Merge remote-tracking branch 'stable/linux-6.12.y' into rpi-6.12.y

Author: popcornmix

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 12
-SUBLEVEL = 66
+SUBLEVEL = 67
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 

arch/loongarch/boot/dts/loongson-2k0500.dtsi

@@ -131,6 +131,7 @@
 			reg-names = "main", "isr0";
 
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <2>;
@@ -149,6 +150,7 @@
 			reg-names = "main", "isr0";
 
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <4>;
@@ -164,6 +166,7 @@
 			compatible = "loongson,ls2k0500-eiointc";
 			reg = <0x0 0x1fe11600 0x0 0xea00>;
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <3>;

arch/loongarch/boot/dts/loongson-2k1000.dtsi

@@ -46,7 +46,7 @@
 	};
 
 	/* i2c of the dvi eeprom edid */
-	i2c-gpio-0 {
+	i2c-0 {
 		compatible = "i2c-gpio";
 		scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
@@ -57,7 +57,7 @@
 	};
 
 	/* i2c of the eeprom edid */
-	i2c-gpio-1 {
+	i2c-1 {
 		compatible = "i2c-gpio";
 		scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
@@ -114,6 +114,7 @@
 			      <0x0 0x1fe01140 0x0 0x8>;
 			reg-names = "main", "isr0", "isr1";
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <2>;
@@ -131,6 +132,7 @@
 			      <0x0 0x1fe01148 0x0 0x8>;
 			reg-names = "main", "isr0", "isr1";
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <3>;

arch/loongarch/boot/dts/loongson-2k2000.dtsi

@@ -126,6 +126,7 @@
 			reg = <0x0 0x1fe01400 0x0 0x64>;
 
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <2>;
@@ -140,6 +141,7 @@
 			compatible = "loongson,ls2k2000-eiointc";
 			reg = <0x0 0x1fe01600 0x0 0xea00>;
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&cpuintc>;
 			interrupts = <3>;
@@ -149,6 +151,7 @@
 			compatible = "loongson,pch-pic-1.0";
 			reg = <0x0 0x10000000 0x0 0x400>;
 			interrupt-controller;
+			#address-cells = <0>;
 			#interrupt-cells = <2>;
 			loongson,pic-base-vec = <0>;
 			interrupt-parent = <&eiointc>;

arch/loongarch/kernel/perf_event.c

@@ -627,22 +627,37 @@ static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 conf
 	return pev;
 }
 
+static inline bool loongarch_pmu_event_requires_counter(const struct perf_event *event)
+{
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_RAW:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int validate_group(struct perf_event *event)
 {
 	struct cpu_hw_events fake_cpuc;
 	struct perf_event *sibling, *leader = event->group_leader;
 
 	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
 
-	if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
+	if (loongarch_pmu_event_requires_counter(leader) &&
+	    loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
 		return -EINVAL;
 
 	for_each_sibling_event(sibling, leader) {
-		if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
+		if (loongarch_pmu_event_requires_counter(sibling) &&
+		    loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
 			return -EINVAL;
 	}
 
-	if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
+	if (loongarch_pmu_event_requires_counter(event) &&
+	    loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
 		return -EINVAL;
 
 	return 0;

arch/x86/kernel/cpu/resctrl/core.c

@@ -892,7 +892,8 @@ static __init bool get_mem_config(void)
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		return __get_mem_config_intel(&hw_res->r_resctrl);
-	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+		 boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 		return __rdt_get_mem_config_amd(&hw_res->r_resctrl);
 
 	return false;
@@ -1043,7 +1044,8 @@ static __init void rdt_init_res_defs(void)
 {
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		rdt_init_res_defs_intel();
-	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+		 boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 		rdt_init_res_defs_amd();
 }
 
@@ -1074,8 +1076,19 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 		c->x86_cache_occ_scale = ebx;
 		c->x86_cache_mbm_width_offset = eax & 0xff;
 
-		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
-			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
+		if (!c->x86_cache_mbm_width_offset) {
+			switch (c->x86_vendor) {
+			case X86_VENDOR_AMD:
+				c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
+				break;
+			case X86_VENDOR_HYGON:
+				c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_HYGON;
+				break;
+			default:
+				/* Leave c->x86_cache_mbm_width_offset as 0 */
+				break;
+			}
+		}
 	}
 }
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -23,6 +23,9 @@
 #define MBA_IS_LINEAR			0x4
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
+/* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */
+#define MBM_CNTR_WIDTH_OFFSET_HYGON	8
+
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
 /*

arch/x86/kernel/fpu/core.c

@@ -294,10 +294,29 @@ EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features);
 #ifdef CONFIG_X86_64
 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
 {
+	struct fpstate *fpstate = guest_fpu->fpstate;
+
 	fpregs_lock();
-	guest_fpu->fpstate->xfd = xfd;
-	if (guest_fpu->fpstate->in_use)
-		xfd_update_state(guest_fpu->fpstate);
+
+	/*
+	 * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the
+	 * save state to its initial configuration.  Likewise, KVM_GET_XSAVE does
+	 * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1.
+	 *
+	 * If the guest's FPU state is in hardware, just update XFD: the XSAVE
+	 * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1.
+	 *
+	 * If however the guest's FPU state is NOT resident in hardware, clear
+	 * disabled components in XSTATE_BV now, or a subsequent XRSTOR will
+	 * attempt to load disabled components and generate #NM _in the host_.
+	 */
+	if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD))
+		fpstate->regs.xsave.header.xfeatures &= ~xfd;
+
+	fpstate->xfd = xfd;
+	if (fpstate->in_use)
+		xfd_update_state(fpstate);
+
 	fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
@@ -405,6 +424,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 	if (ustate->xsave.header.xfeatures & ~xcr0)
 		return -EINVAL;
 
+	/*
+	 * Disabled features must be in their initial state, otherwise XRSTOR
+	 * causes an exception.
+	 */
+	if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd))
+		return -EINVAL;
+
 	/*
 	 * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
 	 * in the header.  KVM's odd ABI is to leave PKRU untouched in this

arch/x86/kvm/x86.c

@@ -5625,9 +5625,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
+	union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region;
+
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
 		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
+	/*
+	 * For backwards compatibility, do not expect disabled features to be in
+	 * their initial state.  XSTATE_BV[i] must still be cleared whenever
+	 * XFD[i]=1, or XRSTOR would cause a #NM.
+	 */
+	xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd;
+
 	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
 					      guest_xsave->region,
 					      kvm_caps.supported_xcr0,

arch/x86/mm/kaslr.c

@@ -111,12 +111,12 @@ void __init kernel_randomize_memory(void)
 
 	/*
 	 * Adapt physical memory region size based on available memory,
-	 * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
-	 * device BAR space assuming the direct map space is large enough
-	 * for creating a ZONE_DEVICE mapping in the direct map corresponding
-	 * to the physical BAR address.
+	 * except when CONFIG_ZONE_DEVICE is enabled. ZONE_DEVICE wants to map
+	 * any physical address into the direct-map. KASLR wants to reliably
+	 * steal some physical address bits. Those design choices are in direct
+	 * conflict.
 	 */
-	if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
+	if (!IS_ENABLED(CONFIG_ZONE_DEVICE) && (memory_tb < kaslr_regions[0].size_tb))
 		kaslr_regions[0].size_tb = memory_tb;
 
 	/*