| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <2025030719-macaw-zero-17ca@gregkh>
Date: Fri, 7 Mar 2025 17:25:43 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org,
akpm@...ux-foundation.org,
torvalds@...ux-foundation.org,
stable@...r.kernel.org
Cc: lwn@....net,
jslaby@...e.cz,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Subject: Re: Linux 6.6.81
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d83a3f47e200..184f2f96f6a5 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3287,6 +3287,11 @@
mga= [HW,DRM]
+ microcode.force_minrev= [X86]
+ Format: <bool>
+ Enable or disable the microcode minimal revision
+ enforcement for the runtime microcode loader.
+
min_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory below this
physical address is ignored.
diff --git a/Makefile b/Makefile
index 67c5799f259e..892ed237b1e1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 6
-SUBLEVEL = 80
+SUBLEVEL = 81
EXTRAVERSION =
NAME = Pinguïn Aangedreven
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index 5fcc5f32be2d..2963d634baba 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -367,6 +367,11 @@ &u2phy_host {
status = "okay";
};
+&uart5 {
+ /delete-property/ dmas;
+ /delete-property/ dma-names;
+};
+
/* Mule UCAN */
&usb_host0_ehci {
status = "okay";
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index fc8130f995c1..6907c456ac8c 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \
_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \
: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
- : [ov] "Jr" (oldval), [nv] "Jr" (newval)
+ : [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
: "memory");
__disable_user_access();
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 1ebf20dfbaa6..459e61ad7d2b 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -236,8 +236,9 @@ struct kvm_vcpu_arch {
/* Cache pages needed to program page tables with spinlock held */
struct kvm_mmu_memory_cache mmu_page_cache;
- /* VCPU power-off state */
- bool power_off;
+ /* VCPU power state */
+ struct kvm_mp_state mp_state;
+ spinlock_t mp_state_lock;
/* Don't run the VCPU (blocked) */
bool pause;
@@ -351,7 +352,10 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu);
bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
+void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu);
#endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b2608..048b9b23d754 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -211,12 +211,6 @@ static size_t get_rt_frame_size(bool cal_all)
if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
total_context_size += riscv_v_sc_size;
}
- /*
- * Preserved a __riscv_ctx_hdr for END signal context header if an
- * extension uses __riscv_extra_ext_header
- */
- if (total_context_size)
- total_context_size += sizeof(struct __riscv_ctx_hdr);
frame_size += total_context_size;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 82229db1ce73..9584d62c96ee 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -100,6 +100,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
struct kvm_cpu_context *cntx;
struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
+ spin_lock_init(&vcpu->arch.mp_state_lock);
+
/* Mark this VCPU never ran */
vcpu->arch.ran_atleast_once = false;
vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
@@ -193,7 +195,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
- !vcpu->arch.power_off && !vcpu->arch.pause);
+ !kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause);
}
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
@@ -421,26 +423,42 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask);
}
-void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
+void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
{
- vcpu->arch.power_off = true;
+ WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
kvm_make_request(KVM_REQ_SLEEP, vcpu);
kvm_vcpu_kick(vcpu);
}
-void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
{
- vcpu->arch.power_off = false;
+ spin_lock(&vcpu->arch.mp_state_lock);
+ __kvm_riscv_vcpu_power_off(vcpu);
+ spin_unlock(&vcpu->arch.mp_state_lock);
+}
+
+void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
+{
+ WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE);
kvm_vcpu_wake_up(vcpu);
}
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
+{
+ spin_lock(&vcpu->arch.mp_state_lock);
+ __kvm_riscv_vcpu_power_on(vcpu);
+ spin_unlock(&vcpu->arch.mp_state_lock);
+}
+
+bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu)
+{
+ return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED;
+}
+
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- if (vcpu->arch.power_off)
- mp_state->mp_state = KVM_MP_STATE_STOPPED;
- else
- mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+ *mp_state = READ_ONCE(vcpu->arch.mp_state);
return 0;
}
@@ -450,17 +468,21 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
{
int ret = 0;
+ spin_lock(&vcpu->arch.mp_state_lock);
+
switch (mp_state->mp_state) {
case KVM_MP_STATE_RUNNABLE:
- vcpu->arch.power_off = false;
+ WRITE_ONCE(vcpu->arch.mp_state, *mp_state);
break;
case KVM_MP_STATE_STOPPED:
- kvm_riscv_vcpu_power_off(vcpu);
+ __kvm_riscv_vcpu_power_off(vcpu);
break;
default:
ret = -EINVAL;
}
+ spin_unlock(&vcpu->arch.mp_state_lock);
+
return ret;
}
@@ -561,11 +583,11 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
kvm_vcpu_srcu_read_unlock(vcpu);
rcuwait_wait_event(wait,
- (!vcpu->arch.power_off) && (!vcpu->arch.pause),
+ (!kvm_riscv_vcpu_stopped(vcpu)) && (!vcpu->arch.pause),
TASK_INTERRUPTIBLE);
kvm_vcpu_srcu_read_lock(vcpu);
- if (vcpu->arch.power_off || vcpu->arch.pause) {
+ if (kvm_riscv_vcpu_stopped(vcpu) || vcpu->arch.pause) {
/*
* Awaken to handle a signal, request to
* sleep again later.
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index 7a7fe40d0930..be43278109f4 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -102,8 +102,11 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
unsigned long i;
struct kvm_vcpu *tmp;
- kvm_for_each_vcpu(i, tmp, vcpu->kvm)
- tmp->arch.power_off = true;
+ kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+ spin_lock(&vcpu->arch.mp_state_lock);
+ WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
+ spin_unlock(&vcpu->arch.mp_state_lock);
+ }
kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
memset(&run->system_event, 0, sizeof(run->system_event));
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index 7dca0e9381d9..7e349b4ee926 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -18,12 +18,18 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu)
struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
struct kvm_vcpu *target_vcpu;
unsigned long target_vcpuid = cp->a0;
+ int ret = 0;
target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
if (!target_vcpu)
return SBI_ERR_INVALID_PARAM;
- if (!target_vcpu->arch.power_off)
- return SBI_ERR_ALREADY_AVAILABLE;
+
+ spin_lock(&target_vcpu->arch.mp_state_lock);
+
+ if (!kvm_riscv_vcpu_stopped(target_vcpu)) {
+ ret = SBI_ERR_ALREADY_AVAILABLE;
+ goto out;
+ }
reset_cntx = &target_vcpu->arch.guest_reset_context;
/* start address */
@@ -34,19 +40,31 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu)
reset_cntx->a1 = cp->a2;
kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu);
- kvm_riscv_vcpu_power_on(target_vcpu);
+ __kvm_riscv_vcpu_power_on(target_vcpu);
- return 0;
+out:
+ spin_unlock(&target_vcpu->arch.mp_state_lock);
+
+ return ret;
}
static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.power_off)
- return SBI_ERR_FAILURE;
+ int ret = 0;
- kvm_riscv_vcpu_power_off(vcpu);
+ spin_lock(&vcpu->arch.mp_state_lock);
- return 0;
+ if (kvm_riscv_vcpu_stopped(vcpu)) {
+ ret = SBI_ERR_FAILURE;
+ goto out;
+ }
+
+ __kvm_riscv_vcpu_power_off(vcpu);
+
+out:
+ spin_unlock(&vcpu->arch.mp_state_lock);
+
+ return ret;
}
static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
@@ -58,12 +76,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
if (!target_vcpu)
return SBI_ERR_INVALID_PARAM;
- if (!target_vcpu->arch.power_off)
- return SBI_HSM_STATE_STARTED;
- else if (vcpu->stat.generic.blocking)
+ if (kvm_riscv_vcpu_stopped(target_vcpu))
+ return SBI_HSM_STATE_STOPPED;
+ else if (target_vcpu->stat.generic.blocking)
return SBI_HSM_STATE_SUSPENDED;
else
- return SBI_HSM_STATE_STOPPED;
+ return SBI_HSM_STATE_STARTED;
}
static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
@@ -71,14 +89,11 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
{
int ret = 0;
struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
- struct kvm *kvm = vcpu->kvm;
unsigned long funcid = cp->a6;
switch (funcid) {
case SBI_EXT_HSM_HART_START:
- mutex_lock(&kvm->lock);
ret = kvm_sbi_hsm_vcpu_start(vcpu);
- mutex_unlock(&kvm->lock);
break;
case SBI_EXT_HSM_HART_STOP:
ret = kvm_sbi_hsm_vcpu_stop(vcpu);
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 7c4d5d38a339..87ec68ed52d7 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
u64 next_cycle;
if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
- retdata->err_val = SBI_ERR_INVALID_PARAM;
+ retdata->err_val = SBI_ERR_NOT_SUPPORTED;
return 0;
}
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
unsigned long hmask = cp->a0;
unsigned long hbase = cp->a1;
+ unsigned long hart_bit = 0, sentmask = 0;
if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
- retdata->err_val = SBI_ERR_INVALID_PARAM;
+ retdata->err_val = SBI_ERR_NOT_SUPPORTED;
return 0;
}
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
if (hbase != -1UL) {
if (tmp->vcpu_id < hbase)
continue;
- if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+ hart_bit = tmp->vcpu_id - hbase;
+ if (hart_bit >= __riscv_xlen)
+ goto done;
+ if (!(hmask & (1UL << hart_bit)))
continue;
}
ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
if (ret < 0)
break;
+ sentmask |= 1UL << hart_bit;
kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
}
+done:
+ if (hbase != -1UL && (hmask ^ sentmask))
+ retdata->err_val = SBI_ERR_INVALID_PARAM;
+
return ret;
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 989d432b5834..1e666454ebdc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1313,17 +1313,39 @@ config X86_REBOOTFIXUPS
config MICROCODE
def_bool y
depends on CPU_SUP_AMD || CPU_SUP_INTEL
+ select CRYPTO_LIB_SHA256 if CPU_SUP_AMD
config MICROCODE_LATE_LOADING
bool "Late microcode loading (DANGEROUS)"
default n
- depends on MICROCODE
+ depends on MICROCODE && SMP
help
Loading microcode late, when the system is up and executing instructions
is a tricky business and should be avoided if possible. Just the sequence
of synchronizing all cores and SMT threads is one fragile dance which does
not guarantee that cores might not softlock after the loading. Therefore,
- use this at your own risk. Late loading taints the kernel too.
+ use this at your own risk. Late loading taints the kernel unless the
+ microcode header indicates that it is safe for late loading via the
+ minimal revision check. This minimal revision check can be enforced on
+ the kernel command line with "microcode.minrev=Y".
+
+config MICROCODE_LATE_FORCE_MINREV
+ bool "Enforce late microcode loading minimal revision check"
+ default n
+ depends on MICROCODE_LATE_LOADING
+ help
+ To prevent that users load microcode late which modifies already
+ in use features, newer microcode patches have a minimum revision field
+ in the microcode header, which tells the kernel which minimum
+ revision must be active in the CPU to safely load that new microcode
+ late into the running system. If disabled the check will not
+ be enforced but the kernel will be tainted when the minimal
+ revision check fails.
+
+ This minimal revision check can also be controlled via the
+ "microcode.minrev" parameter on the kernel command line.
+
+ If unsure say Y.
config X86_MSR
tristate "/dev/cpu/*/msr - Model-specific register support"
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 150a365b4fbc..1458ccaa6a05 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -623,7 +623,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.type == event->pmu->type)
event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
- if (event->attr.sample_period && x86_pmu.limit_period) {
+ if (!event->attr.freq && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
x86_pmu.limit_period(event, &left);
if (left > event->attr.sample_period)
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 33aa0c31c21c..a2258c894244 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -277,7 +277,8 @@ struct apic {
u32 disable_esr : 1,
dest_mode_logical : 1,
- x2apic_set_max_apicid : 1;
+ x2apic_set_max_apicid : 1,
+ nmi_to_offline_cpu : 1;
u32 (*calc_dest_apicid)(unsigned int cpu);
@@ -543,6 +544,8 @@ extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
extern int default_cpu_present_to_apicid(int mps_cpu);
+void apic_send_nmi_to_offline_cpu(unsigned int cpu);
+
#else /* CONFIG_X86_LOCAL_APIC */
static inline unsigned int read_apic_id(void) { return 0; }
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 25050d953eee..fecc4fe1d68a 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -71,26 +71,12 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
extern __noendbr void cet_disable(void);
-struct ucode_cpu_info;
+struct cpu_signature;
-int intel_cpu_collect_info(struct ucode_cpu_info *uci);
-
-static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1,
- unsigned int s2, unsigned int p2)
-{
- if (s1 != s2)
- return false;
-
- /* Processor flags are either both 0 ... */
- if (!p1 && !p2)
- return true;
-
- /* ... or they intersect. */
- return p1 & p2;
-}
+void intel_collect_cpu_info(struct cpu_signature *sig);
extern u64 x86_read_arch_cap_msr(void);
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf);
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig);
int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type);
extern struct cpumask cpus_stop_mask;
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index bbbe9d744977..1ab475a518e9 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -68,11 +68,19 @@ static inline u32 intel_get_microcode_revision(void)
return rev;
}
+#endif /* !CONFIG_CPU_SUP_INTEL */
-void show_ucode_info_early(void);
+bool microcode_nmi_handler(void);
+void microcode_offline_nmi_handler(void);
-#else /* CONFIG_CPU_SUP_INTEL */
-static inline void show_ucode_info_early(void) { }
-#endif /* !CONFIG_CPU_SUP_INTEL */
+#ifdef CONFIG_MICROCODE_LATE_LOADING
+DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable);
+static __always_inline bool microcode_nmi_handler_enabled(void)
+{
+ return static_branch_unlikely(µcode_nmi_handler_enable);
+}
+#else
+static __always_inline bool microcode_nmi_handler_enabled(void) { return false; }
+#endif
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 032a84e2c3cc..cd16228611ce 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -103,6 +103,7 @@ static struct apic apic_flat __ro_after_init = {
.send_IPI_allbutself = default_send_IPI_allbutself,
.send_IPI_all = default_send_IPI_all,
.send_IPI_self = default_send_IPI_self,
+ .nmi_to_offline_cpu = true,
.read = native_apic_mem_read,
.write = native_apic_mem_write,
@@ -175,6 +176,7 @@ static struct apic apic_physflat __ro_after_init = {
.send_IPI_allbutself = default_send_IPI_allbutself,
.send_IPI_all = default_send_IPI_all,
.send_IPI_self = default_send_IPI_self,
+ .nmi_to_offline_cpu = true,
.read = native_apic_mem_read,
.write = native_apic_mem_write,
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index a44ba7209ef3..edad86f32e38 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -97,6 +97,14 @@ void native_send_call_func_ipi(const struct cpumask *mask)
__apic_send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
}
+void apic_send_nmi_to_offline_cpu(unsigned int cpu)
+{
+ if (WARN_ON_ONCE(!apic->nmi_to_offline_cpu))
+ return;
+ if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, &cpus_booted_once_mask)))
+ return;
+ apic->send_IPI(cpu, NMI_VECTOR);
+}
#endif /* CONFIG_SMP */
static inline int __prepare_ICR2(unsigned int mask)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index affbff65e497..a8306089c91b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -251,6 +251,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
.send_IPI_all = x2apic_send_IPI_all,
.send_IPI_self = x2apic_send_IPI_self,
+ .nmi_to_offline_cpu = true,
.read = native_apic_msr_read,
.write = native_apic_msr_write,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 788cdb4ee394..c8ac1b12b8ac 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -166,6 +166,7 @@ static struct apic apic_x2apic_phys __ro_after_init = {
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
.send_IPI_all = x2apic_send_IPI_all,
.send_IPI_self = x2apic_send_IPI_self,
+ .nmi_to_offline_cpu = true,
.read = native_apic_msr_read,
.write = native_apic_msr_write,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8bc90a501e7b..a844110691f9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2224,8 +2224,6 @@ static inline void setup_getcpu(int cpu)
}
#ifdef CONFIG_X86_64
-static inline void ucode_cpu_init(int cpu) { }
-
static inline void tss_setup_ist(struct tss_struct *tss)
{
/* Set up the per-CPU TSS IST stacks */
@@ -2236,16 +2234,8 @@ static inline void tss_setup_ist(struct tss_struct *tss)
/* Only mapped when SEV-ES is active */
tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC);
}
-
#else /* CONFIG_X86_64 */
-
-static inline void ucode_cpu_init(int cpu)
-{
- show_ucode_info_early();
-}
-
static inline void tss_setup_ist(struct tss_struct *tss) { }
-
#endif /* !CONFIG_X86_64 */
static inline void tss_setup_io_bitmap(struct tss_struct *tss)
@@ -2301,8 +2291,6 @@ void cpu_init(void)
struct task_struct *cur = current;
int cpu = raw_smp_processor_id();
- ucode_cpu_init(cpu);
-
#ifdef CONFIG_NUMA
if (this_cpu_read(numa_node) == 0 &&
early_cpu_to_node(cpu) != NUMA_NO_NODE)
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1..dfec2c61e354 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
u8 ccr3;
local_irq_save(flags);
- /* Suspend on halt power saving and enable #SUSP pin */
- setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+ /* Suspend on halt power saving */
+ setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
ccr3 = getCx86(CX86_CCR3);
setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index bbd1dc38ea03..13a632da09ed 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -23,20 +23,35 @@
#include <linux/earlycpio.h>
#include <linux/firmware.h>
+#include <linux/bsearch.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/initrd.h>
#include <linux/kernel.h>
#include <linux/pci.h>
+#include <crypto/sha2.h>
+
#include <asm/microcode.h>
#include <asm/processor.h>
+#include <asm/cmdline.h>
#include <asm/setup.h>
#include <asm/cpu.h>
#include <asm/msr.h>
+#include <asm/tlb.h>
#include "internal.h"
+struct ucode_patch {
+ struct list_head plist;
+ void *data;
+ unsigned int size;
+ u32 patch_id;
+ u16 equiv_cpu;
+};
+
+static LIST_HEAD(microcode_cache);
+
#define UCODE_MAGIC 0x00414d44
#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
#define UCODE_UCODE_TYPE 0x00000001
@@ -81,6 +96,31 @@ static struct equiv_cpu_table {
struct equiv_cpu_entry *entry;
} equiv_table;
+union zen_patch_rev {
+ struct {
+ __u32 rev : 8,
+ stepping : 4,
+ model : 4,
+ __reserved : 4,
+ ext_model : 4,
+ ext_fam : 8;
+ };
+ __u32 ucode_rev;
+};
+
+union cpuid_1_eax {
+ struct {
+ __u32 stepping : 4,
+ model : 4,
+ family : 4,
+ __reserved0 : 4,
+ ext_model : 4,
+ ext_fam : 8,
+ __reserved1 : 4;
+ };
+ __u32 full;
+};
+
/*
* This points to the current valid container of microcode patches which we will
* save from the initrd/builtin before jettisoning its contents. @mc is the
@@ -88,14 +128,11 @@ static struct equiv_cpu_table {
*/
struct cont_desc {
struct microcode_amd *mc;
- u32 cpuid_1_eax;
u32 psize;
u8 *data;
size_t size;
};
-static u32 ucode_new_rev;
-
/*
* Microcode patch container file is prepended to the initrd in cpio
* format. See Documentation/arch/x86/microcode.rst
@@ -103,10 +140,143 @@ static u32 ucode_new_rev;
static const char
ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
+/*
+ * This is CPUID(1).EAX on the BSP. It is used in two ways:
+ *
+ * 1. To ignore the equivalence table on Zen1 and newer.
+ *
+ * 2. To match which patches to load because the patch revision ID
+ * already contains the f/m/s for which the microcode is destined
+ * for.
+ */
+static u32 bsp_cpuid_1_eax __ro_after_init;
+
+static bool sha_check = true;
+
+struct patch_digest {
+ u32 patch_id;
+ u8 sha256[SHA256_DIGEST_SIZE];
+};
+
+#include "amd_shas.c"
+
+static int cmp_id(const void *key, const void *elem)
+{
+ struct patch_digest *pd = (struct patch_digest *)elem;
+ u32 patch_id = *(u32 *)key;
+
+ if (patch_id == pd->patch_id)
+ return 0;
+ else if (patch_id < pd->patch_id)
+ return -1;
+ else
+ return 1;
+}
+
+static bool need_sha_check(u32 cur_rev)
+{
+ switch (cur_rev >> 8) {
+ case 0x80012: return cur_rev <= 0x800126f; break;
+ case 0x83010: return cur_rev <= 0x830107c; break;
+ case 0x86001: return cur_rev <= 0x860010e; break;
+ case 0x86081: return cur_rev <= 0x8608108; break;
+ case 0x87010: return cur_rev <= 0x8701034; break;
+ case 0x8a000: return cur_rev <= 0x8a0000a; break;
+ case 0xa0011: return cur_rev <= 0xa0011da; break;
+ case 0xa0012: return cur_rev <= 0xa001243; break;
+ case 0xa1011: return cur_rev <= 0xa101153; break;
+ case 0xa1012: return cur_rev <= 0xa10124e; break;
+ case 0xa1081: return cur_rev <= 0xa108109; break;
+ case 0xa2010: return cur_rev <= 0xa20102f; break;
+ case 0xa2012: return cur_rev <= 0xa201212; break;
+ case 0xa6012: return cur_rev <= 0xa60120a; break;
+ case 0xa7041: return cur_rev <= 0xa704109; break;
+ case 0xa7052: return cur_rev <= 0xa705208; break;
+ case 0xa7080: return cur_rev <= 0xa708009; break;
+ case 0xa70c0: return cur_rev <= 0xa70C009; break;
+ case 0xaa002: return cur_rev <= 0xaa00218; break;
+ default: break;
+ }
+
+ pr_info("You should not be seeing this. Please send the following couple of lines to x86-<at>-kernel.org\n");
+ pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev);
+ return true;
+}
+
+static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
+{
+ struct patch_digest *pd = NULL;
+ u8 digest[SHA256_DIGEST_SIZE];
+ struct sha256_state s;
+ int i;
+
+ if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
+ x86_family(bsp_cpuid_1_eax) > 0x19)
+ return true;
+
+ if (!need_sha_check(cur_rev))
+ return true;
+
+ if (!sha_check)
+ return true;
+
+ pd = bsearch(&patch_id, phashes, ARRAY_SIZE(phashes), sizeof(struct patch_digest), cmp_id);
+ if (!pd) {
+ pr_err("No sha256 digest for patch ID: 0x%x found\n", patch_id);
+ return false;
+ }
+
+ sha256_init(&s);
+ sha256_update(&s, data, len);
+ sha256_final(&s, digest);
+
+ if (memcmp(digest, pd->sha256, sizeof(digest))) {
+ pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE; i++)
+ pr_cont("0x%x ", digest[i]);
+ pr_info("\n");
+
+ return false;
+ }
+
+ return true;
+}
+
+static u32 get_patch_level(void)
+{
+ u32 rev, dummy __always_unused;
+
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+ return rev;
+}
+
+static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val)
+{
+ union zen_patch_rev p;
+ union cpuid_1_eax c;
+
+ p.ucode_rev = val;
+ c.full = 0;
+
+ c.stepping = p.stepping;
+ c.model = p.model;
+ c.ext_model = p.ext_model;
+ c.family = 0xf;
+ c.ext_fam = p.ext_fam;
+
+ return c;
+}
+
static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
{
unsigned int i;
+ /* Zen and newer do not need an equivalence table. */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17)
+ return 0;
+
if (!et || !et->num_entries)
return 0;
@@ -121,24 +291,20 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
/*
* Check whether there is a valid microcode container file at the beginning
- * of @buf of size @buf_size. Set @early to use this function in the early path.
+ * of @buf of size @buf_size.
*/
-static bool verify_container(const u8 *buf, size_t buf_size, bool early)
+static bool verify_container(const u8 *buf, size_t buf_size)
{
u32 cont_magic;
if (buf_size <= CONTAINER_HDR_SZ) {
- if (!early)
- pr_debug("Truncated microcode container header.\n");
-
+ pr_debug("Truncated microcode container header.\n");
return false;
}
cont_magic = *(const u32 *)buf;
if (cont_magic != UCODE_MAGIC) {
- if (!early)
- pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
-
+ pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
return false;
}
@@ -147,23 +313,24 @@ static bool verify_container(const u8 *buf, size_t buf_size, bool early)
/*
* Check whether there is a valid, non-truncated CPU equivalence table at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
*/
-static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
+static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
{
const u32 *hdr = (const u32 *)buf;
u32 cont_type, equiv_tbl_len;
- if (!verify_container(buf, buf_size, early))
+ if (!verify_container(buf, buf_size))
return false;
+ /* Zen and newer do not need an equivalence table. */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17)
+ return true;
+
cont_type = hdr[1];
if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) {
- if (!early)
- pr_debug("Wrong microcode container equivalence table type: %u.\n",
- cont_type);
-
+ pr_debug("Wrong microcode container equivalence table type: %u.\n",
+ cont_type);
return false;
}
@@ -172,9 +339,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
equiv_tbl_len = hdr[2];
if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) ||
buf_size < equiv_tbl_len) {
- if (!early)
- pr_debug("Truncated equivalence table.\n");
-
+ pr_debug("Truncated equivalence table.\n");
return false;
}
@@ -183,22 +348,19 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
/*
* Check whether there is a valid, non-truncated microcode patch section at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
*
* On success, @sh_psize returns the patch size according to the section header,
* to the caller.
*/
static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early)
+__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
{
u32 p_type, p_size;
const u32 *hdr;
if (buf_size < SECTION_HDR_SIZE) {
- if (!early)
- pr_debug("Truncated patch section.\n");
-
+ pr_debug("Truncated patch section.\n");
return false;
}
@@ -207,17 +369,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early
p_size = hdr[1];
if (p_type != UCODE_UCODE_TYPE) {
- if (!early)
- pr_debug("Invalid type field (0x%x) in container file section header.\n",
- p_type);
-
+ pr_debug("Invalid type field (0x%x) in container file section header.\n",
+ p_type);
return false;
}
if (p_size < sizeof(struct microcode_header_amd)) {
- if (!early)
- pr_debug("Patch of size %u too short.\n", p_size);
-
+ pr_debug("Patch of size %u too short.\n", p_size);
return false;
}
@@ -232,12 +390,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early
* exceed the per-family maximum). @sh_psize is the size read from the section
* header.
*/
-static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size)
+static bool __verify_patch_size(u32 sh_psize, size_t buf_size)
{
+ u8 family = x86_family(bsp_cpuid_1_eax);
u32 max_size;
if (family >= 0x15)
- return min_t(u32, sh_psize, buf_size);
+ goto ret;
#define F1XH_MPB_MAX_SIZE 2048
#define F14H_MPB_MAX_SIZE 1824
@@ -251,13 +410,15 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size
break;
default:
WARN(1, "%s: WTF family: 0x%x\n", __func__, family);
- return 0;
+ return false;
}
- if (sh_psize > min_t(u32, buf_size, max_size))
- return 0;
+ if (sh_psize > max_size)
+ return false;
- return sh_psize;
+ret:
+ /* Working with the whole buffer so < is ok. */
+ return sh_psize <= buf_size;
}
/*
@@ -268,16 +429,15 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size
* positive: patch is not for this family, skip it
* 0: success
*/
-static int
-verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early)
+static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size)
{
+ u8 family = x86_family(bsp_cpuid_1_eax);
struct microcode_header_amd *mc_hdr;
- unsigned int ret;
u32 sh_psize;
u16 proc_id;
u8 patch_fam;
- if (!__verify_patch_section(buf, buf_size, &sh_psize, early))
+ if (!__verify_patch_section(buf, buf_size, &sh_psize))
return -1;
/*
@@ -292,16 +452,12 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
* size sh_psize, as the section claims.
*/
if (buf_size < sh_psize) {
- if (!early)
- pr_debug("Patch of size %u truncated.\n", sh_psize);
-
+ pr_debug("Patch of size %u truncated.\n", sh_psize);
return -1;
}
- ret = __verify_patch_size(family, sh_psize, buf_size);
- if (!ret) {
- if (!early)
- pr_debug("Per-family patch size mismatch.\n");
+ if (!__verify_patch_size(sh_psize, buf_size)) {
+ pr_debug("Per-family patch size mismatch.\n");
return -1;
}
@@ -309,8 +465,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
mc_hdr = (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE);
if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
- if (!early)
- pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
+ pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
return -1;
}
@@ -322,6 +477,15 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
return 0;
}
+static bool mc_patch_matches(struct microcode_amd *mc, u16 eq_id)
+{
+ /* Zen and newer do not need an equivalence table. */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17)
+ return ucode_rev_to_cpuid(mc->hdr.patch_id).full == bsp_cpuid_1_eax;
+ else
+ return eq_id == mc->hdr.processor_rev_id;
+}
+
/*
* This scans the ucode blob for the proper container as we can have multiple
* containers glued together. Returns the equivalence ID from the equivalence
@@ -337,7 +501,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
u16 eq_id;
u8 *buf;
- if (!verify_equivalence_table(ucode, size, true))
+ if (!verify_equivalence_table(ucode, size))
return 0;
buf = ucode;
@@ -350,7 +514,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
* doesn't contain a patch for the CPU, scan through the whole container
* so that it can be skipped in case there are other containers appended.
*/
- eq_id = find_equiv_id(&table, desc->cpuid_1_eax);
+ eq_id = find_equiv_id(&table, bsp_cpuid_1_eax);
buf += hdr[2] + CONTAINER_HDR_SZ;
size -= hdr[2] + CONTAINER_HDR_SZ;
@@ -364,7 +528,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
u32 patch_size;
int ret;
- ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
+ ret = verify_patch(buf, size, &patch_size);
if (ret < 0) {
/*
* Patch verification failed, skip to the next container, if
@@ -377,7 +541,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
}
mc = (struct microcode_amd *)(buf + SECTION_HDR_SIZE);
- if (eq_id == mc->hdr.processor_rev_id) {
+ if (mc_patch_matches(mc, eq_id)) {
desc->psize = patch_size;
desc->mc = mc;
}
@@ -427,73 +591,42 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
}
}
-static int __apply_microcode_amd(struct microcode_amd *mc)
+static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
+ unsigned int psize)
{
- u32 rev, dummy;
+ unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
- native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code);
-
- /* verify patch application was successful */
- native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- if (rev != mc->hdr.patch_id)
+ if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
return -1;
- return 0;
-}
-
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- *
- * Returns true if container found (sets @desc), false otherwise.
- */
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
-{
- struct cont_desc desc = { 0 };
- struct microcode_amd *mc;
- u32 rev, dummy, *new_rev;
- bool ret = false;
-
-#ifdef CONFIG_X86_32
- new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-#else
- new_rev = &ucode_new_rev;
-#endif
-
- desc.cpuid_1_eax = cpuid_1_eax;
-
- scan_containers(ucode, size, &desc);
-
- mc = desc.mc;
- if (!mc)
- return ret;
+ native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
- native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+ if (x86_family(bsp_cpuid_1_eax) == 0x17) {
+ unsigned long p_addr_end = p_addr + psize - 1;
- /*
- * Allow application of the same revision to pick up SMT-specific
- * changes even if the revision of the other SMT thread is already
- * up-to-date.
- */
- if (rev > mc->hdr.patch_id)
- return ret;
+ invlpg(p_addr);
- if (!__apply_microcode_amd(mc)) {
- *new_rev = mc->hdr.patch_id;
- ret = true;
+ /*
+ * Flush next page too if patch image is crossing a page
+ * boundary.
+ */
+ if (p_addr >> PAGE_SHIFT != p_addr_end >> PAGE_SHIFT)
+ invlpg(p_addr_end);
}
- return ret;
+ /* verify patch application was successful */
+ *cur_rev = get_patch_level();
+ if (*cur_rev != mc->hdr.patch_id)
+ return false;
+
+ return true;
}
-static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
+
+static bool get_builtin_microcode(struct cpio_data *cp)
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
+ u8 family = x86_family(bsp_cpuid_1_eax);
struct firmware fw;
if (IS_ENABLED(CONFIG_X86_32))
@@ -512,93 +645,144 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
return false;
}
-static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
+static bool __init find_blobs_in_containers(struct cpio_data *ret)
{
- struct ucode_cpu_info *uci;
struct cpio_data cp;
- const char *path;
- bool use_pa;
-
- if (IS_ENABLED(CONFIG_X86_32)) {
- uci = (struct ucode_cpu_info *)__pa_nodebug(ucode_cpu_info);
- path = (const char *)__pa_nodebug(ucode_path);
- use_pa = true;
- } else {
- uci = ucode_cpu_info;
- path = ucode_path;
- use_pa = false;
- }
+ bool found;
- if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax)))
- cp = find_microcode_in_initrd(path, use_pa);
+ if (!get_builtin_microcode(&cp))
+ cp = find_microcode_in_initrd(ucode_path);
- /* Needed in load_microcode_amd() */
- uci->cpu_sig.sig = cpuid_1_eax;
+ found = cp.data && cp.size;
+ if (found)
+ *ret = cp;
- *ret = cp;
+ return found;
}
-static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
+void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
{
+ struct cont_desc desc = { };
+ struct microcode_amd *mc;
struct cpio_data cp = { };
+ char buf[4];
+ u32 rev;
+
+ if (cmdline_find_option(boot_command_line, "microcode.amd_sha_check", buf, 4)) {
+ if (!strncmp(buf, "off", 3)) {
+ sha_check = false;
+ pr_warn_once("It is a very very bad idea to disable the blobs SHA check!\n");
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+ }
+ }
- find_blobs_in_containers(cpuid_1_eax, &cp);
- if (!(cp.data && cp.size))
- return;
+ bsp_cpuid_1_eax = cpuid_1_eax;
- early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
-}
+ rev = get_patch_level();
+ ed->old_rev = rev;
-void load_ucode_amd_early(unsigned int cpuid_1_eax)
-{
- return apply_ucode_from_containers(cpuid_1_eax);
-}
+ /* Needed in load_microcode_amd() */
+ ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
-static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+ if (!find_blobs_in_containers(&cp))
+ return;
-int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
-{
- struct cont_desc desc = { 0 };
- enum ucode_state ret;
- struct cpio_data cp;
+ scan_containers(cp.data, cp.size, &desc);
- cp = find_microcode_in_initrd(ucode_path, false);
- if (!(cp.data && cp.size))
- return -EINVAL;
+ mc = desc.mc;
+ if (!mc)
+ return;
- desc.cpuid_1_eax = cpuid_1_eax;
+ /*
+ * Allow application of the same revision to pick up SMT-specific
+ * changes even if the revision of the other SMT thread is already
+ * up-to-date.
+ */
+ if (ed->old_rev > mc->hdr.patch_id)
+ return;
- scan_containers(cp.data, cp.size, &desc);
- if (!desc.mc)
- return -EINVAL;
+ if (__apply_microcode_amd(mc, &rev, desc.psize))
+ ed->new_rev = rev;
+}
- ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
- if (ret > UCODE_UPDATED)
- return -EINVAL;
+static inline bool patch_cpus_equivalent(struct ucode_patch *p,
+ struct ucode_patch *n,
+ bool ignore_stepping)
+{
+ /* Zen and newer hardcode the f/m/s in the patch ID */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
+ union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id);
+ union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id);
+
+ if (ignore_stepping) {
+ p_cid.stepping = 0;
+ n_cid.stepping = 0;
+ }
- return 0;
+ return p_cid.full == n_cid.full;
+ } else {
+ return p->equiv_cpu == n->equiv_cpu;
+ }
}
/*
* a small, trivial cache of per-family ucode patches
*/
-static struct ucode_patch *cache_find_patch(u16 equiv_cpu)
+static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equiv_cpu)
{
struct ucode_patch *p;
+ struct ucode_patch n;
+
+ n.equiv_cpu = equiv_cpu;
+ n.patch_id = uci->cpu_sig.rev;
+
+ WARN_ON_ONCE(!n.patch_id);
list_for_each_entry(p, µcode_cache, plist)
- if (p->equiv_cpu == equiv_cpu)
+ if (patch_cpus_equivalent(p, &n, false))
return p;
+
return NULL;
}
+static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n)
+{
+ /* Zen and newer hardcode the f/m/s in the patch ID */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
+ union zen_patch_rev zp, zn;
+
+ zp.ucode_rev = p->patch_id;
+ zn.ucode_rev = n->patch_id;
+
+ if (zn.stepping != zp.stepping)
+ return -1;
+
+ return zn.rev > zp.rev;
+ } else {
+ return n->patch_id > p->patch_id;
+ }
+}
+
static void update_cache(struct ucode_patch *new_patch)
{
struct ucode_patch *p;
+ int ret;
list_for_each_entry(p, µcode_cache, plist) {
- if (p->equiv_cpu == new_patch->equiv_cpu) {
- if (p->patch_id >= new_patch->patch_id) {
+ if (patch_cpus_equivalent(p, new_patch, true)) {
+ ret = patch_newer(p, new_patch);
+ if (ret < 0)
+ continue;
+ else if (!ret) {
/* we already have the latest patch */
kfree(new_patch->data);
kfree(new_patch);
@@ -629,14 +813,17 @@ static void free_cache(void)
static struct ucode_patch *find_patch(unsigned int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- u16 equiv_id;
+ u16 equiv_id = 0;
+ uci->cpu_sig.rev = get_patch_level();
- equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
- if (!equiv_id)
- return NULL;
+ if (x86_family(bsp_cpuid_1_eax) < 0x17) {
+ equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
+ if (!equiv_id)
+ return NULL;
+ }
- return cache_find_patch(equiv_id);
+ return cache_find_patch(uci, equiv_id);
}
void reload_ucode_amd(unsigned int cpu)
@@ -651,24 +838,20 @@ void reload_ucode_amd(unsigned int cpu)
mc = p->data;
- rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
+ rev = get_patch_level();
if (rev < mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc)) {
- ucode_new_rev = mc->hdr.patch_id;
- pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
- }
+ if (__apply_microcode_amd(mc, &rev, p->size))
+ pr_info_once("reload revision: 0x%08x\n", rev);
}
}
static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu);
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
struct ucode_patch *p;
csig->sig = cpuid_eax(0x00000001);
- csig->rev = c->microcode;
+ csig->rev = get_patch_level();
/*
* a patch could have been loaded early, set uci->mc so that
@@ -678,8 +861,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
if (p && (p->patch_id == csig->rev))
uci->mc = p->data;
- pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
-
return 0;
}
@@ -690,7 +871,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
struct ucode_cpu_info *uci;
struct ucode_patch *p;
enum ucode_state ret;
- u32 rev, dummy __always_unused;
+ u32 rev;
BUG_ON(raw_smp_processor_id() != cpu);
@@ -700,18 +881,18 @@ static enum ucode_state apply_microcode_amd(int cpu)
if (!p)
return UCODE_NFOUND;
+ rev = uci->cpu_sig.rev;
+
mc_amd = p->data;
uci->mc = p->data;
- rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
/* need to apply patch? */
if (rev > mc_amd->hdr.patch_id) {
ret = UCODE_OK;
goto out;
}
- if (__apply_microcode_amd(mc_amd)) {
+ if (!__apply_microcode_amd(mc_amd, &rev, p->size)) {
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
return UCODE_ERROR;
@@ -720,8 +901,6 @@ static enum ucode_state apply_microcode_amd(int cpu)
rev = mc_amd->hdr.patch_id;
ret = UCODE_UPDATED;
- pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
-
out:
uci->cpu_sig.rev = rev;
c->microcode = rev;
@@ -733,17 +912,29 @@ static enum ucode_state apply_microcode_amd(int cpu)
return ret;
}
+void load_ucode_amd_ap(unsigned int cpuid_1_eax)
+{
+ unsigned int cpu = smp_processor_id();
+
+ ucode_cpu_info[cpu].cpu_sig.sig = cpuid_1_eax;
+ apply_microcode_amd(cpu);
+}
+
static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
{
u32 equiv_tbl_len;
const u32 *hdr;
- if (!verify_equivalence_table(buf, buf_size, false))
+ if (!verify_equivalence_table(buf, buf_size))
return 0;
hdr = (const u32 *)buf;
equiv_tbl_len = hdr[2];
+ /* Zen and newer do not need an equivalence table. */
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17)
+ goto out;
+
equiv_table.entry = vmalloc(equiv_tbl_len);
if (!equiv_table.entry) {
pr_err("failed to allocate equivalent CPU table\n");
@@ -753,12 +944,16 @@ static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
memcpy(equiv_table.entry, buf + CONTAINER_HDR_SZ, equiv_tbl_len);
equiv_table.num_entries = equiv_tbl_len / sizeof(struct equiv_cpu_entry);
+out:
/* add header length */
return equiv_tbl_len + CONTAINER_HDR_SZ;
}
static void free_equiv_cpu_table(void)
{
+ if (x86_family(bsp_cpuid_1_eax) >= 0x17)
+ return;
+
vfree(equiv_table.entry);
memset(&equiv_table, 0, sizeof(equiv_table));
}
@@ -784,7 +979,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
u16 proc_id;
int ret;
- ret = verify_patch(family, fw, leftover, patch_size, false);
+ ret = verify_patch(fw, leftover, patch_size);
if (ret)
return ret;
@@ -809,7 +1004,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
patch->patch_id = mc_hdr->patch_id;
patch->equiv_cpu = proc_id;
- pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n",
+ pr_debug("%s: Adding patch_id: 0x%08x, proc_id: 0x%04x\n",
__func__, patch->patch_id, proc_id);
/* ... and add to cache. */
@@ -819,8 +1014,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
}
/* Scan the blob in @data and add microcode patches to the cache. */
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
- size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size)
{
u8 *fw = (u8 *)data;
size_t offset;
@@ -853,21 +1047,30 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
return UCODE_OK;
}
-static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size)
{
- struct cpuinfo_x86 *c;
- unsigned int nid, cpu;
- struct ucode_patch *p;
enum ucode_state ret;
/* free old equiv table */
free_equiv_cpu_table();
ret = __load_microcode_amd(family, data, size);
- if (ret != UCODE_OK) {
+ if (ret != UCODE_OK)
cleanup();
+
+ return ret;
+}
+
+static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+{
+ struct cpuinfo_x86 *c;
+ unsigned int nid, cpu;
+ struct ucode_patch *p;
+ enum ucode_state ret;
+
+ ret = _load_microcode_amd(family, data, size);
+ if (ret != UCODE_OK)
return ret;
- }
for_each_node(nid) {
cpu = cpumask_first(cpumask_of_node(nid));
@@ -886,6 +1089,32 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
return ret;
}
+static int __init save_microcode_in_initrd(void)
+{
+ unsigned int cpuid_1_eax = native_cpuid_eax(1);
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+ struct cont_desc desc = { 0 };
+ enum ucode_state ret;
+ struct cpio_data cp;
+
+ if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+ return 0;
+
+ if (!find_blobs_in_containers(&cp))
+ return -EINVAL;
+
+ scan_containers(cp.data, cp.size, &desc);
+ if (!desc.mc)
+ return -EINVAL;
+
+ ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+ if (ret > UCODE_UPDATED)
+ return -EINVAL;
+
+ return 0;
+}
+early_initcall(save_microcode_in_initrd);
+
/*
* AMD microcode firmware naming convention, up to family 15h they are in
* the legacy file:
@@ -909,6 +1138,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
+ if (force_minrev)
+ return UCODE_NFOUND;
+
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
@@ -918,7 +1150,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
}
ret = UCODE_ERROR;
- if (!verify_container(fw->data, fw->size, false))
+ if (!verify_container(fw->data, fw->size))
goto fw_release;
ret = load_microcode_amd(c->x86, fw->data, fw->size);
@@ -938,10 +1170,11 @@ static void microcode_fini_cpu_amd(int cpu)
}
static struct microcode_ops microcode_amd_ops = {
- .request_microcode_fw = request_microcode_amd,
- .collect_cpu_info = collect_cpu_info_amd,
- .apply_microcode = apply_microcode_amd,
- .microcode_fini_cpu = microcode_fini_cpu_amd,
+ .request_microcode_fw = request_microcode_amd,
+ .collect_cpu_info = collect_cpu_info_amd,
+ .apply_microcode = apply_microcode_amd,
+ .microcode_fini_cpu = microcode_fini_cpu_amd,
+ .nmi_safe = true,
};
struct microcode_ops * __init init_amd_microcode(void)
@@ -952,11 +1185,6 @@ struct microcode_ops * __init init_amd_microcode(void)
pr_warn("AMD CPU family 0x%x not supported\n", c->x86);
return NULL;
}
-
- if (ucode_new_rev)
- pr_info_once("microcode updated early to new patch_level=0x%08x\n",
- ucode_new_rev);
-
return µcode_amd_ops;
}
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
new file mode 100644
index 000000000000..2a1655b1fdd8
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -0,0 +1,444 @@
+/* Keep 'em sorted. */
+static const struct patch_digest phashes[] = {
+ { 0x8001227, {
+ 0x99,0xc0,0x9b,0x2b,0xcc,0x9f,0x52,0x1b,
+ 0x1a,0x5f,0x1d,0x83,0xa1,0x6c,0xc4,0x46,
+ 0xe2,0x6c,0xda,0x73,0xfb,0x2d,0x23,0xa8,
+ 0x77,0xdc,0x15,0x31,0x33,0x4a,0x46,0x18,
+ }
+ },
+ { 0x8001250, {
+ 0xc0,0x0b,0x6b,0x19,0xfd,0x5c,0x39,0x60,
+ 0xd5,0xc3,0x57,0x46,0x54,0xe4,0xd1,0xaa,
+ 0xa8,0xf7,0x1f,0xa8,0x6a,0x60,0x3e,0xe3,
+ 0x27,0x39,0x8e,0x53,0x30,0xf8,0x49,0x19,
+ }
+ },
+ { 0x800126e, {
+ 0xf3,0x8b,0x2b,0xb6,0x34,0xe3,0xc8,0x2c,
+ 0xef,0xec,0x63,0x6d,0xc8,0x76,0x77,0xb3,
+ 0x25,0x5a,0xb7,0x52,0x8c,0x83,0x26,0xe6,
+ 0x4c,0xbe,0xbf,0xe9,0x7d,0x22,0x6a,0x43,
+ }
+ },
+ { 0x800126f, {
+ 0x2b,0x5a,0xf2,0x9c,0xdd,0xd2,0x7f,0xec,
+ 0xec,0x96,0x09,0x57,0xb0,0x96,0x29,0x8b,
+ 0x2e,0x26,0x91,0xf0,0x49,0x33,0x42,0x18,
+ 0xdd,0x4b,0x65,0x5a,0xd4,0x15,0x3d,0x33,
+ }
+ },
+ { 0x800820d, {
+ 0x68,0x98,0x83,0xcd,0x22,0x0d,0xdd,0x59,
+ 0x73,0x2c,0x5b,0x37,0x1f,0x84,0x0e,0x67,
+ 0x96,0x43,0x83,0x0c,0x46,0x44,0xab,0x7c,
+ 0x7b,0x65,0x9e,0x57,0xb5,0x90,0x4b,0x0e,
+ }
+ },
+ { 0x8301025, {
+ 0xe4,0x7d,0xdb,0x1e,0x14,0xb4,0x5e,0x36,
+ 0x8f,0x3e,0x48,0x88,0x3c,0x6d,0x76,0xa1,
+ 0x59,0xc6,0xc0,0x72,0x42,0xdf,0x6c,0x30,
+ 0x6f,0x0b,0x28,0x16,0x61,0xfc,0x79,0x77,
+ }
+ },
+ { 0x8301055, {
+ 0x81,0x7b,0x99,0x1b,0xae,0x2d,0x4f,0x9a,
+ 0xef,0x13,0xce,0xb5,0x10,0xaf,0x6a,0xea,
+ 0xe5,0xb0,0x64,0x98,0x10,0x68,0x34,0x3b,
+ 0x9d,0x7a,0xd6,0x22,0x77,0x5f,0xb3,0x5b,
+ }
+ },
+ { 0x8301072, {
+ 0xcf,0x76,0xa7,0x1a,0x49,0xdf,0x2a,0x5e,
+ 0x9e,0x40,0x70,0xe5,0xdd,0x8a,0xa8,0x28,
+ 0x20,0xdc,0x91,0xd8,0x2c,0xa6,0xa0,0xb1,
+ 0x2d,0x22,0x26,0x94,0x4b,0x40,0x85,0x30,
+ }
+ },
+ { 0x830107a, {
+ 0x2a,0x65,0x8c,0x1a,0x5e,0x07,0x21,0x72,
+ 0xdf,0x90,0xa6,0x51,0x37,0xd3,0x4b,0x34,
+ 0xc4,0xda,0x03,0xe1,0x8a,0x6c,0xfb,0x20,
+ 0x04,0xb2,0x81,0x05,0xd4,0x87,0xf4,0x0a,
+ }
+ },
+ { 0x830107b, {
+ 0xb3,0x43,0x13,0x63,0x56,0xc1,0x39,0xad,
+ 0x10,0xa6,0x2b,0xcc,0x02,0xe6,0x76,0x2a,
+ 0x1e,0x39,0x58,0x3e,0x23,0x6e,0xa4,0x04,
+ 0x95,0xea,0xf9,0x6d,0xc2,0x8a,0x13,0x19,
+ }
+ },
+ { 0x830107c, {
+ 0x21,0x64,0xde,0xfb,0x9f,0x68,0x96,0x47,
+ 0x70,0x5c,0xe2,0x8f,0x18,0x52,0x6a,0xac,
+ 0xa4,0xd2,0x2e,0xe0,0xde,0x68,0x66,0xc3,
+ 0xeb,0x1e,0xd3,0x3f,0xbc,0x51,0x1d,0x38,
+ }
+ },
+ { 0x860010d, {
+ 0x86,0xb6,0x15,0x83,0xbc,0x3b,0x9c,0xe0,
+ 0xb3,0xef,0x1d,0x99,0x84,0x35,0x15,0xf7,
+ 0x7c,0x2a,0xc6,0x42,0xdb,0x73,0x07,0x5c,
+ 0x7d,0xc3,0x02,0xb5,0x43,0x06,0x5e,0xf8,
+ }
+ },
+ { 0x8608108, {
+ 0x14,0xfe,0x57,0x86,0x49,0xc8,0x68,0xe2,
+ 0x11,0xa3,0xcb,0x6e,0xff,0x6e,0xd5,0x38,
+ 0xfe,0x89,0x1a,0xe0,0x67,0xbf,0xc4,0xcc,
+ 0x1b,0x9f,0x84,0x77,0x2b,0x9f,0xaa,0xbd,
+ }
+ },
+ { 0x8701034, {
+ 0xc3,0x14,0x09,0xa8,0x9c,0x3f,0x8d,0x83,
+ 0x9b,0x4c,0xa5,0xb7,0x64,0x8b,0x91,0x5d,
+ 0x85,0x6a,0x39,0x26,0x1e,0x14,0x41,0xa8,
+ 0x75,0xea,0xa6,0xf9,0xc9,0xd1,0xea,0x2b,
+ }
+ },
+ { 0x8a00008, {
+ 0xd7,0x2a,0x93,0xdc,0x05,0x2f,0xa5,0x6e,
+ 0x0c,0x61,0x2c,0x07,0x9f,0x38,0xe9,0x8e,
+ 0xef,0x7d,0x2a,0x05,0x4d,0x56,0xaf,0x72,
+ 0xe7,0x56,0x47,0x6e,0x60,0x27,0xd5,0x8c,
+ }
+ },
+ { 0x8a0000a, {
+ 0x73,0x31,0x26,0x22,0xd4,0xf9,0xee,0x3c,
+ 0x07,0x06,0xe7,0xb9,0xad,0xd8,0x72,0x44,
+ 0x33,0x31,0xaa,0x7d,0xc3,0x67,0x0e,0xdb,
+ 0x47,0xb5,0xaa,0xbc,0xf5,0xbb,0xd9,0x20,
+ }
+ },
+ { 0xa00104c, {
+ 0x3c,0x8a,0xfe,0x04,0x62,0xd8,0x6d,0xbe,
+ 0xa7,0x14,0x28,0x64,0x75,0xc0,0xa3,0x76,
+ 0xb7,0x92,0x0b,0x97,0x0a,0x8e,0x9c,0x5b,
+ 0x1b,0xc8,0x9d,0x3a,0x1e,0x81,0x3d,0x3b,
+ }
+ },
+ { 0xa00104e, {
+ 0xc4,0x35,0x82,0x67,0xd2,0x86,0xe5,0xb2,
+ 0xfd,0x69,0x12,0x38,0xc8,0x77,0xba,0xe0,
+ 0x70,0xf9,0x77,0x89,0x10,0xa6,0x74,0x4e,
+ 0x56,0x58,0x13,0xf5,0x84,0x70,0x28,0x0b,
+ }
+ },
+ { 0xa001053, {
+ 0x92,0x0e,0xf4,0x69,0x10,0x3b,0xf9,0x9d,
+ 0x31,0x1b,0xa6,0x99,0x08,0x7d,0xd7,0x25,
+ 0x7e,0x1e,0x89,0xba,0x35,0x8d,0xac,0xcb,
+ 0x3a,0xb4,0xdf,0x58,0x12,0xcf,0xc0,0xc3,
+ }
+ },
+ { 0xa001058, {
+ 0x33,0x7d,0xa9,0xb5,0x4e,0x62,0x13,0x36,
+ 0xef,0x66,0xc9,0xbd,0x0a,0xa6,0x3b,0x19,
+ 0xcb,0xf5,0xc2,0xc3,0x55,0x47,0x20,0xec,
+ 0x1f,0x7b,0xa1,0x44,0x0e,0x8e,0xa4,0xb2,
+ }
+ },
+ { 0xa001075, {
+ 0x39,0x02,0x82,0xd0,0x7c,0x26,0x43,0xe9,
+ 0x26,0xa3,0xd9,0x96,0xf7,0x30,0x13,0x0a,
+ 0x8a,0x0e,0xac,0xe7,0x1d,0xdc,0xe2,0x0f,
+ 0xcb,0x9e,0x8d,0xbc,0xd2,0xa2,0x44,0xe0,
+ }
+ },
+ { 0xa001078, {
+ 0x2d,0x67,0xc7,0x35,0xca,0xef,0x2f,0x25,
+ 0x4c,0x45,0x93,0x3f,0x36,0x01,0x8c,0xce,
+ 0xa8,0x5b,0x07,0xd3,0xc1,0x35,0x3c,0x04,
+ 0x20,0xa2,0xfc,0xdc,0xe6,0xce,0x26,0x3e,
+ }
+ },
+ { 0xa001079, {
+ 0x43,0xe2,0x05,0x9c,0xfd,0xb7,0x5b,0xeb,
+ 0x5b,0xe9,0xeb,0x3b,0x96,0xf4,0xe4,0x93,
+ 0x73,0x45,0x3e,0xac,0x8d,0x3b,0xe4,0xdb,
+ 0x10,0x31,0xc1,0xe4,0xa2,0xd0,0x5a,0x8a,
+ }
+ },
+ { 0xa00107a, {
+ 0x5f,0x92,0xca,0xff,0xc3,0x59,0x22,0x5f,
+ 0x02,0xa0,0x91,0x3b,0x4a,0x45,0x10,0xfd,
+ 0x19,0xe1,0x8a,0x6d,0x9a,0x92,0xc1,0x3f,
+ 0x75,0x78,0xac,0x78,0x03,0x1d,0xdb,0x18,
+ }
+ },
+ { 0xa001143, {
+ 0x56,0xca,0xf7,0x43,0x8a,0x4c,0x46,0x80,
+ 0xec,0xde,0xe5,0x9c,0x50,0x84,0x9a,0x42,
+ 0x27,0xe5,0x51,0x84,0x8f,0x19,0xc0,0x8d,
+ 0x0c,0x25,0xb4,0xb0,0x8f,0x10,0xf3,0xf8,
+ }
+ },
+ { 0xa001144, {
+ 0x42,0xd5,0x9b,0xa7,0xd6,0x15,0x29,0x41,
+ 0x61,0xc4,0x72,0x3f,0xf3,0x06,0x78,0x4b,
+ 0x65,0xf3,0x0e,0xfa,0x9c,0x87,0xde,0x25,
+ 0xbd,0xb3,0x9a,0xf4,0x75,0x13,0x53,0xdc,
+ }
+ },
+ { 0xa00115d, {
+ 0xd4,0xc4,0x49,0x36,0x89,0x0b,0x47,0xdd,
+ 0xfb,0x2f,0x88,0x3b,0x5f,0xf2,0x8e,0x75,
+ 0xc6,0x6c,0x37,0x5a,0x90,0x25,0x94,0x3e,
+ 0x36,0x9c,0xae,0x02,0x38,0x6c,0xf5,0x05,
+ }
+ },
+ { 0xa001173, {
+ 0x28,0xbb,0x9b,0xd1,0xa0,0xa0,0x7e,0x3a,
+ 0x59,0x20,0xc0,0xa9,0xb2,0x5c,0xc3,0x35,
+ 0x53,0x89,0xe1,0x4c,0x93,0x2f,0x1d,0xc3,
+ 0xe5,0xf7,0xf3,0xc8,0x9b,0x61,0xaa,0x9e,
+ }
+ },
+ { 0xa0011a8, {
+ 0x97,0xc6,0x16,0x65,0x99,0xa4,0x85,0x3b,
+ 0xf6,0xce,0xaa,0x49,0x4a,0x3a,0xc5,0xb6,
+ 0x78,0x25,0xbc,0x53,0xaf,0x5d,0xcf,0xf4,
+ 0x23,0x12,0xbb,0xb1,0xbc,0x8a,0x02,0x2e,
+ }
+ },
+ { 0xa0011ce, {
+ 0xcf,0x1c,0x90,0xa3,0x85,0x0a,0xbf,0x71,
+ 0x94,0x0e,0x80,0x86,0x85,0x4f,0xd7,0x86,
+ 0xae,0x38,0x23,0x28,0x2b,0x35,0x9b,0x4e,
+ 0xfe,0xb8,0xcd,0x3d,0x3d,0x39,0xc9,0x6a,
+ }
+ },
+ { 0xa0011d1, {
+ 0xdf,0x0e,0xca,0xde,0xf6,0xce,0x5c,0x1e,
+ 0x4c,0xec,0xd7,0x71,0x83,0xcc,0xa8,0x09,
+ 0xc7,0xc5,0xfe,0xb2,0xf7,0x05,0xd2,0xc5,
+ 0x12,0xdd,0xe4,0xf3,0x92,0x1c,0x3d,0xb8,
+ }
+ },
+ { 0xa0011d3, {
+ 0x91,0xe6,0x10,0xd7,0x57,0xb0,0x95,0x0b,
+ 0x9a,0x24,0xee,0xf7,0xcf,0x56,0xc1,0xa6,
+ 0x4a,0x52,0x7d,0x5f,0x9f,0xdf,0xf6,0x00,
+ 0x65,0xf7,0xea,0xe8,0x2a,0x88,0xe2,0x26,
+ }
+ },
+ { 0xa0011d5, {
+ 0xed,0x69,0x89,0xf4,0xeb,0x64,0xc2,0x13,
+ 0xe0,0x51,0x1f,0x03,0x26,0x52,0x7d,0xb7,
+ 0x93,0x5d,0x65,0xca,0xb8,0x12,0x1d,0x62,
+ 0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
+ }
+ },
+ { 0xa001223, {
+ 0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
+ 0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
+ 0x83,0x75,0x94,0xdd,0xeb,0x7e,0xb7,0x15,
+ 0x8e,0x3b,0x50,0x29,0x8a,0x9c,0xcc,0x45,
+ }
+ },
+ { 0xa001224, {
+ 0x0e,0x0c,0xdf,0xb4,0x89,0xee,0x35,0x25,
+ 0xdd,0x9e,0xdb,0xc0,0x69,0x83,0x0a,0xad,
+ 0x26,0xa9,0xaa,0x9d,0xfc,0x3c,0xea,0xf9,
+ 0x6c,0xdc,0xd5,0x6d,0x8b,0x6e,0x85,0x4a,
+ }
+ },
+ { 0xa001227, {
+ 0xab,0xc6,0x00,0x69,0x4b,0x50,0x87,0xad,
+ 0x5f,0x0e,0x8b,0xea,0x57,0x38,0xce,0x1d,
+ 0x0f,0x75,0x26,0x02,0xf6,0xd6,0x96,0xe9,
+ 0x87,0xb9,0xd6,0x20,0x27,0x7c,0xd2,0xe0,
+ }
+ },
+ { 0xa001229, {
+ 0x7f,0x49,0x49,0x48,0x46,0xa5,0x50,0xa6,
+ 0x28,0x89,0x98,0xe2,0x9e,0xb4,0x7f,0x75,
+ 0x33,0xa7,0x04,0x02,0xe4,0x82,0xbf,0xb4,
+ 0xa5,0x3a,0xba,0x24,0x8d,0x31,0x10,0x1d,
+ }
+ },
+ { 0xa00122e, {
+ 0x56,0x94,0xa9,0x5d,0x06,0x68,0xfe,0xaf,
+ 0xdf,0x7a,0xff,0x2d,0xdf,0x74,0x0f,0x15,
+ 0x66,0xfb,0x00,0xb5,0x51,0x97,0x9b,0xfa,
+ 0xcb,0x79,0x85,0x46,0x25,0xb4,0xd2,0x10,
+ }
+ },
+ { 0xa001231, {
+ 0x0b,0x46,0xa5,0xfc,0x18,0x15,0xa0,0x9e,
+ 0xa6,0xdc,0xb7,0xff,0x17,0xf7,0x30,0x64,
+ 0xd4,0xda,0x9e,0x1b,0xc3,0xfc,0x02,0x3b,
+ 0xe2,0xc6,0x0e,0x41,0x54,0xb5,0x18,0xdd,
+ }
+ },
+ { 0xa001234, {
+ 0x88,0x8d,0xed,0xab,0xb5,0xbd,0x4e,0xf7,
+ 0x7f,0xd4,0x0e,0x95,0x34,0x91,0xff,0xcc,
+ 0xfb,0x2a,0xcd,0xf7,0xd5,0xdb,0x4c,0x9b,
+ 0xd6,0x2e,0x73,0x50,0x8f,0x83,0x79,0x1a,
+ }
+ },
+ { 0xa001236, {
+ 0x3d,0x30,0x00,0xb9,0x71,0xba,0x87,0x78,
+ 0xa8,0x43,0x55,0xc4,0x26,0x59,0xcf,0x9d,
+ 0x93,0xce,0x64,0x0e,0x8b,0x72,0x11,0x8b,
+ 0xa3,0x8f,0x51,0xe9,0xca,0x98,0xaa,0x25,
+ }
+ },
+ { 0xa001238, {
+ 0x72,0xf7,0x4b,0x0c,0x7d,0x58,0x65,0xcc,
+ 0x00,0xcc,0x57,0x16,0x68,0x16,0xf8,0x2a,
+ 0x1b,0xb3,0x8b,0xe1,0xb6,0x83,0x8c,0x7e,
+ 0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
+ }
+ },
+ { 0xa00820c, {
+ 0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
+ 0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
+ 0xf1,0x8c,0x88,0x45,0xd7,0x82,0x80,0xd1,
+ 0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
+ }
+ },
+ { 0xa10113e, {
+ 0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
+ 0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
+ 0x15,0xe3,0x3f,0x4b,0x1d,0x0d,0x0a,0xd5,
+ 0xfa,0x90,0xc4,0xed,0x9d,0x90,0xaf,0x53,
+ }
+ },
+ { 0xa101144, {
+ 0xb3,0x0b,0x26,0x9a,0xf8,0x7c,0x02,0x26,
+ 0x35,0x84,0x53,0xa4,0xd3,0x2c,0x7c,0x09,
+ 0x68,0x7b,0x96,0xb6,0x93,0xef,0xde,0xbc,
+ 0xfd,0x4b,0x15,0xd2,0x81,0xd3,0x51,0x47,
+ }
+ },
+ { 0xa101148, {
+ 0x20,0xd5,0x6f,0x40,0x4a,0xf6,0x48,0x90,
+ 0xc2,0x93,0x9a,0xc2,0xfd,0xac,0xef,0x4f,
+ 0xfa,0xc0,0x3d,0x92,0x3c,0x6d,0x01,0x08,
+ 0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
+ }
+ },
+ { 0xa10123e, {
+ 0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
+ 0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
+ 0x1d,0x13,0x53,0x63,0xfe,0x42,0x6f,0xfc,
+ 0x19,0x0f,0xf1,0xfc,0xa7,0xdd,0x89,0x1b,
+ }
+ },
+ { 0xa101244, {
+ 0x71,0x56,0xb5,0x9f,0x21,0xbf,0xb3,0x3c,
+ 0x8c,0xd7,0x36,0xd0,0x34,0x52,0x1b,0xb1,
+ 0x46,0x2f,0x04,0xf0,0x37,0xd8,0x1e,0x72,
+ 0x24,0xa2,0x80,0x84,0x83,0x65,0x84,0xc0,
+ }
+ },
+ { 0xa101248, {
+ 0xed,0x3b,0x95,0xa6,0x68,0xa7,0x77,0x3e,
+ 0xfc,0x17,0x26,0xe2,0x7b,0xd5,0x56,0x22,
+ 0x2c,0x1d,0xef,0xeb,0x56,0xdd,0xba,0x6e,
+ 0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
+ }
+ },
+ { 0xa108108, {
+ 0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
+ 0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
+ 0xf5,0xd4,0x3f,0x7b,0x14,0xd5,0x60,0x2c,
+ 0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
+ }
+ },
+ { 0xa20102d, {
+ 0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
+ 0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
+ 0x8b,0x89,0x2f,0xb5,0xbb,0x82,0xef,0x23,
+ 0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
+ }
+ },
+ { 0xa201210, {
+ 0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
+ 0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
+ 0x6d,0x3d,0x0e,0x6b,0xa7,0xac,0xe3,0x68,
+ 0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
+ }
+ },
+ { 0xa404107, {
+ 0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
+ 0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
+ 0x8b,0x0d,0x9f,0xf9,0x3a,0xdf,0xc6,0x81,
+ 0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
+ }
+ },
+ { 0xa500011, {
+ 0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
+ 0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
+ 0xd7,0x5b,0x65,0x3a,0x7d,0xab,0xdf,0xa2,
+ 0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
+ }
+ },
+ { 0xa601209, {
+ 0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
+ 0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
+ 0x15,0x86,0xcc,0x5d,0x97,0x0f,0xc0,0x46,
+ 0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
+ }
+ },
+ { 0xa704107, {
+ 0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
+ 0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
+ 0x2a,0xad,0x8e,0x6b,0xea,0x9b,0xb7,0xc2,
+ 0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
+ }
+ },
+ { 0xa705206, {
+ 0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
+ 0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
+ 0x67,0x6f,0x04,0x18,0xae,0x20,0x87,0x4b,
+ 0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
+ }
+ },
+ { 0xa708007, {
+ 0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
+ 0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
+ 0x07,0xaa,0x3a,0xe0,0x57,0x13,0x72,0x80,
+ 0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
+ }
+ },
+ { 0xa70c005, {
+ 0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
+ 0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
+ 0x1f,0x1f,0xf1,0x97,0xeb,0xfe,0x56,0x55,
+ 0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
+ }
+ },
+ { 0xaa00116, {
+ 0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
+ 0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
+ 0xfe,0x1d,0x5e,0x65,0xc7,0xaa,0x92,0x4d,
+ 0x91,0xee,0x76,0xbb,0x4c,0x66,0x78,0xc9,
+ }
+ },
+ { 0xaa00212, {
+ 0xbd,0x57,0x5d,0x0a,0x0a,0x30,0xc1,0x75,
+ 0x95,0x58,0x5e,0x93,0x02,0x28,0x43,0x71,
+ 0xed,0x42,0x29,0xc8,0xec,0x34,0x2b,0xb2,
+ 0x1a,0x65,0x4b,0xfe,0x07,0x0f,0x34,0xa1,
+ }
+ },
+ { 0xaa00213, {
+ 0xed,0x58,0xb7,0x76,0x81,0x7f,0xd9,0x3a,
+ 0x1a,0xff,0x8b,0x34,0xb8,0x4a,0x99,0x0f,
+ 0x28,0x49,0x6c,0x56,0x2b,0xdc,0xb7,0xed,
+ 0x96,0xd5,0x9d,0xc1,0x7a,0xd4,0x51,0x9b,
+ }
+ },
+ { 0xaa00215, {
+ 0x55,0xd3,0x28,0xcb,0x87,0xa9,0x32,0xe9,
+ 0x4e,0x85,0x4b,0x7c,0x6b,0xd5,0x7c,0xd4,
+ 0x1b,0x51,0x71,0x3a,0x0e,0x0b,0xdc,0x9b,
+ 0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
+ }
+ },
+};
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index a4ebd5e0ae82..c15c7b862bec 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -23,6 +23,7 @@
#include <linux/miscdevice.h>
#include <linux/capability.h>
#include <linux/firmware.h>
+#include <linux/cpumask.h>
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/mutex.h>
@@ -31,6 +32,7 @@
#include <linux/fs.h>
#include <linux/mm.h>
+#include <asm/apic.h>
#include <asm/cpu_device_id.h>
#include <asm/perf_event.h>
#include <asm/processor.h>
@@ -42,11 +44,10 @@
#define DRIVER_VERSION "2.2"
static struct microcode_ops *microcode_ops;
-static bool dis_ucode_ldr = true;
+bool dis_ucode_ldr = true;
-bool initrd_gone;
-
-LIST_HEAD(microcode_cache);
+bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
+module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
/*
* Synchronization.
@@ -76,6 +77,8 @@ static u32 final_levels[] = {
0, /* T-101 terminator */
};
+struct early_load_data early_data;
+
/*
* Check the current patch level on this CPU.
*
@@ -90,10 +93,7 @@ static bool amd_check_current_patch_level(void)
native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
- if (IS_ENABLED(CONFIG_X86_32))
- levels = (u32 *)__pa_nodebug(&final_levels);
- else
- levels = final_levels;
+ levels = final_levels;
for (i = 0; levels[i]; i++) {
if (lvl == levels[i])
@@ -105,17 +105,8 @@ static bool amd_check_current_patch_level(void)
static bool __init check_loader_disabled_bsp(void)
{
static const char *__dis_opt_str = "dis_ucode_ldr";
-
-#ifdef CONFIG_X86_32
- const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
- const char *option = (const char *)__pa_nodebug(__dis_opt_str);
- bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr);
-
-#else /* CONFIG_X86_64 */
const char *cmdline = boot_command_line;
const char *option = __dis_opt_str;
- bool *res = &dis_ucode_ldr;
-#endif
/*
* CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
@@ -123,17 +114,17 @@ static bool __init check_loader_disabled_bsp(void)
* that's good enough as they don't land on the BSP path anyway.
*/
if (native_cpuid_ecx(1) & BIT(31))
- return *res;
+ return true;
if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
if (amd_check_current_patch_level())
- return *res;
+ return true;
}
if (cmdline_find_option_bool(cmdline, option) <= 0)
- *res = false;
+ dis_ucode_ldr = false;
- return *res;
+ return dis_ucode_ldr;
}
void __init load_ucode_bsp(void)
@@ -166,25 +157,16 @@ void __init load_ucode_bsp(void)
return;
if (intel)
- load_ucode_intel_bsp();
+ load_ucode_intel_bsp(&early_data);
else
- load_ucode_amd_early(cpuid_1_eax);
-}
-
-static bool check_loader_disabled_ap(void)
-{
-#ifdef CONFIG_X86_32
- return *((bool *)__pa_nodebug(&dis_ucode_ldr));
-#else
- return dis_ucode_ldr;
-#endif
+ load_ucode_amd_bsp(&early_data, cpuid_1_eax);
}
void load_ucode_ap(void)
{
unsigned int cpuid_1_eax;
- if (check_loader_disabled_ap())
+ if (dis_ucode_ldr)
return;
cpuid_1_eax = native_cpuid_eax(1);
@@ -196,103 +178,44 @@ void load_ucode_ap(void)
break;
case X86_VENDOR_AMD:
if (x86_family(cpuid_1_eax) >= 0x10)
- load_ucode_amd_early(cpuid_1_eax);
+ load_ucode_amd_ap(cpuid_1_eax);
break;
default:
break;
}
}
-static int __init save_microcode_in_initrd(void)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
- int ret = -EINVAL;
-
- if (dis_ucode_ldr) {
- ret = 0;
- goto out;
- }
-
- switch (c->x86_vendor) {
- case X86_VENDOR_INTEL:
- if (c->x86 >= 6)
- ret = save_microcode_in_initrd_intel();
- break;
- case X86_VENDOR_AMD:
- if (c->x86 >= 0x10)
- ret = save_microcode_in_initrd_amd(cpuid_eax(1));
- break;
- default:
- break;
- }
-
-out:
- initrd_gone = true;
-
- return ret;
-}
-
-struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
+struct cpio_data __init find_microcode_in_initrd(const char *path)
{
#ifdef CONFIG_BLK_DEV_INITRD
unsigned long start = 0;
size_t size;
#ifdef CONFIG_X86_32
- struct boot_params *params;
-
- if (use_pa)
- params = (struct boot_params *)__pa_nodebug(&boot_params);
- else
- params = &boot_params;
-
- size = params->hdr.ramdisk_size;
-
- /*
- * Set start only if we have an initrd image. We cannot use initrd_start
- * because it is not set that early yet.
- */
+ size = boot_params.hdr.ramdisk_size;
+ /* Early load on BSP has a temporary mapping. */
if (size)
- start = params->hdr.ramdisk_image;
+ start = initrd_start_early;
-# else /* CONFIG_X86_64 */
+#else /* CONFIG_X86_64 */
size = (unsigned long)boot_params.ext_ramdisk_size << 32;
size |= boot_params.hdr.ramdisk_size;
if (size) {
start = (unsigned long)boot_params.ext_ramdisk_image << 32;
start |= boot_params.hdr.ramdisk_image;
-
start += PAGE_OFFSET;
}
-# endif
+#endif
/*
* Fixup the start address: after reserve_initrd() runs, initrd_start
* has the virtual address of the beginning of the initrd. It also
* possibly relocates the ramdisk. In either case, initrd_start contains
* the updated address so use that instead.
- *
- * initrd_gone is for the hotplug case where we've thrown out initrd
- * already.
*/
- if (!use_pa) {
- if (initrd_gone)
- return (struct cpio_data){ NULL, 0, "" };
- if (initrd_start)
- start = initrd_start;
- } else {
- /*
- * The picture with physical addresses is a bit different: we
- * need to get the *physical* address to which the ramdisk was
- * relocated, i.e., relocated_ramdisk (not initrd_start) and
- * since we're running from physical addresses, we need to access
- * relocated_ramdisk through its *physical* address too.
- */
- u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk);
- if (*rr)
- start = *rr;
- }
+ if (initrd_start)
+ start = initrd_start;
return find_cpio_data(path, (void *)start, size, NULL);
#else /* !CONFIG_BLK_DEV_INITRD */
@@ -336,117 +259,298 @@ static struct platform_device *microcode_pdev;
* requirement can be relaxed in the future. Right now, this is conservative
* and good.
*/
-#define SPINUNIT 100 /* 100 nsec */
+enum sibling_ctrl {
+ /* Spinwait with timeout */
+ SCTRL_WAIT,
+ /* Invoke the microcode_apply() callback */
+ SCTRL_APPLY,
+ /* Proceed without invoking the microcode_apply() callback */
+ SCTRL_DONE,
+};
-static int check_online_cpus(void)
+struct microcode_ctrl {
+ enum sibling_ctrl ctrl;
+ enum ucode_state result;
+ unsigned int ctrl_cpu;
+ bool nmi_enabled;
+};
+
+DEFINE_STATIC_KEY_FALSE(microcode_nmi_handler_enable);
+static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl);
+static atomic_t late_cpus_in, offline_in_nmi;
+static unsigned int loops_per_usec;
+static cpumask_t cpu_offline_mask;
+
+static noinstr bool wait_for_cpus(atomic_t *cnt)
{
- unsigned int cpu;
+ unsigned int timeout, loops;
- /*
- * Make sure all CPUs are online. It's fine for SMT to be disabled if
- * all the primary threads are still online.
- */
- for_each_present_cpu(cpu) {
- if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) {
- pr_err("Not all CPUs online, aborting microcode update.\n");
- return -EINVAL;
+ WARN_ON_ONCE(raw_atomic_dec_return(cnt) < 0);
+
+ for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+ if (!raw_atomic_read(cnt))
+ return true;
+
+ for (loops = 0; loops < loops_per_usec; loops++)
+ cpu_relax();
+
+ /* If invoked directly, tickle the NMI watchdog */
+ if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) {
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
}
}
-
- return 0;
+ /* Prevent the late comers from making progress and let them time out */
+ raw_atomic_inc(cnt);
+ return false;
}
-static atomic_t late_cpus_in;
-static atomic_t late_cpus_out;
-
-static int __wait_for_cpus(atomic_t *t, long long timeout)
+static noinstr bool wait_for_ctrl(void)
{
- int all_cpus = num_online_cpus();
-
- atomic_inc(t);
+ unsigned int timeout, loops;
- while (atomic_read(t) < all_cpus) {
- if (timeout < SPINUNIT) {
- pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
- all_cpus - atomic_read(t));
- return 1;
- }
+ for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+ if (raw_cpu_read(ucode_ctrl.ctrl) != SCTRL_WAIT)
+ return true;
- ndelay(SPINUNIT);
- timeout -= SPINUNIT;
+ for (loops = 0; loops < loops_per_usec; loops++)
+ cpu_relax();
- touch_nmi_watchdog();
+ /* If invoked directly, tickle the NMI watchdog */
+ if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) {
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
+ }
}
- return 0;
+ return false;
}
/*
- * Returns:
- * < 0 - on error
- * 0 - success (no update done or microcode was updated)
+ * Protected against instrumentation up to the point where the primary
+ * thread completed the update. See microcode_nmi_handler() for details.
*/
-static int __reload_late(void *info)
+static noinstr bool load_secondary_wait(unsigned int ctrl_cpu)
{
- int cpu = smp_processor_id();
- enum ucode_state err;
- int ret = 0;
+ /* Initial rendezvous to ensure that all CPUs have arrived */
+ if (!wait_for_cpus(&late_cpus_in)) {
+ raw_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+ return false;
+ }
/*
- * Wait for all CPUs to arrive. A load will not be attempted unless all
- * CPUs show up.
- * */
- if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
- return -1;
+ * Wait for primary threads to complete. If one of them hangs due
+ * to the update, there is no way out. This is non-recoverable
+ * because the CPU might hold locks or resources and confuse the
+ * scheduler, watchdogs etc. There is no way to safely evacuate the
+ * machine.
+ */
+ if (wait_for_ctrl())
+ return true;
+
+ instrumentation_begin();
+ panic("Microcode load: Primary CPU %d timed out\n", ctrl_cpu);
+ instrumentation_end();
+}
+
+/*
+ * Protected against instrumentation up to the point where the primary
+ * thread completed the update. See microcode_nmi_handler() for details.
+ */
+static noinstr void load_secondary(unsigned int cpu)
+{
+ unsigned int ctrl_cpu = raw_cpu_read(ucode_ctrl.ctrl_cpu);
+ enum ucode_state ret;
+
+ if (!load_secondary_wait(ctrl_cpu)) {
+ instrumentation_begin();
+ pr_err_once("load: %d CPUs timed out\n",
+ atomic_read(&late_cpus_in) - 1);
+ instrumentation_end();
+ return;
+ }
+ /* Primary thread completed. Allow to invoke instrumentable code */
+ instrumentation_begin();
/*
- * On an SMT system, it suffices to load the microcode on one sibling of
- * the core because the microcode engine is shared between the threads.
- * Synchronization still needs to take place so that no concurrent
- * loading attempts happen on multiple threads of an SMT core. See
- * below.
+ * If the primary succeeded then invoke the apply() callback,
+ * otherwise copy the state from the primary thread.
*/
- if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
- err = microcode_ops->apply_microcode(cpu);
+ if (this_cpu_read(ucode_ctrl.ctrl) == SCTRL_APPLY)
+ ret = microcode_ops->apply_microcode(cpu);
else
- goto wait_for_siblings;
+ ret = per_cpu(ucode_ctrl.result, ctrl_cpu);
- if (err >= UCODE_NFOUND) {
- if (err == UCODE_ERROR) {
- pr_warn("Error reloading microcode on CPU %d\n", cpu);
- ret = -1;
- }
+ this_cpu_write(ucode_ctrl.result, ret);
+ this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
+ instrumentation_end();
+}
+
+static void __load_primary(unsigned int cpu)
+{
+ struct cpumask *secondaries = topology_sibling_cpumask(cpu);
+ enum sibling_ctrl ctrl;
+ enum ucode_state ret;
+ unsigned int sibling;
+
+ /* Initial rendezvous to ensure that all CPUs have arrived */
+ if (!wait_for_cpus(&late_cpus_in)) {
+ this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+ pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1);
+ return;
}
-wait_for_siblings:
- if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
- panic("Timeout during microcode update!\n");
+ ret = microcode_ops->apply_microcode(cpu);
+ this_cpu_write(ucode_ctrl.result, ret);
+ this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
/*
- * At least one thread has completed update on each core.
- * For others, simply call the update to make sure the
- * per-cpu cpuinfo can be updated with right microcode
- * revision.
+ * If the update was successful, let the siblings run the apply()
+ * callback. If not, tell them it's done. This also covers the
+ * case where the CPU has uniform loading at package or system
+ * scope implemented but does not advertise it.
*/
- if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
- err = microcode_ops->apply_microcode(cpu);
+ if (ret == UCODE_UPDATED || ret == UCODE_OK)
+ ctrl = SCTRL_APPLY;
+ else
+ ctrl = SCTRL_DONE;
+
+ for_each_cpu(sibling, secondaries) {
+ if (sibling != cpu)
+ per_cpu(ucode_ctrl.ctrl, sibling) = ctrl;
+ }
+}
+
+static bool kick_offline_cpus(unsigned int nr_offl)
+{
+ unsigned int cpu, timeout;
+
+ for_each_cpu(cpu, &cpu_offline_mask) {
+ /* Enable the rendezvous handler and send NMI */
+ per_cpu(ucode_ctrl.nmi_enabled, cpu) = true;
+ apic_send_nmi_to_offline_cpu(cpu);
+ }
+
+ /* Wait for them to arrive */
+ for (timeout = 0; timeout < (USEC_PER_SEC / 2); timeout++) {
+ if (atomic_read(&offline_in_nmi) == nr_offl)
+ return true;
+ udelay(1);
+ }
+ /* Let the others time out */
+ return false;
+}
+
+static void release_offline_cpus(void)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, &cpu_offline_mask)
+ per_cpu(ucode_ctrl.ctrl, cpu) = SCTRL_DONE;
+}
+
+static void load_primary(unsigned int cpu)
+{
+ unsigned int nr_offl = cpumask_weight(&cpu_offline_mask);
+ bool proceed = true;
+
+ /* Kick soft-offlined SMT siblings if required */
+ if (!cpu && nr_offl)
+ proceed = kick_offline_cpus(nr_offl);
- return ret;
+ /* If the soft-offlined CPUs did not respond, abort */
+ if (proceed)
+ __load_primary(cpu);
+
+ /* Unconditionally release soft-offlined SMT siblings if required */
+ if (!cpu && nr_offl)
+ release_offline_cpus();
}
/*
- * Reload microcode late on all CPUs. Wait for a sec until they
- * all gather together.
+ * Minimal stub rendezvous handler for soft-offlined CPUs which participate
+ * in the NMI rendezvous to protect against a concurrent NMI on affected
+ * CPUs.
*/
-static int microcode_reload_late(void)
+void noinstr microcode_offline_nmi_handler(void)
{
- int old = boot_cpu_data.microcode, ret;
+ if (!raw_cpu_read(ucode_ctrl.nmi_enabled))
+ return;
+ raw_cpu_write(ucode_ctrl.nmi_enabled, false);
+ raw_cpu_write(ucode_ctrl.result, UCODE_OFFLINE);
+ raw_atomic_inc(&offline_in_nmi);
+ wait_for_ctrl();
+}
+
+static noinstr bool microcode_update_handler(void)
+{
+ unsigned int cpu = raw_smp_processor_id();
+
+ if (raw_cpu_read(ucode_ctrl.ctrl_cpu) == cpu) {
+ instrumentation_begin();
+ load_primary(cpu);
+ instrumentation_end();
+ } else {
+ load_secondary(cpu);
+ }
+
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
+
+ return true;
+}
+
+/*
+ * Protection against instrumentation is required for CPUs which are not
+ * safe against an NMI which is delivered to the secondary SMT sibling
+ * while the primary thread updates the microcode. Instrumentation can end
+ * up in #INT3, #DB and #PF. The IRET from those exceptions reenables NMI
+ * which is the opposite of what the NMI rendezvous is trying to achieve.
+ *
+ * The primary thread is safe versus instrumentation as the actual
+ * microcode update handles this correctly. It's only the sibling code
+ * path which must be NMI safe until the primary thread completed the
+ * update.
+ */
+bool noinstr microcode_nmi_handler(void)
+{
+ if (!raw_cpu_read(ucode_ctrl.nmi_enabled))
+ return false;
+
+ raw_cpu_write(ucode_ctrl.nmi_enabled, false);
+ return microcode_update_handler();
+}
+
+static int load_cpus_stopped(void *unused)
+{
+ if (microcode_ops->use_nmi) {
+ /* Enable the NMI handler and raise NMI */
+ this_cpu_write(ucode_ctrl.nmi_enabled, true);
+ apic->send_IPI(smp_processor_id(), NMI_VECTOR);
+ } else {
+ /* Just invoke the handler directly */
+ microcode_update_handler();
+ }
+ return 0;
+}
+
+static int load_late_stop_cpus(bool is_safe)
+{
+ unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0;
+ unsigned int nr_offl, offline = 0;
+ int old_rev = boot_cpu_data.microcode;
struct cpuinfo_x86 prev_info;
- pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
- pr_err("You should switch to early loading, if possible.\n");
+ if (!is_safe) {
+ pr_err("Late microcode loading without minimal revision check.\n");
+ pr_err("You should switch to early loading, if possible.\n");
+ }
- atomic_set(&late_cpus_in, 0);
- atomic_set(&late_cpus_out, 0);
+ atomic_set(&late_cpus_in, num_online_cpus());
+ atomic_set(&offline_in_nmi, 0);
+ loops_per_usec = loops_per_jiffy / (TICK_NSEC / 1000);
/*
* Take a snapshot before the microcode update in order to compare and
@@ -454,52 +558,162 @@ static int microcode_reload_late(void)
*/
store_cpu_caps(&prev_info);
- ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
- if (!ret) {
- pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n",
- old, boot_cpu_data.microcode);
- microcode_check(&prev_info);
- } else {
- pr_info("Reload failed, current microcode revision: 0x%x\n",
- boot_cpu_data.microcode);
+ if (microcode_ops->use_nmi)
+ static_branch_enable_cpuslocked(µcode_nmi_handler_enable);
+
+ stop_machine_cpuslocked(load_cpus_stopped, NULL, cpu_online_mask);
+
+ if (microcode_ops->use_nmi)
+ static_branch_disable_cpuslocked(µcode_nmi_handler_enable);
+
+ /* Analyze the results */
+ for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
+ switch (per_cpu(ucode_ctrl.result, cpu)) {
+ case UCODE_UPDATED: updated++; break;
+ case UCODE_TIMEOUT: timedout++; break;
+ case UCODE_OK: siblings++; break;
+ case UCODE_OFFLINE: offline++; break;
+ default: failed++; break;
+ }
+ }
+
+ if (microcode_ops->finalize_late_load)
+ microcode_ops->finalize_late_load(!updated);
+
+ if (!updated) {
+ /* Nothing changed. */
+ if (!failed && !timedout)
+ return 0;
+
+ nr_offl = cpumask_weight(&cpu_offline_mask);
+ if (offline < nr_offl) {
+ pr_warn("%u offline siblings did not respond.\n",
+ nr_offl - atomic_read(&offline_in_nmi));
+ return -EIO;
+ }
+ pr_err("update failed: %u CPUs failed %u CPUs timed out\n",
+ failed, timedout);
+ return -EIO;
+ }
+
+ if (!is_safe || failed || timedout)
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+ pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings);
+ if (failed || timedout) {
+ pr_err("load incomplete. %u CPUs timed out or failed\n",
+ num_online_cpus() - (updated + siblings));
}
+ pr_info("revision: 0x%x -> 0x%x\n", old_rev, boot_cpu_data.microcode);
+ microcode_check(&prev_info);
- return ret;
+ return updated + siblings == num_online_cpus() ? 0 : -EIO;
+}
+
+/*
+ * This function does two things:
+ *
+ * 1) Ensure that all required CPUs which are present and have been booted
+ * once are online.
+ *
+ * To pass this check, all primary threads must be online.
+ *
+ * If the microcode load is not safe against NMI then all SMT threads
+ * must be online as well because they still react to NMIs when they are
+ * soft-offlined and parked in one of the play_dead() variants. So if a
+ * NMI hits while the primary thread updates the microcode the resulting
+ * behaviour is undefined. The default play_dead() implementation on
+ * modern CPUs uses MWAIT, which is also not guaranteed to be safe
+ * against a microcode update which affects MWAIT.
+ *
+ * As soft-offlined CPUs still react on NMIs, the SMT sibling
+ * restriction can be lifted when the vendor driver signals to use NMI
+ * for rendezvous and the APIC provides a mechanism to send an NMI to a
+ * soft-offlined CPU. The soft-offlined CPUs are then able to
+ * participate in the rendezvous in a trivial stub handler.
+ *
+ * 2) Initialize the per CPU control structure and create a cpumask
+ * which contains "offline"; secondary threads, so they can be handled
+ * correctly by a control CPU.
+ */
+static bool setup_cpus(void)
+{
+ struct microcode_ctrl ctrl = { .ctrl = SCTRL_WAIT, .result = -1, };
+ bool allow_smt_offline;
+ unsigned int cpu;
+
+ allow_smt_offline = microcode_ops->nmi_safe ||
+ (microcode_ops->use_nmi && apic->nmi_to_offline_cpu);
+
+ cpumask_clear(&cpu_offline_mask);
+
+ for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
+ /*
+ * Offline CPUs sit in one of the play_dead() functions
+ * with interrupts disabled, but they still react on NMIs
+ * and execute arbitrary code. Also MWAIT being updated
+ * while the offline CPU sits there is not necessarily safe
+ * on all CPU variants.
+ *
+ * Mark them in the offline_cpus mask which will be handled
+ * by CPU0 later in the update process.
+ *
+ * Ensure that the primary thread is online so that it is
+ * guaranteed that all cores are updated.
+ */
+ if (!cpu_online(cpu)) {
+ if (topology_is_primary_thread(cpu) || !allow_smt_offline) {
+ pr_err("CPU %u not online, loading aborted\n", cpu);
+ return false;
+ }
+ cpumask_set_cpu(cpu, &cpu_offline_mask);
+ per_cpu(ucode_ctrl, cpu) = ctrl;
+ continue;
+ }
+
+ /*
+ * Initialize the per CPU state. This is core scope for now,
+ * but prepared to take package or system scope into account.
+ */
+ ctrl.ctrl_cpu = cpumask_first(topology_sibling_cpumask(cpu));
+ per_cpu(ucode_ctrl, cpu) = ctrl;
+ }
+ return true;
+}
+
+static int load_late_locked(void)
+{
+ if (!setup_cpus())
+ return -EBUSY;
+
+ switch (microcode_ops->request_microcode_fw(0, µcode_pdev->dev)) {
+ case UCODE_NEW:
+ return load_late_stop_cpus(false);
+ case UCODE_NEW_SAFE:
+ return load_late_stop_cpus(true);
+ case UCODE_NFOUND:
+ return -ENOENT;
+ default:
+ return -EBADFD;
+ }
}
static ssize_t reload_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
- enum ucode_state tmp_ret = UCODE_OK;
- int bsp = boot_cpu_data.cpu_index;
unsigned long val;
- ssize_t ret = 0;
+ ssize_t ret;
ret = kstrtoul(buf, 0, &val);
if (ret || val != 1)
return -EINVAL;
cpus_read_lock();
-
- ret = check_online_cpus();
- if (ret)
- goto put;
-
- tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev);
- if (tmp_ret != UCODE_NEW)
- goto put;
-
- ret = microcode_reload_late();
-put:
+ ret = load_late_locked();
cpus_read_unlock();
- if (ret == 0)
- ret = size;
-
- add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
-
- return ret;
+ return ret ? : size;
}
static DEVICE_ATTR_WO(reload);
@@ -541,17 +755,6 @@ static void microcode_fini_cpu(int cpu)
microcode_ops->microcode_fini_cpu(cpu);
}
-static enum ucode_state microcode_init_cpu(int cpu)
-{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
- memset(uci, 0, sizeof(*uci));
-
- microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig);
-
- return microcode_ops->apply_microcode(cpu);
-}
-
/**
* microcode_bsp_resume - Update boot CPU microcode during resume.
*/
@@ -570,19 +773,18 @@ static struct syscore_ops mc_syscore_ops = {
.resume = microcode_bsp_resume,
};
-static int mc_cpu_starting(unsigned int cpu)
-{
- enum ucode_state err = microcode_ops->apply_microcode(cpu);
-
- pr_debug("%s: CPU%d, err: %d\n", __func__, cpu, err);
-
- return err == UCODE_ERROR;
-}
-
static int mc_cpu_online(unsigned int cpu)
{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
struct device *dev = get_cpu_device(cpu);
+ memset(uci, 0, sizeof(*uci));
+
+ microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig);
+ cpu_data(cpu).microcode = uci->cpu_sig.rev;
+ if (!cpu)
+ boot_cpu_data.microcode = uci->cpu_sig.rev;
+
if (sysfs_create_group(&dev->kobj, &mc_attr_group))
pr_err("Failed to create group for CPU%d\n", cpu);
return 0;
@@ -590,33 +792,13 @@ static int mc_cpu_online(unsigned int cpu)
static int mc_cpu_down_prep(unsigned int cpu)
{
- struct device *dev;
-
- dev = get_cpu_device(cpu);
+ struct device *dev = get_cpu_device(cpu);
microcode_fini_cpu(cpu);
-
- /* Suspend is in progress, only remove the interface */
sysfs_remove_group(&dev->kobj, &mc_attr_group);
- pr_debug("%s: CPU%d\n", __func__, cpu);
-
return 0;
}
-static void setup_online_cpu(struct work_struct *work)
-{
- int cpu = smp_processor_id();
- enum ucode_state err;
-
- err = microcode_init_cpu(cpu);
- if (err == UCODE_ERROR) {
- pr_err("Error applying microcode on CPU%d\n", cpu);
- return;
- }
-
- mc_cpu_online(cpu);
-}
-
static struct attribute *cpu_root_microcode_attrs[] = {
#ifdef CONFIG_MICROCODE_LATE_LOADING
&dev_attr_reload.attr,
@@ -648,6 +830,11 @@ static int __init microcode_init(void)
if (!microcode_ops)
return -ENODEV;
+ pr_info_once("Current revision: 0x%08x\n", (early_data.new_rev ?: early_data.old_rev));
+
+ if (early_data.new_rev)
+ pr_info_once("Updated early from: 0x%08x\n", early_data.old_rev);
+
microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0);
if (IS_ERR(microcode_pdev))
return PTR_ERR(microcode_pdev);
@@ -662,14 +849,9 @@ static int __init microcode_init(void)
}
}
- /* Do per-CPU setup */
- schedule_on_each_cpu(setup_online_cpu);
-
register_syscore_ops(&mc_syscore_ops);
- cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
- mc_cpu_starting, NULL);
- cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
- mc_cpu_online, mc_cpu_down_prep);
+ cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
+ mc_cpu_online, mc_cpu_down_prep);
pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
@@ -680,5 +862,4 @@ static int __init microcode_init(void)
return error;
}
-fs_initcall(save_microcode_in_initrd);
late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 94dd6af9c963..9d7baf2573bc 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -14,7 +14,6 @@
#include <linux/earlycpio.h>
#include <linux/firmware.h>
#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
#include <linux/initrd.h>
#include <linux/kernel.h>
#include <linux/slab.h>
@@ -32,11 +31,14 @@
static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
+#define UCODE_BSP_LOADED ((struct microcode_intel *)0x1UL)
+
/* Current microcode patch used in early patching on the APs. */
-static struct microcode_intel *intel_ucode_patch;
+static struct microcode_intel *ucode_patch_va __read_mostly;
+static struct microcode_intel *ucode_patch_late __read_mostly;
/* last level cache size per core */
-static int llc_size_per_core;
+static unsigned int llc_size_per_core __ro_after_init;
/* microcode format is extended from prescott processors */
struct extended_signature {
@@ -66,60 +68,52 @@ static inline unsigned int exttable_size(struct extended_sigtable *et)
return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE;
}
-int intel_cpu_collect_info(struct ucode_cpu_info *uci)
+void intel_collect_cpu_info(struct cpu_signature *sig)
{
- unsigned int val[2];
- unsigned int family, model;
- struct cpu_signature csig = { 0 };
- unsigned int eax, ebx, ecx, edx;
-
- memset(uci, 0, sizeof(*uci));
-
- eax = 0x00000001;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- csig.sig = eax;
+ sig->sig = cpuid_eax(1);
+ sig->pf = 0;
+ sig->rev = intel_get_microcode_revision();
- family = x86_family(eax);
- model = x86_model(eax);
+ if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) {
+ unsigned int val[2];
- if (model >= 5 || family > 6) {
/* get processor flags from MSR 0x17 */
native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
- csig.pf = 1 << ((val[1] >> 18) & 7);
+ sig->pf = 1 << ((val[1] >> 18) & 7);
}
+}
+EXPORT_SYMBOL_GPL(intel_collect_cpu_info);
- csig.rev = intel_get_microcode_revision();
-
- uci->cpu_sig = csig;
+static inline bool cpu_signatures_match(struct cpu_signature *s1, unsigned int sig2,
+ unsigned int pf2)
+{
+ if (s1->sig != sig2)
+ return false;
- return 0;
+ /* Processor flags are either both 0 or they intersect. */
+ return ((!s1->pf && !pf2) || (s1->pf & pf2));
}
-EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf)
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig)
{
struct microcode_header_intel *mc_hdr = mc;
- struct extended_sigtable *ext_hdr;
struct extended_signature *ext_sig;
+ struct extended_sigtable *ext_hdr;
int i;
- if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
- return 1;
+ if (cpu_signatures_match(sig, mc_hdr->sig, mc_hdr->pf))
+ return true;
/* Look for ext. headers: */
if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE)
- return 0;
+ return false;
ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE;
ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
for (i = 0; i < ext_hdr->count; i++) {
- if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
- return 1;
+ if (cpu_signatures_match(sig, ext_sig->sig, ext_sig->pf))
+ return true;
ext_sig++;
}
return 0;
@@ -240,516 +234,245 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
}
EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
-{
- struct microcode_header_intel *mc_hdr = mc;
-
- if (mc_hdr->rev <= new_rev)
- return 0;
-
- return intel_find_matching_signature(mc, csig, cpf);
-}
-
-static struct ucode_patch *memdup_patch(void *data, unsigned int size)
-{
- struct ucode_patch *p;
-
- p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
- if (!p)
- return NULL;
-
- p->data = kmemdup(data, size, GFP_KERNEL);
- if (!p->data) {
- kfree(p);
- return NULL;
- }
-
- return p;
-}
-
-static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size)
+static void update_ucode_pointer(struct microcode_intel *mc)
{
- struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
- struct ucode_patch *iter, *tmp, *p = NULL;
- bool prev_found = false;
- unsigned int sig, pf;
-
- mc_hdr = (struct microcode_header_intel *)data;
-
- list_for_each_entry_safe(iter, tmp, µcode_cache, plist) {
- mc_saved_hdr = (struct microcode_header_intel *)iter->data;
- sig = mc_saved_hdr->sig;
- pf = mc_saved_hdr->pf;
-
- if (intel_find_matching_signature(data, sig, pf)) {
- prev_found = true;
-
- if (mc_hdr->rev <= mc_saved_hdr->rev)
- continue;
-
- p = memdup_patch(data, size);
- if (!p)
- pr_err("Error allocating buffer %p\n", data);
- else {
- list_replace(&iter->plist, &p->plist);
- kfree(iter->data);
- kfree(iter);
- }
- }
- }
+ kvfree(ucode_patch_va);
/*
- * There weren't any previous patches found in the list cache; save the
- * newly found.
+ * Save the virtual address for early loading and for eventual free
+ * on late loading.
*/
- if (!prev_found) {
- p = memdup_patch(data, size);
- if (!p)
- pr_err("Error allocating buffer for %p\n", data);
- else
- list_add_tail(&p->plist, µcode_cache);
- }
-
- if (!p)
- return;
+ ucode_patch_va = mc;
+}
- if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf))
- return;
+static void save_microcode_patch(struct microcode_intel *patch)
+{
+ unsigned int size = get_totalsize(&patch->hdr);
+ struct microcode_intel *mc;
- /*
- * Save for early loading. On 32-bit, that needs to be a physical
- * address as the APs are running from physical addresses, before
- * paging has been enabled.
- */
- if (IS_ENABLED(CONFIG_X86_32))
- intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data);
+ mc = kvmemdup(patch, size, GFP_KERNEL);
+ if (mc)
+ update_ucode_pointer(mc);
else
- intel_ucode_patch = p->data;
+ pr_err("Unable to allocate microcode memory size: %u\n", size);
}
-/*
- * Get microcode matching with BSP's model. Only CPUs with the same model as
- * BSP can stay in the platform.
- */
-static struct microcode_intel *
-scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save)
+/* Scan blob for microcode matching the boot CPUs family, model, stepping */
+static __init struct microcode_intel *scan_microcode(void *data, size_t size,
+ struct ucode_cpu_info *uci,
+ bool save)
{
struct microcode_header_intel *mc_header;
struct microcode_intel *patch = NULL;
+ u32 cur_rev = uci->cpu_sig.rev;
unsigned int mc_size;
- while (size) {
- if (size < sizeof(struct microcode_header_intel))
- break;
-
+ for (; size >= sizeof(struct microcode_header_intel); size -= mc_size, data += mc_size) {
mc_header = (struct microcode_header_intel *)data;
mc_size = get_totalsize(mc_header);
- if (!mc_size ||
- mc_size > size ||
+ if (!mc_size || mc_size > size ||
intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0)
break;
- size -= mc_size;
-
- if (!intel_find_matching_signature(data, uci->cpu_sig.sig,
- uci->cpu_sig.pf)) {
- data += mc_size;
+ if (!intel_find_matching_signature(data, &uci->cpu_sig))
continue;
- }
+ /*
+ * For saving the early microcode, find the matching revision which
+ * was loaded on the BSP.
+ *
+ * On the BSP during early boot, find a newer revision than
+ * actually loaded in the CPU.
+ */
if (save) {
- save_microcode_patch(uci, data, mc_size);
- goto next;
- }
-
-
- if (!patch) {
- if (!has_newer_microcode(data,
- uci->cpu_sig.sig,
- uci->cpu_sig.pf,
- uci->cpu_sig.rev))
- goto next;
-
- } else {
- struct microcode_header_intel *phdr = &patch->hdr;
-
- if (!has_newer_microcode(data,
- phdr->sig,
- phdr->pf,
- phdr->rev))
- goto next;
+ if (cur_rev != mc_header->rev)
+ continue;
+ } else if (cur_rev >= mc_header->rev) {
+ continue;
}
- /* We have a newer patch, save it. */
patch = data;
-
-next:
- data += mc_size;
+ cur_rev = mc_header->rev;
}
- if (size)
- return NULL;
-
- return patch;
+ return size ? NULL : patch;
}
-static bool load_builtin_intel_microcode(struct cpio_data *cp)
+static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
+ struct microcode_intel *mc,
+ u32 *cur_rev)
{
- unsigned int eax = 1, ebx, ecx = 0, edx;
- struct firmware fw;
- char name[30];
-
- if (IS_ENABLED(CONFIG_X86_32))
- return false;
-
- native_cpuid(&eax, &ebx, &ecx, &edx);
-
- sprintf(name, "intel-ucode/%02x-%02x-%02x",
- x86_family(eax), x86_model(eax), x86_stepping(eax));
-
- if (firmware_request_builtin(&fw, name)) {
- cp->size = fw.size;
- cp->data = (void *)fw.data;
- return true;
- }
-
- return false;
-}
-
-static void print_ucode_info(int old_rev, int new_rev, unsigned int date)
-{
- pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
- old_rev,
- new_rev,
- date & 0xffff,
- date >> 24,
- (date >> 16) & 0xff);
-}
-
-#ifdef CONFIG_X86_32
-
-static int delay_ucode_info;
-static int current_mc_date;
-static int early_old_rev;
-
-/*
- * Print early updated ucode info after printk works. This is delayed info dump.
- */
-void show_ucode_info_early(void)
-{
- struct ucode_cpu_info uci;
-
- if (delay_ucode_info) {
- intel_cpu_collect_info(&uci);
- print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date);
- delay_ucode_info = 0;
- }
-}
-
-/*
- * At this point, we can not call printk() yet. Delay printing microcode info in
- * show_ucode_info_early() until printk() works.
- */
-static void print_ucode(int old_rev, int new_rev, int date)
-{
- int *delay_ucode_info_p;
- int *current_mc_date_p;
- int *early_old_rev_p;
-
- delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
- current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date);
- early_old_rev_p = (int *)__pa_nodebug(&early_old_rev);
-
- *delay_ucode_info_p = 1;
- *current_mc_date_p = date;
- *early_old_rev_p = old_rev;
-}
-#else
-
-static inline void print_ucode(int old_rev, int new_rev, int date)
-{
- print_ucode_info(old_rev, new_rev, date);
-}
-#endif
-
-static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
-{
- struct microcode_intel *mc;
- u32 rev, old_rev;
+ u32 rev;
- mc = uci->mc;
if (!mc)
- return 0;
+ return UCODE_NFOUND;
/*
* Save us the MSR write below - which is a particular expensive
* operation - when the other hyperthread has updated the microcode
* already.
*/
- rev = intel_get_microcode_revision();
- if (rev >= mc->hdr.rev) {
- uci->cpu_sig.rev = rev;
+ *cur_rev = intel_get_microcode_revision();
+ if (*cur_rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = *cur_rev;
return UCODE_OK;
}
- old_rev = rev;
-
- /*
- * Writeback and invalidate caches before updating microcode to avoid
- * internal issues depending on what the microcode is updating.
- */
- native_wbinvd();
-
/* write microcode via MSR 0x79 */
native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
rev = intel_get_microcode_revision();
if (rev != mc->hdr.rev)
- return -1;
+ return UCODE_ERROR;
uci->cpu_sig.rev = rev;
+ return UCODE_UPDATED;
+}
- if (early)
- print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date);
- else
- print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date);
+static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc = uci->mc;
+ u32 cur_rev;
- return 0;
+ return __apply_microcode(uci, mc, &cur_rev);
}
-int __init save_microcode_in_initrd_intel(void)
+static __init bool load_builtin_intel_microcode(struct cpio_data *cp)
{
- struct ucode_cpu_info uci;
- struct cpio_data cp;
-
- /*
- * initrd is going away, clear patch ptr. We will scan the microcode one
- * last time before jettisoning and save a patch, if found. Then we will
- * update that pointer too, with a stable patch address to use when
- * resuming the cores.
- */
- intel_ucode_patch = NULL;
+ unsigned int eax = 1, ebx, ecx = 0, edx;
+ struct firmware fw;
+ char name[30];
- if (!load_builtin_intel_microcode(&cp))
- cp = find_microcode_in_initrd(ucode_path, false);
+ if (IS_ENABLED(CONFIG_X86_32))
+ return false;
- if (!(cp.data && cp.size))
- return 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
- intel_cpu_collect_info(&uci);
+ sprintf(name, "intel-ucode/%02x-%02x-%02x",
+ x86_family(eax), x86_model(eax), x86_stepping(eax));
- scan_microcode(cp.data, cp.size, &uci, true);
- return 0;
+ if (firmware_request_builtin(&fw, name)) {
+ cp->size = fw.size;
+ cp->data = (void *)fw.data;
+ return true;
+ }
+ return false;
}
-/*
- * @res_patch, output: a pointer to the patch we found.
- */
-static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci)
+static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *uci, bool save)
{
- static const char *path;
struct cpio_data cp;
- bool use_pa;
-
- if (IS_ENABLED(CONFIG_X86_32)) {
- path = (const char *)__pa_nodebug(ucode_path);
- use_pa = true;
- } else {
- path = ucode_path;
- use_pa = false;
- }
- /* try built-in microcode first */
+ intel_collect_cpu_info(&uci->cpu_sig);
+
if (!load_builtin_intel_microcode(&cp))
- cp = find_microcode_in_initrd(path, use_pa);
+ cp = find_microcode_in_initrd(ucode_path);
if (!(cp.data && cp.size))
return NULL;
- intel_cpu_collect_info(uci);
-
- return scan_microcode(cp.data, cp.size, uci, false);
+ return scan_microcode(cp.data, cp.size, uci, save);
}
-void __init load_ucode_intel_bsp(void)
+/*
+ * Invoked from an early init call to save the microcode blob which was
+ * selected during early boot when mm was not usable. The microcode must be
+ * saved because initrd is going away. It's an early init call so the APs
+ * just can use the pointer and do not have to scan initrd/builtin firmware
+ * again.
+ */
+static int __init save_builtin_microcode(void)
{
- struct microcode_intel *patch;
struct ucode_cpu_info uci;
- patch = __load_ucode_intel(&uci);
- if (!patch)
- return;
+ if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
+ return 0;
- uci.mc = patch;
+ if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return 0;
- apply_microcode_early(&uci, true);
+ uci.mc = get_microcode_blob(&uci, true);
+ if (uci.mc)
+ save_microcode_patch(uci.mc);
+ return 0;
}
+early_initcall(save_builtin_microcode);
-void load_ucode_intel_ap(void)
+/* Load microcode on BSP from initrd or builtin blobs */
+void __init load_ucode_intel_bsp(struct early_load_data *ed)
{
- struct microcode_intel *patch, **iup;
struct ucode_cpu_info uci;
- if (IS_ENABLED(CONFIG_X86_32))
- iup = (struct microcode_intel **) __pa_nodebug(&intel_ucode_patch);
- else
- iup = &intel_ucode_patch;
+ uci.mc = get_microcode_blob(&uci, false);
+ ed->old_rev = uci.cpu_sig.rev;
- if (!*iup) {
- patch = __load_ucode_intel(&uci);
- if (!patch)
- return;
-
- *iup = patch;
+ if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) {
+ ucode_patch_va = UCODE_BSP_LOADED;
+ ed->new_rev = uci.cpu_sig.rev;
}
-
- uci.mc = *iup;
-
- apply_microcode_early(&uci, true);
}
-static struct microcode_intel *find_patch(struct ucode_cpu_info *uci)
+void load_ucode_intel_ap(void)
{
- struct microcode_header_intel *phdr;
- struct ucode_patch *iter, *tmp;
-
- list_for_each_entry_safe(iter, tmp, µcode_cache, plist) {
-
- phdr = (struct microcode_header_intel *)iter->data;
-
- if (phdr->rev <= uci->cpu_sig.rev)
- continue;
-
- if (!intel_find_matching_signature(phdr,
- uci->cpu_sig.sig,
- uci->cpu_sig.pf))
- continue;
+ struct ucode_cpu_info uci;
- return iter->data;
- }
- return NULL;
+ uci.mc = ucode_patch_va;
+ if (uci.mc)
+ apply_microcode_early(&uci);
}
+/* Reload microcode on resume */
void reload_ucode_intel(void)
{
- struct microcode_intel *p;
- struct ucode_cpu_info uci;
-
- intel_cpu_collect_info(&uci);
-
- p = find_patch(&uci);
- if (!p)
- return;
-
- uci.mc = p;
+ struct ucode_cpu_info uci = { .mc = ucode_patch_va, };
- apply_microcode_early(&uci, false);
+ if (uci.mc)
+ apply_microcode_early(&uci);
}
static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu_num);
- unsigned int val[2];
-
- memset(csig, 0, sizeof(*csig));
-
- csig->sig = cpuid_eax(0x00000001);
-
- if ((c->x86_model >= 5) || (c->x86 > 6)) {
- /* get processor flags from MSR 0x17 */
- rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
- csig->pf = 1 << ((val[1] >> 18) & 7);
- }
-
- csig->rev = c->microcode;
-
+ intel_collect_cpu_info(csig);
return 0;
}
-static enum ucode_state apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_late(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
- struct microcode_intel *mc;
+ struct microcode_intel *mc = ucode_patch_late;
enum ucode_state ret;
- static int prev_rev;
- u32 rev;
+ u32 cur_rev;
- /* We should bind the task to the CPU */
- if (WARN_ON(raw_smp_processor_id() != cpu))
+ if (WARN_ON_ONCE(smp_processor_id() != cpu))
return UCODE_ERROR;
- /* Look for a newer patch in our cache: */
- mc = find_patch(uci);
- if (!mc) {
- mc = uci->mc;
- if (!mc)
- return UCODE_NFOUND;
- }
+ ret = __apply_microcode(uci, mc, &cur_rev);
+ if (ret != UCODE_UPDATED && ret != UCODE_OK)
+ return ret;
- /*
- * Save us the MSR write below - which is a particular expensive
- * operation - when the other hyperthread has updated the microcode
- * already.
- */
- rev = intel_get_microcode_revision();
- if (rev >= mc->hdr.rev) {
- ret = UCODE_OK;
- goto out;
- }
-
- /*
- * Writeback and invalidate caches before updating microcode to avoid
- * internal issues depending on what the microcode is updating.
- */
- native_wbinvd();
-
- /* write microcode via MSR 0x79 */
- wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
-
- rev = intel_get_microcode_revision();
-
- if (rev != mc->hdr.rev) {
- pr_err("CPU%d update to revision 0x%x failed\n",
- cpu, mc->hdr.rev);
- return UCODE_ERROR;
- }
-
- if (bsp && rev != prev_rev) {
- pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
- rev,
- mc->hdr.date & 0xffff,
- mc->hdr.date >> 24,
+ if (!cpu && uci->cpu_sig.rev != cur_rev) {
+ pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n",
+ uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24,
(mc->hdr.date >> 16) & 0xff);
- prev_rev = rev;
}
- ret = UCODE_UPDATED;
-
-out:
- uci->cpu_sig.rev = rev;
- c->microcode = rev;
-
- /* Update boot_cpu_data's revision too, if we're on the BSP: */
- if (bsp)
- boot_cpu_data.microcode = rev;
+ cpu_data(cpu).microcode = uci->cpu_sig.rev;
+ if (!cpu)
+ boot_cpu_data.microcode = uci->cpu_sig.rev;
return ret;
}
-static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
+static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- unsigned int curr_mc_size = 0, new_mc_size = 0;
- enum ucode_state ret = UCODE_OK;
- int new_rev = uci->cpu_sig.rev;
+ int cur_rev = uci->cpu_sig.rev;
+ unsigned int curr_mc_size = 0;
u8 *new_mc = NULL, *mc = NULL;
- unsigned int csig, cpf;
+
+ if (force_minrev)
+ return UCODE_NFOUND;
while (iov_iter_count(iter)) {
struct microcode_header_intel mc_header;
@@ -758,68 +481,61 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
pr_err("error! Truncated or inaccessible header in microcode data file\n");
- break;
+ goto fail;
}
mc_size = get_totalsize(&mc_header);
if (mc_size < sizeof(mc_header)) {
pr_err("error! Bad data in microcode data file (totalsize too small)\n");
- break;
+ goto fail;
}
data_size = mc_size - sizeof(mc_header);
if (data_size > iov_iter_count(iter)) {
pr_err("error! Bad data in microcode data file (truncated file?)\n");
- break;
+ goto fail;
}
/* For performance reasons, reuse mc area when possible */
if (!mc || mc_size > curr_mc_size) {
- vfree(mc);
- mc = vmalloc(mc_size);
+ kvfree(mc);
+ mc = kvmalloc(mc_size, GFP_KERNEL);
if (!mc)
- break;
+ goto fail;
curr_mc_size = mc_size;
}
memcpy(mc, &mc_header, sizeof(mc_header));
data = mc + sizeof(mc_header);
if (!copy_from_iter_full(data, data_size, iter) ||
- intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) {
- break;
- }
+ intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0)
+ goto fail;
- csig = uci->cpu_sig.sig;
- cpf = uci->cpu_sig.pf;
- if (has_newer_microcode(mc, csig, cpf, new_rev)) {
- vfree(new_mc);
- new_rev = mc_header.rev;
- new_mc = mc;
- new_mc_size = mc_size;
- mc = NULL; /* trigger new vmalloc */
- ret = UCODE_NEW;
- }
- }
+ if (cur_rev >= mc_header.rev)
+ continue;
- vfree(mc);
+ if (!intel_find_matching_signature(mc, &uci->cpu_sig))
+ continue;
- if (iov_iter_count(iter)) {
- vfree(new_mc);
- return UCODE_ERROR;
+ kvfree(new_mc);
+ cur_rev = mc_header.rev;
+ new_mc = mc;
+ mc = NULL;
}
+ if (iov_iter_count(iter))
+ goto fail;
+
+ kvfree(mc);
if (!new_mc)
return UCODE_NFOUND;
- vfree(uci->mc);
- uci->mc = (struct microcode_intel *)new_mc;
-
- /* Save for CPU hotplug */
- save_microcode_patch(uci, new_mc, new_mc_size);
+ ucode_patch_late = (struct microcode_intel *)new_mc;
+ return UCODE_NEW;
- pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
- cpu, new_rev, uci->cpu_sig.rev);
-
- return ret;
+fail:
+ kvfree(mc);
+ kvfree(new_mc);
+ return UCODE_ERROR;
}
static bool is_blacklisted(unsigned int cpu)
@@ -829,7 +545,7 @@ static bool is_blacklisted(unsigned int cpu)
/*
* Late loading on model 79 with microcode revision less than 0x0b000021
* and LLC size per core bigger than 2.5MB may result in a system hang.
- * This behavior is documented in item BDF90, #334165 (Intel Xeon
+ * This behavior is documented in item BDX90, #334165 (Intel Xeon
* Processor E7-8800/4800 v4 Product Family).
*/
if (c->x86 == 6 &&
@@ -837,7 +553,7 @@ static bool is_blacklisted(unsigned int cpu)
c->x86_stepping == 0x01 &&
llc_size_per_core > 2621440 &&
c->microcode < 0x0b000021) {
- pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
+ pr_err_once("Erratum BDX90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
return true;
}
@@ -868,26 +584,36 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
kvec.iov_base = (void *)firmware->data;
kvec.iov_len = firmware->size;
iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size);
- ret = generic_load_microcode(cpu, &iter);
+ ret = parse_microcode_blobs(cpu, &iter);
release_firmware(firmware);
return ret;
}
+static void finalize_late_load(int result)
+{
+ if (!result)
+ update_ucode_pointer(ucode_patch_late);
+ else
+ kvfree(ucode_patch_late);
+ ucode_patch_late = NULL;
+}
+
static struct microcode_ops microcode_intel_ops = {
- .request_microcode_fw = request_microcode_fw,
- .collect_cpu_info = collect_cpu_info,
- .apply_microcode = apply_microcode_intel,
+ .request_microcode_fw = request_microcode_fw,
+ .collect_cpu_info = collect_cpu_info,
+ .apply_microcode = apply_microcode_late,
+ .finalize_late_load = finalize_late_load,
+ .use_nmi = IS_ENABLED(CONFIG_X86_64),
};
-static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c)
{
u64 llc_size = c->x86_cache_size * 1024ULL;
do_div(llc_size, c->x86_max_cores);
-
- return (int)llc_size;
+ llc_size_per_core = (unsigned int)llc_size;
}
struct microcode_ops * __init init_intel_microcode(void)
@@ -900,7 +626,7 @@ struct microcode_ops * __init init_intel_microcode(void)
return NULL;
}
- llc_size_per_core = calc_llc_size_per_core(c);
+ calc_llc_size_per_core(c);
return µcode_intel_ops;
}
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index bf883aa71233..21776c529fa9 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -8,43 +8,43 @@
#include <asm/cpu.h>
#include <asm/microcode.h>
-struct ucode_patch {
- struct list_head plist;
- void *data; /* Intel uses only this one */
- unsigned int size;
- u32 patch_id;
- u16 equiv_cpu;
-};
-
-extern struct list_head microcode_cache;
-
struct device;
enum ucode_state {
UCODE_OK = 0,
UCODE_NEW,
+ UCODE_NEW_SAFE,
UCODE_UPDATED,
UCODE_NFOUND,
UCODE_ERROR,
+ UCODE_TIMEOUT,
+ UCODE_OFFLINE,
};
struct microcode_ops {
enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev);
-
void (*microcode_fini_cpu)(int cpu);
/*
- * The generic 'microcode_core' part guarantees that
- * the callbacks below run on a target cpu when they
- * are being called.
+ * The generic 'microcode_core' part guarantees that the callbacks
+ * below run on a target CPU when they are being called.
* See also the "Synchronization" section in microcode_core.c.
*/
- enum ucode_state (*apply_microcode)(int cpu);
- int (*collect_cpu_info)(int cpu, struct cpu_signature *csig);
+ enum ucode_state (*apply_microcode)(int cpu);
+ int (*collect_cpu_info)(int cpu, struct cpu_signature *csig);
+ void (*finalize_late_load)(int result);
+ unsigned int nmi_safe : 1,
+ use_nmi : 1;
+};
+
+struct early_load_data {
+ u32 old_rev;
+ u32 new_rev;
};
+extern struct early_load_data early_data;
extern struct ucode_cpu_info ucode_cpu_info[];
-struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa);
+struct cpio_data find_microcode_in_initrd(const char *path);
#define MAX_UCODE_COUNT 128
@@ -94,20 +94,19 @@ static inline unsigned int x86_cpuid_family(void)
return x86_family(eax);
}
-extern bool initrd_gone;
+extern bool dis_ucode_ldr;
+extern bool force_minrev;
#ifdef CONFIG_CPU_SUP_AMD
-void load_ucode_amd_bsp(unsigned int family);
+void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
void load_ucode_amd_ap(unsigned int family);
-void load_ucode_amd_early(unsigned int cpuid_1_eax);
int save_microcode_in_initrd_amd(unsigned int family);
void reload_ucode_amd(unsigned int cpu);
struct microcode_ops *init_amd_microcode(void);
void exit_amd_microcode(void);
#else /* CONFIG_CPU_SUP_AMD */
-static inline void load_ucode_amd_bsp(unsigned int family) { }
+static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline void load_ucode_amd_early(unsigned int family) { }
static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
static inline void reload_ucode_amd(unsigned int cpu) { }
static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
@@ -115,15 +114,13 @@ static inline void exit_amd_microcode(void) { }
#endif /* !CONFIG_CPU_SUP_AMD */
#ifdef CONFIG_CPU_SUP_INTEL
-void load_ucode_intel_bsp(void);
+void load_ucode_intel_bsp(struct early_load_data *ed);
void load_ucode_intel_ap(void);
-int save_microcode_in_initrd_intel(void);
void reload_ucode_intel(void);
struct microcode_ops *init_intel_microcode(void);
#else /* CONFIG_CPU_SUP_INTEL */
-static inline void load_ucode_intel_bsp(void) { }
+static inline void load_ucode_intel_bsp(struct early_load_data *ed) { }
static inline void load_ucode_intel_ap(void) { }
-static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; }
static inline void reload_ucode_intel(void) { }
static inline struct microcode_ops *init_intel_microcode(void) { return NULL; }
#endif /* !CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 246a609f889b..bde27a35bf2e 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -19,6 +19,7 @@
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/bios_ebda.h>
+#include <asm/microcode.h>
#include <asm/tlbflush.h>
#include <asm/bootparam_utils.h>
@@ -34,6 +35,8 @@ asmlinkage __visible void __init __noreturn i386_start_kernel(void)
/* Make sure IDT is set up before any exception happens */
idt_setup_early_handler();
+ load_ucode_bsp();
+
cr4_init_shadow();
sanitize_boot_params(&boot_params);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c9318993f959..63f6ff4b28eb 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -118,11 +118,6 @@ SYM_CODE_START(startup_32)
movl %eax, pa(olpc_ofw_pgd)
#endif
-#ifdef CONFIG_MICROCODE
- /* Early load ucode on BSP. */
- call load_ucode_bsp
-#endif
-
/* Create early pagetables. */
call mk_early_pgtbl_32
@@ -157,11 +152,6 @@ SYM_FUNC_START(startup_32_smp)
movl %eax,%ss
leal -__PAGE_OFFSET(%ecx),%esp
-#ifdef CONFIG_MICROCODE
- /* Early load ucode on AP. */
- call load_ucode_ap
-#endif
-
.Ldefault_entry:
movl $(CR0_STATE & ~X86_CR0_PG),%eax
movl %eax,%cr0
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 87aee638e1a5..6da2cfa23c29 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -33,6 +33,7 @@
#include <asm/reboot.h>
#include <asm/cache.h>
#include <asm/nospec-branch.h>
+#include <asm/microcode.h>
#include <asm/sev.h>
#define CREATE_TRACE_POINTS
@@ -343,6 +344,9 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
instrumentation_begin();
+ if (microcode_nmi_handler_enabled() && microcode_nmi_handler())
+ goto out;
+
handled = nmi_handle(NMI_LOCAL, regs);
__this_cpu_add(nmi_stats.normal, handled);
if (handled) {
@@ -498,8 +502,11 @@ DEFINE_IDTENTRY_RAW(exc_nmi)
if (IS_ENABLED(CONFIG_NMI_CHECK_CPU))
raw_atomic_long_inc(&nsp->idt_calls);
- if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
+ if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) {
+ if (microcode_nmi_handler_enabled())
+ microcode_offline_nmi_handler();
return;
+ }
if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
this_cpu_write(nmi_state, NMI_LATCHED);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a8f2ab816d5a..77f0d9ccb2c0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -259,12 +259,9 @@ static void notrace start_secondary(void *unused)
cpu_init_exception_handling();
/*
- * 32-bit systems load the microcode from the ASM startup code for
- * historical reasons.
- *
- * On 64-bit systems load it before reaching the AP alive
- * synchronization point below so it is not part of the full per
- * CPU serialized bringup part when "parallel" bringup is enabled.
+ * Load the microcode before reaching the AP alive synchronization
+ * point below so it is not part of the full per CPU serialized
+ * bringup part when "parallel" bringup is enabled.
*
* That's even safe when hyperthreading is enabled in the CPU as
* the core code starts the primary threads first and leaves the
@@ -277,8 +274,7 @@ static void notrace start_secondary(void *unused)
* CPUID, MSRs etc. must be strictly serialized to maintain
* software state correctness.
*/
- if (IS_ENABLED(CONFIG_X86_64))
- load_ucode_ap();
+ load_ucode_ap();
/*
* Synchronization point with the hotplug core. Sets this CPUs
diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index e62ffffe5fb8..4ce5681be18f 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1562,8 +1562,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
goto out_fw;
}
- ret = regmap_raw_write_async(regmap, reg, buf->buf,
- le32_to_cpu(region->len));
+ ret = regmap_raw_write(regmap, reg, buf->buf,
+ le32_to_cpu(region->len));
if (ret != 0) {
cs_dsp_err(dsp,
"%s.%d: Failed to write %d bytes at %d in %s: %d\n",
@@ -1578,12 +1578,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
regions++;
}
- ret = regmap_async_complete(regmap);
- if (ret != 0) {
- cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
- goto out_fw;
- }
-
if (pos > firmware->size)
cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
file, regions, pos - firmware->size);
@@ -1591,7 +1585,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
cs_dsp_debugfs_save_wmfwname(dsp, file);
out_fw:
- regmap_async_complete(regmap);
cs_dsp_buf_free(&buf_list);
kfree(text);
@@ -2287,8 +2280,8 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n",
file, blocks, le32_to_cpu(blk->len),
reg);
- ret = regmap_raw_write_async(regmap, reg, buf->buf,
- le32_to_cpu(blk->len));
+ ret = regmap_raw_write(regmap, reg, buf->buf,
+ le32_to_cpu(blk->len));
if (ret != 0) {
cs_dsp_err(dsp,
"%s.%d: Failed to write to %x in %s: %d\n",
@@ -2300,10 +2293,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
blocks++;
}
- ret = regmap_async_complete(regmap);
- if (ret != 0)
- cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-
if (pos > firmware->size)
cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
file, blocks, pos - firmware->size);
@@ -2311,7 +2300,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
cs_dsp_debugfs_save_binname(dsp, file);
out_fw:
- regmap_async_complete(regmap);
cs_dsp_buf_free(&buf_list);
kfree(text);
@@ -2523,8 +2511,8 @@ static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp)
{
int ret;
- ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL,
- ADSP2_SYS_ENA, ADSP2_SYS_ENA);
+ ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
+ ADSP2_SYS_ENA, ADSP2_SYS_ENA);
if (ret != 0)
return ret;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 51467f132c26..da47e68b10ce 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -891,6 +891,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
struct drm_device *dev = adev_to_drm(adev);
struct drm_connector *connector;
struct drm_connector_list_iter iter;
+ int i;
drm_connector_list_iter_begin(dev, &iter);
drm_for_each_connector_iter(connector, &iter) {
@@ -912,6 +913,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
}
}
drm_connector_list_iter_end(&iter);
+
+ /* Update reference counts for HPDs */
+ for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+ if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+ drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i);
+ }
}
/**
@@ -927,6 +934,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
struct drm_device *dev = adev_to_drm(adev);
struct drm_connector *connector;
struct drm_connector_list_iter iter;
+ int i;
drm_connector_list_iter_begin(dev, &iter);
drm_for_each_connector_iter(connector, &iter) {
@@ -947,4 +955,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
}
}
drm_connector_list_iter_end(&iter);
+
+ /* Update reference counts for HPDs */
+ for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+ if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+ drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i);
+ }
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 08ce3bb8f640..fe96bab7d05d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -51,7 +51,8 @@ static bool link_supports_psrsu(struct dc_link *link)
!link->dpcd_caps.psr_info.psr2_su_y_granularity_cap)
return false;
- return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
+ /* Temporarily disable PSR-SU to avoid glitches */
+ return false;
}
/*
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index c8586cb7d0fe..4d193313a6d6 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3043,6 +3043,7 @@ static int kv_dpm_hw_init(void *handle)
if (!amdgpu_dpm)
return 0;
+ mutex_lock(&adev->pm.mutex);
kv_dpm_setup_asic(adev);
ret = kv_dpm_enable(adev);
if (ret)
@@ -3050,6 +3051,8 @@ static int kv_dpm_hw_init(void *handle)
else
adev->pm.dpm_enabled = true;
amdgpu_legacy_dpm_compute_clocks(adev);
+ mutex_unlock(&adev->pm.mutex);
+
return ret;
}
@@ -3067,32 +3070,42 @@ static int kv_dpm_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ cancel_work_sync(&adev->pm.dpm.thermal.work);
+
if (adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
+ adev->pm.dpm_enabled = false;
/* disable dpm */
kv_dpm_disable(adev);
/* reset the power state */
adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+ mutex_unlock(&adev->pm.mutex);
}
return 0;
}
static int kv_dpm_resume(void *handle)
{
- int ret;
+ int ret = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->pm.dpm_enabled) {
+ if (!amdgpu_dpm)
+ return 0;
+
+ if (!adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
/* asic init will reset to the boot state */
kv_dpm_setup_asic(adev);
ret = kv_dpm_enable(adev);
- if (ret)
+ if (ret) {
adev->pm.dpm_enabled = false;
- else
+ } else {
adev->pm.dpm_enabled = true;
- if (adev->pm.dpm_enabled)
amdgpu_legacy_dpm_compute_clocks(adev);
+ }
+ mutex_unlock(&adev->pm.mutex);
}
- return 0;
+ return ret;
}
static bool kv_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index 60377747bab4..48ad413d72af 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -1018,9 +1018,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
int temp, size = sizeof(temp);
- if (!adev->pm.dpm_enabled)
- return;
+ mutex_lock(&adev->pm.mutex);
+ if (!adev->pm.dpm_enabled) {
+ mutex_unlock(&adev->pm.mutex);
+ return;
+ }
if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
AMDGPU_PP_SENSOR_GPU_TEMP,
(void *)&temp,
@@ -1042,4 +1045,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
adev->pm.dpm.state = dpm_state;
amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
+ mutex_unlock(&adev->pm.mutex);
}
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 99dde52a4290..e7b1fa2feb92 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7789,6 +7789,7 @@ static int si_dpm_hw_init(void *handle)
if (!amdgpu_dpm)
return 0;
+ mutex_lock(&adev->pm.mutex);
si_dpm_setup_asic(adev);
ret = si_dpm_enable(adev);
if (ret)
@@ -7796,6 +7797,7 @@ static int si_dpm_hw_init(void *handle)
else
adev->pm.dpm_enabled = true;
amdgpu_legacy_dpm_compute_clocks(adev);
+ mutex_unlock(&adev->pm.mutex);
return ret;
}
@@ -7813,32 +7815,44 @@ static int si_dpm_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ cancel_work_sync(&adev->pm.dpm.thermal.work);
+
if (adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
+ adev->pm.dpm_enabled = false;
/* disable dpm */
si_dpm_disable(adev);
/* reset the power state */
adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+ mutex_unlock(&adev->pm.mutex);
}
+
return 0;
}
static int si_dpm_resume(void *handle)
{
- int ret;
+ int ret = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->pm.dpm_enabled) {
+ if (!amdgpu_dpm)
+ return 0;
+
+ if (!adev->pm.dpm_enabled) {
/* asic init will reset to the boot state */
+ mutex_lock(&adev->pm.mutex);
si_dpm_setup_asic(adev);
ret = si_dpm_enable(adev);
- if (ret)
+ if (ret) {
adev->pm.dpm_enabled = false;
- else
+ } else {
adev->pm.dpm_enabled = true;
- if (adev->pm.dpm_enabled)
amdgpu_legacy_dpm_compute_clocks(adev);
+ }
+ mutex_unlock(&adev->pm.mutex);
}
- return 0;
+
+ return ret;
}
static bool si_dpm_is_idle(void *handle)
diff --git a/drivers/i2c/busses/i2c-ls2x.c b/drivers/i2c/busses/i2c-ls2x.c
index ebae6035701d..d74625d72f4c 100644
--- a/drivers/i2c/busses/i2c-ls2x.c
+++ b/drivers/i2c/busses/i2c-ls2x.c
@@ -10,6 +10,7 @@
* Rewritten for mainline by Binbin Zhou <zhoubinbin@...ngson.cn>
*/
+#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/completion.h>
#include <linux/device.h>
@@ -26,7 +27,8 @@
#include <linux/units.h>
/* I2C Registers */
-#define I2C_LS2X_PRER 0x0 /* Freq Division Register(16 bits) */
+#define I2C_LS2X_PRER_LO 0x0 /* Freq Division Low Byte Register */
+#define I2C_LS2X_PRER_HI 0x1 /* Freq Division High Byte Register */
#define I2C_LS2X_CTR 0x2 /* Control Register */
#define I2C_LS2X_TXR 0x3 /* Transport Data Register */
#define I2C_LS2X_RXR 0x3 /* Receive Data Register */
@@ -93,6 +95,7 @@ static irqreturn_t ls2x_i2c_isr(int this_irq, void *dev_id)
*/
static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
{
+ u16 val;
struct i2c_timings *t = &priv->i2c_t;
struct device *dev = priv->adapter.dev.parent;
u32 acpi_speed = i2c_acpi_find_bus_speed(dev);
@@ -104,9 +107,14 @@ static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
else
t->bus_freq_hz = LS2X_I2C_FREQ_STD;
- /* Calculate and set i2c frequency. */
- writew(LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1,
- priv->base + I2C_LS2X_PRER);
+ /*
+ * According to the chip manual, we can only access the registers as bytes,
+ * otherwise the high bits will be truncated.
+ * So set the I2C frequency with a sequential writeb() instead of writew().
+ */
+ val = LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1;
+ writeb(FIELD_GET(GENMASK(7, 0), val), priv->base + I2C_LS2X_PRER_LO);
+ writeb(FIELD_GET(GENMASK(15, 8), val), priv->base + I2C_LS2X_PRER_HI);
}
static void ls2x_i2c_init(struct ls2x_i2c_priv *priv)
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index ae4bae63ad4f..91f508d50e7a 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2333,6 +2333,13 @@ static int npcm_i2c_probe_bus(struct platform_device *pdev)
if (irq < 0)
return irq;
+ /*
+ * Disable the interrupt to avoid the interrupt handler being triggered
+ * incorrectly by the asynchronous interrupt status since the machine
+ * might do a warm reset during the last smbus/i2c transfer session.
+ */
+ npcm_i2c_int_enable(bus, false);
+
ret = devm_request_irq(bus->dev, irq, npcm_i2c_bus_irq, 0,
dev_name(bus->dev), bus);
if (ret)
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 45500d2d5b4b..44842f243f40 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,6 +56,7 @@
#include <asm/nospec-branch.h>
#include <asm/mwait.h>
#include <asm/msr.h>
+#include <asm/tsc.h>
#include <asm/fpu/api.h>
#define INTEL_IDLE_VERSION "0.5.1"
@@ -1573,6 +1574,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
if (intel_idle_state_needs_timer_stop(state))
state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+ if (cx->type > ACPI_STATE_C1 && !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+ mark_tsc_unstable("TSC halts in idle");
+
state->enter = intel_idle;
state->enter_s2idle = intel_idle_s2idle;
}
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index ec5efdc16660..9f97bef02149 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -342,6 +342,10 @@ static ssize_t rate_show(struct ib_device *ibdev, u32 port_num,
speed = " NDR";
rate = 1000;
break;
+ case IB_SPEED_XDR:
+ speed = " XDR";
+ rate = 2000;
+ break;
case IB_SPEED_SDR:
default: /* default to SDR for invalid rates */
speed = " SDR";
diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index 049684880ae0..fb0555647336 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -203,6 +203,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_PORT)(
copy_port_attr_to_resp(&attr, &resp.legacy_resp, ib_dev, port_num);
resp.port_cap_flags2 = attr.port_cap_flags2;
+ resp.active_speed_ex = attr.active_speed;
return uverbs_copy_to_struct_or_zero(attrs, UVERBS_ATTR_QUERY_PORT_RESP,
&resp, sizeof(resp));
@@ -461,7 +462,7 @@ DECLARE_UVERBS_NAMED_METHOD(
UVERBS_ATTR_PTR_OUT(
UVERBS_ATTR_QUERY_PORT_RESP,
UVERBS_ATTR_STRUCT(struct ib_uverbs_query_port_resp_ex,
- reserved),
+ active_speed_ex),
UA_MANDATORY));
DECLARE_UVERBS_NAMED_METHOD(
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 186ed3c22ec9..ba05de0380e9 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -147,6 +147,7 @@ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate)
case IB_RATE_50_GBPS: return 20;
case IB_RATE_400_GBPS: return 160;
case IB_RATE_600_GBPS: return 240;
+ case IB_RATE_800_GBPS: return 320;
default: return -1;
}
}
@@ -176,6 +177,7 @@ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult)
case 20: return IB_RATE_50_GBPS;
case 160: return IB_RATE_400_GBPS;
case 240: return IB_RATE_600_GBPS;
+ case 320: return IB_RATE_800_GBPS;
default: return IB_RATE_PORT_CURRENT;
}
}
@@ -205,6 +207,7 @@ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate)
case IB_RATE_50_GBPS: return 53125;
case IB_RATE_400_GBPS: return 425000;
case IB_RATE_600_GBPS: return 637500;
+ case IB_RATE_800_GBPS: return 850000;
default: return -1;
}
}
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 85717482a616..6fa9b1253299 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -180,7 +180,7 @@ static int mana_gd_allocate_doorbell_page(struct gdma_context *gc,
req.resource_type = GDMA_RESOURCE_DOORBELL_PAGE;
req.num_resources = 1;
- req.alignment = 1;
+ req.alignment = PAGE_SIZE / MANA_PAGE_SIZE;
/* Have GDMA start searching from 0 */
req.allocated_resources = 0;
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 505bc47fd575..99036afb3aef 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -67,7 +67,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
ah->av.tclass = grh->traffic_class;
}
- ah->av.stat_rate_sl = (rdma_ah_get_static_rate(ah_attr) << 4);
+ ah->av.stat_rate_sl =
+ (mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr)) << 4);
if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
if (init_attr->xmit_slave)
diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 8300ce622835..b049bba21579 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -542,6 +542,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
struct ib_qp *qp)
{
struct mlx5_ib_dev *dev = to_mdev(qp->device);
+ bool new = false;
int err;
if (!counter->id) {
@@ -556,6 +557,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
return err;
counter->id =
MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+ new = true;
}
err = mlx5_ib_qp_set_counter(qp, counter);
@@ -565,8 +567,10 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
return 0;
fail_set_counter:
- mlx5_ib_counter_dealloc(counter);
- counter->id = 0;
+ if (new) {
+ mlx5_ib_counter_dealloc(counter);
+ counter->id = 0;
+ }
return err;
}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 71a856409cee..0a9ae84600b2 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3433,11 +3433,11 @@ static int ib_to_mlx5_rate_map(u8 rate)
return 0;
}
-static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate)
{
u32 stat_rate_support;
- if (rate == IB_RATE_PORT_CURRENT)
+ if (rate == IB_RATE_PORT_CURRENT || rate == IB_RATE_800_GBPS)
return 0;
if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_600_GBPS)
@@ -3582,7 +3582,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
sizeof(grh->dgid.raw));
}
- err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
+ err = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah));
if (err < 0)
return err;
MLX5_SET(ads, path, stat_rate, err);
@@ -4555,6 +4555,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
MLX5_SET(dctc, dctc, counter_set_id, set_id);
+
+ qp->port = attr->port_num;
} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
struct mlx5_ib_modify_qp_resp resp = {};
u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {};
@@ -5045,7 +5047,7 @@ static int mlx5_ib_dct_query_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *mqp,
}
if (qp_attr_mask & IB_QP_PORT)
- qp_attr->port_num = MLX5_GET(dctc, dctc, port);
+ qp_attr->port_num = mqp->port;
if (qp_attr_mask & IB_QP_MIN_RNR_TIMER)
qp_attr->min_rnr_timer = MLX5_GET(dctc, dctc, min_rnr_nak);
if (qp_attr_mask & IB_QP_AV) {
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index b6ee7c3ee1ca..2530e7730635 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -56,4 +56,5 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
int mlx5_ib_qp_event_init(void);
void mlx5_ib_qp_event_cleanup(void);
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate);
#endif /* _MLX5_IB_QP_H */
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 78c972bb1d96..9fb5a18e056d 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1270,6 +1270,8 @@ struct macb {
struct clk *rx_clk;
struct clk *tsu_clk;
struct net_device *dev;
+ /* Protects hw_stats and ethtool_stats */
+ spinlock_t stats_lock;
union {
struct macb_stats macb;
struct gem_stats gem;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 8f61731e4554..4325d0ace1f2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1992,10 +1992,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
if (status & MACB_BIT(ISR_ROVR)) {
/* We missed at least one packet */
+ spin_lock(&bp->stats_lock);
if (macb_is_gem(bp))
bp->hw_stats.gem.rx_overruns++;
else
bp->hw_stats.macb.rx_overruns++;
+ spin_unlock(&bp->stats_lock);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -3084,6 +3086,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
if (!netif_running(bp->dev))
return nstat;
+ spin_lock_irq(&bp->stats_lock);
gem_update_stats(bp);
nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
@@ -3113,6 +3116,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
nstat->tx_fifo_errors = hwstat->tx_underrun;
+ spin_unlock_irq(&bp->stats_lock);
return nstat;
}
@@ -3120,12 +3124,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
static void gem_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
- struct macb *bp;
+ struct macb *bp = netdev_priv(dev);
- bp = netdev_priv(dev);
+ spin_lock_irq(&bp->stats_lock);
gem_update_stats(bp);
memcpy(data, &bp->ethtool_stats, sizeof(u64)
* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+ spin_unlock_irq(&bp->stats_lock);
}
static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3175,6 +3180,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
return gem_get_stats(bp);
/* read stats from hardware */
+ spin_lock_irq(&bp->stats_lock);
macb_update_stats(bp);
/* Convert HW stats into netdevice stats */
@@ -3208,6 +3214,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
nstat->tx_fifo_errors = hwstat->tx_underruns;
/* Don't know about heartbeat or window errors... */
+ spin_unlock_irq(&bp->stats_lock);
return nstat;
}
@@ -5063,6 +5070,7 @@ static int macb_probe(struct platform_device *pdev)
}
}
spin_lock_init(&bp->lock);
+ spin_lock_init(&bp->stats_lock);
/* setup capabilities */
macb_configure_caps(bp, macb_config);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 87b27bd7a13b..9aa57134f460 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -145,6 +145,24 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp,
return 0;
}
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+ while (count--) {
+ struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+ enetc_free_tx_frame(tx_ring, tx_swbd);
+ if (i == 0)
+ i = tx_ring->bd_count;
+ i--;
+ }
+}
+
static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
{
bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -235,9 +253,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
}
if (do_onestep_tstamp) {
- u32 lo, hi, val;
- u64 sec, nsec;
+ __be32 new_sec_l, new_nsec;
+ u32 lo, hi, nsec, val;
+ __be16 new_sec_h;
u8 *data;
+ u64 sec;
lo = enetc_rd_hot(hw, ENETC_SICTR0);
hi = enetc_rd_hot(hw, ENETC_SICTR1);
@@ -251,13 +271,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
/* Update originTimestamp field of Sync packet
* - 48 bits seconds field
* - 32 bits nanseconds field
+ *
+ * In addition, the UDP checksum needs to be updated
+ * by software after updating originTimestamp field,
+ * otherwise the hardware will calculate the wrong
+ * checksum when updating the correction field and
+ * update it to the packet.
*/
data = skb_mac_header(skb);
- *(__be16 *)(data + offset2) =
- htons((sec >> 32) & 0xffff);
- *(__be32 *)(data + offset2 + 2) =
- htonl(sec & 0xffffffff);
- *(__be32 *)(data + offset2 + 6) = htonl(nsec);
+ new_sec_h = htons((sec >> 32) & 0xffff);
+ new_sec_l = htonl(sec & 0xffffffff);
+ new_nsec = htonl(nsec);
+ if (udp) {
+ struct udphdr *uh = udp_hdr(skb);
+ __be32 old_sec_l, old_nsec;
+ __be16 old_sec_h;
+
+ old_sec_h = *(__be16 *)(data + offset2);
+ inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+ new_sec_h, false);
+
+ old_sec_l = *(__be32 *)(data + offset2 + 2);
+ inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+ new_sec_l, false);
+
+ old_nsec = *(__be32 *)(data + offset2 + 6);
+ inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+ new_nsec, false);
+ }
+
+ *(__be16 *)(data + offset2) = new_sec_h;
+ *(__be32 *)(data + offset2 + 2) = new_sec_l;
+ *(__be32 *)(data + offset2 + 6) = new_nsec;
/* Configure single-step register */
val = ENETC_PM0_SINGLE_STEP_EN;
@@ -328,25 +373,20 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
dma_err:
dev_err(tx_ring->dev, "DMA map error");
- do {
- tx_swbd = &tx_ring->tx_swbd[i];
- enetc_free_tx_frame(tx_ring, tx_swbd);
- if (i == 0)
- i = tx_ring->bd_count;
- i--;
- } while (count--);
+ enetc_unwind_tx_frame(tx_ring, count, i);
return 0;
}
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
- struct enetc_tx_swbd *tx_swbd,
- union enetc_tx_bd *txbd, int *i, int hdr_len,
- int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+ struct enetc_tx_swbd *tx_swbd,
+ union enetc_tx_bd *txbd, int *i, int hdr_len,
+ int data_len)
{
union enetc_tx_bd txbd_tmp;
u8 flags = 0, e_flags = 0;
dma_addr_t addr;
+ int count = 1;
enetc_clear_tx_bd(&txbd_tmp);
addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -389,7 +429,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
/* Write the BD */
txbd_tmp.ext.e_flags = e_flags;
*txbd = txbd_tmp;
+ count++;
}
+
+ return count;
}
static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -521,9 +564,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
/* compute the csum over the L4 header */
csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
- enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+ count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+ &i, hdr_len, data_len);
bd_data_num = 0;
- count++;
while (data_len > 0) {
int size;
@@ -547,8 +590,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
tso.data, size,
size == data_len);
- if (err)
+ if (err) {
+ if (i == 0)
+ i = tx_ring->bd_count;
+ i--;
+
goto err_map_data;
+ }
data_len -= size;
count++;
@@ -577,13 +625,7 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
dev_err(tx_ring->dev, "DMA map error");
err_chained_bd:
- do {
- tx_swbd = &tx_ring->tx_swbd[i];
- enetc_free_tx_frame(tx_ring, tx_swbd);
- if (i == 0)
- i = tx_ring->bd_count;
- i--;
- } while (count--);
+ enetc_unwind_tx_frame(tx_ring, count, i);
return 0;
}
@@ -1626,7 +1668,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
enetc_xdp_drop(rx_ring, orig_i, i);
tx_ring->stats.xdp_tx_drops++;
} else {
- tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+ tx_ring->stats.xdp_tx++;
rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
xdp_tx_frm_cnt++;
/* The XDP_TX enqueue was successful, so we
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 0d1e681be250..d59e28c86775 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -1030,6 +1030,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv)
return gve_xdp_tx_queue_id(priv, 0);
}
+static inline bool gve_supports_xdp_xmit(struct gve_priv *priv)
+{
+ switch (priv->queue_format) {
+ case GVE_GQI_QPL_FORMAT:
+ return true;
+ default:
+ return false;
+ }
+}
+
/* buffers */
int gve_alloc_page(struct gve_priv *priv, struct device *dev,
struct page **page, dma_addr_t *dma,
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 90d433b36799..8cd098fe88ef 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1753,6 +1753,8 @@ static void gve_turndown(struct gve_priv *priv)
/* Stop tx queues */
netif_tx_disable(priv->dev);
+ xdp_features_clear_redirect_target(priv->dev);
+
gve_clear_napi_enabled(priv);
gve_clear_report_stats(priv);
@@ -1793,6 +1795,9 @@ static void gve_turnup(struct gve_priv *priv)
}
}
+ if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv))
+ xdp_features_set_redirect_target(priv->dev, false);
+
gve_set_napi_enabled(priv);
}
@@ -2014,7 +2019,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv)
if (priv->queue_format == GVE_GQI_QPL_FORMAT) {
xdp_features = NETDEV_XDP_ACT_BASIC;
xdp_features |= NETDEV_XDP_ACT_REDIRECT;
- xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
} else {
xdp_features = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index f943964ec05a..e29a7ffd5f14 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -202,6 +202,7 @@ enum ice_feature {
ICE_F_GNSS,
ICE_F_ROCE_LAG,
ICE_F_SRIOV_LAG,
+ ICE_F_MBX_LIMIT,
ICE_F_MAX
};
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 80deca45ab59..983332cbace2 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
#include "ice_common.h"
#include "ice_sched.h"
@@ -153,6 +153,12 @@ static int ice_set_mac_type(struct ice_hw *hw)
case ICE_DEV_ID_E823L_SFP:
hw->mac_type = ICE_MAC_GENERIC;
break;
+ case ICE_DEV_ID_E830_BACKPLANE:
+ case ICE_DEV_ID_E830_QSFP56:
+ case ICE_DEV_ID_E830_SFP:
+ case ICE_DEV_ID_E830_SFP_DD:
+ hw->mac_type = ICE_MAC_E830;
+ break;
default:
hw->mac_type = ICE_MAC_UNKNOWN;
break;
@@ -684,8 +690,7 @@ static void
ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw,
struct ice_aqc_set_mac_cfg *cmd)
{
- u16 fc_thres_val, tx_timer_val;
- u32 val;
+ u32 val, fc_thres_m;
/* We read back the transmit timer and FC threshold value of
* LFC. Thus, we will use index =
@@ -694,19 +699,32 @@ ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw,
* Also, because we are operating on transmit timer and FC
* threshold of LFC, we don't turn on any bit in tx_tmr_priority
*/
-#define IDX_OF_LFC PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX
-
- /* Retrieve the transmit timer */
- val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(IDX_OF_LFC));
- tx_timer_val = val &
- PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M;
- cmd->tx_tmr_value = cpu_to_le16(tx_timer_val);
-
- /* Retrieve the FC threshold */
- val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(IDX_OF_LFC));
- fc_thres_val = val & PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M;
-
- cmd->fc_refresh_threshold = cpu_to_le16(fc_thres_val);
+#define E800_IDX_OF_LFC E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX
+#define E800_REFRESH_TMR E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR
+
+ if (hw->mac_type == ICE_MAC_E830) {
+ /* Retrieve the transmit timer */
+ val = rd32(hw, E830_PRTMAC_CL01_PS_QNT);
+ cmd->tx_tmr_value =
+ le16_encode_bits(val, E830_PRTMAC_CL01_PS_QNT_CL0_M);
+
+ /* Retrieve the fc threshold */
+ val = rd32(hw, E830_PRTMAC_CL01_QNT_THR);
+ fc_thres_m = E830_PRTMAC_CL01_QNT_THR_CL0_M;
+ } else {
+ /* Retrieve the transmit timer */
+ val = rd32(hw,
+ E800_PRTMAC_HSEC_CTL_TX_PS_QNT(E800_IDX_OF_LFC));
+ cmd->tx_tmr_value =
+ le16_encode_bits(val,
+ E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M);
+
+ /* Retrieve the fc threshold */
+ val = rd32(hw,
+ E800_REFRESH_TMR(E800_IDX_OF_LFC));
+ fc_thres_m = E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M;
+ }
+ cmd->fc_refresh_threshold = le16_encode_bits(val, fc_thres_m);
}
/**
@@ -2389,16 +2407,21 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
static void
ice_parse_fdir_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p)
{
- u32 reg_val, val;
+ u32 reg_val, gsize, bsize;
reg_val = rd32(hw, GLQF_FD_SIZE);
- val = (reg_val & GLQF_FD_SIZE_FD_GSIZE_M) >>
- GLQF_FD_SIZE_FD_GSIZE_S;
- func_p->fd_fltr_guar =
- ice_get_num_per_func(hw, val);
- val = (reg_val & GLQF_FD_SIZE_FD_BSIZE_M) >>
- GLQF_FD_SIZE_FD_BSIZE_S;
- func_p->fd_fltr_best_effort = val;
+ switch (hw->mac_type) {
+ case ICE_MAC_E830:
+ gsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_GSIZE_M, reg_val);
+ bsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_BSIZE_M, reg_val);
+ break;
+ case ICE_MAC_E810:
+ default:
+ gsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_GSIZE_M, reg_val);
+ bsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_BSIZE_M, reg_val);
+ }
+ func_p->fd_fltr_guar = ice_get_num_per_func(hw, gsize);
+ func_p->fd_fltr_best_effort = bsize;
ice_debug(hw, ICE_DBG_INIT, "func caps: fd_fltr_guar = %d\n",
func_p->fd_fltr_guar);
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index 6d560d1c74a4..a2d384dbfc76 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
#ifndef _ICE_DEVIDS_H_
#define _ICE_DEVIDS_H_
@@ -16,6 +16,14 @@
#define ICE_DEV_ID_E823L_1GBE 0x124F
/* Intel(R) Ethernet Connection E823-L for QSFP */
#define ICE_DEV_ID_E823L_QSFP 0x151D
+/* Intel(R) Ethernet Controller E830-C for backplane */
+#define ICE_DEV_ID_E830_BACKPLANE 0x12D1
+/* Intel(R) Ethernet Controller E830-C for QSFP */
+#define ICE_DEV_ID_E830_QSFP56 0x12D2
+/* Intel(R) Ethernet Controller E830-C for SFP */
+#define ICE_DEV_ID_E830_SFP 0x12D3
+/* Intel(R) Ethernet Controller E830-C for SFP-DD */
+#define ICE_DEV_ID_E830_SFP_DD 0x12D4
/* Intel(R) Ethernet Controller E810-C for backplane */
#define ICE_DEV_ID_E810C_BACKPLANE 0x1591
/* Intel(R) Ethernet Controller E810-C for QSFP */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index b6bbf2376ef5..d43b642cbc01 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2018-2020, Intel Corporation. */
+/* Copyright (C) 2018-2023, Intel Corporation. */
/* flow director ethtool support for ice */
@@ -540,16 +540,24 @@ int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
/* total guaranteed filters assigned to this VSI */
num_guar = vsi->num_gfltr;
- /* minus the guaranteed filters programed by this VSI */
- num_guar -= (rd32(hw, VSIQF_FD_CNT(vsi_num)) &
- VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S;
-
/* total global best effort filters */
num_be = hw->func_caps.fd_fltr_best_effort;
- /* minus the global best effort filters programmed */
- num_be -= (rd32(hw, GLQF_FD_CNT) & GLQF_FD_CNT_FD_BCNT_M) >>
- GLQF_FD_CNT_FD_BCNT_S;
+ /* Subtract the number of programmed filters from the global values */
+ switch (hw->mac_type) {
+ case ICE_MAC_E830:
+ num_guar -= FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M,
+ rd32(hw, VSIQF_FD_CNT(vsi_num)));
+ num_be -= FIELD_GET(E830_GLQF_FD_CNT_FD_BCNT_M,
+ rd32(hw, GLQF_FD_CNT));
+ break;
+ case ICE_MAC_E810:
+ default:
+ num_guar -= FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M,
+ rd32(hw, VSIQF_FD_CNT(vsi_num)));
+ num_be -= FIELD_GET(E800_GLQF_FD_CNT_FD_BCNT_M,
+ rd32(hw, GLQF_FD_CNT));
+ }
return num_guar + num_be;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 531cc2194741..96f70c0a9659 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
/* Machine-generated file */
@@ -284,11 +284,11 @@
#define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16)
#define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4))
#define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0)
-#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i) (0x001E36E0 + ((_i) * 32))
-#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8
-#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M ICE_M(0xFFFF, 0)
-#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3800 + ((_i) * 32))
-#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M ICE_M(0xFFFF, 0)
+#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT(_i) (0x001E36E0 + ((_i) * 32))
+#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX 8
+#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M GENMASK(15, 0)
+#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR(_i) (0x001E3800 + ((_i) * 32))
+#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M GENMASK(15, 0)
#define GL_MDCK_TX_TDPU 0x00049348
#define GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M BIT(1)
#define GL_MDET_RX 0x00294C00
@@ -311,7 +311,11 @@
#define GL_MDET_TX_PQM_MAL_TYPE_S 26
#define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26)
#define GL_MDET_TX_PQM_VALID_M BIT(31)
-#define GL_MDET_TX_TCLAN 0x000FC068
+#define GL_MDET_TX_TCLAN_BY_MAC(hw) \
+ ((hw)->mac_type == ICE_MAC_E830 ? E830_GL_MDET_TX_TCLAN : \
+ E800_GL_MDET_TX_TCLAN)
+#define E800_GL_MDET_TX_TCLAN 0x000FC068
+#define E830_GL_MDET_TX_TCLAN 0x000FCCC0
#define GL_MDET_TX_TCLAN_QNUM_S 0
#define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0)
#define GL_MDET_TX_TCLAN_VF_NUM_S 15
@@ -325,7 +329,11 @@
#define PF_MDET_RX_VALID_M BIT(0)
#define PF_MDET_TX_PQM 0x002D2C80
#define PF_MDET_TX_PQM_VALID_M BIT(0)
-#define PF_MDET_TX_TCLAN 0x000FC000
+#define PF_MDET_TX_TCLAN_BY_MAC(hw) \
+ ((hw)->mac_type == ICE_MAC_E830 ? E830_PF_MDET_TX_TCLAN : \
+ E800_PF_MDET_TX_TCLAN)
+#define E800_PF_MDET_TX_TCLAN 0x000FC000
+#define E830_PF_MDET_TX_TCLAN 0x000FCC00
#define PF_MDET_TX_TCLAN_VALID_M BIT(0)
#define VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4))
#define VP_MDET_RX_VALID_M BIT(0)
@@ -335,6 +343,8 @@
#define VP_MDET_TX_TCLAN_VALID_M BIT(0)
#define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4))
#define VP_MDET_TX_TDPU_VALID_M BIT(0)
+#define E800_GL_MNG_FWSM_FW_MODES_M GENMASK(2, 0)
+#define E830_GL_MNG_FWSM_FW_MODES_M GENMASK(1, 0)
#define GL_MNG_FWSM 0x000B6134
#define GL_MNG_FWSM_FW_LOADING_M BIT(30)
#define GLNVM_FLA 0x000B6108
@@ -363,13 +373,18 @@
#define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30
#define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30)
#define GLQF_FD_CNT 0x00460018
+#define E800_GLQF_FD_CNT_FD_GCNT_M GENMASK(14, 0)
+#define E830_GLQF_FD_CNT_FD_GCNT_M GENMASK(15, 0)
#define GLQF_FD_CNT_FD_BCNT_S 16
-#define GLQF_FD_CNT_FD_BCNT_M ICE_M(0x7FFF, 16)
+#define E800_GLQF_FD_CNT_FD_BCNT_M GENMASK(30, 16)
+#define E830_GLQF_FD_CNT_FD_BCNT_M GENMASK(31, 16)
#define GLQF_FD_SIZE 0x00460010
#define GLQF_FD_SIZE_FD_GSIZE_S 0
-#define GLQF_FD_SIZE_FD_GSIZE_M ICE_M(0x7FFF, 0)
+#define E800_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(14, 0)
+#define E830_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(15, 0)
#define GLQF_FD_SIZE_FD_BSIZE_S 16
-#define GLQF_FD_SIZE_FD_BSIZE_M ICE_M(0x7FFF, 16)
+#define E800_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(30, 16)
+#define E830_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(31, 16)
#define GLQF_FDINSET(_i, _j) (0x00412000 + ((_i) * 4 + (_j) * 512))
#define GLQF_FDMASK(_i) (0x00410800 + ((_i) * 4))
#define GLQF_FDMASK_MAX_INDEX 31
@@ -388,6 +403,10 @@
#define GLQF_HMASK_SEL(_i) (0x00410000 + ((_i) * 4))
#define GLQF_HMASK_SEL_MAX_INDEX 127
#define GLQF_HMASK_SEL_MASK_SEL_S 0
+#define E800_PFQF_FD_CNT_FD_GCNT_M GENMASK(14, 0)
+#define E830_PFQF_FD_CNT_FD_GCNT_M GENMASK(15, 0)
+#define E800_PFQF_FD_CNT_FD_BCNT_M GENMASK(30, 16)
+#define E830_PFQF_FD_CNT_FD_BCNT_M GENMASK(31, 16)
#define PFQF_FD_ENA 0x0043A000
#define PFQF_FD_ENA_FD_ENA_M BIT(0)
#define PFQF_FD_SIZE 0x00460100
@@ -478,6 +497,7 @@
#define GLTSYN_SYNC_DLAY 0x00088818
#define GLTSYN_TGT_H_0(_i) (0x00088930 + ((_i) * 4))
#define GLTSYN_TGT_L_0(_i) (0x00088928 + ((_i) * 4))
+#define GLTSYN_TIME_0(_i) (0x000888C8 + ((_i) * 4))
#define GLTSYN_TIME_H(_i) (0x000888D8 + ((_i) * 4))
#define GLTSYN_TIME_L(_i) (0x000888D0 + ((_i) * 4))
#define PFHH_SEM 0x000A4200 /* Reset Source: PFR */
@@ -486,9 +506,11 @@
#define PFTSYN_SEM_BUSY_M BIT(0)
#define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4))
#define VSIQF_FD_CNT_FD_GCNT_S 0
-#define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0)
+#define E800_VSIQF_FD_CNT_FD_GCNT_M GENMASK(13, 0)
+#define E830_VSIQF_FD_CNT_FD_GCNT_M GENMASK(15, 0)
#define VSIQF_FD_CNT_FD_BCNT_S 16
-#define VSIQF_FD_CNT_FD_BCNT_M ICE_M(0x3FFF, 16)
+#define E800_VSIQF_FD_CNT_FD_BCNT_M GENMASK(29, 16)
+#define E830_VSIQF_FD_CNT_FD_BCNT_M GENMASK(31, 16)
#define VSIQF_FD_SIZE(_VSI) (0x00462000 + ((_VSI) * 4))
#define VSIQF_HKEY_MAX_INDEX 12
#define PFPM_APM 0x000B8080
@@ -500,7 +522,14 @@
#define PFPM_WUS_MAG_M BIT(1)
#define PFPM_WUS_MNG_M BIT(3)
#define PFPM_WUS_FW_RST_WK_M BIT(31)
+#define E830_PRTMAC_CL01_PS_QNT 0x001E32A0
+#define E830_PRTMAC_CL01_PS_QNT_CL0_M GENMASK(15, 0)
+#define E830_PRTMAC_CL01_QNT_THR 0x001E3320
+#define E830_PRTMAC_CL01_QNT_THR_CL0_M GENMASK(15, 0)
#define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4))
#define VFINT_DYN_CTLN_CLEARPBA_M BIT(1)
+#define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH 0x00234000
+#define E830_MBX_VF_DEC_TRIG(_VF) (0x00233800 + (_VF) * 4)
+#define E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(_VF) (0x00233000 + (_VF) * 4)
#endif /* _ICE_HW_AUTOGEN_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 3a0ef56d3edc..1fc4805353eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -4023,6 +4023,9 @@ void ice_init_feature_support(struct ice_pf *pf)
default:
break;
}
+
+ if (pf->hw.mac_type == ICE_MAC_E830)
+ ice_set_feature_support(pf, ICE_F_MBX_LIMIT);
}
/**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 9f12c9a0fe29..0ae7bdfff83f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
/* Intel(R) Ethernet Connection E800 Series Linux Driver */
@@ -1514,12 +1514,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
ice_vf_lan_overflow_event(pf, &event);
break;
case ice_mbx_opc_send_msg_to_pf:
- data.num_msg_proc = i;
- data.num_pending_arq = pending;
- data.max_num_msgs_mbx = hw->mailboxq.num_rq_entries;
- data.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK;
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) {
+ ice_vc_process_vf_msg(pf, &event, NULL);
+ ice_mbx_vf_dec_trig_e830(hw, &event);
+ } else {
+ u16 val = hw->mailboxq.num_rq_entries;
+
+ data.max_num_msgs_mbx = val;
+ val = ICE_MBX_OVERFLOW_WATERMARK;
+ data.async_watermark_val = val;
+ data.num_msg_proc = i;
+ data.num_pending_arq = pending;
- ice_vc_process_vf_msg(pf, &event, &data);
+ ice_vc_process_vf_msg(pf, &event, &data);
+ }
break;
case ice_aqc_opc_fw_logging:
ice_output_fw_log(hw, &event.desc, event.msg_buf);
@@ -1748,7 +1756,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
}
- reg = rd32(hw, GL_MDET_TX_TCLAN);
+ reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw));
if (reg & GL_MDET_TX_TCLAN_VALID_M) {
u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
GL_MDET_TX_TCLAN_PF_NUM_S;
@@ -1762,7 +1770,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
event, queue, pf_num, vf_num);
- wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
+ wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
}
reg = rd32(hw, GL_MDET_RX);
@@ -1790,9 +1798,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n");
}
- reg = rd32(hw, PF_MDET_TX_TCLAN);
+ reg = rd32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw));
if (reg & PF_MDET_TX_TCLAN_VALID_M) {
- wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF);
+ wr32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw), 0xffff);
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n");
}
@@ -3873,7 +3881,8 @@ static void ice_set_pf_caps(struct ice_pf *pf)
}
clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
- if (func_caps->common_cap.ieee_1588)
+ if (func_caps->common_cap.ieee_1588 &&
+ !(pf->hw.mac_type == ICE_MAC_E830))
set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
pf->max_pf_txqs = func_caps->common_cap.num_txq;
@@ -3919,7 +3928,11 @@ static int ice_init_pf(struct ice_pf *pf)
mutex_init(&pf->vfs.table_lock);
hash_init(pf->vfs.table);
- ice_mbx_init_snapshot(&pf->hw);
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+ wr32(&pf->hw, E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH,
+ ICE_MBX_OVERFLOW_WATERMARK);
+ else
+ ice_mbx_init_snapshot(&pf->hw);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 31314e7540f8..56345fe65370 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
hash_del_rcu(&vf->entry);
+ ice_deinitialize_vf_entry(vf);
ice_put_vf(vf);
}
}
@@ -194,9 +195,6 @@ void ice_free_vfs(struct ice_pf *pf)
wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
}
- /* clear malicious info since the VF is getting released */
- list_del(&vf->mbx_info.list_entry);
-
mutex_unlock(&vf->cfg_lock);
}
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 5e353b0cbe6f..35ee5b29ea34 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
#ifndef _ICE_TYPE_H_
#define _ICE_TYPE_H_
@@ -129,6 +129,7 @@ enum ice_set_fc_aq_failures {
enum ice_mac_type {
ICE_MAC_UNKNOWN = 0,
ICE_MAC_E810,
+ ICE_MAC_E830,
ICE_MAC_GENERIC,
};
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 03b9d7d74851..58f9ac81dfbb 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -701,6 +701,23 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m)
return 0;
}
+/**
+ * ice_reset_vf_mbx_cnt - reset VF mailbox message count
+ * @vf: pointer to the VF structure
+ *
+ * This function clears the VF mailbox message count, and should be called on
+ * VF reset.
+ */
+static void ice_reset_vf_mbx_cnt(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+ ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id);
+ else
+ ice_mbx_clear_malvf(&vf->mbx_info);
+}
+
/**
* ice_reset_all_vfs - reset all allocated VFs in one go
* @pf: pointer to the PF structure
@@ -727,7 +744,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
/* clear all malicious info if the VFs are getting reset */
ice_for_each_vf(pf, bkt, vf)
- ice_mbx_clear_malvf(&vf->mbx_info);
+ ice_reset_vf_mbx_cnt(vf);
/* If VFs have been disabled, there is no need to reset */
if (test_and_set_bit(ICE_VF_DIS, pf->state)) {
@@ -944,7 +961,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
ice_eswitch_update_repr(vsi);
/* if the VF has been reset allow it to come up again */
- ice_mbx_clear_malvf(&vf->mbx_info);
+ ice_reset_vf_mbx_cnt(vf);
out_unlock:
if (lag && lag->bonded && lag->primary &&
@@ -994,11 +1011,22 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
ice_vf_fdir_init(vf);
/* Initialize mailbox info for this VF */
- ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info);
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+ ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id);
+ else
+ ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info);
mutex_init(&vf->cfg_lock);
}
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+
+ if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+ list_del(&vf->mbx_info.list_entry);
+}
+
/**
* ice_dis_vf_qs - Disable the VF queues
* @vf: pointer to the VF structure
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09f..5392b0404986 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
#endif
void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
void ice_dis_vf_qs(struct ice_vf *vf);
int ice_check_vf_init(struct ice_vf *vf);
enum virtchnl_status_code ice_err_to_virt_err(int err);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
index 40cb4ba0789c..75c8113e58ee 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
@@ -210,6 +210,38 @@ ice_mbx_detect_malvf(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info,
return 0;
}
+/**
+ * ice_mbx_vf_dec_trig_e830 - Decrements the VF mailbox queue counter
+ * @hw: pointer to the HW struct
+ * @event: pointer to the control queue receive event
+ *
+ * This function triggers to decrement the counter
+ * MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT when the driver replenishes
+ * the buffers at the PF mailbox queue.
+ */
+void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+ const struct ice_rq_event_info *event)
+{
+ u16 vfid = le16_to_cpu(event->desc.retval);
+
+ wr32(hw, E830_MBX_VF_DEC_TRIG(vfid), 1);
+}
+
+/**
+ * ice_mbx_vf_clear_cnt_e830 - Clear the VF mailbox queue count
+ * @hw: pointer to the HW struct
+ * @vf_id: VF ID in the PF space
+ *
+ * This function clears the counter MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT, and should
+ * be called when a VF is created and on VF reset.
+ */
+void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id)
+{
+ u32 reg = rd32(hw, E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(vf_id));
+
+ wr32(hw, E830_MBX_VF_DEC_TRIG(vf_id), reg);
+}
+
/**
* ice_mbx_vf_state_handler - Handle states of the overflow algorithm
* @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
index 44bc030d17e0..684de89e5c5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
@@ -19,6 +19,9 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
u8 *msg, u16 msglen, struct ice_sq_cd *cd);
u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed);
+void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+ const struct ice_rq_event_info *event);
+void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id);
int
ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data,
struct ice_mbx_vf_info *vf_info, bool *report_malvf);
@@ -47,5 +50,11 @@ static inline void ice_mbx_init_snapshot(struct ice_hw *hw)
{
}
+static inline void
+ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+ const struct ice_rq_event_info *event)
+{
+}
+
#endif /* CONFIG_PCI_IOV */
#endif /* _ICE_VF_MBX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 9f7268bb2ee3..e709b10a2976 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -3899,8 +3899,10 @@ ice_is_malicious_vf(struct ice_vf *vf, struct ice_mbx_data *mbxdata)
* @event: pointer to the AQ event
* @mbxdata: information used to detect VF attempting mailbox overflow
*
- * called from the common asq/arq handler to
- * process request from VF
+ * Called from the common asq/arq handler to process request from VF. When this
+ * flow is used for devices with hardware VF to PF message queue overflow
+ * support (ICE_F_MBX_LIMIT) mbxdata is set to NULL and ice_is_malicious_vf
+ * check is skipped.
*/
void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
struct ice_mbx_data *mbxdata)
@@ -3926,7 +3928,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
mutex_lock(&vf->cfg_lock);
/* Check if the VF is trying to overflow the mailbox */
- if (ice_is_malicious_vf(vf, mbxdata))
+ if (mbxdata && ice_is_malicious_vf(vf, mbxdata))
goto finish;
/* Check if VF is disabled. */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 974c71490d97..3ca5f44dea26 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2021, Intel Corporation. */
+/* Copyright (C) 2021-2023, Intel Corporation. */
#include "ice.h"
#include "ice_base.h"
@@ -1421,8 +1421,8 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi,
*/
static void ice_vf_fdir_dump_info(struct ice_vf *vf)
{
+ u32 fd_size, fd_cnt, fd_size_g, fd_cnt_g, fd_size_b, fd_cnt_b;
struct ice_vsi *vf_vsi;
- u32 fd_size, fd_cnt;
struct device *dev;
struct ice_pf *pf;
struct ice_hw *hw;
@@ -1441,12 +1441,25 @@ static void ice_vf_fdir_dump_info(struct ice_vf *vf)
fd_size = rd32(hw, VSIQF_FD_SIZE(vsi_num));
fd_cnt = rd32(hw, VSIQF_FD_CNT(vsi_num));
- dev_dbg(dev, "VF %d: space allocated: guar:0x%x, be:0x%x, space consumed: guar:0x%x, be:0x%x\n",
- vf->vf_id,
- (fd_size & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S,
- (fd_size & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S,
- (fd_cnt & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S,
- (fd_cnt & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S);
+ switch (hw->mac_type) {
+ case ICE_MAC_E830:
+ fd_size_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_size);
+ fd_size_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_size);
+ fd_cnt_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt);
+ fd_cnt_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt);
+ break;
+ case ICE_MAC_E810:
+ default:
+ fd_size_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_size);
+ fd_size_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_size);
+ fd_cnt_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt);
+ fd_cnt_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt);
+ }
+
+ dev_dbg(dev, "VF %d: Size in the FD table: guaranteed:0x%x, best effort:0x%x\n",
+ vf->vf_id, fd_size_g, fd_size_b);
+ dev_dbg(dev, "VF %d: Filter counter in the FD table: guaranteed:0x%x, best effort:0x%x\n",
+ vf->vf_id, fd_cnt_g, fd_cnt_b);
}
/**
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 40aeaa7bd739..d2757cc11613 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
MVPP2_PRS_RI_VLAN_MASK),
/* Non IP flow, with vlan tag */
MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
- MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP22_CLS_HEK_TAGGED,
0, 0),
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 6bac8ad70ba6..a8d6fd18c0f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -617,7 +617,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
- name, size, start);
+ name ? name : "mlx5_pcif_pool", size, start);
return pool;
}
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index f06cdec14ed7..3f9a030471fe 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -110,7 +110,6 @@ struct icss_iep {
struct ptp_clock_info ptp_info;
struct ptp_clock *ptp_clock;
struct mutex ptp_clk_mutex; /* PHC access serializer */
- spinlock_t irq_lock; /* CMP IRQ vs icss_iep_ptp_enable access */
u32 def_inc;
s16 slow_cmp_inc;
u32 slow_cmp_count;
@@ -192,14 +191,11 @@ static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns)
*/
static void icss_iep_settime(struct icss_iep *iep, u64 ns)
{
- unsigned long flags;
-
if (iep->ops && iep->ops->settime) {
iep->ops->settime(iep->clockops_data, ns);
return;
}
- spin_lock_irqsave(&iep->irq_lock, flags);
if (iep->pps_enabled || iep->perout_enabled)
writel(0, iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]);
@@ -210,7 +206,6 @@ static void icss_iep_settime(struct icss_iep *iep, u64 ns)
writel(IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN,
iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]);
}
- spin_unlock_irqrestore(&iep->irq_lock, flags);
}
/**
@@ -549,36 +544,13 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
static int icss_iep_perout_enable(struct icss_iep *iep,
struct ptp_perout_request *req, int on)
{
- unsigned long flags;
- int ret = 0;
-
- mutex_lock(&iep->ptp_clk_mutex);
-
- if (iep->pps_enabled) {
- ret = -EBUSY;
- goto exit;
- }
-
- if (iep->perout_enabled == !!on)
- goto exit;
-
- spin_lock_irqsave(&iep->irq_lock, flags);
- ret = icss_iep_perout_enable_hw(iep, req, on);
- if (!ret)
- iep->perout_enabled = !!on;
- spin_unlock_irqrestore(&iep->irq_lock, flags);
-
-exit:
- mutex_unlock(&iep->ptp_clk_mutex);
-
- return ret;
+ return -EOPNOTSUPP;
}
static int icss_iep_pps_enable(struct icss_iep *iep, int on)
{
struct ptp_clock_request rq;
struct timespec64 ts;
- unsigned long flags;
int ret = 0;
u64 ns;
@@ -592,8 +564,6 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
if (iep->pps_enabled == !!on)
goto exit;
- spin_lock_irqsave(&iep->irq_lock, flags);
-
rq.perout.index = 0;
if (on) {
ns = icss_iep_gettime(iep, NULL);
@@ -610,8 +580,6 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
if (!ret)
iep->pps_enabled = !!on;
- spin_unlock_irqrestore(&iep->irq_lock, flags);
-
exit:
mutex_unlock(&iep->ptp_clk_mutex);
@@ -861,7 +829,6 @@ static int icss_iep_probe(struct platform_device *pdev)
iep->ptp_info = icss_iep_ptp_info;
mutex_init(&iep->ptp_clk_mutex);
- spin_lock_init(&iep->irq_lock);
dev_set_drvdata(dev, iep);
icss_iep_disable(iep);
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index fef4eff7753a..ca62188a317a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -2,6 +2,9 @@
/* Copyright (c) 2014 Mahesh Bandewar <maheshb@...gle.com>
*/
+#include <net/inet_dscp.h>
+#include <net/ip.h>
+
#include "ipvlan.h"
static u32 ipvlan_jhash_secret __read_mostly;
@@ -413,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
{
- const struct iphdr *ip4h = ip_hdr(skb);
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
- struct rtable *rt;
int err, ret = NET_XMIT_DROP;
+ const struct iphdr *ip4h;
+ struct rtable *rt;
struct flowi4 fl4 = {
.flowi4_oif = dev->ifindex,
- .flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC,
.flowi4_mark = skb->mark,
- .daddr = ip4h->daddr,
- .saddr = ip4h->saddr,
};
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+ goto err;
+
+ ip4h = ip_hdr(skb);
+ fl4.daddr = ip4h->daddr;
+ fl4.saddr = ip4h->saddr;
+ fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h));
+
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto err;
@@ -485,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
struct net_device *dev = skb->dev;
int err, ret = NET_XMIT_DROP;
+ if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) {
+ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+ return ret;
+ }
+
err = ipvlan_route_v6_outbound(dev, skb);
if (unlikely(err)) {
DEV_STATS_INC(dev, tx_errors);
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index f6eab66c2660..6aa00f62b1f9 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -247,8 +247,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+ kfree_skb(skb);
+ return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+ struct neighbour *n)
+{
+ n->output = blackhole_neigh_output;
+ return 0;
+}
+
static const struct net_device_ops blackhole_netdev_ops = {
.ndo_start_xmit = blackhole_netdev_xmit,
+ .ndo_neigh_construct = blackhole_neigh_construct,
};
/* This is a dst-dummy device used specifically for invalidated
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index 46af78caf457..0bfa37c14059 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf)
{
dev->hard_mtu = GL_RCV_BUF_SIZE;
dev->net->hard_header_len += 4;
- dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in);
- dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out);
- return 0;
+ return usbnet_get_endpoints(dev, intf);
}
static const struct driver_info genelink_info = {
diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
index 9c231094ba35..2354ce8b2159 100644
--- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
@@ -309,7 +309,10 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy
priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk");
- priv->phy_rst = devm_reset_control_get(dev, "phy");
+ priv->phy_rst = devm_reset_control_get_exclusive(dev, "phy");
+ /* fallback to old behaviour */
+ if (PTR_ERR(priv->phy_rst) == -ENOENT)
+ priv->phy_rst = devm_reset_control_array_get_exclusive(dev);
if (IS_ERR(priv->phy_rst))
return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n");
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 3f310b28bfff..fea76f2ce6ff 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -319,9 +319,9 @@ exynos5_usbdrd_pipe3_set_refclk(struct phy_usb_instance *inst)
reg |= PHYCLKRST_REFCLKSEL_EXT_REFCLK;
/* FSEL settings corresponding to reference clock */
- reg &= ~PHYCLKRST_FSEL_PIPE_MASK |
- PHYCLKRST_MPLL_MULTIPLIER_MASK |
- PHYCLKRST_SSC_REFCLKSEL_MASK;
+ reg &= ~(PHYCLKRST_FSEL_PIPE_MASK |
+ PHYCLKRST_MPLL_MULTIPLIER_MASK |
+ PHYCLKRST_SSC_REFCLKSEL_MASK);
switch (phy_drd->extrefclk) {
case EXYNOS5_FSEL_50MHZ:
reg |= (PHYCLKRST_MPLL_MULTIPLIER_50M_REF |
@@ -363,9 +363,9 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
reg &= ~PHYCLKRST_REFCLKSEL_MASK;
reg |= PHYCLKRST_REFCLKSEL_EXT_REFCLK;
- reg &= ~PHYCLKRST_FSEL_UTMI_MASK |
- PHYCLKRST_MPLL_MULTIPLIER_MASK |
- PHYCLKRST_SSC_REFCLKSEL_MASK;
+ reg &= ~(PHYCLKRST_FSEL_UTMI_MASK |
+ PHYCLKRST_MPLL_MULTIPLIER_MASK |
+ PHYCLKRST_SSC_REFCLKSEL_MASK);
reg |= PHYCLKRST_FSEL(phy_drd->extrefclk);
return reg;
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 0f60d5d1c167..fae6242aa730 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -928,6 +928,7 @@ static int tegra186_utmi_phy_init(struct phy *phy)
unsigned int index = lane->index;
struct device *dev = padctl->dev;
int err;
+ u32 reg;
port = tegra_xusb_find_usb2_port(padctl, index);
if (!port) {
@@ -935,6 +936,16 @@ static int tegra186_utmi_phy_init(struct phy *phy)
return -ENODEV;
}
+ if (port->mode == USB_DR_MODE_OTG ||
+ port->mode == USB_DR_MODE_PERIPHERAL) {
+ /* reset VBUS&ID OVERRIDE */
+ reg = padctl_readl(padctl, USB2_VBUS_ID);
+ reg &= ~VBUS_OVERRIDE;
+ reg &= ~ID_OVERRIDE(~0);
+ reg |= ID_OVERRIDE_FLOATING;
+ padctl_writel(padctl, reg, USB2_VBUS_ID);
+ }
+
if (port->supply && port->mode == USB_DR_MODE_HOST) {
err = regulator_enable(port->supply);
if (err) {
diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c
index 53d957d4eea4..1c50ecd8a032 100644
--- a/drivers/platform/x86/intel/ifs/load.c
+++ b/drivers/platform/x86/intel/ifs/load.c
@@ -227,7 +227,7 @@ static int scan_chunks_sanity_check(struct device *dev)
static int image_sanity_check(struct device *dev, const struct microcode_header_intel *data)
{
- struct ucode_cpu_info uci;
+ struct cpu_signature sig;
/* Provide a specific error message when loading an older/unsupported image */
if (data->hdrver != MC_HEADER_TYPE_IFS) {
@@ -240,11 +240,9 @@ static int image_sanity_check(struct device *dev, const struct microcode_header_
return -EINVAL;
}
- intel_cpu_collect_info(&uci);
+ intel_collect_cpu_info(&sig);
- if (!intel_find_matching_signature((void *)data,
- uci.cpu_sig.sig,
- uci.cpu_sig.pf)) {
+ if (!intel_find_matching_signature((void *)data, &sig)) {
dev_err(dev, "cpu signature, processor flags not matching\n");
return -EINVAL;
}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index f026377f1cf1..e6dc2c556fde 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1570,13 +1570,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
if (in_flight)
__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
- /*
- * Only clear the driver-private command data if the LLD does not supply
- * a function to initialize that data.
- */
- if (!shost->hostt->init_cmd_priv)
- memset(cmd + 1, 0, shost->hostt->cmd_size);
-
cmd->prot_op = SCSI_PROT_NORMAL;
if (blk_rq_bytes(req))
cmd->sc_data_direction = rq_dma_dir(req);
@@ -1743,6 +1736,13 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
if (!scsi_host_queue_ready(q, shost, sdev, cmd))
goto out_dec_target_busy;
+ /*
+ * Only clear the driver-private command data if the LLD does not supply
+ * a function to initialize that data.
+ */
+ if (shost->hostt->cmd_size && !shost->hostt->init_cmd_priv)
+ memset(cmd + 1, 0, shost->hostt->cmd_size);
+
if (!(req->rq_flags & RQF_DONTPREP)) {
ret = scsi_prepare_cmd(req);
if (ret != BLK_STS_OK)
diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 8fbd46cd8c2b..0043d69077b6 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -194,10 +194,12 @@ static int ufs_bsg_request(struct bsg_job *job)
ufshcd_rpm_put_sync(hba);
kfree(buff);
bsg_reply->result = ret;
- job->reply_len = !rpmb ? sizeof(struct ufs_bsg_reply) : sizeof(struct ufs_rpmb_reply);
/* complete the job here only if no error */
- if (ret == 0)
+ if (ret == 0) {
+ job->reply_len = rpmb ? sizeof(struct ufs_rpmb_reply) :
+ sizeof(struct ufs_bsg_reply);
bsg_job_done(job, ret, bsg_reply->reply_payload_rcv_len);
+ }
return ret;
}
diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
index 524863b157e8..dffc932285ac 100644
--- a/drivers/ufs/core/ufshcd-priv.h
+++ b/drivers/ufs/core/ufshcd-priv.h
@@ -324,6 +324,11 @@ static inline int ufshcd_rpm_get_sync(struct ufs_hba *hba)
return pm_runtime_get_sync(&hba->ufs_device_wlun->sdev_gendev);
}
+static inline int ufshcd_rpm_get_if_active(struct ufs_hba *hba)
+{
+ return pm_runtime_get_if_active(&hba->ufs_device_wlun->sdev_gendev, true);
+}
+
static inline int ufshcd_rpm_put_sync(struct ufs_hba *hba)
{
return pm_runtime_put_sync(&hba->ufs_device_wlun->sdev_gendev);
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0ac0b6aaf9c6..6d53dd7d411a 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -98,6 +98,9 @@
/* Polling time to wait for fDeviceInit */
#define FDEVICEINIT_COMPL_TIMEOUT 1500 /* millisecs */
+/* Default RTC update every 10 seconds */
+#define UFS_RTC_UPDATE_INTERVAL_MS (10 * MSEC_PER_SEC)
+
/* UFSHC 4.0 compliant HC support this mode. */
static bool use_mcq_mode = true;
@@ -234,6 +237,17 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
return UFS_PM_LVL_0;
}
+static bool ufshcd_has_pending_tasks(struct ufs_hba *hba)
+{
+ return hba->outstanding_tasks || hba->active_uic_cmd ||
+ hba->uic_async_done;
+}
+
+static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
+{
+ return scsi_host_busy(hba->host) || ufshcd_has_pending_tasks(hba);
+}
+
static const struct ufs_dev_quirk ufs_fixups[] = {
/* UFS cards deviations table */
{ .wmanufacturerid = UFS_VENDOR_MICRON,
@@ -602,8 +616,8 @@ static void ufshcd_print_host_state(struct ufs_hba *hba)
const struct scsi_device *sdev_ufs = hba->ufs_device_wlun;
dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
- dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
- hba->outstanding_reqs, hba->outstanding_tasks);
+ dev_err(hba->dev, "%d outstanding reqs, tasks=0x%lx\n",
+ scsi_host_busy(hba->host), hba->outstanding_tasks);
dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
hba->saved_err, hba->saved_uic_err);
dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -676,6 +690,8 @@ static void ufshcd_device_reset(struct ufs_hba *hba)
hba->dev_info.wb_enabled = false;
hba->dev_info.wb_buf_flush_enabled = false;
}
+ if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+ hba->dev_info.rtc_time_baseline = 0;
}
if (err != -EOPNOTSUPP)
ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
@@ -1816,10 +1832,9 @@ static void ufshcd_gate_work(struct work_struct *work)
goto rel_lock;
}
- if (hba->clk_gating.active_reqs
- || hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
- || hba->outstanding_reqs || hba->outstanding_tasks
- || hba->active_uic_cmd || hba->uic_async_done)
+ if (ufshcd_is_ufs_dev_busy(hba) ||
+ hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
+ hba->clk_gating.active_reqs)
goto rel_lock;
spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -1875,8 +1890,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
- hba->outstanding_tasks || !hba->clk_gating.is_initialized ||
- hba->active_uic_cmd || hba->uic_async_done ||
+ ufshcd_has_pending_tasks(hba) || !hba->clk_gating.is_initialized ||
hba->clk_gating.state == CLKS_OFF)
return;
@@ -8146,6 +8160,77 @@ static void ufs_fixup_device_setup(struct ufs_hba *hba)
ufshcd_vops_fixup_dev_quirks(hba);
}
+static void ufshcd_update_rtc(struct ufs_hba *hba)
+{
+ struct timespec64 ts64;
+ int err;
+ u32 val;
+
+ ktime_get_real_ts64(&ts64);
+
+ if (ts64.tv_sec < hba->dev_info.rtc_time_baseline) {
+ dev_warn_once(hba->dev, "%s: Current time precedes previous setting!\n", __func__);
+ return;
+ }
+
+ /*
+ * The Absolute RTC mode has a 136-year limit, spanning from 2010 to 2146. If a time beyond
+ * 2146 is required, it is recommended to choose the relative RTC mode.
+ */
+ val = ts64.tv_sec - hba->dev_info.rtc_time_baseline;
+
+ /* Skip update RTC if RPM state is not RPM_ACTIVE */
+ if (ufshcd_rpm_get_if_active(hba) <= 0)
+ return;
+
+ err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
+ 0, 0, &val);
+ ufshcd_rpm_put(hba);
+
+ if (err)
+ dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err);
+ else if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+ hba->dev_info.rtc_time_baseline = ts64.tv_sec;
+}
+
+static void ufshcd_rtc_work(struct work_struct *work)
+{
+ struct ufs_hba *hba;
+
+ hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work);
+
+ /* Update RTC only when there are no requests in progress and UFSHCI is operational */
+ if (!ufshcd_is_ufs_dev_busy(hba) &&
+ hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL &&
+ !hba->clk_gating.active_reqs)
+ ufshcd_update_rtc(hba);
+
+ if (ufshcd_is_ufs_dev_active(hba))
+ schedule_delayed_work(&hba->ufs_rtc_update_work,
+ msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
+}
+
+static void ufs_init_rtc(struct ufs_hba *hba, u8 *desc_buf)
+{
+ u16 periodic_rtc_update = get_unaligned_be16(&desc_buf[DEVICE_DESC_PARAM_FRQ_RTC]);
+ struct ufs_dev_info *dev_info = &hba->dev_info;
+
+ if (periodic_rtc_update & UFS_RTC_TIME_BASELINE) {
+ dev_info->rtc_type = UFS_RTC_ABSOLUTE;
+
+ /*
+ * The concept of measuring time in Linux as the number of seconds elapsed since
+ * 00:00:00 UTC on January 1, 1970, and UFS ABS RTC is elapsed from January 1st
+ * 2010 00:00, here we need to adjust ABS baseline.
+ */
+ dev_info->rtc_time_baseline = mktime64(2010, 1, 1, 0, 0, 0) -
+ mktime64(1970, 1, 1, 0, 0, 0);
+ } else {
+ dev_info->rtc_type = UFS_RTC_RELATIVE;
+ dev_info->rtc_time_baseline = 0;
+ }
+}
+
static int ufs_get_device_desc(struct ufs_hba *hba)
{
int err;
@@ -8198,6 +8283,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
ufshcd_temp_notif_probe(hba, desc_buf);
+ ufs_init_rtc(hba, desc_buf);
+
if (hba->ext_iid_sup)
ufshcd_ext_iid_probe(hba, desc_buf);
@@ -8591,6 +8678,14 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
ufshcd_init_clk_scaling_sysfs(hba);
}
+ /*
+ * The RTC update code accesses the hba->ufs_device_wlun->sdev_gendev
+ * pointer and hence must only be started after the WLUN pointer has
+ * been initialized by ufshcd_scsi_add_wlus().
+ */
+ schedule_delayed_work(&hba->ufs_rtc_update_work,
+ msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
+
ufs_bsg_probe(hba);
scsi_scan_host(hba->host);
@@ -8887,7 +8982,7 @@ static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
dev_info(hba->dev, "%s() finished; outstanding_tasks = %#lx.\n",
__func__, hba->outstanding_tasks);
- return hba->outstanding_reqs ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
+ return scsi_host_busy(hba->host) ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
}
static const struct attribute_group *ufshcd_driver_groups[] = {
@@ -9695,6 +9790,8 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
ret = ufshcd_vops_suspend(hba, pm_op, POST_CHANGE);
if (ret)
goto set_link_active;
+
+ cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
goto out;
set_link_active:
@@ -9789,6 +9886,8 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
if (ret)
goto set_old_link_state;
ufshcd_set_timestamp_attr(hba);
+ schedule_delayed_work(&hba->ufs_rtc_update_work,
+ msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
}
if (ufshcd_keep_autobkops_enabled_except_suspend(hba))
@@ -10160,6 +10259,7 @@ void ufshcd_remove(struct ufs_hba *hba)
ufs_hwmon_remove(hba);
ufs_bsg_remove(hba);
ufs_sysfs_remove_nodes(hba->dev);
+ cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
blk_mq_destroy_queue(hba->tmf_queue);
blk_put_queue(hba->tmf_queue);
blk_mq_free_tag_set(&hba->tmf_tag_set);
@@ -10497,8 +10597,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
UFS_SLEEP_PWR_MODE,
UIC_LINK_HIBERN8_STATE);
- INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work,
- ufshcd_rpm_dev_flush_recheck_work);
+ INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
+ INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
/* Set the default auto-hiberate idle timer value to 150 ms */
if (ufshcd_is_auto_hibern8_supported(hba) && !hba->ahit) {
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 926cb1188eba..7c0dce8eecad 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -161,6 +161,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
refcount_set(&cell->ref, 1);
atomic_set(&cell->active, 0);
INIT_WORK(&cell->manager, afs_manage_cell_work);
+ spin_lock_init(&cell->vs_lock);
cell->volumes = RB_ROOT;
INIT_HLIST_HEAD(&cell->proc_volumes);
seqlock_init(&cell->volume_lock);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 2f135d19545b..0973cd0a3969 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -379,6 +379,7 @@ struct afs_cell {
unsigned int debug_id;
/* The volumes belonging to this cell */
+ spinlock_t vs_lock; /* Lock for server->volumes */
struct rb_root volumes; /* Tree of volumes on this server */
struct hlist_head proc_volumes; /* procfs volume list */
seqlock_t volume_lock; /* For volumes */
@@ -502,6 +503,7 @@ struct afs_server {
struct hlist_node addr4_link; /* Link in net->fs_addresses4 */
struct hlist_node addr6_link; /* Link in net->fs_addresses6 */
struct hlist_node proc_link; /* Link in net->fs_proc */
+ struct list_head volumes; /* RCU list of afs_server_entry objects */
struct work_struct initcb_work; /* Work for CB.InitCallBackState* */
struct afs_server *gc_next; /* Next server in manager's list */
time64_t unuse_time; /* Time at which last unused */
@@ -550,12 +552,14 @@ struct afs_server {
*/
struct afs_server_entry {
struct afs_server *server;
+ struct afs_volume *volume;
+ struct list_head slink; /* Link in server->volumes */
};
struct afs_server_list {
struct rcu_head rcu;
- afs_volid_t vids[AFS_MAXTYPES]; /* Volume IDs */
refcount_t usage;
+ bool attached; /* T if attached to servers */
unsigned char nr_servers;
unsigned char preferred; /* Preferred server */
unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */
@@ -568,10 +572,9 @@ struct afs_server_list {
* Live AFS volume management.
*/
struct afs_volume {
- union {
- struct rcu_head rcu;
- afs_volid_t vid; /* volume ID */
- };
+ struct rcu_head rcu;
+ afs_volid_t vid; /* The volume ID of this volume */
+ afs_volid_t vids[AFS_MAXTYPES]; /* All associated volume IDs */
refcount_t ref;
time64_t update_at; /* Time at which to next update */
struct afs_cell *cell; /* Cell to which belongs (pins ref) */
@@ -1453,10 +1456,14 @@ static inline struct afs_server_list *afs_get_serverlist(struct afs_server_list
}
extern void afs_put_serverlist(struct afs_net *, struct afs_server_list *);
-extern struct afs_server_list *afs_alloc_server_list(struct afs_cell *, struct key *,
- struct afs_vldb_entry *,
- u8);
+struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
+ struct key *key,
+ struct afs_vldb_entry *vldb);
extern bool afs_annotate_server_list(struct afs_server_list *, struct afs_server_list *);
+void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist);
+void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist,
+ struct afs_server_list *old);
+void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist);
/*
* super.c
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 0bd2f5ba6900..87381c2ffe37 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -236,6 +236,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
server->addr_version = alist->version;
server->uuid = *uuid;
rwlock_init(&server->fs_lock);
+ INIT_LIST_HEAD(&server->volumes);
INIT_WORK(&server->initcb_work, afs_server_init_callback_work);
init_waitqueue_head(&server->probe_wq);
INIT_LIST_HEAD(&server->probe_link);
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index b59896b1de0a..89c75d934f79 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -24,13 +24,13 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist)
/*
* Build a server list from a VLDB record.
*/
-struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
+struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
struct key *key,
- struct afs_vldb_entry *vldb,
- u8 type_mask)
+ struct afs_vldb_entry *vldb)
{
struct afs_server_list *slist;
struct afs_server *server;
+ unsigned int type_mask = 1 << volume->type;
int ret = -ENOMEM, nr_servers = 0, i, j;
for (i = 0; i < vldb->nr_servers; i++)
@@ -44,15 +44,12 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
refcount_set(&slist->usage, 1);
rwlock_init(&slist->lock);
- for (i = 0; i < AFS_MAXTYPES; i++)
- slist->vids[i] = vldb->vid[i];
-
/* Make sure a records exists for each server in the list. */
for (i = 0; i < vldb->nr_servers; i++) {
if (!(vldb->fs_mask[i] & type_mask))
continue;
- server = afs_lookup_server(cell, key, &vldb->fs_server[i],
+ server = afs_lookup_server(volume->cell, key, &vldb->fs_server[i],
vldb->addr_version[i]);
if (IS_ERR(server)) {
ret = PTR_ERR(server);
@@ -70,8 +67,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
break;
if (j < slist->nr_servers) {
if (slist->servers[j].server == server) {
- afs_put_server(cell->net, server,
- afs_server_trace_put_slist_isort);
+ afs_unuse_server(volume->cell->net, server,
+ afs_server_trace_put_slist_isort);
continue;
}
@@ -81,6 +78,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
}
slist->servers[j].server = server;
+ slist->servers[j].volume = volume;
slist->nr_servers++;
}
@@ -92,7 +90,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
return slist;
error_2:
- afs_put_serverlist(cell->net, slist);
+ afs_put_serverlist(volume->cell->net, slist);
error:
return ERR_PTR(ret);
}
@@ -127,3 +125,99 @@ bool afs_annotate_server_list(struct afs_server_list *new,
return true;
}
+
+/*
+ * Attach a volume to the servers it is going to use.
+ */
+void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist)
+{
+ struct afs_server_entry *se, *pe;
+ struct afs_server *server;
+ struct list_head *p;
+ unsigned int i;
+
+ spin_lock(&volume->cell->vs_lock);
+
+ for (i = 0; i < slist->nr_servers; i++) {
+ se = &slist->servers[i];
+ server = se->server;
+
+ list_for_each(p, &server->volumes) {
+ pe = list_entry(p, struct afs_server_entry, slink);
+ if (volume->vid <= pe->volume->vid)
+ break;
+ }
+ list_add_tail_rcu(&se->slink, p);
+ }
+
+ slist->attached = true;
+ spin_unlock(&volume->cell->vs_lock);
+}
+
+/*
+ * Reattach a volume to the servers it is going to use when server list is
+ * replaced. We try to switch the attachment points to avoid rewalking the
+ * lists.
+ */
+void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *new,
+ struct afs_server_list *old)
+{
+ unsigned int n = 0, o = 0;
+
+ spin_lock(&volume->cell->vs_lock);
+
+ while (n < new->nr_servers || o < old->nr_servers) {
+ struct afs_server_entry *pn = n < new->nr_servers ? &new->servers[n] : NULL;
+ struct afs_server_entry *po = o < old->nr_servers ? &old->servers[o] : NULL;
+ struct afs_server_entry *s;
+ struct list_head *p;
+ int diff;
+
+ if (pn && po && pn->server == po->server) {
+ list_replace_rcu(&po->slink, &pn->slink);
+ n++;
+ o++;
+ continue;
+ }
+
+ if (pn && po)
+ diff = memcmp(&pn->server->uuid, &po->server->uuid,
+ sizeof(pn->server->uuid));
+ else
+ diff = pn ? -1 : 1;
+
+ if (diff < 0) {
+ list_for_each(p, &pn->server->volumes) {
+ s = list_entry(p, struct afs_server_entry, slink);
+ if (volume->vid <= s->volume->vid)
+ break;
+ }
+ list_add_tail_rcu(&pn->slink, p);
+ n++;
+ } else {
+ list_del_rcu(&po->slink);
+ o++;
+ }
+ }
+
+ spin_unlock(&volume->cell->vs_lock);
+}
+
+/*
+ * Detach a volume from the servers it has been using.
+ */
+void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist)
+{
+ unsigned int i;
+
+ if (!slist->attached)
+ return;
+
+ spin_lock(&volume->cell->vs_lock);
+
+ for (i = 0; i < slist->nr_servers; i++)
+ list_del_rcu(&slist->servers[i].slink);
+
+ slist->attached = false;
+ spin_unlock(&volume->cell->vs_lock);
+}
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index 83cf1bfbe343..b2cc10df9530 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -126,7 +126,7 @@ static int afs_compare_volume_slists(const struct afs_volume *vol_a,
lb = rcu_dereference(vol_b->servers);
for (i = 0; i < AFS_MAXTYPES; i++)
- if (la->vids[i] != lb->vids[i])
+ if (vol_a->vids[i] != vol_b->vids[i])
return 0;
while (a < la->nr_servers && b < lb->nr_servers) {
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index c028598a903c..0f64b9758127 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -72,11 +72,11 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume)
*/
static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
struct afs_vldb_entry *vldb,
- unsigned long type_mask)
+ struct afs_server_list **_slist)
{
struct afs_server_list *slist;
struct afs_volume *volume;
- int ret = -ENOMEM;
+ int ret = -ENOMEM, i;
volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL);
if (!volume)
@@ -95,13 +95,16 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
rwlock_init(&volume->cb_v_break_lock);
memcpy(volume->name, vldb->name, vldb->name_len + 1);
- slist = afs_alloc_server_list(params->cell, params->key, vldb, type_mask);
+ for (i = 0; i < AFS_MAXTYPES; i++)
+ volume->vids[i] = vldb->vid[i];
+
+ slist = afs_alloc_server_list(volume, params->key, vldb);
if (IS_ERR(slist)) {
ret = PTR_ERR(slist);
goto error_1;
}
- refcount_set(&slist->usage, 1);
+ *_slist = slist;
rcu_assign_pointer(volume->servers, slist);
trace_afs_volume(volume->vid, 1, afs_volume_trace_alloc);
return volume;
@@ -117,17 +120,19 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
* Look up or allocate a volume record.
*/
static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params,
- struct afs_vldb_entry *vldb,
- unsigned long type_mask)
+ struct afs_vldb_entry *vldb)
{
+ struct afs_server_list *slist;
struct afs_volume *candidate, *volume;
- candidate = afs_alloc_volume(params, vldb, type_mask);
+ candidate = afs_alloc_volume(params, vldb, &slist);
if (IS_ERR(candidate))
return candidate;
volume = afs_insert_volume_into_cell(params->cell, candidate);
- if (volume != candidate)
+ if (volume == candidate)
+ afs_attach_volume_to_servers(volume, slist);
+ else
afs_put_volume(params->net, candidate, afs_volume_trace_put_cell_dup);
return volume;
}
@@ -208,8 +213,7 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params)
goto error;
}
- type_mask = 1UL << params->type;
- volume = afs_lookup_volume(params, vldb, type_mask);
+ volume = afs_lookup_volume(params, vldb);
error:
kfree(vldb);
@@ -221,14 +225,17 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params)
*/
static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
{
+ struct afs_server_list *slist = rcu_access_pointer(volume->servers);
+
_enter("%p", volume);
#ifdef CONFIG_AFS_FSCACHE
ASSERTCMP(volume->cache, ==, NULL);
#endif
+ afs_detach_volume_from_servers(volume, slist);
afs_remove_volume_from_cell(volume);
- afs_put_serverlist(net, rcu_access_pointer(volume->servers));
+ afs_put_serverlist(net, slist);
afs_put_cell(volume->cell, afs_cell_trace_put_vol);
trace_afs_volume(volume->vid, refcount_read(&volume->ref),
afs_volume_trace_free);
@@ -362,8 +369,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
}
/* See if the volume's server list got updated. */
- new = afs_alloc_server_list(volume->cell, key,
- vldb, (1 << volume->type));
+ new = afs_alloc_server_list(volume, key, vldb);
if (IS_ERR(new)) {
ret = PTR_ERR(new);
goto error_vldb;
@@ -384,9 +390,11 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
volume->update_at = ktime_get_real_seconds() + afs_volume_record_life;
write_unlock(&volume->servers_lock);
- ret = 0;
+ if (discard == old)
+ afs_reattach_volume_to_servers(volume, new, old);
afs_put_serverlist(volume->cell->net, discard);
+ ret = 0;
error_vldb:
kfree(vldb);
error:
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 18e018cb1811..dbf7b3cd70ca 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -570,7 +570,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
err = PTR_ERR(upper);
if (!IS_ERR(upper)) {
err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper);
- dput(upper);
if (!err) {
/* Restore timestamps on parent (best effort) */
@@ -578,6 +577,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
ovl_dentry_set_upper_alias(c->dentry);
ovl_dentry_update_reval(c->dentry, upper);
}
+ dput(upper);
}
inode_unlock(udir);
if (err)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7e11ca6f86dc..cf3f8b9bf43f 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -445,7 +445,7 @@
. = ALIGN((align)); \
.rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \
__start_rodata = .; \
- *(.rodata) *(.rodata.*) \
+ *(.rodata) *(.rodata.*) *(.data.rel.ro*) \
SCHED_DATA \
RO_AFTER_INIT_DATA /* Read only after init */ \
. = ALIGN(8); \
diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h
index 2c8bfd0f1b6b..6322d8c1c6b4 100644
--- a/include/linux/rcuref.h
+++ b/include/linux/rcuref.h
@@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref)
return rcuref_get_slowpath(ref);
}
-extern __must_check bool rcuref_put_slowpath(rcuref_t *ref);
+extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt);
/*
* Internal helper. Do not invoke directly.
*/
static __always_inline __must_check bool __rcuref_put(rcuref_t *ref)
{
+ int cnt;
+
RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(),
"suspicious rcuref_put_rcusafe() usage");
/*
* Unconditionally decrease the reference count. The saturation and
* dead zones provide enough tolerance for this.
*/
- if (likely(!atomic_add_negative_release(-1, &ref->refcnt)))
+ cnt = atomic_sub_return_release(1, &ref->refcnt);
+ if (likely(cnt >= 0))
return false;
/*
* Handle the last reference drop and cases inside the saturation
* and dead zones.
*/
- return rcuref_put_slowpath(ref);
+ return rcuref_put_slowpath(ref, cnt);
}
/**
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 8f9bee0e21c3..a220b28904ca 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -140,13 +140,14 @@ struct rpc_task_setup {
#define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT)
#define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE)
-#define RPC_TASK_RUNNING 0
-#define RPC_TASK_QUEUED 1
-#define RPC_TASK_ACTIVE 2
-#define RPC_TASK_NEED_XMIT 3
-#define RPC_TASK_NEED_RECV 4
-#define RPC_TASK_MSG_PIN_WAIT 5
-#define RPC_TASK_SIGNALLED 6
+enum {
+ RPC_TASK_RUNNING,
+ RPC_TASK_QUEUED,
+ RPC_TASK_ACTIVE,
+ RPC_TASK_NEED_XMIT,
+ RPC_TASK_NEED_RECV,
+ RPC_TASK_MSG_PIN_WAIT,
+};
#define rpc_test_and_set_running(t) \
test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
@@ -158,7 +159,7 @@ struct rpc_task_setup {
#define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
-#define RPC_SIGNALLED(t) test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+#define RPC_SIGNALLED(t) (READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS)
/*
* Task priorities.
diff --git a/include/net/dst.h b/include/net/dst.h
index 78884429deed..16b7b99b5f30 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -448,6 +448,15 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout)
dst->expires = expires;
}
+static inline unsigned int dst_dev_overhead(struct dst_entry *dst,
+ struct sk_buff *skb)
+{
+ if (likely(dst))
+ return LL_RESERVED_SPACE(dst->dev);
+
+ return skb->mac_len;
+}
+
INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *,
struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *,
diff --git a/include/net/ip.h b/include/net/ip.h
index 7db5912e0c5f..d8bf1f0a6919 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -415,6 +415,11 @@ int ip_decrease_ttl(struct iphdr *iph)
return --iph->ttl;
}
+static inline dscp_t ip4h_dscp(const struct iphdr *ip4h)
+{
+ return inet_dsfield_to_dscp(ip4h->tos);
+}
+
static inline int ip_mtu_locked(const struct dst_entry *dst)
{
const struct rtable *rt = (const struct rtable *)dst;
diff --git a/include/net/route.h b/include/net/route.h
index 0171e9e1bbea..27c17aff0bbe 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -200,12 +200,13 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
const struct sk_buff *hint);
static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin)
+ dscp_t dscp, struct net_device *devin)
{
int err;
rcu_read_lock();
- err = ip_route_input_noref(skb, dst, src, tos, devin);
+ err = ip_route_input_noref(skb, dst, src, inet_dscp_to_dsfield(dscp),
+ devin);
if (!err) {
skb_dst_force(skb);
if (!skb_dst(skb))
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 62f9d126a71a..bc459d061629 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -561,6 +561,7 @@ enum ib_port_speed {
IB_SPEED_EDR = 32,
IB_SPEED_HDR = 64,
IB_SPEED_NDR = 128,
+ IB_SPEED_XDR = 256,
};
enum ib_stat_flag {
@@ -840,6 +841,7 @@ enum ib_rate {
IB_RATE_50_GBPS = 20,
IB_RATE_400_GBPS = 21,
IB_RATE_600_GBPS = 22,
+ IB_RATE_800_GBPS = 23,
};
/**
diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h
new file mode 100644
index 000000000000..31559796949a
--- /dev/null
+++ b/include/trace/events/icmp.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM icmp
+
+#if !defined(_TRACE_ICMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ICMP_H
+
+#include <linux/icmp.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(icmp_send,
+
+ TP_PROTO(const struct sk_buff *skb, int type, int code),
+
+ TP_ARGS(skb, type, code),
+
+ TP_STRUCT__entry(
+ __field(const void *, skbaddr)
+ __field(int, type)
+ __field(int, code)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __field(unsigned short, ulen)
+ ),
+
+ TP_fast_assign(
+ struct iphdr *iph = ip_hdr(skb);
+ struct udphdr *uh = udp_hdr(skb);
+ int proto_4 = iph->protocol;
+ __be32 *p32;
+
+ __entry->skbaddr = skb;
+ __entry->type = type;
+ __entry->code = code;
+
+ if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head ||
+ (u8 *)uh + sizeof(struct udphdr)
+ > skb_tail_pointer(skb)) {
+ __entry->sport = 0;
+ __entry->dport = 0;
+ __entry->ulen = 0;
+ } else {
+ __entry->sport = ntohs(uh->source);
+ __entry->dport = ntohs(uh->dest);
+ __entry->ulen = ntohs(uh->len);
+ }
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = iph->saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = iph->daddr;
+ ),
+
+ TP_printk("icmp_send: type=%d, code=%d. From %pI4:%u to %pI4:%u ulen=%d skbaddr=%p",
+ __entry->type, __entry->code,
+ __entry->saddr, __entry->sport, __entry->daddr,
+ __entry->dport, __entry->ulen, __entry->skbaddr)
+);
+
+#endif /* _TRACE_ICMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 6beb38c1dcb5..9eba2ca0a6ff 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -360,8 +360,7 @@ TRACE_EVENT(rpc_request,
{ (1UL << RPC_TASK_ACTIVE), "ACTIVE" }, \
{ (1UL << RPC_TASK_NEED_XMIT), "NEED_XMIT" }, \
{ (1UL << RPC_TASK_NEED_RECV), "NEED_RECV" }, \
- { (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" }, \
- { (1UL << RPC_TASK_SIGNALLED), "SIGNALLED" })
+ { (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" })
DECLARE_EVENT_CLASS(rpc_task_running,
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index d7c5aaa32744..fe15bc7e9f70 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -220,7 +220,8 @@ enum ib_uverbs_advise_mr_flag {
struct ib_uverbs_query_port_resp_ex {
struct ib_uverbs_query_port_resp legacy_resp;
__u16 port_cap_flags2;
- __u8 reserved[6];
+ __u8 reserved[2];
+ __u32 active_speed_ex;
};
struct ib_uverbs_qp_cap {
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index 49c90795a2a6..571a08ce9124 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -14,6 +14,7 @@
#include <linux/bitops.h>
#include <linux/types.h>
#include <uapi/scsi/scsi_bsg_ufs.h>
+#include <linux/time64.h>
/*
* Using static_assert() is not allowed in UAPI header files. Hence the check
@@ -550,6 +551,14 @@ struct ufs_vreg_info {
struct ufs_vreg *vdd_hba;
};
+/* UFS device descriptor wPeriodicRTCUpdate bit9 defines RTC time baseline */
+#define UFS_RTC_TIME_BASELINE BIT(9)
+
+enum ufs_rtc_time {
+ UFS_RTC_RELATIVE,
+ UFS_RTC_ABSOLUTE
+};
+
struct ufs_dev_info {
bool f_power_on_wp_en;
/* Keeps information if any of the LU is power on write protected */
@@ -577,6 +586,10 @@ struct ufs_dev_info {
/* UFS EXT_IID Enable */
bool b_ext_iid_en;
+
+ /* UFS RTC */
+ enum ufs_rtc_time rtc_type;
+ time64_t rtc_time_baseline;
};
/*
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 20d129914121..d5aa832f8dba 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -908,6 +908,8 @@ enum ufshcd_mcq_opr {
* @mcq_base: Multi circular queue registers base address
* @uhq: array of supported hardware queues
* @dev_cmd_queue: Queue for issuing device management commands
+ * @mcq_opr: MCQ operation and runtime registers
+ * @ufs_rtc_update_work: A work for UFS RTC periodic update
*/
struct ufs_hba {
void __iomem *mmio_base;
@@ -1068,6 +1070,8 @@ struct ufs_hba {
struct ufs_hw_queue *uhq;
struct ufs_hw_queue *dev_cmd_queue;
struct ufshcd_mcq_opr_info_t mcq_opr[OPR_MAX];
+
+ struct delayed_work ufs_rtc_update_work;
};
/**
diff --git a/io_uring/net.c b/io_uring/net.c
index 56091292950f..1a0e98e19dc0 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -303,7 +303,9 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
if (unlikely(ret))
return ret;
- return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+ ret = __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+ sr->msg_control = iomsg->msg.msg_control_user;
+ return ret;
}
#endif
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5d6458ea675e..4f6b18ecfdb2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4842,7 +4842,7 @@ static struct perf_event_pmu_context *
find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
struct perf_event *event)
{
- struct perf_event_pmu_context *new = NULL, *epc;
+ struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc;
void *task_ctx_data = NULL;
if (!ctx->task) {
@@ -4899,12 +4899,19 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
atomic_inc(&epc->refcount);
goto found_epc;
}
+ /* Make sure the pmu_ctx_list is sorted by PMU type: */
+ if (!pos && epc->pmu->type > pmu->type)
+ pos = epc;
}
epc = new;
new = NULL;
- list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+ if (!pos)
+ list_add_tail(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+ else
+ list_add(&epc->pmu_ctx_entry, pos->pmu_ctx_entry.prev);
+
epc->ctx = ctx;
found_epc:
@@ -5854,14 +5861,15 @@ static int _perf_event_period(struct perf_event *event, u64 value)
if (!value)
return -EINVAL;
- if (event->attr.freq && value > sysctl_perf_event_sample_rate)
- return -EINVAL;
-
- if (perf_event_check_period(event, value))
- return -EINVAL;
-
- if (!event->attr.freq && (value & (1ULL << 63)))
- return -EINVAL;
+ if (event->attr.freq) {
+ if (value > sysctl_perf_event_sample_rate)
+ return -EINVAL;
+ } else {
+ if (perf_event_check_period(event, value))
+ return -EINVAL;
+ if (value & (1ULL << 63))
+ return -EINVAL;
+ }
event_function_call(event, __perf_event_period, &value);
@@ -8106,7 +8114,8 @@ void perf_event_exec(void)
perf_event_enable_on_exec(ctx);
perf_event_remove_on_exec(ctx);
- perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
+ scoped_guard(rcu)
+ perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
perf_unpin_context(ctx);
put_ctx(ctx);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 6dac0b579821..7e2edd1b0693 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -481,6 +481,11 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
if (ret <= 0)
goto put_old;
+ if (is_zero_page(old_page)) {
+ ret = -EINVAL;
+ goto put_old;
+ }
+
if (WARN(!is_register && PageCompound(old_page),
"uprobe unregister should never work on compound page\n")) {
ret = -EINVAL;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c686d826a91c..784a4f840945 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8561,7 +8561,7 @@ SYSCALL_DEFINE0(sched_yield)
#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
int __sched __cond_resched(void)
{
- if (should_resched(0)) {
+ if (should_resched(0) && !irqs_disabled()) {
preempt_schedule_common();
return 1;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6e6b2a5aa140..99fdeee3bcd8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -538,6 +538,7 @@ static int function_stat_show(struct seq_file *m, void *v)
static struct trace_seq s;
unsigned long long avg;
unsigned long long stddev;
+ unsigned long long stddev_denom;
#endif
mutex_lock(&ftrace_profile_lock);
@@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_puts(m, " ");
- /* Sample standard deviation (s^2) */
- if (rec->counter <= 1)
- stddev = 0;
- else {
- /*
- * Apply Welford's method:
- * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
- */
+ /*
+ * Variance formula:
+ * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+ * Maybe Welford's method is better here?
+ * Divide only by 1000 for ns^2 -> us^2 conversion.
+ * trace_print_graph_duration will divide by 1000 again.
+ */
+ stddev = 0;
+ stddev_denom = rec->counter * (rec->counter - 1) * 1000;
+ if (stddev_denom) {
stddev = rec->counter * rec->time_squared -
rec->time * rec->time;
-
- /*
- * Divide only 1000 for ns^2 -> us^2 conversion.
- * trace_print_graph_duration will divide 1000 again.
- */
- stddev = div64_ul(stddev,
- rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev, stddev_denom);
}
trace_seq_init(&s);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index dd16faf0d150..604d63380a90 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6660,27 +6660,27 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
if (existing_hist_update_only(glob, trigger_data, file))
goto out_free;
- ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
- if (ret < 0)
- goto out_free;
+ if (!get_named_trigger_data(trigger_data)) {
- if (get_named_trigger_data(trigger_data))
- goto enable;
+ ret = create_actions(hist_data);
+ if (ret)
+ goto out_free;
- ret = create_actions(hist_data);
- if (ret)
- goto out_unreg;
+ if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+ ret = save_hist_vars(hist_data);
+ if (ret)
+ goto out_free;
+ }
- if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
- ret = save_hist_vars(hist_data);
+ ret = tracing_map_init(hist_data->map);
if (ret)
- goto out_unreg;
+ goto out_free;
}
- ret = tracing_map_init(hist_data->map);
- if (ret)
- goto out_unreg;
-enable:
+ ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+ if (ret < 0)
+ goto out_free;
+
ret = hist_trigger_enable(trigger_data, file);
if (ret)
goto out_unreg;
diff --git a/lib/rcuref.c b/lib/rcuref.c
index 5ec00a4a64d1..185967b8508e 100644
--- a/lib/rcuref.c
+++ b/lib/rcuref.c
@@ -220,6 +220,7 @@ EXPORT_SYMBOL_GPL(rcuref_get_slowpath);
/**
* rcuref_put_slowpath - Slowpath of __rcuref_put()
* @ref: Pointer to the reference count
+ * @cnt: The resulting value of the fastpath decrement
*
* Invoked when the reference count is outside of the valid zone.
*
@@ -233,10 +234,8 @@ EXPORT_SYMBOL_GPL(rcuref_get_slowpath);
* with a concurrent get()/put() pair. Caller is not allowed to
* deconstruct the protected object.
*/
-bool rcuref_put_slowpath(rcuref_t *ref)
+bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt)
{
- unsigned int cnt = atomic_read(&ref->refcnt);
-
/* Did this drop the last reference? */
if (likely(cnt == RCUREF_NOREF)) {
/*
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index acb148759bd0..304ebb31cebb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -636,7 +636,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
test_bit(FLAG_HOLD_HCI_CONN, &chan->flags))
hci_conn_hold(conn->hcon);
- list_add(&chan->list, &conn->chan_l);
+ /* Append to the list since the order matters for ECRED */
+ list_add_tail(&chan->list, &conn->chan_l);
}
void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
@@ -3774,7 +3775,11 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data)
{
struct l2cap_ecred_rsp_data *rsp = data;
- if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags))
+ /* Check if channel for outgoing connection or if it wasn't deferred
+ * since in those cases it must be skipped.
+ */
+ if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags) ||
+ !test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags))
return;
/* Reset ident so only one response is sent */
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index a1cfa75bbadb..2a4958e995f2 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -366,9 +366,9 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
*/
static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb->dev, *br_indev;
- struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+ struct net_device *dev = skb->dev, *br_indev;
+ const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
int err;
@@ -386,7 +386,9 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
}
nf_bridge->in_prerouting = 0;
if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
- if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
+ err = ip_route_input(skb, iph->daddr, iph->saddr,
+ ip4h_dscp(iph), dev);
+ if (err) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* If err equals -EHOSTUNREACH the error is due to a
diff --git a/net/core/gro.c b/net/core/gro.c
index 85d3f686ba53..397cf5984250 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -627,6 +627,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0;
+ skb->ip_summed = CHECKSUM_NONE;
skb_shinfo(skb)->gso_type = 0;
skb_shinfo(skb)->gso_size = 0;
if (unlikely(skb->slow_gro)) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f0a9ef1aeaa2..21a83e26f004 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5867,11 +5867,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
skb->offload_fwd_mark = 0;
skb->offload_l3_fwd_mark = 0;
#endif
+ ipvs_reset(skb);
if (!xnet)
return;
- ipvs_reset(skb);
skb->mark = 0;
skb_clear_tstamp(skb);
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 0b15272dd2d3..a7fa17b6a129 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -31,6 +31,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
+static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -613,7 +614,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
+ .extra1 = &netdev_budget_usecs_min,
},
{
.procname = "fb_tunnels_only_for_init_net",
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index a21d32b3ae6c..94501bb30c43 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -93,6 +93,9 @@
#include <net/ip_fib.h>
#include <net/l3mdev.h>
#include <net/addrconf.h>
+#include <net/inet_dscp.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/icmp.h>
/*
* Build xmit assembly blocks
@@ -481,13 +484,11 @@ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
return route_lookup_dev;
}
-static struct rtable *icmp_route_lookup(struct net *net,
- struct flowi4 *fl4,
+static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
struct sk_buff *skb_in,
- const struct iphdr *iph,
- __be32 saddr, u8 tos, u32 mark,
- int type, int code,
- struct icmp_bxm *param)
+ const struct iphdr *iph, __be32 saddr,
+ dscp_t dscp, u32 mark, int type,
+ int code, struct icmp_bxm *param)
{
struct net_device *route_lookup_dev;
struct rtable *rt, *rt2;
@@ -500,7 +501,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->saddr = saddr;
fl4->flowi4_mark = mark;
fl4->flowi4_uid = sock_net_uid(net, NULL);
- fl4->flowi4_tos = RT_TOS(tos);
+ fl4->flowi4_tos = inet_dscp_to_dsfield(dscp);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
@@ -548,7 +549,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
orefdst = skb_in->_skb_refdst; /* save old refdst */
skb_dst_set(skb_in, NULL);
err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
- RT_TOS(tos), rt2->dst.dev);
+ dscp, rt2->dst.dev);
dst_release(&rt2->dst);
rt2 = skb_rtable(skb_in);
@@ -744,8 +745,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
ipc.opt = &icmp_param.replyopts.opt;
ipc.sockc.mark = mark;
- rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
- type, code, &icmp_param);
+ rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr,
+ inet_dsfield_to_dscp(tos), mark, type, code,
+ &icmp_param);
if (IS_ERR(rt))
goto out_unlock;
@@ -778,6 +780,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
if (!fl4.saddr)
fl4.saddr = htonl(INADDR_DUMMY);
+ trace_icmp_send(skb_in, type, code);
+
icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index a9e22a098872..b4c59708fc09 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -617,7 +617,8 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
orefdst = skb->_skb_refdst;
skb_dst_set(skb, NULL);
- err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
+ err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph),
+ dev);
rt2 = skb_rtable(skb);
if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
skb_dst_drop(skb);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index cc2b608b1a8e..ddb90b9057e7 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -754,12 +754,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
/* In sequence, PAWS is OK. */
- /* TODO: We probably should defer ts_recent change once
- * we take ownership of @req.
- */
- if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
- WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
-
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
/* Truncate SYN, it is out of window starting
at tcp_rsk(req)->rcv_isn + 1. */
@@ -808,6 +802,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
+ if (own_req && tmp_opt.saw_tstamp &&
+ !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+ tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval;
+
if (own_req && rsk_drop_req(req)) {
reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 97905d4174ec..d645d022ce77 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -628,8 +628,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
skb_dst_set(skb2, &rt->dst);
} else {
- if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
- skb2->dev) ||
+ if (ip_route_input(skb2, eiph->daddr, eiph->saddr,
+ ip4h_dscp(eiph), skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
goto out;
}
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index db3c19a42e1c..28fc7fae5797 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -125,7 +125,8 @@ static void rpl_destroy_state(struct lwtunnel_state *lwt)
}
static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
- const struct ipv6_rpl_sr_hdr *srh)
+ const struct ipv6_rpl_sr_hdr *srh,
+ struct dst_entry *cache_dst)
{
struct ipv6_rpl_sr_hdr *isrh, *csrh;
const struct ipv6hdr *oldhdr;
@@ -153,7 +154,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
hdrlen = ((csrh->hdrlen + 1) << 3);
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err)) {
kfree(buf);
return err;
@@ -186,7 +187,8 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
return 0;
}
-static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
+static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt,
+ struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct rpl_iptunnel_encap *tinfo;
@@ -196,7 +198,7 @@ static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
tinfo = rpl_encap_lwtunnel(dst->lwtstate);
- return rpl_do_srh_inline(skb, rlwt, tinfo->srh);
+ return rpl_do_srh_inline(skb, rlwt, tinfo->srh, cache_dst);
}
static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -208,14 +210,14 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
- err = rpl_do_srh(skb, rlwt);
- if (unlikely(err))
- goto drop;
-
local_bh_disable();
dst = dst_cache_get(&rlwt->cache);
local_bh_enable();
+ err = rpl_do_srh(skb, rlwt, dst);
+ if (unlikely(err))
+ goto drop;
+
if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct flowi6 fl6;
@@ -237,15 +239,15 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
local_bh_disable();
dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
local_bh_enable();
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
-
return dst_output(net, sk, skb);
drop:
@@ -257,34 +259,46 @@ static int rpl_input(struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct rpl_lwt *rlwt;
int err;
- rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
- err = rpl_do_srh(skb, rlwt);
- if (unlikely(err))
- goto drop;
+ rlwt = rpl_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&rlwt->cache);
+ local_bh_enable();
+
+ err = rpl_do_srh(skb, rlwt, dst);
+ if (unlikely(err))
+ goto drop;
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
+ local_bh_disable();
dst_cache_set_ip6(&rlwt->cache, dst,
&ipv6_hdr(skb)->saddr);
+ local_bh_enable();
}
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
} else {
skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
- local_bh_enable();
-
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
return dst_input(skb);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 098632adc9b5..c44e4c0824e0 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -124,8 +124,8 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
return flowlabel;
}
-/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
-int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+ int proto, struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct net *net = dev_net(dst->dev);
@@ -137,7 +137,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
hdrlen = (osrh->hdrlen + 1) << 3;
tot_len = hdrlen + sizeof(*hdr);
- err = skb_cow_head(skb, tot_len + skb->mac_len);
+ err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -197,11 +197,18 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
return 0;
}
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+{
+ return __seg6_do_srh_encap(skb, osrh, proto, NULL);
+}
EXPORT_SYMBOL_GPL(seg6_do_srh_encap);
/* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */
static int seg6_do_srh_encap_red(struct sk_buff *skb,
- struct ipv6_sr_hdr *osrh, int proto)
+ struct ipv6_sr_hdr *osrh, int proto,
+ struct dst_entry *cache_dst)
{
__u8 first_seg = osrh->first_segment;
struct dst_entry *dst = skb_dst(skb);
@@ -230,7 +237,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb,
tot_len = red_hdrlen + sizeof(struct ipv6hdr);
- err = skb_cow_head(skb, tot_len + skb->mac_len);
+ err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -317,8 +324,8 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb,
return 0;
}
-/* insert an SRH within an IPv6 packet, just after the IPv6 header */
-int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+ struct dst_entry *cache_dst)
{
struct ipv6hdr *hdr, *oldhdr;
struct ipv6_sr_hdr *isrh;
@@ -326,7 +333,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
hdrlen = (osrh->hdrlen + 1) << 3;
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -369,9 +376,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
return 0;
}
-EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
-static int seg6_do_srh(struct sk_buff *skb)
+static int seg6_do_srh(struct sk_buff *skb, struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct seg6_iptunnel_encap *tinfo;
@@ -384,7 +390,7 @@ static int seg6_do_srh(struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
return -EINVAL;
- err = seg6_do_srh_inline(skb, tinfo->srh);
+ err = __seg6_do_srh_inline(skb, tinfo->srh, cache_dst);
if (err)
return err;
break;
@@ -402,9 +408,11 @@ static int seg6_do_srh(struct sk_buff *skb)
return -EINVAL;
if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP)
- err = seg6_do_srh_encap(skb, tinfo->srh, proto);
+ err = __seg6_do_srh_encap(skb, tinfo->srh,
+ proto, cache_dst);
else
- err = seg6_do_srh_encap_red(skb, tinfo->srh, proto);
+ err = seg6_do_srh_encap_red(skb, tinfo->srh,
+ proto, cache_dst);
if (err)
return err;
@@ -425,11 +433,13 @@ static int seg6_do_srh(struct sk_buff *skb)
skb_push(skb, skb->mac_len);
if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP)
- err = seg6_do_srh_encap(skb, tinfo->srh,
- IPPROTO_ETHERNET);
+ err = __seg6_do_srh_encap(skb, tinfo->srh,
+ IPPROTO_ETHERNET,
+ cache_dst);
else
err = seg6_do_srh_encap_red(skb, tinfo->srh,
- IPPROTO_ETHERNET);
+ IPPROTO_ETHERNET,
+ cache_dst);
if (err)
return err;
@@ -444,6 +454,13 @@ static int seg6_do_srh(struct sk_buff *skb)
return 0;
}
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ return __seg6_do_srh_inline(skb, osrh, NULL);
+}
+EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
+
static int seg6_input_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
@@ -455,34 +472,46 @@ static int seg6_input_core(struct net *net, struct sock *sk,
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct seg6_lwt *slwt;
int err;
- err = seg6_do_srh(skb);
- if (unlikely(err))
- goto drop;
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
- slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+ slwt = seg6_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&slwt->cache);
+ local_bh_enable();
+
+ err = seg6_do_srh(skb, dst);
+ if (unlikely(err))
+ goto drop;
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
+ local_bh_disable();
dst_cache_set_ip6(&slwt->cache, dst,
&ipv6_hdr(skb)->saddr);
+ local_bh_enable();
}
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
} else {
skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
- local_bh_enable();
-
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
@@ -528,16 +557,16 @@ static int seg6_output_core(struct net *net, struct sock *sk,
struct seg6_lwt *slwt;
int err;
- err = seg6_do_srh(skb);
- if (unlikely(err))
- goto drop;
-
slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
local_bh_disable();
dst = dst_cache_get(&slwt->cache);
local_bh_enable();
+ err = seg6_do_srh(skb, dst);
+ if (unlikely(err))
+ goto drop;
+
if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct flowi6 fl6;
@@ -559,15 +588,15 @@ static int seg6_output_core(struct net *net, struct sock *sk,
local_bh_disable();
dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
local_bh_enable();
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
-
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
NULL, skb_dst(skb)->dev, dst_output);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2b63c5492eed..5f16e2fa2de6 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1559,11 +1559,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
if (mptcp_pm_is_userspace(msk))
goto next;
- if (list_empty(&msk->conn_list)) {
- mptcp_pm_remove_anno_addr(msk, addr, false);
- goto next;
- }
-
lock_sock(sk);
remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 282ecc8bf75e..b3eeeb948b61 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1109,7 +1109,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
if (data_len == 0) {
pr_debug("infinite mapping received\n");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
- subflow->map_data_len = 0;
return MAPPING_INVALID;
}
@@ -1251,18 +1250,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
mptcp_schedule_work(sk);
}
-static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
-{
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
- if (subflow->mp_join)
- return false;
- else if (READ_ONCE(msk->csum_enabled))
- return !subflow->valid_csum_seen;
- else
- return READ_ONCE(msk->allow_infinite_fallback);
-}
-
static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1358,7 +1345,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
return true;
}
- if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
+ if (!READ_ONCE(msk->allow_infinite_fallback)) {
/* fatal protocol error, close the socket.
* subflow_error_report() will introduce the appropriate barriers
*/
diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c
index 085e7892d310..b1536da2246b 100644
--- a/net/rxrpc/rxperf.c
+++ b/net/rxrpc/rxperf.c
@@ -478,6 +478,18 @@ static int rxperf_deliver_request(struct rxperf_call *call)
call->unmarshal++;
fallthrough;
case 2:
+ ret = rxperf_extract_data(call, true);
+ if (ret < 0)
+ return ret;
+
+ /* Deal with the terminal magic cookie. */
+ call->iov_len = 4;
+ call->kvec[0].iov_len = call->iov_len;
+ call->kvec[0].iov_base = call->tmp;
+ iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len);
+ call->unmarshal++;
+ fallthrough;
+ case 3:
ret = rxperf_extract_data(call, false);
if (ret < 0)
return ret;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 3298da2e37e4..cb6a6bc9fea7 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1675,12 +1675,14 @@ static void remove_cache_proc_entries(struct cache_detail *cd)
}
}
-#ifdef CONFIG_PROC_FS
static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
struct proc_dir_entry *p;
struct sunrpc_net *sn;
+ if (!IS_ENABLED(CONFIG_PROC_FS))
+ return 0;
+
sn = net_generic(net, sunrpc_net_id);
cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc);
if (cd->procfs == NULL)
@@ -1708,12 +1710,6 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
remove_cache_proc_entries(cd);
return -ENOMEM;
}
-#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
-{
- return 0;
-}
-#endif
void __init cache_initialize(void)
{
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index cef623ea1506..9b45fbdc90ca 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -864,8 +864,6 @@ void rpc_signal_task(struct rpc_task *task)
if (!rpc_task_set_rpc_status(task, -ERESTARTSYS))
return;
trace_rpc_task_signalled(task, task->tk_action);
- set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate);
- smp_mb__after_atomic();
queue = READ_ONCE(task->tk_waitqueue);
if (queue)
rpc_wake_up_queued_task(queue, task);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1c4bc8234ea8..29df05879c8e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2561,7 +2561,15 @@ static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid)
struct sock_xprt *lower_transport =
container_of(lower_xprt, struct sock_xprt, xprt);
- lower_transport->xprt_err = status ? -EACCES : 0;
+ switch (status) {
+ case 0:
+ case -EACCES:
+ case -ETIMEDOUT:
+ lower_transport->xprt_err = status;
+ break;
+ default:
+ lower_transport->xprt_err = -EACCES;
+ }
complete(&lower_transport->handshake_done);
xprt_put(lower_xprt);
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 75162e5f712b..822bd9a00892 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10084,23 +10084,27 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
- SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
- SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
- SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC),
- SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC),
- SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601VV/VU/VJ/VQ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x14d3, "ASUS G614JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
- SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA", ALC287_FIXUP_CS35L41_I2C_2),
- SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
- SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
- SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY),
+ SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY),
SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x18d3, "ASUS UM3504DA", ALC294_FIXUP_CS35L41_I2C_2),
@@ -10111,7 +10115,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
- SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
@@ -10125,10 +10128,13 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
- SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
- SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+ SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
- SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS G713PI/PU/PV/PVN", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index 0bd9ba5a11b4..43792e175d75 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -234,7 +234,6 @@ static const struct snd_kcontrol_new es8328_right_line_controls =
/* Left Mixer */
static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
- SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 7, 1, 0),
SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 6, 1, 0),
SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 7, 1, 0),
SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 6, 1, 0),
@@ -244,7 +243,6 @@ static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
static const struct snd_kcontrol_new es8328_right_mixer_controls[] = {
SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 7, 1, 0),
SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 6, 1, 0),
- SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 7, 1, 0),
SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 6, 1, 0),
};
@@ -337,10 +335,10 @@ static const struct snd_soc_dapm_widget es8328_dapm_widgets[] = {
SND_SOC_DAPM_DAC("Left DAC", "Left Playback", ES8328_DACPOWER,
ES8328_DACPOWER_LDAC_OFF, 1),
- SND_SOC_DAPM_MIXER("Left Mixer", SND_SOC_NOPM, 0, 0,
+ SND_SOC_DAPM_MIXER("Left Mixer", ES8328_DACCONTROL17, 7, 0,
&es8328_left_mixer_controls[0],
ARRAY_SIZE(es8328_left_mixer_controls)),
- SND_SOC_DAPM_MIXER("Right Mixer", SND_SOC_NOPM, 0, 0,
+ SND_SOC_DAPM_MIXER("Right Mixer", ES8328_DACCONTROL20, 7, 0,
&es8328_right_mixer_controls[0],
ARRAY_SIZE(es8328_right_mixer_controls)),
@@ -419,19 +417,14 @@ static const struct snd_soc_dapm_route es8328_dapm_routes[] = {
{ "Right Line Mux", "PGA", "Right PGA Mux" },
{ "Right Line Mux", "Differential", "Differential Mux" },
- { "Left Out 1", NULL, "Left DAC" },
- { "Right Out 1", NULL, "Right DAC" },
- { "Left Out 2", NULL, "Left DAC" },
- { "Right Out 2", NULL, "Right DAC" },
-
- { "Left Mixer", "Playback Switch", "Left DAC" },
+ { "Left Mixer", NULL, "Left DAC" },
{ "Left Mixer", "Left Bypass Switch", "Left Line Mux" },
{ "Left Mixer", "Right Playback Switch", "Right DAC" },
{ "Left Mixer", "Right Bypass Switch", "Right Line Mux" },
{ "Right Mixer", "Left Playback Switch", "Left DAC" },
{ "Right Mixer", "Left Bypass Switch", "Left Line Mux" },
- { "Right Mixer", "Playback Switch", "Right DAC" },
+ { "Right Mixer", NULL, "Right DAC" },
{ "Right Mixer", "Right Bypass Switch", "Right Line Mux" },
{ "DAC DIG", NULL, "DAC STM" },
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 6b0993258e03..6d861046b582 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1145,7 +1145,7 @@ static int snd_usbmidi_output_close(struct snd_rawmidi_substream *substream)
{
struct usbmidi_out_port *port = substream->runtime->private_data;
- cancel_work_sync(&port->ep->work);
+ flush_work(&port->ep->work);
return substream_open(substream, 0, 0);
}
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 93d9ed8983df..d9d4c5922a50 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1775,6 +1775,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
subs->stream_offset_adj = 2;
break;
+ case USB_ID(0x2b73, 0x000a): /* Pioneer DJM-900NXS2 */
case USB_ID(0x2b73, 0x0013): /* Pioneer DJM-450 */
pioneer_djm_set_format_quirk(subs, 0x0082);
break;
diff --git a/tools/testing/selftests/rseq/rseq-riscv-bits.h b/tools/testing/selftests/rseq/rseq-riscv-bits.h
index de31a0143139..f02f411d550d 100644
--- a/tools/testing/selftests/rseq/rseq-riscv-bits.h
+++ b/tools/testing/selftests/rseq/rseq-riscv-bits.h
@@ -243,7 +243,7 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
#ifdef RSEQ_COMPARE_TWICE
RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]")
#endif
- RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, 3)
+ RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3)
RSEQ_INJECT_ASM(4)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
@@ -251,8 +251,8 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
[current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
[rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[ptr] "r" (ptr),
- [off] "er" (off),
- [inc] "er" (inc)
+ [off] "r" (off),
+ [inc] "r" (inc)
RSEQ_INJECT_INPUT
: "memory", RSEQ_ASM_TMP_REG_1
RSEQ_INJECT_CLOBBER
diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h
index 37e598d0a365..67d544aaa9a3 100644
--- a/tools/testing/selftests/rseq/rseq-riscv.h
+++ b/tools/testing/selftests/rseq/rseq-riscv.h
@@ -158,7 +158,7 @@ do { \
"bnez " RSEQ_ASM_TMP_REG_1 ", 222b\n" \
"333:\n"
-#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, post_commit_label) \
+#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label) \
"mv " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "]\n" \
RSEQ_ASM_OP_R_ADD(off) \
REG_L RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n" \
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index a985e5795482..198cdf75c837 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -905,7 +905,7 @@ timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_param
* On kernels without support, user threads will have already failed
* on missing timerlat_fd, and kernel threads do not need it.
*/
- retval = osnoise_set_workload(tool->context, params->kernel_workload);
+ retval = osnoise_set_workload(tool->context, !params->user_hist);
if (retval < -1) {
err_msg("Failed to set OSNOISE_WORKLOAD option\n");
goto out_err;
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 1fed4c8d8520..7212855d3364 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -684,7 +684,7 @@ timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params *
* On kernels without support, user threads will have already failed
* on missing timerlat_fd, and kernel threads do not need it.
*/
- retval = osnoise_set_workload(top->context, params->kernel_workload);
+ retval = osnoise_set_workload(top->context, !params->user_top);
if (retval < -1) {
err_msg("Failed to set OSNOISE_WORKLOAD option\n");
goto out_err;
Powered by blists - more mailing lists