Linux 5.12.8

Linux 5.12.8

[Greg Kroah-Hartman]

I'm announcing the release of the 5.12.8 kernel.

All users of the 5.12 kernel series must upgrade.

The updated 5.12.y git tree can be found at:
	git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-5.12.y
and can be browsed at the normal kernel.org git web browser:
	https://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary

thanks,

greg k-h

------------

 Makefile                         |    2 -
 arch/x86/kvm/svm/svm.c           |    6 ++---
 arch/x86/kvm/vmx/vmx.c           |    6 ++---
 arch/x86/kvm/x86.c               |    9 +++++++
 include/linux/context_tracking.h |   25 +++++++++++++++++----
 include/net/nfc/nci_core.h       |    1 
 kernel/bpf/verifier.c            |   46 +++++++++++++++++++++++----------------
 net/nfc/nci/core.c               |    1 
 net/nfc/nci/hci.c                |    5 ++++
 9 files changed, 72 insertions(+), 29 deletions(-)

Daniel Borkmann (3):
      bpf: Wrap aux data inside bpf_sanitize_info container
      bpf: Fix mask direction swap upon off reg sign change
      bpf: No need to simulate speculative domain for immediates

Dongliang Mu (1):
      NFC: nci: fix memory leak in nci_allocate_device

Greg Kroah-Hartman (1):
      Linux 5.12.8

Wanpeng Li (3):
      context_tracking: Move guest exit context tracking to separate helpers
      context_tracking: Move guest exit vtime accounting to separate helpers
      KVM: x86: Defer vtime accounting 'til after IRQ handling

Re: Linux 5.12.8

[Greg Kroah-Hartman]

diff --git a/Makefile b/Makefile
index 6a73dee7c221..a20afcb7d2bf 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 12
-SUBLEVEL = 7
+SUBLEVEL = 8
 EXTRAVERSION =
 NAME = Frozen Wasteland
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 48ee3deab64b..9a6825feaf53 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3815,15 +3815,15 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	 * have them in state 'on' as recorded before entering guest mode.
 	 * Same as enter_from_user_mode().
 	 *
-	 * guest_exit_irqoff() restores host context and reinstates RCU if
-	 * enabled and required.
+	 * context_tracking_guest_exit() restores host context and reinstates
+	 * RCU if enabled and required.
 	 *
 	 * This needs to be done before the below as native_read_msr()
 	 * contains a tracepoint and x86_spec_ctrl_restore_host() calls
 	 * into world and some more.
 	 */
 	lockdep_hardirqs_off(CALLER_ADDR0);
-	guest_exit_irqoff();
+	context_tracking_guest_exit();
 
 	instrumentation_begin();
 	trace_hardirqs_off_finish();
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f68ed9a1abcc..ae63d59be38c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6701,15 +6701,15 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	 * have them in state 'on' as recorded before entering guest mode.
 	 * Same as enter_from_user_mode().
 	 *
-	 * guest_exit_irqoff() restores host context and reinstates RCU if
-	 * enabled and required.
+	 * context_tracking_guest_exit() restores host context and reinstates
+	 * RCU if enabled and required.
 	 *
 	 * This needs to be done before the below as native_read_msr()
 	 * contains a tracepoint and x86_spec_ctrl_restore_host() calls
 	 * into world and some more.
 	 */
 	lockdep_hardirqs_off(CALLER_ADDR0);
-	guest_exit_irqoff();
+	context_tracking_guest_exit();
 
 	instrumentation_begin();
 	trace_hardirqs_off_finish();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 87311d39f914..86678f8b3502 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9236,6 +9236,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_after_interrupt(vcpu);
 
+	/*
+	 * Wait until after servicing IRQs to account guest time so that any
+	 * ticks that occurred while running the guest are properly accounted
+	 * to the guest.  Waiting until IRQs are enabled degrades the accuracy
+	 * of accounting via context tracking, but the loss of accuracy is
+	 * acceptable for all known use cases.
+	 */
+	vtime_account_guest_exit();
+
 	if (lapic_in_kernel(vcpu)) {
 		s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
 		if (delta != S64_MIN) {
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index bceb06498521..4f4556232dcf 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -131,16 +131,26 @@ static __always_inline void guest_enter_irqoff(void)
 	}
 }
 
-static __always_inline void guest_exit_irqoff(void)
+static __always_inline void context_tracking_guest_exit(void)
 {
 	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
+}
 
-	instrumentation_begin();
+static __always_inline void vtime_account_guest_exit(void)
+{
 	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;
+}
+
+static __always_inline void guest_exit_irqoff(void)
+{
+	context_tracking_guest_exit();
+
+	instrumentation_begin();
+	vtime_account_guest_exit();
 	instrumentation_end();
 }
 
@@ -159,12 +169,19 @@ static __always_inline void guest_enter_irqoff(void)
 	instrumentation_end();
 }
 
+static __always_inline void context_tracking_guest_exit(void) { }
+
+static __always_inline void vtime_account_guest_exit(void)
+{
+	vtime_account_kernel(current);
+	current->flags &= ~PF_VCPU;
+}
+
 static __always_inline void guest_exit_irqoff(void)
 {
 	instrumentation_begin();
 	/* Flush the guest cputime we spent on the guest */
-	vtime_account_kernel(current);
-	current->flags &= ~PF_VCPU;
+	vtime_account_guest_exit();
 	instrumentation_end();
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 43c9c5d2bedb..33979017b782 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len,
 		      struct sk_buff **resp);
 
 struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev);
+void nci_hci_deallocate(struct nci_dev *ndev);
 int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
 int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7fa6fc6bedf1..21247e49fe82 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5863,18 +5863,10 @@ enum {
 };
 
 static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
-			      const struct bpf_reg_state *off_reg,
-			      u32 *alu_limit, u8 opcode)
+			      u32 *alu_limit, bool mask_to_left)
 {
-	bool off_is_neg = off_reg->smin_value < 0;
-	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
-			    (opcode == BPF_SUB && !off_is_neg);
 	u32 max = 0, ptr_limit = 0;
 
-	if (!tnum_is_const(off_reg->var_off) &&
-	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
-		return REASON_BOUNDS;
-
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
 		/* Offset 0 is out-of-bounds, but acceptable start for the
@@ -5940,15 +5932,20 @@ static bool sanitize_needed(u8 opcode)
 	return opcode == BPF_ADD || opcode == BPF_SUB;
 }
 
+struct bpf_sanitize_info {
+	struct bpf_insn_aux_data aux;
+	bool mask_to_left;
+};
+
 static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
 			    const struct bpf_reg_state *off_reg,
 			    struct bpf_reg_state *dst_reg,
-			    struct bpf_insn_aux_data *tmp_aux,
+			    struct bpf_sanitize_info *info,
 			    const bool commit_window)
 {
-	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
+	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux;
 	struct bpf_verifier_state *vstate = env->cur_state;
 	bool off_is_imm = tnum_is_const(off_reg->var_off);
 	bool off_is_neg = off_reg->smin_value < 0;
@@ -5969,7 +5966,16 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	if (vstate->speculative)
 		goto do_sim;
 
-	err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
+	if (!commit_window) {
+		if (!tnum_is_const(off_reg->var_off) &&
+		    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+			return REASON_BOUNDS;
+
+		info->mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
+				     (opcode == BPF_SUB && !off_is_neg);
+	}
+
+	err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left);
 	if (err < 0)
 		return err;
 
@@ -5977,8 +5983,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 		/* In commit phase we narrow the masking window based on
 		 * the observed pointer move after the simulated operation.
 		 */
-		alu_state = tmp_aux->alu_state;
-		alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+		alu_state = info->aux.alu_state;
+		alu_limit = abs(info->aux.alu_limit - alu_limit);
 	} else {
 		alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
 		alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
@@ -5993,8 +5999,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	/* If we're in commit phase, we're done here given we already
 	 * pushed the truncated dst_reg into the speculative verification
 	 * stack.
+	 *
+	 * Also, when register is a known constant, we rewrite register-based
+	 * operation to immediate-based, and thus do not need masking (and as
+	 * a consequence, do not need to simulate the zero-truncation either).
 	 */
-	if (commit_window)
+	if (commit_window || off_is_imm)
 		return 0;
 
 	/* Simulate and find potential out-of-bounds access under
@@ -6139,7 +6149,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
 	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
 	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
-	struct bpf_insn_aux_data tmp_aux = {};
+	struct bpf_sanitize_info info = {};
 	u8 opcode = BPF_OP(insn->code);
 	u32 dst = insn->dst_reg;
 	int ret;
@@ -6208,7 +6218,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	if (sanitize_needed(opcode)) {
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
-				       &tmp_aux, false);
+				       &info, false);
 		if (ret < 0)
 			return sanitize_err(env, insn, ret, off_reg, dst_reg);
 	}
@@ -6349,7 +6359,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	if (sanitize_needed(opcode)) {
 		ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
-				       &tmp_aux, true);
+				       &info, true);
 		if (ret < 0)
 			return sanitize_err(env, insn, ret, off_reg, dst_reg);
 	}
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 59257400697d..142d71c8d652 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device);
 void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
+	nci_hci_deallocate(ndev);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index 6b275a387a92..96865142104f 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev)
 
 	return hdev;
 }
+
+void nci_hci_deallocate(struct nci_dev *ndev)
+{
+	kfree(ndev->hci_dev);
+}