6.1.46-rc1 review

@@ -71,7 +71,9 @@
 #include "varasm.h"
 #include "stor-layout.h"
 #include "internal-fn.h"
+#include "gimple.h"
 #include "gimple-expr.h"
+#include "gimple-iterator.h"
 #include "gimple-fold.h"
 #include "context.h"
 #include "tree-ssa-alias.h"

@@ -85,10 +87,8 @@
 #include "tree-eh.h"
 #include "stmt.h"
 #include "gimplify.h"
-#include "gimple.h"
 #include "tree-phinodes.h"
 #include "tree-cfg.h"
-#include "gimple-iterator.h"
 #include "gimple-ssa.h"
 #include "ssa-iterators.h"
 

@@ -12,7 +12,6 @@
  */
 #include <linux/init.h>
 #include <linux/acpi.h>
-#include <linux/cpu.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/export.h>

@@ -81,11 +80,6 @@ const char *get_system_type(void)
 	return "generic-loongson-machine";
 }
 
-void __init arch_cpu_finalize_init(void)
-{
-	alternative_instructions();
-}
-
 static const char *dmi_string_parse(const struct dmi_header *dm, u8 s)
 {
 	const u8 *bp = ((u8 *) dm) + dm->length;

@@ -507,70 +507,6 @@ static int tpm_add_legacy_sysfs(struct t
 	return 0;
 }
 
-/*
- * Some AMD fTPM versions may cause stutter
- * https://www.amd.com/en/support/kb/faq/pa-410
- *
- * Fixes are available in two series of fTPM firmware:
- * 6.x.y.z series: 6.0.18.6 +
- * 3.x.y.z series: 3.57.y.5 +
- */
-#ifdef CONFIG_X86
-static bool tpm_amd_is_rng_defective(struct tpm_chip *chip)
-{
-	u32 val1, val2;
-	u64 version;
-	int ret;
-
-	if (!(chip->flags & TPM_CHIP_FLAG_TPM2))
-		return false;
-
-	ret = tpm_request_locality(chip);
-	if (ret)
-		return false;
-
-	ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val1, NULL);
-	if (ret)
-		goto release;
-	if (val1 != 0x414D4400U /* AMD */) {
-		ret = -ENODEV;
-		goto release;
-	}
-	ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_1, &val1, NULL);
-	if (ret)
-		goto release;
-	ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_2, &val2, NULL);
-
-release:
-	tpm_relinquish_locality(chip);
-
-	if (ret)
-		return false;
-
-	version = ((u64)val1 << 32) | val2;
-	if ((version >> 48) == 6) {
-		if (version >= 0x0006000000180006ULL)
-			return false;
-	} else if ((version >> 48) == 3) {
-		if (version >= 0x0003005700000005ULL)
-			return false;
-	} else {
-		return false;
-	}
-
-	dev_warn(&chip->dev,
-		 "AMD fTPM version 0x%llx causes system stutter; hwrng disabled\n",
-		 version);
-
-	return true;
-}
-#else
-static inline bool tpm_amd_is_rng_defective(struct tpm_chip *chip)
-{
-	return false;
-}
-#endif /* CONFIG_X86 */
-
 static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 {
 	struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng);

@@ -585,7 +521,7 @@ static int tpm_hwrng_read(struct hwrng *
 static int tpm_add_hwrng(struct tpm_chip *chip)
 {
 	if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) ||
-	    tpm_amd_is_rng_defective(chip))
+	    chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED)
 		return 0;
 
 	snprintf(chip->hwrng_name, sizeof(chip->hwrng_name),

@@ -716,7 +652,7 @@ void tpm_chip_unregister(struct tpm_chip
 {
 	tpm_del_legacy_sysfs(chip);
 	if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) &&
-	    !tpm_amd_is_rng_defective(chip))
+	    !(chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED))
 		hwrng_unregister(&chip->hwrng);
 	tpm_bios_log_teardown(chip);
 	if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip))

@@ -463,6 +463,28 @@ static bool crb_req_canceled(struct tpm_
 	return (cancel & CRB_CANCEL_INVOKE) == CRB_CANCEL_INVOKE;
 }
 
+static int crb_check_flags(struct tpm_chip *chip)
+{
+	u32 val;
+	int ret;
+
+	ret = crb_request_locality(chip, 0);
+	if (ret)
+		return ret;
+
+	ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val, NULL);
+	if (ret)
+		goto release;
+
+	if (val == 0x414D4400U /* AMD */)
+		chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED;
+
+release:
+	crb_relinquish_locality(chip, 0);
+
+	return ret;
+}
+
 static const struct tpm_class_ops tpm_crb = {
 	.flags = TPM_OPS_AUTO_STARTUP,
 	.status = crb_status,

@@ -800,6 +822,14 @@ static int crb_acpi_add(struct acpi_devi
 	chip->acpi_dev_handle = device->handle;
 	chip->flags = TPM_CHIP_FLAG_TPM2;
 
+	rc = tpm_chip_bootstrap(chip);
+	if (rc)
+		goto out;
+
+	rc = crb_check_flags(chip);
+	if (rc)
+		goto out;
+
 	rc = tpm_chip_register(chip);
 
 out:

@@ -282,6 +282,7 @@ enum tpm_chip_flags {
 	TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED	= BIT(6),
 	TPM_CHIP_FLAG_FIRMWARE_UPGRADE		= BIT(7),
 	TPM_CHIP_FLAG_SUSPENDED			= BIT(8),
+	TPM_CHIP_FLAG_HWRNG_DISABLED		= BIT(9),
 };
 
 #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)

@@ -518,10 +518,20 @@ static int tpm_hwrng_read(struct hwrng *
 	return tpm_get_random(chip, data, max);
 }
 
+static bool tpm_is_hwrng_enabled(struct tpm_chip *chip)
+{
+	if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM))
+		return false;
+	if (tpm_is_firmware_upgrade(chip))
+		return false;
+	if (chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED)
+		return false;
+	return true;
+}
+
 static int tpm_add_hwrng(struct tpm_chip *chip)
 {
-	if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) ||
-	    chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED)
+	if (!tpm_is_hwrng_enabled(chip))
 		return 0;
 
 	snprintf(chip->hwrng_name, sizeof(chip->hwrng_name),

@@ -626,7 +636,7 @@ int tpm_chip_register(struct tpm_chip *c
 	return 0;
 
 out_hwrng:
-	if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip))
+	if (tpm_is_hwrng_enabled(chip))
 		hwrng_unregister(&chip->hwrng);
 out_ppi:
 	tpm_bios_log_teardown(chip);

@@ -651,8 +661,7 @@ EXPORT_SYMBOL_GPL(tpm_chip_register);
 void tpm_chip_unregister(struct tpm_chip *chip)
 {
 	tpm_del_legacy_sysfs(chip);
-	if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) &&
-	    !(chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED))
+	if (tpm_is_hwrng_enabled(chip))
 		hwrng_unregister(&chip->hwrng);
 	tpm_bios_log_teardown(chip);
 	if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip))

@@ -380,13 +380,13 @@ int ksmbd_smb2_check_message(struct ksmb
 	}
 
 	if (smb2_req_struct_sizes[command] != pdu->StructureSize2) {
-		if (command == SMB2_OPLOCK_BREAK_HE &&
-		    le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 &&
-		    le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) {
+		if (!(command == SMB2_OPLOCK_BREAK_HE &&
+		    (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 ||
+		    le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_21))) {
 			/* special case for SMB2.1 lease break message */
 			ksmbd_debug(SMB,
-				    "Illegal request size %d for oplock break\n",
-				    le16_to_cpu(pdu->StructureSize2));
+				"Illegal request size %u for command %d\n",
+				le16_to_cpu(pdu->StructureSize2), command);
 			return 1;
 		}
 	}

@@ -2340,9 +2340,16 @@ next:
 			break;
 		buf_len -= next;
 		eabuf = (struct smb2_ea_info *)((char *)eabuf + next);
-		if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength))
+		if (buf_len < sizeof(struct smb2_ea_info)) {
+			rc = -EINVAL;
 			break;
+		}
 
+		if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength +
+				le16_to_cpu(eabuf->EaValueLength)) {
+			rc = -EINVAL;
+			break;
+		}
 	} while (next != 0);
 
 	kfree(attr_name);

@@ -2410,15 +2410,18 @@ static void sev_es_sync_from_ghcb(struct
 	 */
 	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
 
-	vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb);
+	BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap));
+	memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap));
 
-	svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb);
 
-	if (ghcb_xcr0_is_valid(ghcb)) {
+	svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb);
+
+	if (kvm_ghcb_xcr0_is_valid(svm)) {
 		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
 		kvm_update_cpuid_runtime(vcpu);
 	}

@@ -2429,6 +2432,7 @@ static void sev_es_sync_from_ghcb(struct
 	control->exit_code_hi = upper_32_bits(exit_code);
 	control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb);
 	control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb);
+	svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb);
 
 	/* Clear the valid entries fields */
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));

@@ -2457,56 +2461,56 @@ static int sev_es_validate_vmgexit(struc
 
 	reason = GHCB_ERR_MISSING_INPUT;
 
-	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
-	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
-	    !ghcb_sw_exit_info_2_is_valid(ghcb))
+	if (!kvm_ghcb_sw_exit_code_is_valid(svm) ||
+	    !kvm_ghcb_sw_exit_info_1_is_valid(svm) ||
+	    !kvm_ghcb_sw_exit_info_2_is_valid(svm))
 		goto vmgexit_err;
 
 	switch (ghcb_get_sw_exit_code(ghcb)) {
 	case SVM_EXIT_READ_DR7:
 		break;
 	case SVM_EXIT_WRITE_DR7:
-		if (!ghcb_rax_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_RDTSC:
 		break;
 	case SVM_EXIT_RDPMC:
-		if (!ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_CPUID:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		if (ghcb_get_rax(ghcb) == 0xd)
-			if (!ghcb_xcr0_is_valid(ghcb))
+			if (!kvm_ghcb_xcr0_is_valid(svm))
 				goto vmgexit_err;
 		break;
 	case SVM_EXIT_INVD:
 		break;
 	case SVM_EXIT_IOIO:
 		if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) {
-			if (!ghcb_sw_scratch_is_valid(ghcb))
+			if (!kvm_ghcb_sw_scratch_is_valid(svm))
 				goto vmgexit_err;
 		} else {
 			if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
-				if (!ghcb_rax_is_valid(ghcb))
+				if (!kvm_ghcb_rax_is_valid(svm))
 					goto vmgexit_err;
 		}
 		break;
 	case SVM_EXIT_MSR:
-		if (!ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		if (ghcb_get_sw_exit_info_1(ghcb)) {
-			if (!ghcb_rax_is_valid(ghcb) ||
-			    !ghcb_rdx_is_valid(ghcb))
+			if (!kvm_ghcb_rax_is_valid(svm) ||
+			    !kvm_ghcb_rdx_is_valid(svm))
 				goto vmgexit_err;
 		}
 		break;
 	case SVM_EXIT_VMMCALL:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_cpl_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_cpl_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_RDTSCP:

@@ -2514,19 +2518,19 @@ static int sev_es_validate_vmgexit(struc
 	case SVM_EXIT_WBINVD:
 		break;
 	case SVM_EXIT_MONITOR:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb) ||
-		    !ghcb_rdx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm) ||
+		    !kvm_ghcb_rdx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_MWAIT:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_VMGEXIT_MMIO_READ:
 	case SVM_VMGEXIT_MMIO_WRITE:
-		if (!ghcb_sw_scratch_is_valid(ghcb))
+		if (!kvm_ghcb_sw_scratch_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:

@@ -2556,9 +2560,6 @@ vmgexit_err:
 		dump_ghcb(svm);
 	}
 
-	/* Clear the valid entries fields */
-	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-
 	ghcb_set_sw_exit_info_1(ghcb, 2);
 	ghcb_set_sw_exit_info_2(ghcb, reason);
 

@@ -2579,7 +2580,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *
 		 */
 		if (svm->sev_es.ghcb_sa_sync) {
 			kvm_write_guest(svm->vcpu.kvm,
-					ghcb_get_sw_scratch(svm->sev_es.ghcb),
+					svm->sev_es.sw_scratch,
 					svm->sev_es.ghcb_sa,
 					svm->sev_es.ghcb_sa_len);
 			svm->sev_es.ghcb_sa_sync = false;

@@ -2630,7 +2631,7 @@ static int setup_vmgexit_scratch(struct
 	u64 scratch_gpa_beg, scratch_gpa_end;
 	void *scratch_va;
 
-	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
+	scratch_gpa_beg = svm->sev_es.sw_scratch;
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
 		goto e_scratch;

@@ -2846,11 +2847,11 @@ int sev_handle_vmgexit(struct kvm_vcpu *
 
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
+	sev_es_sync_from_ghcb(svm);
 	ret = sev_es_validate_vmgexit(svm);
 	if (ret)
 		return ret;
 
-	sev_es_sync_from_ghcb(svm);
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 

@@ -196,10 +196,12 @@ struct vcpu_sev_es_state {
 	/* SEV-ES support */
 	struct sev_es_save_area *vmsa;
 	struct ghcb *ghcb;
+	u8 valid_bitmap[16];
 	struct kvm_host_map ghcb_map;
 	bool received_first_sipi;
 
 	/* SEV-ES scratch area support */
+	u64 sw_scratch;
 	void *ghcb_sa;
 	u32 ghcb_sa_len;
 	bool ghcb_sa_sync;

@@ -688,4 +690,28 @@ void sev_es_unmap_ghcb(struct vcpu_svm *
 void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
 void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
 
+#define DEFINE_KVM_GHCB_ACCESSORS(field)						\
+	static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \
+	{									\
+		return test_bit(GHCB_BITMAP_IDX(field),				\
+				(unsigned long *)&svm->sev_es.valid_bitmap);	\
+	}									\
+										\
+	static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \
+	{									\
+		return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0;	\
+	}									\
+
+DEFINE_KVM_GHCB_ACCESSORS(cpl)
+DEFINE_KVM_GHCB_ACCESSORS(rax)
+DEFINE_KVM_GHCB_ACCESSORS(rcx)
+DEFINE_KVM_GHCB_ACCESSORS(rdx)
+DEFINE_KVM_GHCB_ACCESSORS(rbx)
+DEFINE_KVM_GHCB_ACCESSORS(rsi)
+DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code)
+DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1)
+DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2)
+DEFINE_KVM_GHCB_ACCESSORS(sw_scratch)
+DEFINE_KVM_GHCB_ACCESSORS(xcr0)
+
 #endif

@@ -2438,9 +2438,15 @@ static void sev_es_sync_from_ghcb(struct
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
 static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
-	struct kvm_vcpu *vcpu;
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct ghcb *ghcb;
 	u64 exit_code;
 	u64 reason;

@@ -2451,7 +2457,7 @@ static int sev_es_validate_vmgexit(struc
 	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
-	exit_code = ghcb_get_sw_exit_code(ghcb);
+	exit_code = kvm_ghcb_get_sw_exit_code(control);
 
 	/* Only GHCB Usage code 0 is supported */
 	if (ghcb->ghcb_usage) {

@@ -2466,7 +2472,7 @@ static int sev_es_validate_vmgexit(struc
 	    !kvm_ghcb_sw_exit_info_2_is_valid(svm))
 		goto vmgexit_err;
 
-	switch (ghcb_get_sw_exit_code(ghcb)) {
+	switch (exit_code) {
 	case SVM_EXIT_READ_DR7:
 		break;
 	case SVM_EXIT_WRITE_DR7:

@@ -2483,18 +2489,18 @@ static int sev_es_validate_vmgexit(struc
 		if (!kvm_ghcb_rax_is_valid(svm) ||
 		    !kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
-		if (ghcb_get_rax(ghcb) == 0xd)
+		if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd)
 			if (!kvm_ghcb_xcr0_is_valid(svm))
 				goto vmgexit_err;
 		break;
 	case SVM_EXIT_INVD:
 		break;
 	case SVM_EXIT_IOIO:
-		if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) {
+		if (control->exit_info_1 & SVM_IOIO_STR_MASK) {
 			if (!kvm_ghcb_sw_scratch_is_valid(svm))
 				goto vmgexit_err;
 		} else {
-			if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
+			if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK))
 				if (!kvm_ghcb_rax_is_valid(svm))
 					goto vmgexit_err;
 		}

@@ -2502,7 +2508,7 @@ static int sev_es_validate_vmgexit(struc
 	case SVM_EXIT_MSR:
 		if (!kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
-		if (ghcb_get_sw_exit_info_1(ghcb)) {
+		if (control->exit_info_1) {
 			if (!kvm_ghcb_rax_is_valid(svm) ||
 			    !kvm_ghcb_rdx_is_valid(svm))
 				goto vmgexit_err;

@@ -2546,8 +2552,6 @@ static int sev_es_validate_vmgexit(struc
 	return 0;
 
 vmgexit_err:
-	vcpu = &svm->vcpu;
-
 	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    ghcb->ghcb_usage);

@@ -2845,8 +2849,6 @@ int sev_handle_vmgexit(struct kvm_vcpu *
 
 	trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb);
 
-	exit_code = ghcb_get_sw_exit_code(ghcb);
-
 	sev_es_sync_from_ghcb(svm);
 	ret = sev_es_validate_vmgexit(svm);
 	if (ret)

@@ -2855,6 +2857,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
+	exit_code = kvm_ghcb_get_sw_exit_code(control);
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);

@@ -5378,8 +5378,11 @@ nl80211_parse_mbssid_elems(struct wiphy
 	if (!wiphy->mbssid_max_interfaces)
 		return ERR_PTR(-EINVAL);
 
-	nla_for_each_nested(nl_elems, attrs, rem_elems)
+	nla_for_each_nested(nl_elems, attrs, rem_elems) {
+		if (num_elems >= 255)
+			return ERR_PTR(-EINVAL);
 		num_elems++;
+	}
 
 	elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL);
 	if (!elems)

@@ -2209,7 +2209,7 @@ static int cmac_dma_init(struct rtw89_de
 	u32 reg;
 	int ret;
 
-	if (chip_id != RTL8852A && chip_id != RTL8852B)
+	if (chip_id != RTL8852B)
 		return 0;
 
 	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);

@@ -6,7 +6,7 @@
 #include "allowedips.h"
 #include "peer.h"
 
-enum { MAX_ALLOWEDIPS_BITS = 128 };
+enum { MAX_ALLOWEDIPS_DEPTH = 129 };
 
 static struct kmem_cache *node_cache;
 

@@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_n
 		     struct allowedips_node __rcu *p, unsigned int *len)
 {
 	if (rcu_access_pointer(p)) {
-		if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS))
+		if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH))
 			return;
 		stack[(*len)++] = rcu_dereference_raw(p);
 	}

@@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_hea
 
 static void root_free_rcu(struct rcu_head *rcu)
 {
-	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = {
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = {
 		container_of(rcu, struct allowedips_node, rcu) };
 	unsigned int len = 1;
 

@@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_hea
 
 static void root_remove_peer_lists(struct allowedips_node *root)
 {
-	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root };
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root };
 	unsigned int len = 1;
 
 	while (len > 0 && (node = stack[--len])) {

@@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void)
 	wg_allowedips_remove_by_peer(&t, a, &mutex);
 	test_negative(4, a, 192, 168, 0, 1);
 
-	/* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node
+	/* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node
 	 * if something goes wrong.
 	 */
-	for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) {
-		part = cpu_to_be64(~(1LLU << (i % 64)));
-		memset(&ip, 0xff, 16);
-		memcpy((u8 *)&ip + (i < 64) * 8, &part, 8);
+	for (i = 0; i < 64; ++i) {
+		part = cpu_to_be64(~0LLU << i);
+		memset(&ip, 0xff, 8);
+		memcpy((u8 *)&ip + 8, &part, 8);
+		wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
+		memcpy(&ip, &part, 8);
+		memset((u8 *)&ip + 8, 0, 8);
 		wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
 	}
-
+	memset(&ip, 0, 16);
+	wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
 	wg_allowedips_free(&t, &mutex);
 
 	wg_allowedips_init(&t);

@@ -338,13 +338,7 @@ static void moxart_transfer_pio(struct m
 				return;
 			}
 			for (len = 0; len < remain && len < host->fifo_width;) {
-				/* SCR data must be read in big endian. */
-				if (data->mrq->cmd->opcode == SD_APP_SEND_SCR)
-					*sgp = ioread32be(host->base +
-							  REG_DATA_WINDOW);
-				else
-					*sgp = ioread32(host->base +
-							REG_DATA_WINDOW);
+				*sgp = ioread32(host->base + REG_DATA_WINDOW);
 				sgp++;
 				len += 4;
 			}

@@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_opt
 static inline int ndisc_is_useropt(const struct net_device *dev,
 				   struct nd_opt_hdr *opt)
 {
-	return opt->nd_opt_type == ND_OPT_RDNSS ||
+	return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+		opt->nd_opt_type == ND_OPT_RDNSS ||
 		opt->nd_opt_type == ND_OPT_DNSSL ||
 		opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
 		opt->nd_opt_type == ND_OPT_PREF64 ||

@@ -2367,7 +2367,7 @@ static void __mptcp_close_ssk(struct soc
 
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 
-	if (flags & MPTCP_CF_FASTCLOSE) {
+	if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
 		/* be sure to force the tcp_disconnect() path,
 		 * to generate the egress reset
 		 */

@@ -312,7 +312,6 @@ struct mptcp_sock {
 
 	u32 setsockopt_seq;
 	char		ca_name[TCP_CA_NAME_MAX];
-	struct mptcp_sock	*dl_next;
 };
 
 #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)

84 lines not on this page · raw message

@@ -404,6 +404,12 @@ enum desc_status {
 	 */
 	BUSY,
 	/*
+	 * Pause was called while descriptor was BUSY. Due to hardware
+	 * limitations, only termination is possible for descriptors
+	 * that have been paused.
+	 */
+	PAUSED,
+	/*
 	 * Sitting on the channel work_list but xfer done
 	 * by PL330 core
 	 */

@@ -2041,7 +2047,7 @@ static inline void fill_queue(struct dma
 	list_for_each_entry(desc, &pch->work_list, node) {
 
 		/* If already submitted */
-		if (desc->status == BUSY)
+		if (desc->status == BUSY || desc->status == PAUSED)
 			continue;
 
 		ret = pl330_submit_req(pch->thread, desc);

@@ -2326,6 +2332,7 @@ static int pl330_pause(struct dma_chan *
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
 	struct pl330_dmac *pl330 = pch->dmac;
+	struct dma_pl330_desc *desc;
 	unsigned long flags;
 
 	pm_runtime_get_sync(pl330->ddma.dev);

@@ -2335,6 +2342,10 @@ static int pl330_pause(struct dma_chan *
 	_stop(pch->thread);
 	spin_unlock(&pl330->lock);
 
+	list_for_each_entry(desc, &pch->work_list, node) {
+		if (desc->status == BUSY)
+			desc->status = PAUSED;
+	}
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);

@@ -2425,7 +2436,7 @@ pl330_tx_status(struct dma_chan *chan, d
 		else if (running && desc == running)
 			transferred =
 				pl330_get_current_xferred_count(pch, desc);
-		else if (desc->status == BUSY)
+		else if (desc->status == BUSY || desc->status == PAUSED)
 			/*
 			 * Busy but not running means either just enqueued,
 			 * or finished and not yet marked done

@@ -2442,6 +2453,9 @@ pl330_tx_status(struct dma_chan *chan, d
 			case DONE:
 				ret = DMA_COMPLETE;
 				break;
+			case PAUSED:
+				ret = DMA_PAUSED;
+				break;
 			case PREP:
 			case BUSY:
 				ret = DMA_IN_PROGRESS;

@@ -8,6 +8,7 @@
 #include <linux/ethtool.h>
 #include <linux/filter.h>
 #include <linux/mm.h>
+#include <linux/pci.h>
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>

@@ -1972,9 +1973,12 @@ int mana_attach(struct net_device *ndev)
 static int mana_dealloc_queues(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
+	unsigned long timeout = jiffies + 120 * HZ;
 	struct gdma_dev *gd = apc->ac->gdma_dev;
 	struct mana_txq *txq;
+	struct sk_buff *skb;
 	int i, err;
+	u32 tsleep;
 
 	if (apc->port_is_up)
 		return -EINVAL;

@@ -1990,15 +1994,40 @@ static int mana_dealloc_queues(struct ne
 	 * to false, but it doesn't matter since mana_start_xmit() drops any
 	 * new packets due to apc->port_is_up being false.
 	 *
-	 * Drain all the in-flight TX packets
+	 * Drain all the in-flight TX packets.
+	 * A timeout of 120 seconds for all the queues is used.
+	 * This will break the while loop when h/w is not responding.
+	 * This value of 120 has been decided here considering max
+	 * number of queues.
 	 */
+
 	for (i = 0; i < apc->num_queues; i++) {
 		txq = &apc->tx_qp[i].txq;
-
-		while (atomic_read(&txq->pending_sends) > 0)
-			usleep_range(1000, 2000);
+		tsleep = 1000;
+		while (atomic_read(&txq->pending_sends) > 0 &&
+		       time_before(jiffies, timeout)) {
+			usleep_range(tsleep, tsleep + 1000);
+			tsleep <<= 1;
+		}
+		if (atomic_read(&txq->pending_sends)) {
+			err = pcie_flr(to_pci_dev(gd->gdma_context->dev));
+			if (err) {
+				netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n",
+					   err, atomic_read(&txq->pending_sends),
+					   txq->gdma_txq_id);
+			}
+			break;
+		}
 	}
 
+	for (i = 0; i < apc->num_queues; i++) {
+		txq = &apc->tx_qp[i].txq;
+		while ((skb = skb_dequeue(&txq->pending_skbs))) {
+			mana_unmap_skb(skb, apc);
+			dev_kfree_skb_any(skb);
+		}
+		atomic_set(&txq->pending_sends, 0);
+	}
 	/* We're 100% sure the queues can no longer be woken up, because
 	 * we're sure now mana_poll_tx_cq() can't be running.
 	 */

index 38390d3bdcac..c08bb5c3b385 100644
@@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		kbuf.buffer = initrd;
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
-		kbuf.top_down = false;
+		kbuf.top_down = true;
 		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)

@@ -101,9 +101,9 @@ static inline u64 __raw_readq(const vola
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
  * accesses.  These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
- * fences are required to enforce this ordering.
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
  */
 /* FIXME: These are now the same as asm-generic */
 #define __io_rbr()		do {} while (0)

@@ -125,14 +125,14 @@ static inline u64 __raw_readq(const vola
 #endif
 
 /*
- * I/O memory access primitives. Reads are ordered relative to any
- * following Normal memory access. Writes are ordered relative to any prior
- * Normal memory access.  The memory barriers here are necessary as RISC-V
+ * I/O memory access primitives.  Reads are ordered relative to any following
+ * Normal memory read and delay() loop.  Writes are ordered relative to any
+ * prior Normal memory write.  The memory barriers here are necessary as RISC-V
  * doesn't define any ordering between the memory space and the I/O space.
  */
 #define __io_br()	do {} while (0)
-#define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory")
-#define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_ar(v)	({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
+#define __io_bw()	({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
 #define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })

index 5372b708fae2..38390d3bdcac 100644
@@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		 * sym, instead of searching the whole relsec.
 		 */
 		case R_RISCV_PCREL_HI20:
+		case R_RISCV_CALL_PLT:
 		case R_RISCV_CALL:
 			*(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) |
 				 ENCODE_UJTYPE_IMM(val - addr);

@@ -3504,7 +3504,8 @@ static const struct pci_device_id nvme_i
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x144d, 0xa80b),   /* Samsung PM9B1 256G and 512G */
-		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x144d, 0xa809),   /* Samsung MZALQ256HBJD 256G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1cc4, 0x6303),   /* UMIS RPJTJ512MGE1QDY 512G */

@@ -123,6 +123,7 @@ void gk104_grctx_generate_r418800(struct
 
 extern const struct gf100_grctx_func gk110_grctx;
 void gk110_grctx_generate_r419eb0(struct gf100_gr *);
+void gk110_grctx_generate_r419f78(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gk110b_grctx;
 extern const struct gf100_grctx_func gk208_grctx;

@@ -916,7 +916,9 @@ static void
 gk104_grctx_generate_r419f78(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);
+
+	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
+	nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000);
 }
 
 void

@@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf10
 	nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000);
 }
 
+void
+gk110_grctx_generate_r419f78(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+
+	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
+	nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000);
+}
+
 const struct gf100_grctx_func
 gk110_grctx = {
 	.main  = gf100_grctx_generate_main,

@@ -852,4 +861,5 @@ gk110_grctx = {
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
 	.r419eb0 = gk110_grctx_generate_r419eb0,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

@@ -101,4 +101,5 @@ gk110b_grctx = {
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
 	.r419eb0 = gk110_grctx_generate_r419eb0,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

@@ -566,4 +566,5 @@ gk208_grctx = {
 	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

@@ -991,4 +991,5 @@ gm107_grctx = {
 	.r406500 = gm107_grctx_generate_r406500,
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r419e00 = gm107_grctx_generate_r419e00,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

@@ -26,6 +26,8 @@
 #include "head.h"
 #include "ior.h"
 
+#include <drm/display/drm_dp.h>
+
 #include <subdev/bios.h>
 #include <subdev/bios/init.h>
 #include <subdev/gpio.h>

@@ -474,6 +476,50 @@ nvkm_dp_train(struct nvkm_outp *outp, u3
 	return ret;
 }
 
+/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps()
+ * converted to work inside nvkm. This is a temporary holdover until we start
+ * passing the drm_dp_aux device through NVKM
+ */
+static int
+nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp)
+{
+	struct nvkm_i2c_aux *aux = outp->dp.aux;
+	u8 dpcd_ext[DP_RECEIVER_CAP_SIZE];
+	int ret;
+
+	ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Prior to DP1.3 the bit represented by
+	 * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
+	 * If it is set DP_DPCD_REV at 0000h could be at a value less than
+	 * the true capability of the panel. The only way to check is to
+	 * then compare 0000h and 2200h.
+	 */
+	if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+	      DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
+		return 0;
+
+	ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext));
+	if (ret < 0)
+		return ret;
+
+	if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
+		OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n",
+			 outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]);
+		return 0;
+	}
+
+	if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)))
+		return 0;
+
+	memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext));
+
+	return 0;
+}
+
 void
 nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior)
 {

@@ -630,7 +676,7 @@ nvkm_dp_enable(struct nvkm_outp *outp, b
 			memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr));
 		}
 
-		if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) {
+		if (!nvkm_dp_read_dpcd_caps(outp)) {
 			const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 };
 			const u8 *rate;
 			int rate_max;

@@ -622,7 +622,13 @@ int drm_gem_shmem_mmap(struct drm_gem_sh
 	int ret;
 
 	if (obj->import_attach) {
+		/* Reset both vm_ops and vm_private_data, so we don't end up with
+		 * vm_ops pointing to our implementation if the dma-buf backend
+		 * doesn't set those fields.
+		 */
 		vma->vm_private_data = NULL;
+		vma->vm_ops = NULL;
+
 		ret = dma_buf_mmap(obj->dma_buf, vma, 0);
 
 		/* Drop the reference drm_gem_mmap_obj() acquired.*/

@@ -287,7 +287,7 @@ static int amdgpu_cs_pass1(struct amdgpu
 
 	if (!p->gang_size) {
 		ret = -EINVAL;
-		goto free_partial_kdata;
+		goto free_all_kdata;
 	}
 
 	for (i = 0; i < p->gang_size; ++i) {

@@ -357,8 +357,11 @@ void dpp3_set_cursor_attributes(
 	int cur_rom_en = 0;
 
 	if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
-		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA)
-		cur_rom_en = 1;
+		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
+		if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
+			cur_rom_en = 1;
+		}
+	}
 
 	REG_UPDATE_3(CURSOR0_CONTROL,
 			CUR0_MODE, color_format,

@@ -242,6 +242,7 @@ extern int amdgpu_num_kcq;
 
 #define AMDGPU_VCNFW_LOG_SIZE (32 * 1024)
 extern int amdgpu_vcnfw_log;
+extern int amdgpu_sg_display;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)

@@ -185,6 +185,7 @@ int amdgpu_num_kcq = -1;
 int amdgpu_smartshift_bias;
 int amdgpu_use_xgmi_p2p = 1;
 int amdgpu_vcnfw_log;
+int amdgpu_sg_display = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 

@@ -930,6 +931,16 @@ MODULE_PARM_DESC(vcnfw_log, "Enable vcnf
 module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444);
 
 /**
+ * DOC: sg_display (int)
+ * Disable S/G (scatter/gather) display (i.e., display from system memory).
+ * This option is only relevant on APUs.  Set this option to 0 to disable
+ * S/G display if you experience flickering or other issues under memory
+ * pressure and report the issue.
+ */
+MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)");
+module_param_named(sg_display, amdgpu_sg_display, int, 0444);
+
+/**
  * DOC: smu_pptable_id (int)
  * Used to override pptable id. id = 0 use VBIOS pptable.
  * id > 0 use the soft pptable with specicfied id.

@@ -1634,6 +1634,9 @@ static int amdgpu_dm_init(struct amdgpu_
 		}
 		break;
 	}
+	if (init_data.flags.gpu_vm_support &&
+	    (amdgpu_sg_display == 0))
+		init_data.flags.gpu_vm_support = false;
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;

@@ -1263,6 +1263,7 @@ int amdgpu_device_gpu_recover(struct amd
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev);
 bool amdgpu_device_pcie_dynamic_switching_supported(void);
 bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
 bool amdgpu_device_aspm_support_quirk(void);

@@ -1334,6 +1334,32 @@ bool amdgpu_device_need_post(struct amdg
 }
 
 /*
+ * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
+ * Disable S/G on such systems until we have a proper fix.
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
+ */
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
+{
+	switch (amdgpu_sg_display) {
+	case -1:
+		break;
+	case 0:
+		return false;
+	case 1:
+		return true;
+	default:
+		return false;
+	}
+	if ((totalram_pages() << (PAGE_SHIFT - 10)) +
+	    (adev->gmc.real_vram_size / 1024) >= 64000000) {
+		DRM_WARN("Disabling S/G due to >=64GB RAM\n");
+		return false;
+	}
+	return true;
+}
+
+/*
  * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
  * speed switching. Until we have confirmation from Intel that a specific host
  * supports it, it's safer that we keep it disabled for all.

@@ -1634,9 +1634,8 @@ static int amdgpu_dm_init(struct amdgpu_
 		}
 		break;
 	}
-	if (init_data.flags.gpu_vm_support &&
-	    (amdgpu_sg_display == 0))
-		init_data.flags.gpu_vm_support = false;
+	if (init_data.flags.gpu_vm_support)
+		init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev);
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;

@@ -1141,6 +1141,11 @@ static bool detect_link_and_local_sink(s
 					(link->dpcd_caps.dongle_type !=
 							DISPLAY_DONGLE_DP_HDMI_CONVERTER))
 				converter_disable_audio = true;
+
+			/* limited link rate to HBR3 for DPIA until we implement USB4 V2 */
+			if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA &&
+					link->reported_link_cap.link_rate > LINK_RATE_HIGH3)
+				link->reported_link_cap.link_rate = LINK_RATE_HIGH3;
 			break;
 		}
 

@@ -152,6 +152,30 @@ int dt_idle_pd_init_topology(struct devi
 	return 0;
 }
 
+int dt_idle_pd_remove_topology(struct device_node *np)
+{
+	struct device_node *node;
+	struct of_phandle_args child, parent;
+	int ret;
+
+	for_each_child_of_node(np, node) {
+		if (of_parse_phandle_with_args(node, "power-domains",
+					"#power-domain-cells", 0, &parent))
+			continue;
+
+		child.np = node;
+		child.args_count = 0;
+		ret = of_genpd_remove_subdomain(&parent, &child);
+		of_node_put(parent.np);
+		if (ret) {
+			of_node_put(node);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 struct device *dt_idle_attach_cpu(int cpu, const char *name)
 {
 	struct device *dev;

@@ -14,6 +14,8 @@ struct generic_pm_domain *dt_idle_pd_all
 
 int dt_idle_pd_init_topology(struct device_node *np);
 
+int dt_idle_pd_remove_topology(struct device_node *np);
+
 struct device *dt_idle_attach_cpu(int cpu, const char *name);
 
 void dt_idle_detach_cpu(struct device *dev);

@@ -35,6 +37,11 @@ static inline int dt_idle_pd_init_topolo
 {
 	return 0;
 }
+
+static inline int dt_idle_pd_remove_topology(struct device_node *np)
+{
+	return 0;
+}
 
 static inline struct device *dt_idle_attach_cpu(int cpu, const char *name)
 {

@@ -17,12 +17,13 @@
 enum chips {pfe1100, pfe3000};
 
 /*
- * Disable status check for pfe3000 devices, because some devices report
- * communication error (invalid command) for VOUT_MODE command (0x20)
- * although correct VOUT_MODE (0x16) is returned: it leads to incorrect
- * exponent in linear mode.
+ * Disable status check because some devices report communication error
+ * (invalid command) for VOUT_MODE command (0x20) although the correct
+ * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear
+ * mode.
+ * This affects both pfe3000 and pfe1100.
  */
-static struct pmbus_platform_data pfe3000_plat_data = {
+static struct pmbus_platform_data pfe_plat_data = {
 	.flags = PMBUS_SKIP_STATUS_CHECK,
 };
 

@@ -94,16 +95,15 @@ static int pfe_pmbus_probe(struct i2c_cl
 	int model;
 
 	model = (int)i2c_match_id(pfe_device_id, client)->driver_data;
+	client->dev.platform_data = &pfe_plat_data;
 
 	/*
 	 * PFE3000-12-069RA devices may not stay in page 0 during device
 	 * probe which leads to probe failure (read status word failed).
 	 * So let's set the device to page 0 at the beginning.
 	 */
-	if (model == pfe3000) {
-		client->dev.platform_data = &pfe3000_plat_data;
+	if (model == pfe3000)
 		i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0);
-	}
 
 	return pmbus_do_probe(client, &pfe_driver_info[model]);
 }

@@ -177,7 +177,7 @@ void regression1_test(void)
 	nr_threads = 2;
 	pthread_barrier_init(&worker_barrier, NULL, nr_threads);
 
-	threads = malloc(nr_threads * sizeof(pthread_t *));
+	threads = malloc(nr_threads * sizeof(*threads));
 
 	for (i = 0; i < nr_threads; i++) {
 		arg = i;

@@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *i
 
 int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 	struct buffer_head *ibh;
 	int err;
 
+	/*
+	 * Do not dirty inodes after the log writer has been detached
+	 * and its nilfs_root struct has been freed.
+	 */
+	if (unlikely(nilfs_purging(nilfs)))
+		return 0;
+
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
 		nilfs_warn(inode->i_sb,

@@ -2843,6 +2843,7 @@ void nilfs_detach_log_writer(struct supe
 		nilfs_segctor_destroy(nilfs->ns_writer);
 		nilfs->ns_writer = NULL;
 	}
+	set_nilfs_purging(nilfs);
 
 	/* Force to free the list of dirty files */
 	spin_lock(&nilfs->ns_inode_lock);

@@ -2855,4 +2856,5 @@ void nilfs_detach_log_writer(struct supe
 	up_write(&nilfs->ns_segctor_sem);
 
 	nilfs_dispose_list(nilfs, &garbage_list, 1);
+	clear_nilfs_purging(nilfs);
 }

@@ -29,6 +29,7 @@ enum {
 	THE_NILFS_DISCONTINUED,	/* 'next' pointer chain has broken */
 	THE_NILFS_GC_RUNNING,	/* gc process is running */
 	THE_NILFS_SB_DIRTY,	/* super block is dirty */
+	THE_NILFS_PURGING,	/* disposing dirty files for cleanup */
 };
 
 /**

@@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init)
 THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
 
 /*
  * Mount option operations

@@ -139,6 +139,8 @@ enum amd_pp_sensors {
 	AMDGPU_PP_SENSOR_MIN_FAN_RPM,
 	AMDGPU_PP_SENSOR_MAX_FAN_RPM,
 	AMDGPU_PP_SENSOR_VCN_POWER_STATE,
+	AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK,
+	AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK,
 };
 
 enum amd_pp_task {

@@ -2520,6 +2520,14 @@ static int smu_read_sensor(void *handle,
 		*((uint32_t *)data) = pstate_table->uclk_pstate.standard * 100;
 		*size = 4;
 		break;
+	case AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK:
+		*((uint32_t *)data) = pstate_table->gfxclk_pstate.peak * 100;
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK:
+		*((uint32_t *)data) = pstate_table->uclk_pstate.peak * 100;
+		*size = 4;
+		break;
 	case AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK:
 		ret = smu_feature_get_enabled_mask(smu, (uint64_t *)data);
 		*size = 8;

@@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal {
 	int                max_mem_crit_temp;
 	/* memory max emergency(shutdown) temp */
 	int                max_mem_emergency_temp;
+	/* SWCTF threshold */
+	int                sw_ctf_threshold;
 	/* was last interrupt low to high or high to low */
 	bool               high_to_low;
 	/* interrupt source */

@@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct
 		TEMP_RANGE_MAX,
 		TEMP_RANGE_MIN,
 		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX};
+		TEMP_RANGE_MAX,
+		0};
 	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (!hwmgr->not_vf)

@@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct
 	adev->pm.dpm.thermal.min_mem_temp = range.mem_min;
 	adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max;
 	adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max;
+	adev->pm.dpm.thermal.sw_ctf_threshold = range.sw_ctf_threshold;
 
 	return ret;
 }

@@ -5381,6 +5381,8 @@ static int smu7_get_thermal_temperature_
 		thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	thermal_data->sw_ctf_threshold = thermal_data->max;
+
 	return 0;
 }
 

@@ -5221,6 +5221,9 @@ static int vega10_get_thermal_temperatur
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	struct phm_ppt_v2_information *pp_table_info =
+		(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
 
 	memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange));
 

@@ -5237,6 +5240,13 @@ static int vega10_get_thermal_temperatur
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit &&
+	    tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP)
+		thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp;
+	else
+		thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
+	thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
 	return 0;
 }
 

@@ -2742,6 +2742,8 @@ static int vega12_notify_cac_buffer_info
 static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);

@@ -2760,6 +2762,8 @@ static int vega12_get_thermal_temperatur
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }

@@ -4213,6 +4213,8 @@ static int vega20_notify_cac_buffer_info
 static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);

@@ -4231,6 +4233,8 @@ static int vega20_get_thermal_temperatur
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }

@@ -131,6 +131,7 @@ struct PP_TemperatureRange {
 	int mem_min;
 	int mem_crit_max;
 	int mem_emergency_max;
+	int sw_ctf_threshold;
 };
 
 struct PP_StateValidationBlock {

@@ -769,10 +769,16 @@ static int pp_dpm_read_sensor(void *hand
 
 	switch (idx) {
 	case AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK:
-		*((uint32_t *)value) = hwmgr->pstate_sclk;
+		*((uint32_t *)value) = hwmgr->pstate_sclk * 100;
 		return 0;
 	case AMDGPU_PP_SENSOR_STABLE_PSTATE_MCLK:
-		*((uint32_t *)value) = hwmgr->pstate_mclk;
+		*((uint32_t *)value) = hwmgr->pstate_mclk * 100;
+		return 0;
+	case AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK:
+		*((uint32_t *)value) = hwmgr->pstate_sclk_peak * 100;
+		return 0;
+	case AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK:
+		*((uint32_t *)value) = hwmgr->pstate_mclk_peak * 100;
 		return 0;
 	case AMDGPU_PP_SENSOR_MIN_FAN_RPM:
 		*((uint32_t *)value) = hwmgr->thermal_controller.fanInfo.ulMinRPM;

@@ -375,6 +375,17 @@ static int smu10_enable_gfx_off(struct p
 	return 0;
 }
 
+static void smu10_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr)
+{
+	hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK;
+	hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK;
+
+	smum_send_msg_to_smc(hwmgr,
+			     PPSMC_MSG_GetMaxGfxclkFrequency,
+			     &hwmgr->pstate_sclk_peak);
+	hwmgr->pstate_mclk_peak = SMU10_UMD_PSTATE_PEAK_FCLK;
+}
+
 static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;

@@ -398,6 +409,8 @@ static int smu10_enable_dpm_tasks(struct
 			return ret;
 	}
 
+	smu10_populate_umdpstate_clocks(hwmgr);
+
 	return 0;
 }
 

@@ -574,9 +587,6 @@ static int smu10_hwmgr_backend_init(stru
 
 	hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50;
 
-	hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK * 100;
-	hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK * 100;
-
 	/* enable the pp_od_clk_voltage sysfs file */
 	hwmgr->od_enabled = 1;
 	/* disabled fine grain tuning function by default */

122 lines not on this page · raw message

@@ -1016,6 +1016,18 @@ static void smu8_reset_acp_boot_level(st
 	data->acp_boot_level = 0xff;
 }
 
+static void smu8_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr)
+{
+	struct phm_clock_voltage_dependency_table *table =
+				hwmgr->dyn_state.vddc_dependency_on_sclk;
+
+	hwmgr->pstate_sclk = table->entries[0].clk / 100;
+	hwmgr->pstate_mclk = 0;
+
+	hwmgr->pstate_sclk_peak = table->entries[table->count - 1].clk / 100;
+	hwmgr->pstate_mclk_peak = 0;
+}
+
 static int smu8_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	smu8_program_voting_clients(hwmgr);

@@ -1024,6 +1036,8 @@ static int smu8_enable_dpm_tasks(struct
 	smu8_program_bootup_state(hwmgr);
 	smu8_reset_acp_boot_level(hwmgr);
 
+	smu8_populate_umdpstate_clocks(hwmgr);
+
 	return 0;
 }
 

@@ -1167,8 +1181,6 @@ static int smu8_phm_unforce_dpm_levels(s
 
 	data->sclk_dpm.soft_min_clk = table->entries[0].clk;
 	data->sclk_dpm.hard_min_clk = table->entries[0].clk;
-	hwmgr->pstate_sclk = table->entries[0].clk;
-	hwmgr->pstate_mclk = 0;
 
 	level = smu8_get_max_sclk_level(hwmgr) - 1;
 

@@ -3008,6 +3008,30 @@ static int vega10_enable_disable_PCC_lim
 	return 0;
 }
 
+static void vega10_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr)
+{
+	struct phm_ppt_v2_information *table_info =
+			(struct phm_ppt_v2_information *)(hwmgr->pptable);
+
+	if (table_info->vdd_dep_on_sclk->count > VEGA10_UMD_PSTATE_GFXCLK_LEVEL &&
+	    table_info->vdd_dep_on_mclk->count > VEGA10_UMD_PSTATE_MCLK_LEVEL) {
+		hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[VEGA10_UMD_PSTATE_GFXCLK_LEVEL].clk;
+		hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[VEGA10_UMD_PSTATE_MCLK_LEVEL].clk;
+	} else {
+		hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[0].clk;
+		hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[0].clk;
+	}
+
+	hwmgr->pstate_sclk_peak = table_info->vdd_dep_on_sclk->entries[table_info->vdd_dep_on_sclk->count - 1].clk;
+	hwmgr->pstate_mclk_peak = table_info->vdd_dep_on_mclk->entries[table_info->vdd_dep_on_mclk->count - 1].clk;
+
+	/* make sure the output is in Mhz */
+	hwmgr->pstate_sclk /= 100;
+	hwmgr->pstate_mclk /= 100;
+	hwmgr->pstate_sclk_peak /= 100;
+	hwmgr->pstate_mclk_peak /= 100;
+}
+
 static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;

@@ -3082,6 +3106,8 @@ static int vega10_enable_dpm_tasks(struc
 				    result = tmp_result);
 	}
 
+	vega10_populate_umdpstate_clocks(hwmgr);
+
 	return result;
 }
 

@@ -4169,8 +4195,6 @@ static int vega10_get_profiling_clk_mask
 		*sclk_mask = VEGA10_UMD_PSTATE_GFXCLK_LEVEL;
 		*soc_mask = VEGA10_UMD_PSTATE_SOCCLK_LEVEL;
 		*mclk_mask = VEGA10_UMD_PSTATE_MCLK_LEVEL;
-		hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[VEGA10_UMD_PSTATE_GFXCLK_LEVEL].clk;
-		hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[VEGA10_UMD_PSTATE_MCLK_LEVEL].clk;
 	}
 
 	if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {

@@ -4281,9 +4305,6 @@ static int vega10_dpm_force_dpm_level(st
 	uint32_t mclk_mask = 0;
 	uint32_t soc_mask = 0;
 
-	if (hwmgr->pstate_sclk == 0)
-		vega10_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
-
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
 		ret = vega10_force_dpm_highest(hwmgr);

@@ -1026,6 +1026,25 @@ static int vega12_get_all_clock_ranges(s
 	return 0;
 }
 
+static void vega12_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *gfx_dpm_table = &(data->dpm_table.gfx_table);
+	struct vega12_single_dpm_table *mem_dpm_table = &(data->dpm_table.mem_table);
+
+	if (gfx_dpm_table->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
+	    mem_dpm_table->count > VEGA12_UMD_PSTATE_MCLK_LEVEL) {
+		hwmgr->pstate_sclk = gfx_dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+		hwmgr->pstate_mclk = mem_dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+	} else {
+		hwmgr->pstate_sclk = gfx_dpm_table->dpm_levels[0].value;
+		hwmgr->pstate_mclk = mem_dpm_table->dpm_levels[0].value;
+	}
+
+	hwmgr->pstate_sclk_peak = gfx_dpm_table->dpm_levels[gfx_dpm_table->count].value;
+	hwmgr->pstate_mclk_peak = mem_dpm_table->dpm_levels[mem_dpm_table->count].value;
+}
+
 static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;

@@ -1077,6 +1096,9 @@ static int vega12_enable_dpm_tasks(struc
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to setup default DPM tables!",
 			return result);
+
+	vega12_populate_umdpstate_clocks(hwmgr);
+
 	return result;
 }
 

@@ -1555,26 +1555,23 @@ static int vega20_set_mclk_od(
 	return 0;
 }
 
-static int vega20_populate_umdpstate_clocks(
-		struct pp_hwmgr *hwmgr)
+static void vega20_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr)
 {
 	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
 	struct vega20_single_dpm_table *gfx_table = &(data->dpm_table.gfx_table);
 	struct vega20_single_dpm_table *mem_table = &(data->dpm_table.mem_table);
 
-	hwmgr->pstate_sclk = gfx_table->dpm_levels[0].value;
-	hwmgr->pstate_mclk = mem_table->dpm_levels[0].value;
-
 	if (gfx_table->count > VEGA20_UMD_PSTATE_GFXCLK_LEVEL &&
 	    mem_table->count > VEGA20_UMD_PSTATE_MCLK_LEVEL) {
 		hwmgr->pstate_sclk = gfx_table->dpm_levels[VEGA20_UMD_PSTATE_GFXCLK_LEVEL].value;
 		hwmgr->pstate_mclk = mem_table->dpm_levels[VEGA20_UMD_PSTATE_MCLK_LEVEL].value;
+	} else {
+		hwmgr->pstate_sclk = gfx_table->dpm_levels[0].value;
+		hwmgr->pstate_mclk = mem_table->dpm_levels[0].value;
 	}
 
-	hwmgr->pstate_sclk = hwmgr->pstate_sclk * 100;
-	hwmgr->pstate_mclk = hwmgr->pstate_mclk * 100;
-
-	return 0;
+	hwmgr->pstate_sclk_peak = gfx_table->dpm_levels[gfx_table->count - 1].value;
+	hwmgr->pstate_mclk_peak = mem_table->dpm_levels[mem_table->count - 1].value;
 }
 
 static int vega20_get_max_sustainable_clock(struct pp_hwmgr *hwmgr,

@@ -1753,10 +1750,7 @@ static int vega20_enable_dpm_tasks(struc
 			"[EnableDPMTasks] Failed to initialize odn settings!",
 			return result);
 
-	result = vega20_populate_umdpstate_clocks(hwmgr);
-	PP_ASSERT_WITH_CODE(!result,
-			"[EnableDPMTasks] Failed to populate umdpstate clocks!",
-			return result);
+	vega20_populate_umdpstate_clocks(hwmgr);
 
 	result = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetPptLimit,
 			POWER_SOURCE_AC << 16, &hwmgr->default_power_limit);

@@ -809,6 +809,8 @@ struct pp_hwmgr {
 	uint32_t workload_prority[Workload_Policy_Max];
 	uint32_t workload_setting[Workload_Policy_Max];
 	bool gfxoff_state_changed_by_workload;
+	uint32_t pstate_sclk_peak;
+	uint32_t pstate_mclk_peak;
 };
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr);

@@ -284,6 +284,9 @@ extern int amdgpu_sg_display;
 #define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
 #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
 
+/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */
+#define AMDGPU_SWCTF_EXTRA_DELAY		50
+
 struct amdgpu_device;
 struct amdgpu_irq_src;
 struct amdgpu_fpriv;

78 lines not on this page · raw message

@@ -603,21 +603,17 @@ int phm_irq_process(struct amdgpu_device
 			   struct amdgpu_irq_src *source,
 			   struct amdgpu_iv_entry *entry)
 {
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 	uint32_t client_id = entry->client_id;
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) {
 		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) {
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
-		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
+		} else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
 			dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 			/*
 			 * HW CTF just occurred. Shutdown to prevent further damage.

@@ -626,15 +622,10 @@ int phm_irq_process(struct amdgpu_device
 			orderly_poweroff(true);
 		}
 	} else if (client_id == SOC15_IH_CLIENTID_THM) {
-		if (src_id == 0) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else
+		if (src_id == 0)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		else
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
 	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
 		dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");

@@ -811,6 +811,8 @@ struct pp_hwmgr {
 	bool gfxoff_state_changed_by_workload;
 	uint32_t pstate_sclk_peak;
 	uint32_t pstate_mclk_peak;
+
+	struct delayed_work swctf_delayed_work;
 };
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr);

@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/reboot.h>
 
 #include "amdgpu.h"
 #include "amdgpu_smu.h"

@@ -1061,6 +1062,34 @@ static void smu_interrupt_work_fn(struct
 		smu->ppt_funcs->interrupt_work(smu);
 }
 
+static void smu_swctf_delayed_work_handler(struct work_struct *work)
+{
+	struct smu_context *smu =
+		container_of(work, struct smu_context, swctf_delayed_work.work);
+	struct smu_temperature_range *range =
+				&smu->thermal_range;
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t hotspot_tmp, size;
+
+	/*
+	 * If the hotspot temperature is confirmed as below SW CTF setting point
+	 * after the delay enforced, nothing will be done.
+	 * Otherwise, a graceful shutdown will be performed to prevent further damage.
+	 */
+	if (range->software_shutdown_temp &&
+	    smu->ppt_funcs->read_sensor &&
+	    !smu->ppt_funcs->read_sensor(smu,
+					 AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+					 &hotspot_tmp,
+					 &size) &&
+	    hotspot_tmp / 1000 < range->software_shutdown_temp)
+		return;
+
+	dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+	dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+	orderly_poweroff(true);
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;

@@ -1109,6 +1138,9 @@ static int smu_sw_init(void *handle)
 		return ret;
 	}
 
+	INIT_DELAYED_WORK(&smu->swctf_delayed_work,
+			  smu_swctf_delayed_work_handler);
+
 	ret = smu_smc_table_sw_init(smu);
 	if (ret) {
 		dev_err(adev->dev, "Failed to sw init smc table!\n");

@@ -1581,6 +1613,8 @@ static int smu_smc_hw_cleanup(struct smu
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&smu->swctf_delayed_work);
+
 	ret = smu_disable_dpms(smu);
 	if (ret) {
 		dev_err(adev->dev, "Fail to disable dpm features!\n");

@@ -573,6 +573,8 @@ struct smu_context
 	u32 debug_param_reg;
 	u32 debug_msg_reg;
 	u32 debug_resp_reg;
+
+	struct delayed_work		swctf_delayed_work;
 };
 
 struct i2c_adapter;

@@ -1438,13 +1438,8 @@ static int smu_v11_0_irq_process(struct
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 		break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");

@@ -1386,13 +1386,8 @@ static int smu_v13_0_irq_process(struct
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 			break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");

@@ -1942,6 +1942,9 @@ enum dc_status dc_commit_streams(struct
 	struct pipe_ctx *pipe;
 	bool handle_exit_odm2to1 = false;
 
+	if (dc->ctx->dce_environment == DCE_ENV_VIRTUAL_HW)
+		return res;
+
 	if (!streams_changed(dc, streams, stream_count))
 		return res;
 

@@ -1987,21 +1987,17 @@ enum dc_status dc_commit_streams(struct
 
 	dc_resource_state_copy_construct_current(dc, context);
 
-	/*
-	 * Previous validation was perfomred with fast_validation = true and
-	 * the full DML state required for hardware programming was skipped.
-	 *
-	 * Re-validate here to calculate these parameters / watermarks.
-	 */
-	res = dc_validate_global_state(dc, context, false);
+	res = dc_validate_with_context(dc, set, stream_count, context, false);
 	if (res != DC_OK) {
-		DC_LOG_ERROR("DC commit global validation failure: %s (%d)",
-			     dc_status_to_str(res), res);
-		return res;
+		BREAK_TO_DEBUGGER();
+		goto fail;
 	}
 
 	res = dc_commit_state_no_check(dc, context);
 
+fail:
+	dc_release_state(context);
+
 context_alloc_fail:
 
 	DC_LOG_DC("%s Finished.\n", __func__);

235 lines not on this page · raw message

@@ -1298,6 +1298,12 @@ enum dc_status dc_validate_plane(struct
 
 void get_clock_requirements_for_state(struct dc_state *state, struct AsicStateEx *info);
 
+enum dc_status dc_validate_with_context(struct dc *dc,
+					const struct dc_validation_set set[],
+					int set_count,
+					struct dc_state *context,
+					bool fast_validate);
+
 bool dc_set_generic_gpio_for_stereo(bool enable,
 		struct gpio_service *gpio_service);