 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ case SPECTRE_V2_NONE: return;

- case SPECTRE_V2_EIBRS_LFENCE: case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_LFENCE: + case SPECTRE_V2_EIBRS_RETPOLINE: if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { - setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n"); + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); } return;

- case SPECTRE_V2_EIBRS_RETPOLINE: case SPECTRE_V2_RETPOLINE: case SPECTRE_V2_LFENCE: case SPECTRE_V2_IBRS: - setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n"); + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); return; }

From: Daniel Wagner wagi@kernel.org

[ Upstream commit b0b26ad0e1943de25ce82a7e5af3574f31b1cf99 ]

The reference counting code can be simplified. Instead taking a tgtport refrerence at the beginning of nvmet_fc_alloc_hostport and put it back if not a new hostport object is allocated, only take it when a new hostport object is allocated.

Signed-off-by: Daniel Wagner wagi@kernel.org Reviewed-by: Hannes Reinecke hare@suse.de Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/fc.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 8a02ed63b1566..50953e0f9772d 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1044,33 +1044,24 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) struct nvmet_fc_hostport *newhost, *match = NULL; unsigned long flags;

+ /* + * Caller holds a reference on tgtport. + */ + /* if LLDD not implemented, leave as NULL */ if (!hosthandle) return NULL;

- /* - * take reference for what will be the newly allocated hostport if - * we end up using a new allocation - */ - if (!nvmet_fc_tgtport_get(tgtport)) - return ERR_PTR(-EINVAL); - spin_lock_irqsave(&tgtport->lock, flags); match = nvmet_fc_match_hostport(tgtport, hosthandle); spin_unlock_irqrestore(&tgtport->lock, flags);

- if (match) { - /* no new allocation - release reference */ - nvmet_fc_tgtport_put(tgtport); + if (match) return match; - }

newhost = kzalloc(sizeof(*newhost), GFP_KERNEL); - if (!newhost) { - /* no new allocation - release reference */ - nvmet_fc_tgtport_put(tgtport); + if (!newhost) return ERR_PTR(-ENOMEM); - }

spin_lock_irqsave(&tgtport->lock, flags); match = nvmet_fc_match_hostport(tgtport, hosthandle); @@ -1079,6 +1070,7 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) kfree(newhost); newhost = match; } else { + nvmet_fc_tgtport_get(tgtport); newhost->tgtport = tgtport; newhost->hosthandle = hosthandle; INIT_LIST_HEAD(&newhost->host_list);

From: Octavian Purdila tavip@google.com

[ Upstream commit 8c0cea59d40cf6dd13c2950437631dd614fbade6 ]

Many configuration parameters have influence on others (e.g. divisor -> flows -> limit, depth -> limit) and so it is difficult to correctly do all of the validation before applying the configuration. And if a validation error is detected late it is difficult to roll back a partially applied configuration.

To avoid these issues use a temporary work area to update and validate the configuration and only then apply the configuration to the internal state.

Signed-off-by: Octavian Purdila tavip@google.com Acked-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_sfq.c | 56 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 44 insertions(+), 12 deletions(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 60754f366ab7b..68e909e8fabd9 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -631,6 +631,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, struct red_parms *p = NULL; struct sk_buff *to_free = NULL; struct sk_buff *tail = NULL; + unsigned int maxflows; + unsigned int quantum; + unsigned int divisor; + int perturb_period; + u8 headdrop; + u8 maxdepth; + int limit; + u8 flags; +

if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; @@ -656,36 +665,59 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, NL_SET_ERR_MSG_MOD(extack, "invalid limit"); return -EINVAL; } + sch_tree_lock(sch); + + limit = q->limit; + divisor = q->divisor; + headdrop = q->headdrop; + maxdepth = q->maxdepth; + maxflows = q->maxflows; + perturb_period = q->perturb_period; + quantum = q->quantum; + flags = q->flags; + + /* update and validate configuration */ if (ctl->quantum) - q->quantum = ctl->quantum; - WRITE_ONCE(q->perturb_period, ctl->perturb_period * HZ); + quantum = ctl->quantum; + perturb_period = ctl->perturb_period * HZ; if (ctl->flows) - q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); + maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { - q->divisor = ctl->divisor; - q->maxflows = min_t(u32, q->maxflows, q->divisor); + divisor = ctl->divisor; + maxflows = min_t(u32, maxflows, divisor); } if (ctl_v1) { if (ctl_v1->depth) - q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); + maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); if (p) { - swap(q->red_parms, p); - red_set_parms(q->red_parms, + red_set_parms(p, ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Plog, ctl_v1->Scell_log, NULL, ctl_v1->max_P); } - q->flags = ctl_v1->flags; - q->headdrop = ctl_v1->headdrop; + flags = ctl_v1->flags; + headdrop = ctl_v1->headdrop; } if (ctl->limit) { - q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows); - q->maxflows = min_t(u32, q->maxflows, q->limit); + limit = min_t(u32, ctl->limit, maxdepth * maxflows); + maxflows = min_t(u32, maxflows, limit); }

+ /* commit configuration */ + q->limit = limit; + q->divisor = divisor; + q->headdrop = headdrop; + q->maxdepth = maxdepth; + q->maxflows = maxflows; + WRITE_ONCE(q->perturb_period, perturb_period); + q->quantum = quantum; + q->flags = flags; + if (p) + swap(q->red_parms, p); + qlen = sch->q.qlen; while (sch->q.qlen > q->limit) { dropped += sfq_drop(sch, &to_free);

From: Sebastian Andrzej Siewior bigeasy@linutronix.de

[ Upstream commit 92e250c624ea37fde64bfd624fd2556f0d846f18 ]

tick_freeze() acquires a raw spinlock (tick_freeze_lock). Later in the callchain (timekeeping_suspend() -> mc146818_avoid_UIP()) the RTC driver acquires a spinlock which becomes a sleeping lock on PREEMPT_RT. Lockdep complains about this lock nesting.

Add a lockdep override for this special case and a comment explaining why it is okay.

Reported-by: Borislav Petkov bp@alien8.de Reported-by: Chris Bainbridge chris.bainbridge@gmail.com Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/all/20250404133429.pnAzf-eF@linutronix.de Closes: https://lore.kernel.org/all/20250330113202.GAZ-krsjAnurOlTcp-@fat_crate.loca... Closes: https://lore.kernel.org/all/CAP-bSRZ0CWyZZsMtx046YV8L28LhY0fson2g4EqcwRAVN1J... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/tick-common.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 7f2b17fc8ce40..ecdb8c2b2cab2 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -495,6 +495,7 @@ void tick_resume(void)

#ifdef CONFIG_SUSPEND static DEFINE_RAW_SPINLOCK(tick_freeze_lock); +static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP); static unsigned int tick_freeze_depth;

/** @@ -514,9 +515,22 @@ void tick_freeze(void) if (tick_freeze_depth == num_online_cpus()) { trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); + /* + * All other CPUs have their interrupts disabled and are + * suspended to idle. Other tasks have been frozen so there + * is no scheduling happening. This means that there is no + * concurrency in the system at this point. Therefore it is + * okay to acquire a sleeping lock on PREEMPT_RT, such as a + * spinlock, because the lock cannot be held by other CPUs + * or threads and acquiring it cannot block. + * + * Inform lockdep about the situation. + */ + lock_map_acquire_try(&tick_freeze_map); system_state = SYSTEM_SUSPEND; sched_clock_suspend(); timekeeping_suspend(); + lock_map_release(&tick_freeze_map); } else { tick_suspend_local(); } @@ -538,8 +552,16 @@ void tick_unfreeze(void) raw_spin_lock(&tick_freeze_lock);

if (tick_freeze_depth == num_online_cpus()) { + /* + * Similar to tick_freeze(). On resumption the first CPU may + * acquire uncontended sleeping locks while other CPUs block on + * tick_freeze_lock. + */ + lock_map_acquire_try(&tick_freeze_map); timekeeping_resume(); sched_clock_resume(); + lock_map_release(&tick_freeze_map); + system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false);

From: Ojaswin Mujoo ojaswin@linux.ibm.com

[ Upstream commit ccad447a3d331a239477c281533bacb585b54a98 ]

Block validity checks need to be skipped in case they are called for journal blocks since they are part of system's protected zone.

Currently, this is done by checking inode->ino against sbi->s_es->s_journal_inum, which is a direct read from the ext4 sb buffer head. If someone modifies this underneath us then the s_journal_inum field might get corrupted. To prevent against this, change the check to directly compare the inode with journal->j_inode.

**Slight change in behavior**: During journal init path, check_block_validity etc might be called for journal inode when sbi->s_journal is not set yet. In this case we now proceed with ext4_inode_block_valid() instead of returning early. Since systems zones have not been set yet, it is okay to proceed so we can perform basic checks on the blocks.

Suggested-by: Baokun Li libaokun1@huawei.com Reviewed-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://patch.msgid.link/0c06bc9ebfcd6ccfed84a36e79147bf45ff5adc1.1743142920... Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/block_validity.c | 5 ++--- fs/ext4/inode.c | 7 ++++--- 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 6fe3c941b5651..4d6ba140276b5 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -351,10 +351,9 @@ int ext4_check_blockref(const char *function, unsigned int line, { __le32 *bref = p; unsigned int blk; + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;

- if (ext4_has_feature_journal(inode->i_sb) && - (inode->i_ino == - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) + if (journal && inode == journal->j_inode) return 0;

while (bref < p+max) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 19d7bcf16ebb8..731660bf2203e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -378,10 +378,11 @@ static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { - if (ext4_has_feature_journal(inode->i_sb) && - (inode->i_ino == - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + + if (journal && inode == journal->j_inode) return 0; + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu "