Merge 5.10.41 into android12-5.10

Changes in 5.10.41
	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
	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
	perf unwind: Fix separate debug info files when using elfutils' libdw's unwinder
	perf unwind: Set userdata for all __report_module() paths
	NFC: nci: fix memory leak in nci_allocate_device
	Linux 5.10.41

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ie9f14d4b9960fb923eb01303517012fe6274d5ef

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 40
+SUBLEVEL = 41
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/x86/kvm/svm/svm.c

@@ -3532,15 +3532,15 @@ 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();

arch/x86/kvm/vmx/vmx.c

@@ -6640,15 +6640,15 @@ 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();

arch/x86/kvm/x86.c

@@ -9063,6 +9063,15 @@ 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) {

include/linux/context_tracking.h

@@ -129,16 +129,26 @@ 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();
 }
 
@@ -157,12 +167,19 @@ 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 */

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,

kernel/bpf/verifier.c

@@ -5666,18 +5666,10 @@ 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
@@ -5743,15 +5735,20 @@ 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;
@@ -5772,7 +5769,16 @@ 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;
 
@@ -5780,8 +5786,8 @@ 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;
@@ -5796,8 +5802,12 @@ do_sim:
 	/* 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
@@ -5942,7 +5952,7 @@ 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;
@@ -6011,7 +6021,7 @@ 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);
 	}
@@ -6152,7 +6162,7 @@ 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);
 	}

net/nfc/nci/core.c

@@ -1175,6 +1175,7 @@ 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);

net/nfc/nci/hci.c

@@ -795,3 +795,8 @@ 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);
+}

tools/perf/util/unwind-libdw.c

@@ -20,10 +20,24 @@
 
 static char *debuginfo_path;
 
+static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
+			    const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused,
+			    const char *file_name, const char *debuglink_file __maybe_unused,
+			    GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name)
+{
+	const struct dso *dso = *userdata;
+
+	assert(dso);
+	if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename))
+		*debuginfo_file_name = strdup(dso->symsrc_filename);
+	return -1;
+}
+
 static const Dwfl_Callbacks offline_callbacks = {
-	.find_debuginfo		= dwfl_standard_find_debuginfo,
+	.find_debuginfo		= __find_debuginfo,
 	.debuginfo_path		= &debuginfo_path,
 	.section_address	= dwfl_offline_section_address,
+	// .find_elf is not set as we use dwfl_report_elf() instead.
 };
 
 static int __report_module(struct addr_location *al, u64 ip,
@@ -53,9 +67,22 @@ static int __report_module(struct addr_location *al, u64 ip,
 	}
 
 	if (!mod)
-		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
-				      false);
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1,
+				      al->map->start - al->map->pgoff, false);
+	if (!mod) {
+		char filename[PATH_MAX];
+
+		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
+			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
+					      al->map->start - al->map->pgoff, false);
+	}
+
+	if (mod) {
+		void **userdatap;
+
+		dwfl_module_info(mod, &userdatap, NULL, NULL, NULL, NULL, NULL, NULL);
+		*userdatap = dso;
+	}
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
 }