summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/testing/sysfs-devices-system-cpu1
-rw-r--r--Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst4
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt13
-rw-r--r--Documentation/arch/x86/mds.rst8
-rw-r--r--Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml2
-rw-r--r--Documentation/virt/kvm/api.rst37
-rw-r--r--Documentation/virt/kvm/x86/intel-tdx.rst15
-rw-r--r--MAINTAINERS27
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/include/asm/el2_setup.h19
-rw-r--r--arch/arm64/include/asm/kvm_host.h1
-rw-r--r--arch/arm64/kernel/Makefile3
-rw-r--r--arch/arm64/kernel/cpufeature.c57
-rw-r--r--arch/arm64/kernel/efi.c11
-rw-r--r--arch/arm64/kernel/process.c5
-rw-r--r--arch/arm64/kernel/smp.c2
-rw-r--r--arch/arm64/kvm/arm.c16
-rw-r--r--arch/arm64/kvm/fpsimd.c26
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c20
-rw-r--r--arch/arm64/kvm/nested.c26
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3-nested.c4
-rw-r--r--arch/arm64/mm/fault.c30
-rw-r--r--arch/arm64/mm/proc.S1
-rw-r--r--arch/s390/crypto/sha1_s390.c2
-rw-r--r--arch/s390/crypto/sha512_s390.c3
-rw-r--r--arch/x86/Kconfig9
-rw-r--r--arch/x86/entry/entry.S8
-rw-r--r--arch/x86/include/asm/cpufeatures.h6
-rw-r--r--arch/x86/include/asm/irqflags.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h8
-rw-r--r--arch/x86/include/asm/mwait.h27
-rw-r--r--arch/x86/include/asm/nospec-branch.h37
-rw-r--r--arch/x86/include/asm/shared/tdx.h1
-rw-r--r--arch/x86/include/uapi/asm/kvm.h8
-rw-r--r--arch/x86/kernel/cpu/amd.c44
-rw-r--r--arch/x86/kernel/cpu/bugs.c136
-rw-r--r--arch/x86/kernel/cpu/common.c14
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_shas.c112
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kernel/process.c16
-rw-r--r--arch/x86/kvm/cpuid.c10
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/reverse_cpuid.h7
-rw-r--r--arch/x86/kvm/svm/sev.c12
-rw-r--r--arch/x86/kvm/svm/vmenter.S6
-rw-r--r--arch/x86/kvm/vmx/tdx.c30
-rw-r--r--arch/x86/kvm/vmx/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c4
-rw-r--r--arch/x86/kvm/xen.c15
-rw-r--r--drivers/base/cpu.c3
-rw-r--r--drivers/firmware/efi/libstub/zboot.lds6
-rw-r--r--drivers/net/ethernet/airoha/airoha_eth.c1
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c10
-rw-r--r--drivers/net/ethernet/broadcom/genet/bcmgenet.c6
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_main.c12
-rw-r--r--drivers/net/ethernet/renesas/rtsn.c5
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c24
-rw-r--r--drivers/net/ethernet/ti/am65-cpsw-nuss.c4
-rw-r--r--drivers/net/phy/qcom/at803x.c27
-rw-r--r--drivers/net/phy/qcom/qca808x.c2
-rw-r--r--drivers/net/phy/qcom/qcom-phy-lib.c25
-rw-r--r--drivers/net/phy/qcom/qcom.h5
-rw-r--r--drivers/net/phy/smsc.c57
-rw-r--r--drivers/pinctrl/nuvoton/pinctrl-ma35.c10
-rw-r--r--drivers/pinctrl/pinctrl-amd.c11
-rw-r--r--drivers/pinctrl/pinctrl-aw9523.c2
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm.c20
-rw-r--r--drivers/pwm/core.c2
-rw-r--r--drivers/pwm/pwm-mediatek.c13
-rw-r--r--fs/eventpoll.c12
-rw-r--r--include/linux/cpu.h1
-rw-r--r--include/linux/psp-sev.h2
-rw-r--r--include/net/af_vsock.h2
-rw-r--r--include/net/bluetooth/hci_core.h3
-rw-r--r--include/net/pkt_sched.h25
-rw-r--r--include/uapi/linux/bits.h4
-rw-r--r--include/uapi/linux/kvm.h4
-rw-r--r--kernel/dma/contiguous.c5
-rw-r--r--kernel/module/main.c17
-rw-r--r--net/atm/clip.c64
-rw-r--r--net/bluetooth/hci_event.c3
-rw-r--r--net/bluetooth/hci_sync.c4
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/netlink/af_netlink.c81
-rw-r--r--net/rxrpc/ar-internal.h15
-rw-r--r--net/rxrpc/call_accept.c4
-rw-r--r--net/rxrpc/output.c5
-rw-r--r--net/sched/sch_api.c33
-rw-r--r--net/sched/sch_hfsc.c16
-rw-r--r--net/sched/sch_qfq.c2
-rw-r--r--net/tipc/topsrv.c2
-rw-r--r--net/vmw_vsock/af_vsock.c57
-rw-r--r--sound/isa/ad1816a/ad1816a.c2
-rw-r--r--sound/pci/hda/patch_hdmi.c19
-rw-r--r--sound/pci/hda/patch_realtek.c3
-rw-r--r--sound/pci/hda/tas2781_hda.c8
-rw-r--r--sound/soc/codecs/cs35l56-shared.c2
-rw-r--r--sound/soc/fsl/fsl_asrc.c3
-rw-r--r--sound/soc/fsl/fsl_sai.c14
-rw-r--r--sound/soc/intel/boards/Kconfig1
-rw-r--r--sound/soc/intel/boards/sof_sdw.c3
-rw-r--r--sound/soc/intel/common/soc-acpi-intel-arl-match.c12
-rw-r--r--sound/usb/format.c22
-rw-r--r--tools/include/uapi/linux/bits.h4
-rw-r--r--tools/testing/selftests/kvm/x86/monitor_mwait_test.c1
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt53
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json37
-rw-r--r--virt/kvm/kvm_main.c3
109 files changed, 1229 insertions, 427 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index bf85f4de6862..ab8cd337f43a 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -584,6 +584,7 @@ What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/spectre_v1
/sys/devices/system/cpu/vulnerabilities/spectre_v2
/sys/devices/system/cpu/vulnerabilities/srbds
+ /sys/devices/system/cpu/vulnerabilities/tsa
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
index 1302fd1b55e8..6dba18dbb9ab 100644
--- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@@ -157,9 +157,7 @@ This is achieved by using the otherwise unused and obsolete VERW instruction in
combination with a microcode update. The microcode clears the affected CPU
buffers when the VERW instruction is executed.
-Kernel reuses the MDS function to invoke the buffer clearing:
-
- mds_clear_cpu_buffers()
+Kernel does the buffer clearing with x86_clear_cpu_buffers().
On MDS affected CPUs, the kernel already invokes CPU buffer clear on
kernel/userspace, hypervisor/guest and C-state (idle) transitions. No
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1f2c0874da9..07e22ba5bfe3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7488,6 +7488,19 @@
having this key zero'ed is acceptable. E.g. in testing
scenarios.
+ tsa= [X86] Control mitigation for Transient Scheduler
+ Attacks on AMD CPUs. Search the following in your
+ favourite search engine for more details:
+
+ "Technical guidance for mitigating transient scheduler
+ attacks".
+
+ off - disable the mitigation
+ on - enable the mitigation (default)
+ user - mitigate only user/kernel transitions
+ vm - mitigate only guest/host transitions
+
+
tsc= Disable clocksource stability checks for TSC.
Format: <string>
[x86] reliable: mark tsc clocksource as reliable, this
diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst
index 5a2e6c0ef04a..3518671e1a85 100644
--- a/Documentation/arch/x86/mds.rst
+++ b/Documentation/arch/x86/mds.rst
@@ -93,7 +93,7 @@ enters a C-state.
The kernel provides a function to invoke the buffer clearing:
- mds_clear_cpu_buffers()
+ x86_clear_cpu_buffers()
Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path.
Other than CFLAGS.ZF, this macro doesn't clobber any registers.
@@ -185,9 +185,9 @@ Mitigation points
idle clearing would be a window dressing exercise and is therefore not
activated.
- The invocation is controlled by the static key mds_idle_clear which is
- switched depending on the chosen mitigation mode and the SMT state of
- the system.
+ The invocation is controlled by the static key cpu_buf_idle_clear which is
+ switched depending on the chosen mitigation mode and the SMT state of the
+ system.
The buffer clear is only invoked before entering the C-State to prevent
that stale data from the idling CPU from spilling to the Hyper-Thread
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
index 7b6a2fde8175..19934d5c24e5 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
+++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
@@ -23,7 +23,7 @@ properties:
- allwinner,sun20i-d1-emac
- allwinner,sun50i-h6-emac
- allwinner,sun50i-h616-emac0
- - allwinner,sun55i-a523-emac0
+ - allwinner,sun55i-a523-gmac0
- const: allwinner,sun50i-a64-emac
reg:
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9abf93ee5f65..43ed57e048a8 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7196,6 +7196,10 @@ The valid value for 'flags' is:
u64 leaf;
u64 r11, r12, r13, r14;
} get_tdvmcall_info;
+ struct {
+ u64 ret;
+ u64 vector;
+ } setup_event_notify;
};
} tdx;
@@ -7210,21 +7214,24 @@ number from register R11. The remaining field of the union provide the
inputs and outputs of the TDVMCALL. Currently the following values of
``nr`` are defined:
-* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
-signed by a service hosting TD-Quoting Enclave operating on the host.
-Parameters and return value are in the ``get_quote`` field of the union.
-The ``gpa`` field and ``size`` specify the guest physical address
-(without the shared bit set) and the size of a shared-memory buffer, in
-which the TDX guest passes a TD Report. The ``ret`` field represents
-the return value of the GetQuote request. When the request has been
-queued successfully, the TDX guest can poll the status field in the
-shared-memory area to check whether the Quote generation is completed or
-not. When completed, the generated Quote is returned via the same buffer.
-
-* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
-status of TDVMCALLs. The output values for the given leaf should be
-placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
-field of the union.
+ * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+ signed by a service hosting TD-Quoting Enclave operating on the host.
+ Parameters and return value are in the ``get_quote`` field of the union.
+ The ``gpa`` field and ``size`` specify the guest physical address
+ (without the shared bit set) and the size of a shared-memory buffer, in
+ which the TDX guest passes a TD Report. The ``ret`` field represents
+ the return value of the GetQuote request. When the request has been
+ queued successfully, the TDX guest can poll the status field in the
+ shared-memory area to check whether the Quote generation is completed or
+ not. When completed, the generated Quote is returned via the same buffer.
+
+ * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+ status of TDVMCALLs. The output values for the given leaf should be
+ placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+ field of the union.
+
+* ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to
+set up a notification interrupt for vector ``vector``.
KVM may add support for more values in the future that may cause a userspace
exit, even without calls to ``KVM_ENABLE_CAP`` or similar. In this case,
diff --git a/Documentation/virt/kvm/x86/intel-tdx.rst b/Documentation/virt/kvm/x86/intel-tdx.rst
index 76bdd95334d6..5efac62c92c7 100644
--- a/Documentation/virt/kvm/x86/intel-tdx.rst
+++ b/Documentation/virt/kvm/x86/intel-tdx.rst
@@ -79,7 +79,20 @@ to be configured to the TDX guest.
struct kvm_tdx_capabilities {
__u64 supported_attrs;
__u64 supported_xfam;
- __u64 reserved[254];
+
+ /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to
+ * userspace, respectively
+ */
+ __u64 kernel_tdvmcallinfo_1_r11;
+ __u64 user_tdvmcallinfo_1_r11;
+
+ /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel
+ * and forwarded to userspace, respectively
+ */
+ __u64 kernel_tdvmcallinfo_1_r12;
+ __u64 user_tdvmcallinfo_1_r12;
+
+ __u64 reserved[250];
/* Configurable CPUID bits for userspace */
struct kvm_cpuid2 cpuid;
diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..60eba51d8839 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4181,6 +4181,7 @@ F: include/linux/cpumask_types.h
F: include/linux/find.h
F: include/linux/nodemask.h
F: include/linux/nodemask_types.h
+F: include/uapi/linux/bits.h
F: include/vdso/bits.h
F: lib/bitmap-str.c
F: lib/bitmap.c
@@ -4193,6 +4194,7 @@ F: tools/include/linux/bitfield.h
F: tools/include/linux/bitmap.h
F: tools/include/linux/bits.h
F: tools/include/linux/find.h
+F: tools/include/uapi/linux/bits.h
F: tools/include/vdso/bits.h
F: tools/lib/bitmap.c
F: tools/lib/find_bit.c
@@ -16822,8 +16824,8 @@ F: include/dt-bindings/clock/mobileye,eyeq5-clk.h
MODULE SUPPORT
M: Luis Chamberlain <mcgrof@kernel.org>
M: Petr Pavlu <petr.pavlu@suse.com>
+M: Daniel Gomez <da.gomez@kernel.org>
R: Sami Tolvanen <samitolvanen@google.com>
-R: Daniel Gomez <da.gomez@samsung.com>
L: linux-modules@vger.kernel.org
L: linux-kernel@vger.kernel.org
S: Maintained
@@ -17222,10 +17224,10 @@ F: drivers/rtc/rtc-ntxec.c
F: include/linux/mfd/ntxec.h
NETRONOME ETHERNET DRIVERS
-M: Louis Peens <louis.peens@corigine.com>
R: Jakub Kicinski <kuba@kernel.org>
+R: Simon Horman <horms@kernel.org>
L: oss-drivers@corigine.com
-S: Maintained
+S: Odd Fixes
F: drivers/net/ethernet/netronome/
NETWORK BLOCK DEVICE (NBD)
@@ -19601,8 +19603,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git
F: drivers/pinctrl/intel/
PIN CONTROLLER - KEEMBAY
-M: Lakshmi Sowjanya D <lakshmi.sowjanya.d@intel.com>
-S: Supported
+S: Orphan
F: drivers/pinctrl/pinctrl-keembay*
PIN CONTROLLER - MEDIATEK
@@ -20155,21 +20156,15 @@ S: Supported
F: Documentation/devicetree/bindings/soc/qcom/qcom,apr*
F: Documentation/devicetree/bindings/sound/qcom,*
F: drivers/soc/qcom/apr.c
-F: include/dt-bindings/sound/qcom,wcd9335.h
-F: include/dt-bindings/sound/qcom,wcd934x.h
-F: sound/soc/codecs/lpass-rx-macro.*
-F: sound/soc/codecs/lpass-tx-macro.*
-F: sound/soc/codecs/lpass-va-macro.c
-F: sound/soc/codecs/lpass-wsa-macro.*
+F: drivers/soundwire/qcom.c
+F: include/dt-bindings/sound/qcom,wcd93*
+F: sound/soc/codecs/lpass-*.*
F: sound/soc/codecs/msm8916-wcd-analog.c
F: sound/soc/codecs/msm8916-wcd-digital.c
F: sound/soc/codecs/wcd-clsh-v2.*
F: sound/soc/codecs/wcd-mbhc-v2.*
-F: sound/soc/codecs/wcd9335.*
-F: sound/soc/codecs/wcd934x.c
-F: sound/soc/codecs/wsa881x.c
-F: sound/soc/codecs/wsa883x.c
-F: sound/soc/codecs/wsa884x.c
+F: sound/soc/codecs/wcd93*.*
+F: sound/soc/codecs/wsa88*.*
F: sound/soc/qcom/
QCOM EMBEDDED USB DEBUGGER (EUD)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 55fc331af337..393d71124f5d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -256,6 +256,7 @@ config ARM64
select HOTPLUG_SMT if HOTPLUG_CPU
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
+ select JUMP_LABEL
select KASAN_VMALLOC if KASAN
select LOCK_MM_AND_FIND_VMA
select MODULES_USE_ELF_RELA
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index ba5df0df02a4..9f38340d24c2 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -287,17 +287,6 @@
.Lskip_fgt2_\@:
.endm
-.macro __init_el2_gcs
- mrs_s x1, SYS_ID_AA64PFR1_EL1
- ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
- cbz x1, .Lskip_gcs_\@
-
- /* Ensure GCS is not enabled when we start trying to do BLs */
- msr_s SYS_GCSCR_EL1, xzr
- msr_s SYS_GCSCRE0_EL1, xzr
-.Lskip_gcs_\@:
-.endm
-
/**
* Initialize EL2 registers to sane values. This should be called early on all
* cores that were booted in EL2. Note that everything gets initialised as
@@ -319,7 +308,6 @@
__init_el2_cptr
__init_el2_fgt
__init_el2_fgt2
- __init_el2_gcs
.endm
#ifndef __KVM_NVHE_HYPERVISOR__
@@ -371,6 +359,13 @@
msr_s SYS_MPAMHCR_EL2, xzr // clear TRAP_MPAMIDR_EL1 -> EL2
.Lskip_mpam_\@:
+ check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2
+
+.Linit_gcs_\@:
+ msr_s SYS_GCSCR_EL1, xzr
+ msr_s SYS_GCSCRE0_EL1, xzr
+
+.Lskip_gcs_\@:
check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
.Linit_sve_\@: /* SVE register access */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d27079968341..3e41a880b062 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1480,7 +1480,6 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
struct reg_mask_range *range);
/* Guest/host FPSIMD coordination helpers */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2920b0a51403..a2faf0049dab 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -34,7 +34,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
cpufeature.o alternative.o cacheinfo.o \
smp.o smp_spin_table.o topology.o smccc-call.o \
syscall.o proton-pack.o idle.o patching.o pi/ \
- rsi.o
+ rsi.o jump_label.o
obj-$(CONFIG_COMPAT) += sys32.o signal32.o \
sys_compat.o
@@ -47,7 +47,6 @@ obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o
obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_CPU_PM) += sleep.o suspend.o
-obj-$(CONFIG_JUMP_LABEL) += jump_label.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_EFI) += efi.o efi-rt-wrapper.o
obj-$(CONFIG_PCI) += pci.o
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b34044e20128..e151585c6cca 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -3135,6 +3135,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
}
#endif
+#ifdef CONFIG_ARM64_SME
+static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+ return system_supports_sme() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
@@ -3223,31 +3230,31 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
#ifdef CONFIG_ARM64_SME
HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
- HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
- HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
- HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
- HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
- HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
- HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
- HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
+ HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
#endif /* CONFIG_ARM64_SME */
HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 3857fd7ee8d4..62230d6dd919 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -15,6 +15,7 @@
#include <asm/efi.h>
#include <asm/stacktrace.h>
+#include <asm/vmap_stack.h>
static bool region_is_misaligned(const efi_memory_desc_t *md)
{
@@ -214,9 +215,13 @@ static int __init arm64_efi_rt_init(void)
if (!efi_enabled(EFI_RUNTIME_SERVICES))
return 0;
- p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL,
- NUMA_NO_NODE, &&l);
-l: if (!p) {
+ if (!IS_ENABLED(CONFIG_VMAP_STACK)) {
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ return -ENOMEM;
+ }
+
+ p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE);
+ if (!p) {
pr_warn("Failed to allocate EFI runtime stack\n");
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return -ENOMEM;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 5954cec19660..08b7042a2e2d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -673,6 +673,11 @@ static void permission_overlay_switch(struct task_struct *next)
current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
if (current->thread.por_el0 != next->thread.por_el0) {
write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+ /*
+ * No ISB required as we can tolerate spurious Overlay faults -
+ * the fault handler will check again based on the new value
+ * of POR_EL0.
+ */
}
}
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 3b3f6b56e733..21a795303568 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1143,7 +1143,7 @@ static inline unsigned int num_other_online_cpus(void)
void smp_send_stop(void)
{
static unsigned long stop_in_progress;
- cpumask_t mask;
+ static cpumask_t mask;
unsigned long timeout;
/*
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 38a91bb5d4c7..23dd3f3fc3eb 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -825,10 +825,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
if (!kvm_arm_vcpu_is_finalized(vcpu))
return -EPERM;
- ret = kvm_arch_vcpu_run_map_fp(vcpu);
- if (ret)
- return ret;
-
if (likely(vcpu_has_run_once(vcpu)))
return 0;
@@ -2129,7 +2125,7 @@ static void cpu_hyp_init(void *discard)
static void cpu_hyp_uninit(void *discard)
{
- if (__this_cpu_read(kvm_hyp_initialized)) {
+ if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {
cpu_hyp_reset();
__this_cpu_write(kvm_hyp_initialized, 0);
}
@@ -2345,8 +2341,13 @@ static void __init teardown_hyp_mode(void)
free_hyp_pgds();
for_each_possible_cpu(cpu) {
+ if (per_cpu(kvm_hyp_initialized, cpu))
+ continue;
+
free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
- free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+ if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])
+ continue;
if (free_sve) {
struct cpu_sve_state *sve_state;
@@ -2354,6 +2355,9 @@ static void __init teardown_hyp_mode(void)
sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
}
+
+ free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
}
}
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 8f6c8f57c6b9..15e17aca1dec 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -15,32 +15,6 @@
#include <asm/sysreg.h>
/*
- * Called on entry to KVM_RUN unless this vcpu previously ran at least
- * once and the most recent prior KVM_RUN for this vcpu was called from
- * the same task as current (highly likely).
- *
- * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
- * such that on entering hyp the relevant parts of current are already
- * mapped.
- */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
-{
- struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;
- int ret;
-
- /* pKVM has its own tracking of the host fpsimd state. */
- if (is_protected_kvm_enabled())
- return 0;
-
- /* Make sure the host task fpsimd state is visible to hyp: */
- ret = kvm_share_hyp(fpsimd, fpsimd + 1);
- if (ret)
- return ret;
-
- return 0;
-}
-
-/*
* Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
* The actual loading is done by the FPSIMD access trap taken to hyp.
*
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 95d7534c9679..8957734d6183 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -479,6 +479,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
{
struct kvm_mem_range cur;
kvm_pte_t pte;
+ u64 granule;
s8 level;
int ret;
@@ -496,18 +497,21 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
return -EPERM;
}
- do {
- u64 granule = kvm_granule_size(level);
+ for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) {
+ if (!kvm_level_supports_block_mapping(level))
+ continue;
+ granule = kvm_granule_size(level);
cur.start = ALIGN_DOWN(addr, granule);
cur.end = cur.start + granule;
- level++;
- } while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
- !(kvm_level_supports_block_mapping(level) &&
- range_included(&cur, range)));
+ if (!range_included(&cur, range))
+ continue;
+ *range = cur;
+ return 0;
+ }
- *range = cur;
+ WARN_ON(1);
- return 0;
+ return -EINVAL;
}
int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 5b191f4dc566..dc1d26559bfa 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1402,6 +1402,21 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
}
}
+#define has_tgran_2(__r, __sz) \
+ ({ \
+ u64 _s1, _s2, _mmfr0 = __r; \
+ \
+ _s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \
+ TGRAN##__sz##_2, _mmfr0); \
+ \
+ _s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \
+ TGRAN##__sz, _mmfr0); \
+ \
+ ((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI && \
+ _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \
+ (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \
+ _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI)); \
+ })
/*
* Our emulated CPU doesn't support all the possible features. For the
* sake of simplicity (and probably mental sanity), wipe out a number
@@ -1411,6 +1426,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
*/
u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
{
+ u64 orig_val = val;
+
switch (reg) {
case SYS_ID_AA64ISAR0_EL1:
/* Support everything but TME */
@@ -1480,13 +1497,16 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
*/
switch (PAGE_SIZE) {
case SZ_4K:
- val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
+ if (has_tgran_2(orig_val, 4))
+ val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
fallthrough;
case SZ_16K:
- val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
+ if (has_tgran_2(orig_val, 16))
+ val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
fallthrough;
case SZ_64K:
- val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
+ if (has_tgran_2(orig_val, 64))
+ val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
break;
}
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index a50fb7e6841f..679aafe77de2 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -401,9 +401,7 @@ void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
{
bool level;
- level = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
- if (level)
- level &= vgic_v3_get_misr(vcpu);
+ level = (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En) && vgic_v3_get_misr(vcpu);
kvm_vgic_inject_irq(vcpu->kvm, vcpu,
vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index ec0a337891dd..11eb8d1adc84 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr,
}
}
-static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
- unsigned int mm_flags)
+static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags)
{
- unsigned long iss2 = ESR_ELx_ISS2(esr);
-
if (!system_supports_poe())
return false;
- if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay))
- return true;
-
+ /*
+ * We do not check whether an Overlay fault has occurred because we
+ * cannot make a decision based solely on its value:
+ *
+ * - If Overlay is set, a fault did occur due to POE, but it may be
+ * spurious in those cases where we update POR_EL0 without ISB (e.g.
+ * on context-switch). We would then need to manually check POR_EL0
+ * against vma_pkey(vma), which is exactly what
+ * arch_vma_access_permitted() does.
+ *
+ * - If Overlay is not set, we may still need to report a pkey fault.
+ * This is the case if an access was made within a mapping but with no
+ * page mapped, and POR_EL0 forbids the access (according to
+ * vma_pkey()). Such access will result in a SIGSEGV regardless
+ * because core code checks arch_vma_access_permitted(), but in order
+ * to report the correct error code - SEGV_PKUERR - we must handle
+ * that case here.
+ */
return !arch_vma_access_permitted(vma,
mm_flags & FAULT_FLAG_WRITE,
mm_flags & FAULT_FLAG_INSTRUCTION,
@@ -635,7 +647,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
goto bad_area;
}
- if (fault_from_pkey(esr, vma, mm_flags)) {
+ if (fault_from_pkey(vma, mm_flags)) {
pkey = vma_pkey(vma);
vma_end_read(vma);
fault = 0;
@@ -679,7 +691,7 @@ retry:
goto bad_area;
}
- if (fault_from_pkey(esr, vma, mm_flags)) {
+ if (fault_from_pkey(vma, mm_flags)) {
pkey = vma_pkey(vma);
mmap_read_unlock(mm);
fault = 0;
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 80d470aa469d..54dccfd6aa11 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -518,7 +518,6 @@ alternative_else_nop_endif
msr REG_PIR_EL1, x0
orr tcr2, tcr2, TCR2_EL1_PIE
- msr REG_TCR2_EL1, x0
.Lskip_indirection:
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index d229cbd2ba22..9b0d55be1239 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -38,6 +38,7 @@ static int s390_sha1_init(struct shash_desc *desc)
sctx->state[4] = SHA1_H4;
sctx->count = 0;
sctx->func = CPACF_KIMD_SHA_1;
+ sctx->first_message_part = 0;
return 0;
}
@@ -60,6 +61,7 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in)
sctx->count = ictx->count;
memcpy(sctx->state, ictx->state, sizeof(ictx->state));
sctx->func = CPACF_KIMD_SHA_1;
+ sctx->first_message_part = 0;
return 0;
}
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 33711a29618c..6cbbf5e8555f 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -32,6 +32,7 @@ static int sha512_init(struct shash_desc *desc)
ctx->count = 0;
ctx->sha512.count_hi = 0;
ctx->func = CPACF_KIMD_SHA_512;
+ ctx->first_message_part = 0;
return 0;
}
@@ -57,6 +58,7 @@ static int sha512_import(struct shash_desc *desc, const void *in)
memcpy(sctx->state, ictx->state, sizeof(ictx->state));
sctx->func = CPACF_KIMD_SHA_512;
+ sctx->first_message_part = 0;
return 0;
}
@@ -97,6 +99,7 @@ static int sha384_init(struct shash_desc *desc)
ctx->count = 0;
ctx->sha512.count_hi = 0;
ctx->func = CPACF_KIMD_SHA_512;
+ ctx->first_message_part = 0;
return 0;
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 71019b3b54ea..5b3362af7d65 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2695,6 +2695,15 @@ config MITIGATION_ITS
disabled, mitigation cannot be enabled via cmdline.
See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+config MITIGATION_TSA
+ bool "Mitigate Transient Scheduler Attacks"
+ depends on CPU_SUP_AMD
+ default y
+ help
+ Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+ security vulnerability on AMD CPUs which can lead to forwarding of
+ invalid info to subsequent instructions and thus can affect their
+ timing and thereby cause a leakage.
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 175958b02f2b..8e9a0cc20a4a 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb);
/*
* Define the VERW operand that is disguised as entry code so that
- * it can be referenced with KPTI enabled. This ensure VERW can be
+ * it can be referenced with KPTI enabled. This ensures VERW can be
* used late in exit-to-user path after page tables are switched.
*/
.pushsection .entry.text, "ax"
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_START_NOALIGN(mds_verw_sel)
+SYM_CODE_START_NOALIGN(x86_verw_sel)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
.word __KERNEL_DS
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_END(mds_verw_sel);
+SYM_CODE_END(x86_verw_sel);
/* For KVM */
-EXPORT_SYMBOL_GPL(mds_verw_sel);
+EXPORT_SYMBOL_GPL(x86_verw_sel);
.popsection
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index ee176236c2be..286d509f9363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -456,6 +456,7 @@
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */
#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
@@ -487,6 +488,9 @@
#define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */
#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */
#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */
/*
* BUG word(s)
@@ -542,5 +546,5 @@
#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9a9b21b78905..b30e5474c18e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void)
static __always_inline void native_safe_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("sti; hlt": : :"memory");
}
static __always_inline void native_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("hlt": : :"memory");
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 639d9bcee842..f7af967aa16f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -700,8 +700,13 @@ struct kvm_vcpu_hv {
struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
- /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ /*
+ * Preallocated buffers for handling hypercalls that pass sparse vCPU
+ * sets (for high vCPU counts, they're too large to comfortably fit on
+ * the stack).
+ */
u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+ DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct hv_vp_assist_page vp_assist_page;
@@ -764,6 +769,7 @@ enum kvm_only_cpuid_leafs {
CPUID_8000_0022_EAX,
CPUID_7_2_EDX,
CPUID_24_0_EBX,
+ CPUID_8000_0021_ECX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index dd2b129b0418..6ca6516c7492 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,8 +43,6 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
static __always_inline void __mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
-
/*
* Use the instruction mnemonic with implicit operands, as the LLVM
* assembler fails to assemble the mnemonic with explicit operands:
@@ -80,7 +78,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx)
*/
static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
{
- /* No MDS buffer clear as this is AMD/HYGON only */
+ /* No need for TSA buffer clearing on AMD */
/* "mwaitx %eax, %ebx, %ecx" */
asm volatile(".byte 0x0f, 0x01, 0xfb"
@@ -98,7 +96,6 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
*/
static __always_inline void __sti_mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
}
@@ -115,21 +112,29 @@ static __always_inline void __sti_mwait(u32 eax, u32 ecx)
*/
static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
const void *addr = &current_thread_info()->flags;
alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
__monitor(addr, 0, 0);
- if (!need_resched()) {
- if (ecx & 1) {
- __mwait(eax, ecx);
- } else {
- __sti_mwait(eax, ecx);
- raw_local_irq_disable();
- }
+ if (need_resched())
+ goto out;
+
+ if (ecx & 1) {
+ __mwait(eax, ecx);
+ } else {
+ __sti_mwait(eax, ecx);
+ raw_local_irq_disable();
}
}
+
+out:
current_clr_polling();
}
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 20d754b98f3f..10f261678749 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -302,25 +302,31 @@
.endm
/*
- * Macro to execute VERW instruction that mitigate transient data sampling
- * attacks such as MDS. On affected systems a microcode update overloaded VERW
- * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- *
+ * Macro to execute VERW insns that mitigate transient data sampling
+ * attacks such as MDS or TSA. On affected systems a microcode update
+ * overloaded VERW insns to also clear the CPU buffers. VERW clobbers
+ * CFLAGS.ZF.
* Note: Only the memory operand variant of VERW clears the CPU buffers.
*/
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
#ifdef CONFIG_X86_64
- ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
#else
/*
* In 32bit mode, the memory operand must be a %cs reference. The data
* segments may not be usable (vm86 mode), and the stack segment may not
* be flat (ESPFIX32).
*/
- ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
#endif
.endm
+#define CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
#ifdef CONFIG_X86_64
.macro CLEAR_BRANCH_HISTORY
ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
@@ -567,24 +573,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
-DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
-extern u16 mds_verw_sel;
+extern u16 x86_verw_sel;
#include <asm/segment.h>
/**
- * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
+ * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns
*
* This uses the otherwise unused and obsolete VERW instruction in
* combination with microcode which triggers a CPU buffer flush when the
* instruction is executed.
*/
-static __always_inline void mds_clear_cpu_buffers(void)
+static __always_inline void x86_clear_cpu_buffers(void)
{
static const u16 ds = __KERNEL_DS;
@@ -601,14 +607,15 @@ static __always_inline void mds_clear_cpu_buffers(void)
}
/**
- * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
+ * and TSA vulnerabilities.
*
* Clear CPU buffers if the corresponding static key is enabled
*/
-static __always_inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void x86_idle_clear_cpu_buffers(void)
{
- if (static_branch_likely(&mds_idle_clear))
- mds_clear_cpu_buffers();
+ if (static_branch_likely(&cpu_buf_idle_clear))
+ x86_clear_cpu_buffers();
}
#endif /* __ASSEMBLER__ */
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index d8525e6ef50a..8bc074c8d7c6 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -72,6 +72,7 @@
#define TDVMCALL_MAP_GPA 0x10001
#define TDVMCALL_GET_QUOTE 0x10002
#define TDVMCALL_REPORT_FATAL_ERROR 0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
/*
* TDG.VP.VMCALL Status Codes (returned in R10)
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 6f3499507c5e..0f15d683817d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
struct kvm_tdx_capabilities {
__u64 supported_attrs;
__u64 supported_xfam;
- __u64 reserved[254];
+
+ __u64 kernel_tdvmcallinfo_1_r11;
+ __u64 user_tdvmcallinfo_1_r11;
+ __u64 kernel_tdvmcallinfo_1_r12;
+ __u64 user_tdvmcallinfo_1_r12;
+
+ __u64 reserved[250];
/* Configurable CPUID bits for userspace */
struct kvm_cpuid2 cpuid;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 655f44f89ded..b750ac008b78 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
#endif
}
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+ step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+ {},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return;
+
+ if (cpu_has(c, X86_FEATURE_ZEN3) ||
+ cpu_has(c, X86_FEATURE_ZEN4)) {
+ if (x86_match_min_microcode_rev(amd_tsa_microcode))
+ setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+ else
+ pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+ } else {
+ setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+ setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+ }
+}
+
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
bsp_determine_snp(c);
+
+ tsa_init(c);
+
return;
warn:
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7f94e6a5497d..f4d3abb12317 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void);
static void __init its_select_mitigation(void);
static void __init its_update_mitigation(void);
static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -169,9 +171,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
-/* Control MDS CPU buffer clear before idling (halt, mwait) */
-DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
-EXPORT_SYMBOL_GPL(mds_idle_clear);
+/* Control CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_idle_clear);
/*
* Controls whether l1d flush based mitigations are enabled,
@@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void)
gds_select_mitigation();
its_select_mitigation();
bhi_select_mitigation();
+ tsa_select_mitigation();
/*
* After mitigations are selected, some may need to update their
@@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void)
gds_apply_mitigation();
its_apply_mitigation();
bhi_apply_mitigation();
+ tsa_apply_mitigation();
}
/*
@@ -637,7 +641,7 @@ static void __init mmio_apply_mitigation(void)
* is required irrespective of SMT state.
*/
if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
if (mmio_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
@@ -1488,6 +1492,94 @@ static void __init its_apply_mitigation(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+ TSA_MITIGATION_NONE,
+ TSA_MITIGATION_AUTO,
+ TSA_MITIGATION_UCODE_NEEDED,
+ TSA_MITIGATION_USER_KERNEL,
+ TSA_MITIGATION_VM,
+ TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+ [TSA_MITIGATION_NONE] = "Vulnerable",
+ [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
+ [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary",
+ [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM",
+ [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ else if (!strcmp(str, "on"))
+ tsa_mitigation = TSA_MITIGATION_FULL;
+ else if (!strcmp(str, "user"))
+ tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+ else if (!strcmp(str, "vm"))
+ tsa_mitigation = TSA_MITIGATION_VM;
+ else
+ pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+ return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+ if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) {
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ return;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_NONE)
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) {
+ tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+ goto out;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_AUTO)
+ tsa_mitigation = TSA_MITIGATION_FULL;
+
+ /*
+ * No need to set verw_clear_cpu_buf_mitigation_selected - it
+ * doesn't fit all cases here and it is not needed because this
+ * is the only VERW-based mitigation on AMD.
+ */
+out:
+ pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ break;
+ case TSA_MITIGATION_VM:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ case TSA_MITIGATION_FULL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ default:
+ break;
+ }
+}
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
@@ -2249,10 +2341,10 @@ static void update_mds_branch_idle(void)
return;
if (sched_smt_active()) {
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
- static_branch_disable(&mds_idle_clear);
+ static_branch_disable(&cpu_buf_idle_clear);
}
}
@@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void)
break;
}
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ case TSA_MITIGATION_VM:
+ case TSA_MITIGATION_AUTO:
+ case TSA_MITIGATION_FULL:
+ /*
+ * TSA-SQ can potentially lead to info leakage between
+ * SMT threads.
+ */
+ if (sched_smt_active())
+ static_branch_enable(&cpu_buf_idle_clear);
+ else
+ static_branch_disable(&cpu_buf_idle_clear);
+ break;
+ case TSA_MITIGATION_NONE:
+ case TSA_MITIGATION_UCODE_NEEDED:
+ break;
+ }
+
mutex_unlock(&spec_ctrl_mutex);
}
@@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
}
+static ssize_t tsa_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
@@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_ITS:
return its_show_state(buf);
+ case X86_BUG_TSA:
+ return tsa_show_state(buf);
+
default:
break;
}
@@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att
{
return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
}
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 27125e009847..fb50c1dd53ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define ITS BIT(8)
/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
#define ITS_NATIVE_ONLY BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA BIT(10)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
@@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
- VULNBL_AMD(0x19, SRSO),
+ VULNBL_AMD(0x19, SRSO | TSA),
VULNBL_AMD(0x1a, SRSO),
{}
};
@@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
}
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+ !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+ if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+ /* Enable bug on Zen guests to allow for live migration. */
+ (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+ setup_force_cpu_bug(X86_BUG_TSA);
+ }
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
index 2a1655b1fdd8..1fd349cfc802 100644
--- a/arch/x86/kernel/cpu/microcode/amd_shas.c
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = {
0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
}
},
+ { 0xa0011d7, {
+ 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b,
+ 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12,
+ 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2,
+ 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36,
+ }
+ },
{ 0xa001223, {
0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
@@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = {
0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
}
},
+ { 0xa00123b, {
+ 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2,
+ 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3,
+ 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28,
+ 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72,
+ }
+ },
{ 0xa00820c, {
0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
@@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = {
0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
}
},
+ { 0xa00820d, {
+ 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4,
+ 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca,
+ 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1,
+ 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7,
+ }
+ },
{ 0xa10113e, {
0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
@@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = {
0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
}
},
+ { 0xa10114c, {
+ 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64,
+ 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74,
+ 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a,
+ 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0,
+ }
+ },
{ 0xa10123e, {
0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
@@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = {
0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
}
},
+ { 0xa10124c, {
+ 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90,
+ 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46,
+ 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc,
+ 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2,
+ }
+ },
{ 0xa108108, {
0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
@@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = {
0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
}
},
+ { 0xa108109, {
+ 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa,
+ 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b,
+ 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35,
+ 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59,
+ }
+ },
{ 0xa20102d, {
0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
@@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = {
0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
}
},
+ { 0xa20102e, {
+ 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd,
+ 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6,
+ 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5,
+ 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe,
+ }
+ },
{ 0xa201210, {
0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
@@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = {
0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
}
},
+ { 0xa201211, {
+ 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95,
+ 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27,
+ 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff,
+ 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27,
+ }
+ },
{ 0xa404107, {
0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
@@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = {
0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
}
},
+ { 0xa404108, {
+ 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc,
+ 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb,
+ 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19,
+ 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00,
+ }
+ },
{ 0xa500011, {
0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
@@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = {
0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
}
},
+ { 0xa500012, {
+ 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4,
+ 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16,
+ 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f,
+ 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63,
+ }
+ },
{ 0xa601209, {
0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
@@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = {
0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
}
},
+ { 0xa60120a, {
+ 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d,
+ 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b,
+ 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d,
+ 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c,
+ }
+ },
{ 0xa704107, {
0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
@@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = {
0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
}
},
+ { 0xa704108, {
+ 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93,
+ 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98,
+ 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49,
+ 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a,
+ }
+ },
{ 0xa705206, {
0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
@@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = {
0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
}
},
+ { 0xa705208, {
+ 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19,
+ 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2,
+ 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11,
+ 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff,
+ }
+ },
{ 0xa708007, {
0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
@@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = {
0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
}
},
+ { 0xa708008, {
+ 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46,
+ 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab,
+ 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16,
+ 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b,
+ }
+ },
{ 0xa70c005, {
0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
@@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = {
0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
}
},
+ { 0xa70c008, {
+ 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21,
+ 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e,
+ 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66,
+ 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0,
+ }
+ },
{ 0xaa00116, {
0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
@@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = {
0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
}
},
+ { 0xaa00216, {
+ 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5,
+ 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08,
+ 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2,
+ 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1,
+ }
+ },
};
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbf6d71bdf18..b4a1f6732a3a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -50,6 +50,8 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
+ { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 },
+ { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 },
{ X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 704883c21f3a..a838be04f874 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -907,16 +907,24 @@ static __init bool prefer_mwait_c1_over_halt(void)
*/
static __cpuidle void mwait_idle(void)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (!current_set_polling_and_test()) {
const void *addr = &current_thread_info()->flags;
alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
__monitor(addr, 0, 0);
- if (!need_resched()) {
- __sti_mwait(0, 0);
- raw_local_irq_disable();
- }
+ if (need_resched())
+ goto out;
+
+ __sti_mwait(0, 0);
+ raw_local_irq_disable();
}
+
+out:
__current_clr_polling();
}
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b2d006756e02..f84bc0569c9c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1165,6 +1165,8 @@ void kvm_set_cpu_caps(void)
*/
SYNTHESIZED_F(LFENCE_RDTSC),
/* SmmPgCfgLock */
+ /* 4: Resv */
+ SYNTHESIZED_F(VERW_CLEAR),
F(NULL_SEL_CLR_BASE),
/* UpperAddressIgnore */
F(AUTOIBRS),
@@ -1179,6 +1181,11 @@ void kvm_set_cpu_caps(void)
F(SRSO_USER_KERNEL_NO),
);
+ kvm_cpu_cap_init(CPUID_8000_0021_ECX,
+ SYNTHESIZED_F(TSA_SQ_NO),
+ SYNTHESIZED_F(TSA_L1_NO),
+ );
+
kvm_cpu_cap_init(CPUID_8000_0022_EAX,
F(PERFMON_V2),
);
@@ -1748,8 +1755,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x80000021:
- entry->ebx = entry->ecx = entry->edx = 0;
+ entry->ebx = entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0021_EAX);
+ cpuid_entry_override(entry, CPUID_8000_0021_ECX);
break;
/* AMD Extended Performance Monitoring and Debug */
case 0x80000022: {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..ee27064dd72f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1979,6 +1979,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
goto out_flush_all;
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
/*
* Lower 12 bits of 'address' encode the number of additional
* pages to flush.
@@ -2001,11 +2004,11 @@ out_flush_all:
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
/*
* Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index fde0ae986003..c53b92379e6e 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,6 +52,10 @@
/* CPUID level 0x80000022 (EAX) */
#define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0)
+/* CPUID level 0x80000021 (ECX) */
+#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1)
+#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2)
+
struct cpuid_reg {
u32 function;
u32 index;
@@ -82,6 +86,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
[CPUID_7_2_EDX] = { 7, 2, CPUID_EDX},
[CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX},
+ [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX},
};
/*
@@ -121,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO);
+ KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 459c3b791fd4..b201f77fcd49 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
struct kvm_vcpu *src_vcpu;
unsigned long i;
+ if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+ dst->created_vcpus != atomic_read(&dst->online_vcpus))
+ return -EBUSY;
+
if (!sev_es_guest(src))
return 0;
@@ -4445,8 +4449,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
- svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (!svm->sev_es.snp_has_guest_vmsa) {
+ if (svm->sev_es.vmsa)
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ else
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+ }
if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 0c61153b275f..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run)
#endif
mov VCPU_RDI(%_ASM_DI), %_ASM_DI
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
3: vmrun %_ASM_AX
4:
@@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
mov SVM_current_vmcb(%rdi), %rax
mov KVM_VMCB_pa(%rax), %rax
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
1: vmrun %rax
2:
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 1ad20c273f3b..f31ccdeb905b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,6 +173,9 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
tdx_clear_unsupported_cpuid(entry);
}
+#define TDVMCALLINFO_GET_QUOTE BIT(0)
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1)
+
static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
struct kvm_tdx_capabilities *caps)
{
@@ -188,6 +191,10 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
caps->cpuid.nent = td_conf->num_cpuid_config;
+ caps->user_tdvmcallinfo_1_r11 =
+ TDVMCALLINFO_GET_QUOTE |
+ TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
for (i = 0; i < td_conf->num_cpuid_config; i++)
td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
@@ -1530,6 +1537,27 @@ static int tdx_get_quote(struct kvm_vcpu *vcpu)
return 0;
}
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 vector = tdx->vp_enter_args.r12;
+
+ if (vector < 32 || vector > 255) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+ vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.setup_event_notify.vector = vector;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
static int handle_tdvmcall(struct kvm_vcpu *vcpu)
{
switch (tdvmcall_leaf(vcpu)) {
@@ -1541,6 +1569,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
return tdx_get_td_vm_call_info(vcpu);
case TDVMCALL_GET_QUOTE:
return tdx_get_quote(vcpu);
+ case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+ return tdx_setup_event_notify_interrupt(vcpu);
default:
break;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4953846cb30d..191a9ed0da22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7291,7 +7291,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vmx_l1d_flush(vcpu);
else if (static_branch_unlikely(&cpu_buf_vm_clear) &&
kvm_arch_has_assigned_device(vcpu->kvm))
- mds_clear_cpu_buffers();
+ x86_clear_cpu_buffers();
vmx_disable_fb_clear(vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a9d992d5652f..357b9e3a6cef 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,9 +3258,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
/* With all the info we got, fill in the values */
- if (kvm_caps.has_tsc_control)
+ if (kvm_caps.has_tsc_control) {
tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
v->arch.l1_tsc_scaling_ratio);
+ tgt_tsc_khz = tgt_tsc_khz ? : 1;
+ }
if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9b029bb29a16..5fa2cca43653 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
{
struct kvm_vcpu *vcpu;
- if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
- return -EINVAL;
+ /*
+ * Don't check for the port being within range of max_evtchn_port().
+ * Userspace can configure what ever targets it likes; events just won't
+ * be delivered if/while the target is invalid, just like userspace can
+ * configure MSIs which target non-existent APICs.
+ *
+ * This allow on Live Migration and Live Update, the IRQ routing table
+ * can be restored *independently* of other things like creating vCPUs,
+ * without imposing an ordering dependency on userspace. In this
+ * particular case, the problematic ordering would be with setting the
+ * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+ * instead of 1024 event channels.
+ */
/* We only support 2 level event channels for now */
if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 7779ab0ca7ce..efc575a00edd 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -602,6 +602,7 @@ CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
CPU_SHOW_VULN_FALLBACK(ghostwrite);
CPU_SHOW_VULN_FALLBACK(old_microcode);
CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
+CPU_SHOW_VULN_FALLBACK(tsa);
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -620,6 +621,7 @@ static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling
static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL);
static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
+static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@@ -639,6 +641,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_ghostwrite.attr,
&dev_attr_old_microcode.attr,
&dev_attr_indirect_target_selection.attr,
+ &dev_attr_tsa.attr,
NULL
};
diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds
index c3a166675450..367907eb7d86 100644
--- a/drivers/firmware/efi/libstub/zboot.lds
+++ b/drivers/firmware/efi/libstub/zboot.lds
@@ -29,14 +29,12 @@ SECTIONS
. = _etext;
}
-#ifdef CONFIG_EFI_SBAT
.sbat : ALIGN(4096) {
_sbat = .;
*(.sbat)
_esbat = ALIGN(4096);
. = _esbat;
}
-#endif
.data : ALIGN(4096) {
_data = .;
@@ -60,6 +58,6 @@ SECTIONS
PROVIDE(__efistub__gzdata_size =
ABSOLUTE(__efistub__gzdata_end - __efistub__gzdata_start));
-PROVIDE(__data_rawsize = ABSOLUTE(_edata - _etext));
-PROVIDE(__data_size = ABSOLUTE(_end - _etext));
+PROVIDE(__data_rawsize = ABSOLUTE(_edata - _data));
+PROVIDE(__data_size = ABSOLUTE(_end - _data));
PROVIDE(__sbat_size = ABSOLUTE(_esbat - _sbat));
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 06dea3a13e77..9057180051df 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2984,6 +2984,7 @@ static int airoha_probe(struct platform_device *pdev)
error_napi_stop:
for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
airoha_qdma_stop_napi(&eth->qdma[i]);
+ airoha_ppe_deinit(eth);
error_hw_cleanup:
for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
airoha_hw_cleanup(&eth->qdma[i]);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ae89a981e052..243cb13cb01c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11607,11 +11607,9 @@ static void bnxt_free_irq(struct bnxt *bp)
static int bnxt_request_irq(struct bnxt *bp)
{
+ struct cpu_rmap *rmap = NULL;
int i, j, rc = 0;
unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
- struct cpu_rmap *rmap;
-#endif
rc = bnxt_setup_int_mode(bp);
if (rc) {
@@ -11632,15 +11630,15 @@ static int bnxt_request_irq(struct bnxt *bp)
int map_idx = bnxt_cp_num_to_irq_num(bp, i);
struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
-#ifdef CONFIG_RFS_ACCEL
- if (rmap && bp->bnapi[i]->rx_ring) {
+ if (IS_ENABLED(CONFIG_RFS_ACCEL) &&
+ rmap && bp->bnapi[i]->rx_ring) {
rc = irq_cpu_rmap_add(rmap, irq->vector);
if (rc)
netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
j);
j++;
}
-#endif
+
rc = request_irq(irq->vector, irq->handler, flags, irq->name,
bp->bnapi[i]);
if (rc)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index fa0077bc67b7..97585c160de3 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -4092,6 +4092,12 @@ static int bcmgenet_probe(struct platform_device *pdev)
for (i = 0; i <= priv->hw_params->rx_queues; i++)
priv->rx_rings[i].rx_max_coalesced_frames = 1;
+ /* Initialize u64 stats seq counter for 32bit machines */
+ for (i = 0; i <= priv->hw_params->rx_queues; i++)
+ u64_stats_init(&priv->rx_rings[i].stats64.syncp);
+ for (i = 0; i <= priv->hw_params->tx_queues; i++)
+ u64_stats_init(&priv->tx_rings[i].stats64.syncp);
+
/* libphy will determine the link state */
netif_carrier_off(dev);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index aebb9fef3f6e..1be2dc40a1a6 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1578,7 +1578,6 @@ napi_del:
static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
{
struct nicvf *nic = netdev_priv(netdev);
- int orig_mtu = netdev->mtu;
/* For now just support only the usual MTU sized frames,
* plus some headroom for VLAN, QinQ.
@@ -1589,15 +1588,10 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
return -EINVAL;
}
- WRITE_ONCE(netdev->mtu, new_mtu);
-
- if (!netif_running(netdev))
- return 0;
-
- if (nicvf_update_hw_max_frs(nic, new_mtu)) {
- netdev->mtu = orig_mtu;
+ if (netif_running(netdev) && nicvf_update_hw_max_frs(nic, new_mtu))
return -EINVAL;
- }
+
+ WRITE_ONCE(netdev->mtu, new_mtu);
return 0;
}
diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c
index 6b3f7fca8d15..05c4b6c8c9c3 100644
--- a/drivers/net/ethernet/renesas/rtsn.c
+++ b/drivers/net/ethernet/renesas/rtsn.c
@@ -1259,7 +1259,12 @@ static int rtsn_probe(struct platform_device *pdev)
priv = netdev_priv(ndev);
priv->pdev = pdev;
priv->ndev = ndev;
+
priv->ptp_priv = rcar_gen4_ptp_alloc(pdev);
+ if (!priv->ptp_priv) {
+ ret = -ENOMEM;
+ goto error_free;
+ }
spin_lock_init(&priv->lock);
platform_set_drvdata(pdev, priv);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 7840bc403788..5dcc95bc0ad2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -364,19 +364,17 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
}
/* TX/RX NORMAL interrupts */
- if (likely(intr_status & XGMAC_NIS)) {
- if (likely(intr_status & XGMAC_RI)) {
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->rx_normal_irq_n[chan]);
- u64_stats_update_end(&stats->syncp);
- ret |= handle_rx;
- }
- if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->tx_normal_irq_n[chan]);
- u64_stats_update_end(&stats->syncp);
- ret |= handle_tx;
- }
+ if (likely(intr_status & XGMAC_RI)) {
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
+ ret |= handle_rx;
+ }
+ if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
+ ret |= handle_tx;
}
/* Clear interrupts */
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index f20d1ff192ef..231ca141331f 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -856,8 +856,6 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
{
struct sk_buff *skb;
- len += AM65_CPSW_HEADROOM;
-
skb = build_skb(page_addr, len);
if (unlikely(!skb))
return NULL;
@@ -1344,7 +1342,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
}
skb = am65_cpsw_build_skb(page_addr, ndev,
- AM65_CPSW_MAX_PACKET_SIZE, headroom);
+ PAGE_SIZE, headroom);
if (unlikely(!skb)) {
new_page = page;
goto requeue;
diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c
index 26350b962890..8f26e395e39f 100644
--- a/drivers/net/phy/qcom/at803x.c
+++ b/drivers/net/phy/qcom/at803x.c
@@ -26,9 +26,6 @@
#define AT803X_LED_CONTROL 0x18
-#define AT803X_PHY_MMD3_WOL_CTRL 0x8012
-#define AT803X_WOL_EN BIT(5)
-
#define AT803X_REG_CHIP_CONFIG 0x1f
#define AT803X_BT_BX_REG_SEL 0x8000
@@ -866,30 +863,6 @@ static int at8031_config_init(struct phy_device *phydev)
return at803x_config_init(phydev);
}
-static int at8031_set_wol(struct phy_device *phydev,
- struct ethtool_wolinfo *wol)
-{
- int ret;
-
- /* First setup MAC address and enable WOL interrupt */
- ret = at803x_set_wol(phydev, wol);
- if (ret)
- return ret;
-
- if (wol->wolopts & WAKE_MAGIC)
- /* Enable WOL function for 1588 */
- ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
- AT803X_PHY_MMD3_WOL_CTRL,
- 0, AT803X_WOL_EN);
- else
- /* Disable WoL function for 1588 */
- ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
- AT803X_PHY_MMD3_WOL_CTRL,
- AT803X_WOL_EN, 0);
-
- return ret;
-}
-
static int at8031_config_intr(struct phy_device *phydev)
{
struct at803x_priv *priv = phydev->priv;
diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c
index 71498c518f0f..6de16c0eaa08 100644
--- a/drivers/net/phy/qcom/qca808x.c
+++ b/drivers/net/phy/qcom/qca808x.c
@@ -633,7 +633,7 @@ static struct phy_driver qca808x_driver[] = {
.handle_interrupt = at803x_handle_interrupt,
.get_tunable = at803x_get_tunable,
.set_tunable = at803x_set_tunable,
- .set_wol = at803x_set_wol,
+ .set_wol = at8031_set_wol,
.get_wol = at803x_get_wol,
.get_features = qca808x_get_features,
.config_aneg = qca808x_config_aneg,
diff --git a/drivers/net/phy/qcom/qcom-phy-lib.c b/drivers/net/phy/qcom/qcom-phy-lib.c
index d28815ef56bb..af7d0d8e81be 100644
--- a/drivers/net/phy/qcom/qcom-phy-lib.c
+++ b/drivers/net/phy/qcom/qcom-phy-lib.c
@@ -115,6 +115,31 @@ int at803x_set_wol(struct phy_device *phydev,
}
EXPORT_SYMBOL_GPL(at803x_set_wol);
+int at8031_set_wol(struct phy_device *phydev,
+ struct ethtool_wolinfo *wol)
+{
+ int ret;
+
+ /* First setup MAC address and enable WOL interrupt */
+ ret = at803x_set_wol(phydev, wol);
+ if (ret)
+ return ret;
+
+ if (wol->wolopts & WAKE_MAGIC)
+ /* Enable WOL function for 1588 */
+ ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+ AT803X_PHY_MMD3_WOL_CTRL,
+ 0, AT803X_WOL_EN);
+ else
+ /* Disable WoL function for 1588 */
+ ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+ AT803X_PHY_MMD3_WOL_CTRL,
+ AT803X_WOL_EN, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(at8031_set_wol);
+
void at803x_get_wol(struct phy_device *phydev,
struct ethtool_wolinfo *wol)
{
diff --git a/drivers/net/phy/qcom/qcom.h b/drivers/net/phy/qcom/qcom.h
index 4bb541728846..7f7151c8baca 100644
--- a/drivers/net/phy/qcom/qcom.h
+++ b/drivers/net/phy/qcom/qcom.h
@@ -172,6 +172,9 @@
#define AT803X_LOC_MAC_ADDR_16_31_OFFSET 0x804B
#define AT803X_LOC_MAC_ADDR_32_47_OFFSET 0x804A
+#define AT803X_PHY_MMD3_WOL_CTRL 0x8012
+#define AT803X_WOL_EN BIT(5)
+
#define AT803X_DEBUG_ADDR 0x1D
#define AT803X_DEBUG_DATA 0x1E
@@ -215,6 +218,8 @@ int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg,
int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data);
int at803x_set_wol(struct phy_device *phydev,
struct ethtool_wolinfo *wol);
+int at8031_set_wol(struct phy_device *phydev,
+ struct ethtool_wolinfo *wol);
void at803x_get_wol(struct phy_device *phydev,
struct ethtool_wolinfo *wol);
int at803x_ack_interrupt(struct phy_device *phydev);
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 31463b9e5697..b6489da5cfcd 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -155,10 +155,29 @@ static int smsc_phy_reset(struct phy_device *phydev)
static int lan87xx_config_aneg(struct phy_device *phydev)
{
- int rc;
+ u8 mdix_ctrl;
int val;
+ int rc;
+
+ /* When auto-negotiation is disabled (forced mode), the PHY's
+ * Auto-MDIX will continue toggling the TX/RX pairs.
+ *
+ * To establish a stable link, we must select a fixed MDI mode.
+ * If the user has not specified a fixed MDI mode (i.e., mdix_ctrl is
+ * 'auto'), we default to ETH_TP_MDI. This choice of a ETH_TP_MDI mode
+ * mirrors the behavior the hardware would exhibit if the AUTOMDIX_EN
+ * strap were configured for a fixed MDI connection.
+ */
+ if (phydev->autoneg == AUTONEG_DISABLE) {
+ if (phydev->mdix_ctrl == ETH_TP_MDI_AUTO)
+ mdix_ctrl = ETH_TP_MDI;
+ else
+ mdix_ctrl = phydev->mdix_ctrl;
+ } else {
+ mdix_ctrl = phydev->mdix_ctrl;
+ }
- switch (phydev->mdix_ctrl) {
+ switch (mdix_ctrl) {
case ETH_TP_MDI:
val = SPECIAL_CTRL_STS_OVRRD_AMDIX_;
break;
@@ -167,7 +186,8 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
SPECIAL_CTRL_STS_AMDIX_STATE_;
break;
case ETH_TP_MDI_AUTO:
- val = SPECIAL_CTRL_STS_AMDIX_ENABLE_;
+ val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+ SPECIAL_CTRL_STS_AMDIX_ENABLE_;
break;
default:
return genphy_config_aneg(phydev);
@@ -183,7 +203,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
rc |= val;
phy_write(phydev, SPECIAL_CTRL_STS, rc);
- phydev->mdix = phydev->mdix_ctrl;
+ phydev->mdix = mdix_ctrl;
return genphy_config_aneg(phydev);
}
@@ -261,6 +281,33 @@ int lan87xx_read_status(struct phy_device *phydev)
}
EXPORT_SYMBOL_GPL(lan87xx_read_status);
+static int lan87xx_phy_config_init(struct phy_device *phydev)
+{
+ int rc;
+
+ /* The LAN87xx PHY's initial MDI-X mode is determined by the AUTOMDIX_EN
+ * hardware strap, but the driver cannot read the strap's status. This
+ * creates an unpredictable initial state.
+ *
+ * To ensure consistent and reliable behavior across all boards,
+ * override the strap configuration on initialization and force the PHY
+ * into a known state with Auto-MDIX enabled, which is the expected
+ * default for modern hardware.
+ */
+ rc = phy_modify(phydev, SPECIAL_CTRL_STS,
+ SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+ SPECIAL_CTRL_STS_AMDIX_ENABLE_ |
+ SPECIAL_CTRL_STS_AMDIX_STATE_,
+ SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+ SPECIAL_CTRL_STS_AMDIX_ENABLE_);
+ if (rc < 0)
+ return rc;
+
+ phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
+ return smsc_phy_config_init(phydev);
+}
+
static int lan874x_phy_config_init(struct phy_device *phydev)
{
u16 val;
@@ -695,7 +742,7 @@ static struct phy_driver smsc_phy_driver[] = {
/* basic functions */
.read_status = lan87xx_read_status,
- .config_init = smsc_phy_config_init,
+ .config_init = lan87xx_phy_config_init,
.soft_reset = smsc_phy_reset,
.config_aneg = lan87xx_config_aneg,
diff --git a/drivers/pinctrl/nuvoton/pinctrl-ma35.c b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
index 06ae1fe8b8c5..b51704bafd81 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-ma35.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
@@ -1074,7 +1074,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct
u32 idx = 0;
int ret;
- for_each_gpiochip_node(dev, child) {
+ device_for_each_child_node(dev, child) {
+ if (fwnode_property_present(child, "gpio-controller"))
+ continue;
+
npctl->nfunctions++;
npctl->ngroups += of_get_child_count(to_of_node(child));
}
@@ -1092,7 +1095,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct
if (!npctl->groups)
return -ENOMEM;
- for_each_gpiochip_node(dev, child) {
+ device_for_each_child_node(dev, child) {
+ if (fwnode_property_present(child, "gpio-controller"))
+ continue;
+
ret = ma35_pinctrl_parse_functions(child, npctl, idx++);
if (ret) {
fwnode_handle_put(child);
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 5cf3db6d78b7..b3f0d02aeeb3 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -979,6 +979,17 @@ static int amd_gpio_suspend_hibernate_common(struct device *dev, bool is_suspend
pin, is_suspend ? "suspend" : "hibernate");
}
+ /*
+ * debounce enabled over suspend has shown issues with a GPIO
+ * being unable to wake the system, as we're only interested in
+ * the actual wakeup event, clear it.
+ */
+ if (gpio_dev->saved_regs[i] & (DB_CNTRl_MASK << DB_CNTRL_OFF)) {
+ amd_gpio_set_debounce(gpio_dev, pin, 0);
+ pm_pr_dbg("Clearing debounce for GPIO #%d during %s.\n",
+ pin, is_suspend ? "suspend" : "hibernate");
+ }
+
raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
}
diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index 9bf53de20be8..04afb344e9e5 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -784,7 +784,7 @@ static int aw9523_init_gpiochip(struct aw9523 *awi, unsigned int npins)
gc->set_config = gpiochip_generic_config;
gc->parent = dev;
gc->owner = THIS_MODULE;
- gc->can_sleep = false;
+ gc->can_sleep = true;
return 0;
}
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 5c4687de1464..f713c80d7f3e 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1038,6 +1038,25 @@ static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d,
test_bit(d->hwirq, pctrl->skip_wake_irqs);
}
+static void msm_gpio_irq_init_valid_mask(struct gpio_chip *gc,
+ unsigned long *valid_mask,
+ unsigned int ngpios)
+{
+ struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+ const struct msm_pingroup *g;
+ int i;
+
+ bitmap_fill(valid_mask, ngpios);
+
+ for (i = 0; i < ngpios; i++) {
+ g = &pctrl->soc->groups[i];
+
+ if (g->intr_detection_width != 1 &&
+ g->intr_detection_width != 2)
+ clear_bit(i, valid_mask);
+ }
+}
+
static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
{
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1441,6 +1460,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
girq->default_type = IRQ_TYPE_NONE;
girq->handler = handle_bad_irq;
girq->parents[0] = pctrl->irq;
+ girq->init_valid_mask = msm_gpio_irq_init_valid_mask;
ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl);
if (ret) {
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 4d842c692194..edf776b8ad53 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -596,7 +596,7 @@ static bool pwm_state_valid(const struct pwm_state *state)
* and supposed to be ignored. So also ignore any strange values and
* consider the state ok.
*/
- if (state->enabled)
+ if (!state->enabled)
return true;
if (!state->period)
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 7eaab5831499..33d3554b9197 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -130,8 +130,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
return ret;
clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]);
- if (!clk_rate)
- return -EINVAL;
+ if (!clk_rate) {
+ ret = -EINVAL;
+ goto out;
+ }
/* Make sure we use the bus clock and not the 26MHz clock */
if (pc->soc->has_ck_26m_sel)
@@ -150,9 +152,9 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
}
if (clkdiv > PWM_CLK_DIV_MAX) {
- pwm_mediatek_clk_disable(chip, pwm);
dev_err(pwmchip_parent(chip), "period of %d ns not supported\n", period_ns);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
if (pc->soc->pwm45_fixup && pwm->hwpwm > 2) {
@@ -169,9 +171,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
pwm_mediatek_writel(pc, pwm->hwpwm, reg_width, cnt_period);
pwm_mediatek_writel(pc, pwm->hwpwm, reg_thres, cnt_duty);
+out:
pwm_mediatek_clk_disable(chip, pwm);
- return 0;
+ return ret;
}
static int pwm_mediatek_enable(struct pwm_chip *chip, struct pwm_device *pwm)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index a97a771a459c..895256cd2786 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -828,7 +828,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
kfree_rcu(epi, rcu);
percpu_counter_dec(&ep->user->epoll_watches);
- return ep_refcount_dec_and_test(ep);
+ return true;
}
/*
@@ -836,14 +836,14 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
*/
static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi)
{
- WARN_ON_ONCE(__ep_remove(ep, epi, false));
+ if (__ep_remove(ep, epi, false))
+ WARN_ON_ONCE(ep_refcount_dec_and_test(ep));
}
static void ep_clear_and_put(struct eventpoll *ep)
{
struct rb_node *rbp, *next;
struct epitem *epi;
- bool dispose;
/* We need to release all tasks waiting for these file */
if (waitqueue_active(&ep->poll_wait))
@@ -876,10 +876,8 @@ static void ep_clear_and_put(struct eventpoll *ep)
cond_resched();
}
- dispose = ep_refcount_dec_and_test(ep);
mutex_unlock(&ep->mtx);
-
- if (dispose)
+ if (ep_refcount_dec_and_test(ep))
ep_free(ep);
}
@@ -1100,7 +1098,7 @@ again:
dispose = __ep_remove(ep, epi, true);
mutex_unlock(&ep->mtx);
- if (dispose)
+ if (dispose && ep_refcount_dec_and_test(ep))
ep_free(ep);
goto again;
}
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 96a3a0d6a60e..6378370a952f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -82,6 +82,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 0b3a36bdaa90..0f5f94137f6d 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -594,6 +594,7 @@ struct sev_data_snp_addr {
* @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the
* purpose of guest-assisted migration.
* @rsvd: reserved
+ * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest
* @gosvw: guest OS-visible workarounds, as defined by hypervisor
*/
struct sev_data_snp_launch_start {
@@ -603,6 +604,7 @@ struct sev_data_snp_launch_start {
u32 ma_en:1; /* In */
u32 imi_en:1; /* In */
u32 rsvd:30;
+ u32 desired_tsc_khz; /* In */
u8 gosvw[16]; /* In */
} __packed;
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d56e6e135158..d40e978126e3 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -243,8 +243,8 @@ int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
-#ifdef CONFIG_BPF_SYSCALL
extern struct proto vsock_proto;
+#ifdef CONFIG_BPF_SYSCALL
int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void __init vsock_bpf_build_proto(void);
#else
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9fc8f544e20e..0da011fc8146 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1350,8 +1350,7 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state)
rcu_read_lock();
list_for_each_entry_rcu(c, &h->list, list) {
- if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) ||
- c->state != state)
+ if (c->type != BIS_LINK || c->state != state)
continue;
if (handle == c->iso_qos.bcast.big) {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index d7b7b6cd4aa1..8a75c73fc555 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -114,7 +114,6 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
struct netlink_ext_ack *extack);
void qdisc_put_rtab(struct qdisc_rate_table *tab);
void qdisc_put_stab(struct qdisc_size_table *tab);
-void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc);
bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev, struct netdev_queue *txq,
spinlock_t *root_lock, bool validate);
@@ -290,4 +289,28 @@ static inline bool tc_qdisc_stats_dump(struct Qdisc *sch,
return true;
}
+static inline void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
+{
+ if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
+ pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
+ txt, qdisc->ops->id, qdisc->handle >> 16);
+ qdisc->flags |= TCQ_F_WARN_NONWC;
+ }
+}
+
+static inline unsigned int qdisc_peek_len(struct Qdisc *sch)
+{
+ struct sk_buff *skb;
+ unsigned int len;
+
+ skb = sch->ops->peek(sch);
+ if (unlikely(skb == NULL)) {
+ qdisc_warn_nonwc("qdisc_peek_len", sch);
+ return 0;
+ }
+ len = qdisc_pkt_len(skb);
+
+ return len;
+}
+
#endif
diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h
index 682b406e1067..a04afef9efca 100644
--- a/include/uapi/linux/bits.h
+++ b/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
#ifndef _UAPI_LINUX_BITS_H
#define _UAPI_LINUX_BITS_H
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
#define __GENMASK_U128(h, l) \
((_BIT128((h)) << 1) - (_BIT128(l)))
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 37891580d05d..7a4c35ff03fe 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -467,6 +467,10 @@ struct kvm_run {
__u64 leaf;
__u64 r11, r12, r13, r14;
} get_tdvmcall_info;
+ struct {
+ __u64 ret;
+ __u64 vector;
+ } setup_event_notify;
};
} tdx;
/* Fix the size of the union. */
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 8df0dfaaca18..67af8a55185d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -222,7 +222,10 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
if (size_cmdline != -1) {
selected_size = size_cmdline;
selected_base = base_cmdline;
- selected_limit = min_not_zero(limit_cmdline, limit);
+
+ /* Hornor the user setup dma address limit */
+ selected_limit = limit_cmdline ?: limit;
+
if (base_cmdline + size_cmdline == limit_cmdline)
fixed = true;
} else {
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..c2c08007029d 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1573,8 +1573,14 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
if (infosec >= info->hdr->e_shnum)
continue;
- /* Don't bother with non-allocated sections */
- if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
+ /*
+ * Don't bother with non-allocated sections.
+ * An exception is the percpu section, which has separate allocations
+ * for individual CPUs. We relocate the percpu section in the initial
+ * ELF template and subsequently copy it to the per-CPU destinations.
+ */
+ if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC) &&
+ (!infosec || infosec != info->index.pcpu))
continue;
if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)
@@ -2696,9 +2702,8 @@ static int find_module_sections(struct module *mod, struct load_info *info)
static int move_module(struct module *mod, struct load_info *info)
{
- int i;
- enum mod_mem_type t = 0;
- int ret = -ENOMEM;
+ int i, ret;
+ enum mod_mem_type t = MOD_MEM_NUM_TYPES;
bool codetag_section_found = false;
for_each_mod_mem_type(type) {
@@ -2776,7 +2781,7 @@ static int move_module(struct module *mod, struct load_info *info)
return 0;
out_err:
module_memory_restore_rox(mod);
- for (t--; t >= 0; t--)
+ while (t--)
module_memory_free(mod, t);
if (codetag_section_found)
codetag_free_module_sections(mod);
diff --git a/net/atm/clip.c b/net/atm/clip.c
index b234dc3bcb0d..f7a5565e794e 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -45,7 +45,8 @@
#include <net/atmclip.h>
static struct net_device *clip_devs;
-static struct atm_vcc *atmarpd;
+static struct atm_vcc __rcu *atmarpd;
+static DEFINE_MUTEX(atmarpd_lock);
static struct timer_list idle_timer;
static const struct neigh_ops clip_neigh_ops;
@@ -53,24 +54,35 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip)
{
struct sock *sk;
struct atmarp_ctrl *ctrl;
+ struct atm_vcc *vcc;
struct sk_buff *skb;
+ int err = 0;
pr_debug("(%d)\n", type);
- if (!atmarpd)
- return -EUNATCH;
+
+ rcu_read_lock();
+ vcc = rcu_dereference(atmarpd);
+ if (!vcc) {
+ err = -EUNATCH;
+ goto unlock;
+ }
skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC);
- if (!skb)
- return -ENOMEM;
+ if (!skb) {
+ err = -ENOMEM;
+ goto unlock;
+ }
ctrl = skb_put(skb, sizeof(struct atmarp_ctrl));
ctrl->type = type;
ctrl->itf_num = itf;
ctrl->ip = ip;
- atm_force_charge(atmarpd, skb->truesize);
+ atm_force_charge(vcc, skb->truesize);
- sk = sk_atm(atmarpd);
+ sk = sk_atm(vcc);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk);
- return 0;
+unlock:
+ rcu_read_unlock();
+ return err;
}
static void link_vcc(struct clip_vcc *clip_vcc, struct atmarp_entry *entry)
@@ -417,6 +429,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
if (!vcc->push)
return -EBADFD;
+ if (vcc->user_back)
+ return -EINVAL;
clip_vcc = kmalloc(sizeof(struct clip_vcc), GFP_KERNEL);
if (!clip_vcc)
return -ENOMEM;
@@ -607,17 +621,27 @@ static void atmarpd_close(struct atm_vcc *vcc)
{
pr_debug("\n");
- rtnl_lock();
- atmarpd = NULL;
+ mutex_lock(&atmarpd_lock);
+ RCU_INIT_POINTER(atmarpd, NULL);
+ mutex_unlock(&atmarpd_lock);
+
+ synchronize_rcu();
skb_queue_purge(&sk_atm(vcc)->sk_receive_queue);
- rtnl_unlock();
pr_debug("(done)\n");
module_put(THIS_MODULE);
}
+static int atmarpd_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ atm_return_tx(vcc, skb);
+ dev_kfree_skb_any(skb);
+ return 0;
+}
+
static const struct atmdev_ops atmarpd_dev_ops = {
- .close = atmarpd_close
+ .close = atmarpd_close,
+ .send = atmarpd_send
};
@@ -631,15 +655,18 @@ static struct atm_dev atmarpd_dev = {
static int atm_init_atmarp(struct atm_vcc *vcc)
{
- rtnl_lock();
+ if (vcc->push == clip_push)
+ return -EINVAL;
+
+ mutex_lock(&atmarpd_lock);
if (atmarpd) {
- rtnl_unlock();
+ mutex_unlock(&atmarpd_lock);
return -EADDRINUSE;
}
mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ);
- atmarpd = vcc;
+ rcu_assign_pointer(atmarpd, vcc);
set_bit(ATM_VF_META, &vcc->flags);
set_bit(ATM_VF_READY, &vcc->flags);
/* allow replies and avoid getting closed if signaling dies */
@@ -648,13 +675,14 @@ static int atm_init_atmarp(struct atm_vcc *vcc)
vcc->push = NULL;
vcc->pop = NULL; /* crash */
vcc->push_oam = NULL; /* crash */
- rtnl_unlock();
+ mutex_unlock(&atmarpd_lock);
return 0;
}
static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct atm_vcc *vcc = ATM_SD(sock);
+ struct sock *sk = sock->sk;
int err = 0;
switch (cmd) {
@@ -675,14 +703,18 @@ static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
err = clip_create(arg);
break;
case ATMARPD_CTRL:
+ lock_sock(sk);
err = atm_init_atmarp(vcc);
if (!err) {
sock->state = SS_CONNECTED;
__module_get(THIS_MODULE);
}
+ release_sock(sk);
break;
case ATMARP_MKIP:
+ lock_sock(sk);
err = clip_mkip(vcc, arg);
+ release_sock(sk);
break;
case ATMARP_SETENTRY:
err = clip_setentry(vcc, (__force __be32)arg);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4d5ace9d245d..992131f88a45 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6966,7 +6966,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu);
if (!ev->status) {
+ bis->state = BT_CONNECTED;
set_bit(HCI_CONN_BIG_SYNC, &bis->flags);
+ hci_debugfs_create_conn(bis);
+ hci_conn_add_sysfs(bis);
hci_iso_setup_path(bis);
}
}
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 77b3691f3423..5f178db8d40d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1345,7 +1345,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
* Command Disallowed error, so we must first disable the
* instance if it is active.
*/
- if (adv && !adv->pending) {
+ if (adv) {
err = hci_disable_ext_adv_instance_sync(hdev, instance);
if (err)
return err;
@@ -5493,7 +5493,7 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn,
{
struct hci_cp_disconnect cp;
- if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) {
+ if (conn->type == BIS_LINK) {
/* This is a BIS connection, hci_conn_del will
* do the necessary cleanup.
*/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f64f8276a73c..461a9ab540af 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1176,7 +1176,7 @@ restart:
goto do_error;
while (msg_data_left(msg)) {
- ssize_t copy = 0;
+ int copy = 0;
skb = tcp_write_queue_tail(sk);
if (skb)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12c2e6fc85c6..68bc79eb9019 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5181,7 +5181,9 @@ end:
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
- tcp_rcvbuf_grow(sk);
+ /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
+ if (sk->sk_socket)
+ tcp_rcvbuf_grow(sk);
}
static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e8972a857e51..79fbaf7333ce 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
WARN_ON(skb->sk != NULL);
skb->sk = sk;
skb->destructor = netlink_skb_destructor;
- atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
@@ -1212,41 +1211,48 @@ struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk)
{
+ DECLARE_WAITQUEUE(wait, current);
struct netlink_sock *nlk;
+ unsigned int rmem;
nlk = nlk_sk(sk);
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
- if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
- DECLARE_WAITQUEUE(wait, current);
- if (!*timeo) {
- if (!ssk || netlink_is_kernel(ssk))
- netlink_overrun(sk);
- sock_put(sk);
- kfree_skb(skb);
- return -EAGAIN;
- }
-
- __set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&nlk->wait, &wait);
+ if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+ !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
+ netlink_skb_set_owner_r(skb, sk);
+ return 0;
+ }
- if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
- !sock_flag(sk, SOCK_DEAD))
- *timeo = schedule_timeout(*timeo);
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&nlk->wait, &wait);
+ if (!*timeo) {
+ if (!ssk || netlink_is_kernel(ssk))
+ netlink_overrun(sk);
sock_put(sk);
+ kfree_skb(skb);
+ return -EAGAIN;
+ }
- if (signal_pending(current)) {
- kfree_skb(skb);
- return sock_intr_errno(*timeo);
- }
- return 1;
+ __set_current_state(TASK_INTERRUPTIBLE);
+ add_wait_queue(&nlk->wait, &wait);
+ rmem = atomic_read(&sk->sk_rmem_alloc);
+
+ if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) ||
+ test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
+ !sock_flag(sk, SOCK_DEAD))
+ *timeo = schedule_timeout(*timeo);
+
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&nlk->wait, &wait);
+ sock_put(sk);
+
+ if (signal_pending(current)) {
+ kfree_skb(skb);
+ return sock_intr_errno(*timeo);
}
- netlink_skb_set_owner_r(skb, sk);
- return 0;
+
+ return 1;
}
static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
@@ -1307,6 +1313,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
ret = -ECONNREFUSED;
if (nlk->netlink_rcv != NULL) {
ret = skb->len;
+ atomic_add(skb->truesize, &sk->sk_rmem_alloc);
netlink_skb_set_owner_r(skb, sk);
NETLINK_CB(skb).sk = ssk;
netlink_deliver_tap_kernel(sk, ssk, skb);
@@ -1383,13 +1390,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check);
static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
+ unsigned int rmem, rcvbuf;
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+ rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if ((rmem != skb->truesize || rmem <= rcvbuf) &&
!test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
netlink_skb_set_owner_r(skb, sk);
__netlink_sendskb(sk, skb);
- return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
+ return rmem > (rcvbuf >> 1);
}
+
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
return -1;
}
@@ -2249,6 +2262,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
struct module *module;
int err = -ENOBUFS;
int alloc_min_size;
+ unsigned int rmem;
int alloc_size;
if (!lock_taken)
@@ -2258,9 +2272,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
goto errout_skb;
}
- if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
- goto errout_skb;
-
/* NLMSG_GOODSIZE is small to avoid high order allocations being
* required, but it makes sense to _attempt_ a 32KiB allocation
* to reduce number of system calls on dump operations, if user
@@ -2283,6 +2294,12 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
if (!skb)
goto errout_skb;
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+ if (rmem >= READ_ONCE(sk->sk_rcvbuf)) {
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+ goto errout_skb;
+ }
+
/* Trim skb to allocated size. User is expected to provide buffer as
* large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at
* netlink_recvmsg())). dump will pack as many smaller messages as
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5bd3922c310d..376e33dce8c1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -361,12 +361,15 @@ struct rxrpc_local {
struct list_head new_client_calls; /* Newly created client calls need connection */
spinlock_t client_call_lock; /* Lock for ->new_client_calls */
struct sockaddr_rxrpc srx; /* local address */
- /* Provide a kvec table sufficiently large to manage either a DATA
- * packet with a maximum set of jumbo subpackets or a PING ACK padded
- * out to 64K with zeropages for PMTUD.
- */
- struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
- 1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+ union {
+ /* Provide a kvec table sufficiently large to manage either a
+ * DATA packet with a maximum set of jumbo subpackets or a PING
+ * ACK padded out to 64K with zeropages for PMTUD.
+ */
+ struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
+ 1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+ struct bio_vec bvec[3 + 16];
+ };
};
/*
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a4b363b47cca..49fccee1a726 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -149,6 +149,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
id_in_use:
write_unlock(&rx->call_lock);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EBADSLT);
rxrpc_cleanup_call(call);
_leave(" = -EBADSLT");
return -EBADSLT;
@@ -254,6 +255,9 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
unsigned short call_tail, conn_tail, peer_tail;
unsigned short call_count, conn_count;
+ if (!b)
+ return NULL;
+
/* #calls >= #conns >= #peers must hold true. */
call_head = smp_load_acquire(&b->call_backlog_head);
call_tail = b->call_backlog_tail;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 0af19bcdc80a..ef7b3096c95e 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -924,7 +924,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
{
struct rxrpc_skb_priv *sp = rxrpc_skb(response);
struct scatterlist sg[16];
- struct bio_vec bvec[16];
+ struct bio_vec *bvec = conn->local->bvec;
struct msghdr msg;
size_t len = sp->resp.len;
__be32 wserial;
@@ -938,6 +938,9 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
if (ret < 0)
goto fail;
nr_sg = ret;
+ ret = -EIO;
+ if (WARN_ON_ONCE(nr_sg > ARRAY_SIZE(conn->local->bvec)))
+ goto fail;
for (int i = 0; i < nr_sg; i++)
bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d8a33486c511..d7c767b861a4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -336,17 +336,22 @@ out:
return q;
}
-static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
+static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid,
+ struct netlink_ext_ack *extack)
{
unsigned long cl;
const struct Qdisc_class_ops *cops = p->ops->cl_ops;
- if (cops == NULL)
- return NULL;
+ if (cops == NULL) {
+ NL_SET_ERR_MSG(extack, "Parent qdisc is not classful");
+ return ERR_PTR(-EOPNOTSUPP);
+ }
cl = cops->find(p, classid);
- if (cl == 0)
- return NULL;
+ if (cl == 0) {
+ NL_SET_ERR_MSG(extack, "Specified class not found");
+ return ERR_PTR(-ENOENT);
+ }
return cops->leaf(p, cl);
}
@@ -596,16 +601,6 @@ out:
qdisc_skb_cb(skb)->pkt_len = pkt_len;
}
-void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
-{
- if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
- pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
- txt, qdisc->ops->id, qdisc->handle >> 16);
- qdisc->flags |= TCQ_F_WARN_NONWC;
- }
-}
-EXPORT_SYMBOL(qdisc_warn_nonwc);
-
static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
{
struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
@@ -1490,7 +1485,7 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid");
return -ENOENT;
}
- q = qdisc_leaf(p, clid);
+ q = qdisc_leaf(p, clid, extack);
} else if (dev_ingress_queue(dev)) {
q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
}
@@ -1501,6 +1496,8 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device");
return -ENOENT;
}
+ if (IS_ERR(q))
+ return PTR_ERR(q);
if (tcm->tcm_handle && q->handle != tcm->tcm_handle) {
NL_SET_ERR_MSG(extack, "Invalid handle");
@@ -1602,7 +1599,9 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Failed to find specified qdisc");
return -ENOENT;
}
- q = qdisc_leaf(p, clid);
+ q = qdisc_leaf(p, clid, extack);
+ if (IS_ERR(q))
+ return PTR_ERR(q);
} else if (dev_ingress_queue_create(dev)) {
q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 5a7745170e84..d8fd35da32a7 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -835,22 +835,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
}
}
-static unsigned int
-qdisc_peek_len(struct Qdisc *sch)
-{
- struct sk_buff *skb;
- unsigned int len;
-
- skb = sch->ops->peek(sch);
- if (unlikely(skb == NULL)) {
- qdisc_warn_nonwc("qdisc_peek_len", sch);
- return 0;
- }
- len = qdisc_pkt_len(skb);
-
- return len;
-}
-
static void
hfsc_adjust_levels(struct hfsc_class *cl)
{
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bf1282cb22eb..bcce36608871 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -989,7 +989,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
list_del_init(&cl->alist);
- else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
+ else if (cl->deficit < qdisc_peek_len(cl->qdisc)) {
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
}
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 8ee0c07d00e9..ffe577bf6b51 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -704,8 +704,10 @@ static void tipc_topsrv_stop(struct net *net)
for (id = 0; srv->idr_in_use; id++) {
con = idr_find(&srv->conn_idr, id);
if (con) {
+ conn_get(con);
spin_unlock_bh(&srv->idr_lock);
tipc_conn_close(con);
+ conn_put(con);
spin_lock_bh(&srv->idr_lock);
}
}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2e7a3034e965..1053662725f8 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
/* We increase the module refcnt to prevent the transport unloading
* while there are open sockets assigned to it.
*/
- if (!new_transport || !try_module_get(new_transport->module))
- return -ENODEV;
+ if (!new_transport || !try_module_get(new_transport->module)) {
+ ret = -ENODEV;
+ goto err;
+ }
+
+ /* It's safe to release the mutex after a successful try_module_get().
+ * Whichever transport `new_transport` points at, it won't go away until
+ * the last module_put() below or in vsock_deassign_transport().
+ */
+ mutex_unlock(&vsock_register_mutex);
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
@@ -528,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
vsk->transport = new_transport;
return 0;
+err:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+ u32 cid = VMADDR_CID_ANY;
+
+ mutex_lock(&vsock_register_mutex);
+ if (*transport)
+ cid = (*transport)->get_local_cid();
+ mutex_unlock(&vsock_register_mutex);
+
+ return cid;
+}
+
bool vsock_find_cid(unsigned int cid)
{
- if (transport_g2h && cid == transport_g2h->get_local_cid())
+ if (cid == vsock_registered_transport_cid(&transport_g2h))
return true;
if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -2536,18 +2570,19 @@ static long vsock_dev_do_ioctl(struct file *filp,
unsigned int cmd, void __user *ptr)
{
u32 __user *p = ptr;
- u32 cid = VMADDR_CID_ANY;
int retval = 0;
+ u32 cid;
switch (cmd) {
case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
/* To be compatible with the VMCI behavior, we prioritize the
* guest CID instead of well-know host CID (VMADDR_CID_HOST).
*/
- if (transport_g2h)
- cid = transport_g2h->get_local_cid();
- else if (transport_h2g)
- cid = transport_h2g->get_local_cid();
+ cid = vsock_registered_transport_cid(&transport_g2h);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_h2g);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_local);
if (put_user(cid, p) != 0)
retval = -EFAULT;
diff --git a/sound/isa/ad1816a/ad1816a.c b/sound/isa/ad1816a/ad1816a.c
index 99006dc4777e..5c9e2d41d900 100644
--- a/sound/isa/ad1816a/ad1816a.c
+++ b/sound/isa/ad1816a/ad1816a.c
@@ -98,7 +98,7 @@ static int snd_card_ad1816a_pnp(int dev, struct pnp_card_link *card,
pdev = pnp_request_card_device(card, id->devs[1].id, NULL);
if (pdev == NULL) {
mpu_port[dev] = -1;
- dev_warn(&pdev->dev, "MPU401 device busy, skipping.\n");
+ pr_warn("MPU401 device busy, skipping.\n");
return 0;
}
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 08308231b4ed..9a7793eb16e9 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -4551,7 +4551,9 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HDMI/DP1", patch_tegra_hdmi),
HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi),
HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi),
HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi),
+HDA_CODEC_ENTRY(0x10de0033, "SoC 33 HDMI/DP", patch_tegra234_hdmi),
HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP", patch_tegra234_hdmi),
+HDA_CODEC_ENTRY(0x10de0035, "SoC 35 HDMI/DP", patch_tegra234_hdmi),
HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP", patch_nvhdmi),
@@ -4590,15 +4592,32 @@ HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009b, "GPU 9b HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009c, "GPU 9c HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a1, "GPU a1 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a8, "GPU a8 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a9, "GPU a9 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00aa, "GPU aa HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ab, "GPU ab HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ad, "GPU ad HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ae, "GPU ae HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00af, "GPU af HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00b0, "GPU b0 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00b1, "GPU b1 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c0, "GPU c0 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c1, "GPU c1 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c3, "GPU c3 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c4, "GPU c4 HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c5, "GPU c5 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch),
HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch),
HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5d6d01ecfee2..060db37eab83 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10881,6 +10881,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8d07, "HP Victus 15-fb2xxx (MB 8D07)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED),
@@ -11040,6 +11041,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
+ SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
@@ -11424,6 +11426,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13),
SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
SND_PCI_QUIRK(0x2782, 0x1407, "Positivo P15X", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
+ SND_PCI_QUIRK(0x2782, 0x1409, "Positivo K116J", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
SND_PCI_QUIRK(0x2782, 0x1701, "Infinix Y4 Max", ALC269VC_FIXUP_INFINIX_Y4_MAX),
SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
diff --git a/sound/pci/hda/tas2781_hda.c b/sound/pci/hda/tas2781_hda.c
index 5f1d4b3e9688..34217ce9f28e 100644
--- a/sound/pci/hda/tas2781_hda.c
+++ b/sound/pci/hda/tas2781_hda.c
@@ -44,7 +44,7 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
TASDEVICE_REG(0, 0x13, 0x70),
TASDEVICE_REG(0, 0x18, 0x7c),
};
- unsigned int crc, oft;
+ unsigned int crc, oft, node_num;
unsigned char *buf;
int i, j, k, l;
@@ -80,8 +80,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
dev_err(p->dev, "%s: CRC error\n", __func__);
return;
}
+ node_num = tmp_val[1];
- for (j = 0, k = 0; j < tmp_val[1]; j++) {
+ for (j = 0, k = 0; j < node_num; j++) {
oft = j * 6 + 3;
if (tmp_val[oft] == TASDEV_UEFI_CALI_REG_ADDR_FLG) {
for (i = 0; i < TASDEV_CALIB_N; i++) {
@@ -99,8 +100,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
}
data[l] = k;
+ oft++;
for (i = 0; i < TASDEV_CALIB_N * 4; i++)
- data[l + i] = data[4 * oft + i];
+ data[l + i + 1] = data[4 * oft + i];
k++;
}
}
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index d0831d609584..ba653f6ccfae 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -980,7 +980,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
break;
default:
dev_err(cs35l56_base->dev, "Unknown device %x\n", devid);
- return ret;
+ return -ENODEV;
}
cs35l56_base->type = devid & 0xFF;
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index 677529916dc0..745532ccbdba 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -517,7 +517,8 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair, bool use_ideal_rate)
regmap_update_bits(asrc->regmap, REG_ASRCTR,
ASRCTR_ATSi_MASK(index), ASRCTR_ATS(index));
regmap_update_bits(asrc->regmap, REG_ASRCTR,
- ASRCTR_USRi_MASK(index), 0);
+ ASRCTR_IDRi_MASK(index) | ASRCTR_USRi_MASK(index),
+ ASRCTR_USR(index));
/* Set the input and output clock sources */
regmap_update_bits(asrc->regmap, REG_ASRCSR,
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index af1a168d35e3..50af6b725670 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -803,13 +803,15 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir)
* anymore. Add software reset to fix this issue.
* This is a hardware bug, and will be fix in the
* next sai version.
+ *
+ * In consumer mode, this can happen even after a
+ * single open/close, especially if both tx and rx
+ * are running concurrently.
*/
- if (!sai->is_consumer_mode[tx]) {
- /* Software Reset */
- regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR);
- /* Clear SR bit to finish the reset */
- regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0);
- }
+ /* Software Reset */
+ regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR);
+ /* Clear SR bit to finish the reset */
+ regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0);
}
static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd,
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 2df7afa2f469..128b6876af83 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -42,6 +42,7 @@ config SND_SOC_INTEL_SOF_NUVOTON_COMMON
tristate
config SND_SOC_INTEL_SOF_BOARD_HELPERS
+ select SND_SOC_ACPI_INTEL_MATCH
tristate
if SND_SOC_INTEL_CATPT
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 81a914bd7ec2..504887505e68 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -783,6 +783,9 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = {
SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC),
SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC),
{}
};
diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c
index 73e581e93755..1ad704ca2c5f 100644
--- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c
@@ -468,17 +468,17 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = {
.get_function_tplg_files = sof_sdw_get_tplg_files,
},
{
- .link_mask = BIT(2),
- .links = arl_cs42l43_l2,
+ .link_mask = BIT(2) | BIT(3),
+ .links = arl_cs42l43_l2_cs35l56_l3,
.drv_name = "sof_sdw",
- .sof_tplg_filename = "sof-arl-cs42l43-l2.tplg",
+ .sof_tplg_filename = "sof-arl-cs42l43-l2-cs35l56-l3.tplg",
.get_function_tplg_files = sof_sdw_get_tplg_files,
},
{
- .link_mask = BIT(2) | BIT(3),
- .links = arl_cs42l43_l2_cs35l56_l3,
+ .link_mask = BIT(2),
+ .links = arl_cs42l43_l2,
.drv_name = "sof_sdw",
- .sof_tplg_filename = "sof-arl-cs42l43-l2-cs35l56-l3.tplg",
+ .sof_tplg_filename = "sof-arl-cs42l43-l2.tplg",
.get_function_tplg_files = sof_sdw_get_tplg_files,
},
{
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 8cd54f7bf33a..0ee532acbb60 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -310,16 +310,14 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
struct audioformat *fp,
unsigned int rate)
{
- struct usb_interface *iface;
struct usb_host_interface *alts;
unsigned char *fmt;
unsigned int max_rate;
- iface = usb_ifnum_to_if(chip->dev, fp->iface);
- if (!iface)
+ alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
+ if (!alts)
return true;
- alts = &iface->altsetting[fp->altset_idx];
fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen,
NULL, UAC_FORMAT_TYPE);
if (!fmt)
@@ -328,20 +326,20 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
if (fmt[0] == 10) { /* bLength */
max_rate = combine_quad(&fmt[6]);
- /* Validate max rate */
- if (max_rate != 48000 &&
- max_rate != 96000 &&
- max_rate != 192000 &&
- max_rate != 384000) {
-
+ switch (max_rate) {
+ case 48000:
+ return (rate == 44100 || rate == 48000);
+ case 96000:
+ return (rate == 88200 || rate == 96000);
+ case 192000:
+ return (rate == 176400 || rate == 192000);
+ default:
usb_audio_info(chip,
"%u:%d : unexpected max rate: %u\n",
fp->iface, fp->altsetting, max_rate);
return true;
}
-
- return rate <= max_rate;
}
return true;
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 682b406e1067..a04afef9efca 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
#ifndef _UAPI_LINUX_BITS_H
#define _UAPI_LINUX_BITS_H
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
#define __GENMASK_U128(h, l) \
((_BIT128((h)) << 1) - (_BIT128(l)))
diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
index 390ae2d87493..0eb371c62ab8 100644
--- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
@@ -74,6 +74,7 @@ int main(int argc, char *argv[])
int testcase;
char test[80];
+ TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
ksft_print_header();
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
new file mode 100644
index 000000000000..09aabc775e80
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh
+sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"`
+
+// Test that a not-yet-accepted socket does not change
+// its initial sk_rcvbuf (tcp_rmem[1]) when receiving ooo packets.
+
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+ +.1 < . 1:1(0) ack 1 win 257
+ +0 < . 2001:41001(39000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+ +0 < . 41001:101001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+ +0 < . 1:1001(1000) ack 1 win 257
+ +0 > . 1:1(0) ack 1001 <nop,nop,sack 2001:101001>
+ +0 < . 1001:2001(1000) ack 1 win 257
+ +0 > . 1:1(0) ack 101001
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 %{ assert SK_MEMINFO_RCVBUF == 131072, SK_MEMINFO_RCVBUF }%
+
+ +0 close(4) = 0
+ +0 close(3) = 0
+
+// Test that ooo packets for accepted sockets do increase sk_rcvbuf
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 < . 2001:41001(39000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+ +0 < . 41001:101001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+
+ +0 %{ assert SK_MEMINFO_RCVBUF > 131072, SK_MEMINFO_RCVBUF }%
+
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 9aa44d8176d9..5c6851e8d311 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -635,5 +635,42 @@
"$TC qdisc del dev $DUMMY handle 1:0 root",
"$IP addr del 10.10.10.10/24 dev $DUMMY || true"
]
+ },
+ {
+ "id": "d74b",
+ "name": "Test use-after-free with DRR/NETEM/BLACKHOLE chain",
+ "category": [
+ "qdisc",
+ "hfsc",
+ "drr",
+ "netem",
+ "blackhole"
+ ],
+ "plugins": {
+ "requires": [
+ "nsPlugin",
+ "scapyPlugin"
+ ]
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY root handle 1: drr",
+ "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+ "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2: hfsc def 1",
+ "$TC class add dev $DUMMY parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0",
+ "$TC qdisc add dev $DUMMY parent 2:1 handle 3: netem",
+ "$TC qdisc add dev $DUMMY parent 3:1 handle 4: blackhole",
+ "ping -c1 -W0.01 -I $DUMMY 10.10.11.11 || true",
+ "$TC class del dev $DUMMY classid 1:1"
+ ],
+ "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11",
+ "expExitCode": "1",
+ "verifyCmd": "$TC -j class ls dev $DUMMY classid 1:1",
+ "matchJSON": [],
+ "teardown": [
+ "$TC qdisc del dev $DUMMY root handle 1: drr"
+ ]
}
]
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index eec82775c5bf..222f0e894a0c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2572,6 +2572,8 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
if (r)
goto out_unlock;
+
+ cond_resched();
}
kvm_handle_gfn_range(kvm, &pre_set_range);
@@ -2580,6 +2582,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
GFP_KERNEL_ACCOUNT));
KVM_BUG_ON(r, kvm);
+ cond_resched();
}
kvm_handle_gfn_range(kvm, &post_set_range);