Merge tag 'v6.18-rc5' into objtool/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 130 insertions, 118 deletions

diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index a40176b62eb5..3d0a4768d603 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -34,62 +34,6 @@ struct pci_dev *amd_node_get_func(u16 node, u8 func)
 	return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func));
 }
 
-#define DF_BLK_INST_CNT		0x040
-#define	DF_CFG_ADDR_CNTL_LEGACY	0x084
-#define	DF_CFG_ADDR_CNTL_DF4	0xC04
-
-#define DF_MAJOR_REVISION	GENMASK(27, 24)
-
-static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0)
-{
-	u32 reg;
-
-	/*
-	 * Revision fields added for DF4 and later.
-	 *
-	 * Major revision of '0' is found pre-DF4. Field is Read-as-Zero.
-	 */
-	if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, &reg))
-		return 0;
-
-	if (reg & DF_MAJOR_REVISION)
-		return DF_CFG_ADDR_CNTL_DF4;
-
-	return DF_CFG_ADDR_CNTL_LEGACY;
-}
-
-struct pci_dev *amd_node_get_root(u16 node)
-{
-	struct pci_dev *root;
-	u16 cntl_off;
-	u8 bus;
-
-	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
-		return NULL;
-
-	/*
-	 * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl)
-	 * Bits [7:0] (SecBusNum) holds the bus number of the root device for
-	 * this Data Fabric instance. The segment, device, and function will be 0.
-	 */
-	struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0);
-	if (!df_f0)
-		return NULL;
-
-	cntl_off = get_cfg_addr_cntl_offset(df_f0);
-	if (!cntl_off)
-		return NULL;
-
-	if (pci_read_config_byte(df_f0, cntl_off, &bus))
-		return NULL;
-
-	/* Grab the pointer for the actual root device instance. */
-	root = pci_get_domain_bus_and_slot(0, bus, 0);
-
-	pci_dbg(root, "is root for AMD node %u\n", node);
-	return root;
-}
-
 static struct pci_dev **amd_roots;
 
 /* Protect the PCI config register pairs used for SMN. */
@@ -274,51 +218,21 @@ DEFINE_SHOW_STORE_ATTRIBUTE(smn_node);
 DEFINE_SHOW_STORE_ATTRIBUTE(smn_address);
 DEFINE_SHOW_STORE_ATTRIBUTE(smn_value);
 
-static int amd_cache_roots(void)
-{
-	u16 node, num_nodes = amd_num_nodes();
-
-	amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL);
-	if (!amd_roots)
-		return -ENOMEM;
-
-	for (node = 0; node < num_nodes; node++)
-		amd_roots[node] = amd_node_get_root(node);
-
-	return 0;
-}
-
-static int reserve_root_config_spaces(void)
+static struct pci_dev *get_next_root(struct pci_dev *root)
 {
-	struct pci_dev *root = NULL;
-	struct pci_bus *bus = NULL;
-
-	while ((bus = pci_find_next_bus(bus))) {
-		/* Root device is Device 0 Function 0 on each Primary Bus. */
-		root = pci_get_slot(bus, 0);
-		if (!root)
+	while ((root = pci_get_class(PCI_CLASS_BRIDGE_HOST << 8, root))) {
+		/* Root device is Device 0 Function 0. */
+		if (root->devfn)
 			continue;
 
 		if (root->vendor != PCI_VENDOR_ID_AMD &&
 		    root->vendor != PCI_VENDOR_ID_HYGON)
 			continue;
 
-		pci_dbg(root, "Reserving PCI config space\n");
-
-		/*
-		 * There are a few SMN index/data pairs and other registers
-		 * that shouldn't be accessed by user space.
-		 * So reserve the entire PCI config space for simplicity rather
-		 * than covering specific registers piecemeal.
-		 */
-		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
-			pci_err(root, "Failed to reserve config space\n");
-			return -EEXIST;
-		}
+		break;
 	}
 
-	smn_exclusive = true;
-	return 0;
+	return root;
 }
 
 static bool enable_dfs;
@@ -332,7 +246,8 @@ __setup("amd_smn_debugfs_enable", amd_smn_enable_dfs);
 
 static int __init amd_smn_init(void)
 {
-	int err;
+	u16 count, num_roots, roots_per_node, node, num_nodes;
+	struct pci_dev *root;
 
 	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
 		return 0;
@@ -342,13 +257,48 @@ static int __init amd_smn_init(void)
 	if (amd_roots)
 		return 0;
 
-	err = amd_cache_roots();
-	if (err)
-		return err;
+	num_roots = 0;
+	root = NULL;
+	while ((root = get_next_root(root))) {
+		pci_dbg(root, "Reserving PCI config space\n");
 
-	err = reserve_root_config_spaces();
-	if (err)
-		return err;
+		/*
+		 * There are a few SMN index/data pairs and other registers
+		 * that shouldn't be accessed by user space. So reserve the
+		 * entire PCI config space for simplicity rather than covering
+		 * specific registers piecemeal.
+		 */
+		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
+			pci_err(root, "Failed to reserve config space\n");
+			return -EEXIST;
+		}
+
+		num_roots++;
+	}
+
+	pr_debug("Found %d AMD root devices\n", num_roots);
+
+	if (!num_roots)
+		return -ENODEV;
+
+	num_nodes = amd_num_nodes();
+	amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL);
+	if (!amd_roots)
+		return -ENOMEM;
+
+	roots_per_node = num_roots / num_nodes;
+
+	count = 0;
+	node = 0;
+	root = NULL;
+	while (node < num_nodes && (root = get_next_root(root))) {
+		/* Use one root for each node and skip the rest. */
+		if (count++ % roots_per_node)
+			continue;
+
+		pci_dbg(root, "is root for AMD node %u\n", node);
+		amd_roots[node++] = root;
+	}
 
 	if (enable_dfs) {
 		debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir);
@@ -358,6 +308,8 @@ static int __init amd_smn_init(void)
 		debugfs_create_file("value",	0600, debugfs_dir, NULL, &smn_value_fops);
 	}
 
+	smn_exclusive = true;
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5398db4dedb4..2ba9f2d42d8c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -516,7 +516,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
 		case 0x50 ... 0x5f:
-		case 0x90 ... 0xaf:
+		case 0x80 ... 0xaf:
 		case 0xc0 ... 0xcf:
 			setup_force_cpu_cap(X86_FEATURE_ZEN6);
 			break;
@@ -1035,8 +1035,19 @@ static void init_amd_zen4(struct cpuinfo_x86 *c)
 	}
 }
 
+static const struct x86_cpu_id zen5_rdseed_microcode[] = {
+	ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a),
+	ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054),
+	{},
+};
+
 static void init_amd_zen5(struct cpuinfo_x86 *c)
 {
+	if (!x86_match_min_microcode_rev(zen5_rdseed_microcode)) {
+		clear_cpu_cap(c, X86_FEATURE_RDSEED);
+		msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+		pr_emerg_once("RDSEED32 is broken. Disabling the corresponding CPUID bit.\n");
+	}
 }
 
 static void init_amd(struct cpuinfo_x86 *c)
@@ -1355,11 +1366,23 @@ static __init int print_s5_reset_status_mmio(void)
 		return 0;
 
 	value = ioread32(addr);
-	iounmap(addr);
 
 	/* Value with "all bits set" is an error response and should be ignored. */
-	if (value == U32_MAX)
+	if (value == U32_MAX) {
+		iounmap(addr);
 		return 0;
+	}
+
+	/*
+	 * Clear all reason bits so they won't be retained if the next reset
+	 * does not update the register. Besides, some bits are never cleared by
+	 * hardware so it's software's responsibility to clear them.
+	 *
+	 * Writing the value back effectively clears all reason bits as they are
+	 * write-1-to-clear.
+	 */
+	iowrite32(value, addr);
+	iounmap(addr);
 
 	for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
 		if (!(value & BIT(i)))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6a526ae1fe99..d7fa03bf51b4 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1463,7 +1463,9 @@ static void __init retbleed_update_mitigation(void)
 			break;
 		default:
 			if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) {
-				pr_err(RETBLEED_INTEL_MSG);
+				if (retbleed_mitigation != RETBLEED_MITIGATION_NONE)
+					pr_err(RETBLEED_INTEL_MSG);
+
 				retbleed_mitigation = RETBLEED_MITIGATION_NONE;
 			}
 		}
@@ -1825,13 +1827,6 @@ void unpriv_ebpf_notify(int new_state)
 }
 #endif
 
-static inline bool match_option(const char *arg, int arglen, const char *opt)
-{
-	int len = strlen(opt);
-
-	return len == arglen && !strncmp(arg, opt, len);
-}
-
 /* The kernel command line selection for spectre v2 */
 enum spectre_v2_mitigation_cmd {
 	SPECTRE_V2_CMD_NONE,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c7d3512914ca..02d97834a1d4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -78,6 +78,10 @@
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+/* Used for modules: built-in code uses runtime constants */
+unsigned long USER_PTR_MAX;
+EXPORT_SYMBOL(USER_PTR_MAX);
+
 u32 elf_hwcap2 __read_mostly;
 
 /* Number of siblings per CPU package */
@@ -2579,7 +2583,7 @@ void __init arch_cpu_finalize_init(void)
 	alternative_instructions();
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
-		unsigned long USER_PTR_MAX = TASK_SIZE_MAX;
+		USER_PTR_MAX = TASK_SIZE_MAX;
 
 		/*
 		 * Enable this when LAM is gated on LASS support
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index cdce885e2fd5..dc82153009da 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -194,7 +194,7 @@ static bool need_sha_check(u32 cur_rev)
 	}
 
 	switch (cur_rev >> 8) {
-	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x80012: return cur_rev <= 0x8001277; break;
 	case 0x80082: return cur_rev <= 0x800820f; break;
 	case 0x83010: return cur_rev <= 0x830107c; break;
 	case 0x86001: return cur_rev <= 0x860010e; break;
@@ -220,10 +220,12 @@ static bool need_sha_check(u32 cur_rev)
 	case 0xaa001: return cur_rev <= 0xaa00116; break;
 	case 0xaa002: return cur_rev <= 0xaa00218; break;
 	case 0xb0021: return cur_rev <= 0xb002146; break;
+	case 0xb0081: return cur_rev <= 0xb008111; break;
 	case 0xb1010: return cur_rev <= 0xb101046; break;
 	case 0xb2040: return cur_rev <= 0xb204031; break;
 	case 0xb4040: return cur_rev <= 0xb404031; break;
 	case 0xb6000: return cur_rev <= 0xb600031; break;
+	case 0xb6080: return cur_rev <= 0xb608031; break;
 	case 0xb7000: return cur_rev <= 0xb700031; break;
 	default: break;
 	}
@@ -233,13 +235,31 @@ static bool need_sha_check(u32 cur_rev)
 	return true;
 }
 
+static bool cpu_has_entrysign(void)
+{
+	unsigned int fam   = x86_family(bsp_cpuid_1_eax);
+	unsigned int model = x86_model(bsp_cpuid_1_eax);
+
+	if (fam == 0x17 || fam == 0x19)
+		return true;
+
+	if (fam == 0x1a) {
+		if (model <= 0x2f ||
+		    (0x40 <= model && model <= 0x4f) ||
+		    (0x60 <= model && model <= 0x6f))
+			return true;
+	}
+
+	return false;
+}
+
 static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
 {
 	struct patch_digest *pd = NULL;
 	u8 digest[SHA256_DIGEST_SIZE];
 	int i;
 
-	if (x86_family(bsp_cpuid_1_eax) < 0x17)
+	if (!cpu_has_entrysign())
 		return true;
 
 	if (!need_sha_check(cur_rev))
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c8945610d455..fe1a2aa53c16 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -242,7 +242,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	struct arch_mbm_state *am;
 	u64 msr_val;
 	u32 prmid;
 	int ret;
@@ -251,12 +253,16 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 	ret = __rmid_read_phys(prmid, eventid, &msr_val);
-	if (ret)
-		return ret;
 
-	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	if (!ret) {
+		*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	} else if (ret == -EINVAL) {
+		am = get_arch_mbm_state(hw_dom, rmid, eventid);
+		if (am)
+			am->prev_msr = 0;
+	}
 
-	return 0;
+	return ret;
 }
 
 static int __cntr_id_read(u32 cntr_id, u64 *val)
@@ -452,7 +458,16 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
-	if (rdt_cpu_has(X86_FEATURE_ABMC)) {
+	/*
+	 * resctrl assumes a system that supports assignable counters can
+	 * switch to "default" mode. Ensure that there is a "default" mode
+	 * to switch to. This enforces a dependency between the independent
+	 * X86_FEATURE_ABMC and X86_FEATURE_CQM_MBM_TOTAL/X86_FEATURE_CQM_MBM_LOCAL
+	 * hardware features.
+	 */
+	if (rdt_cpu_has(X86_FEATURE_ABMC) &&
+	    (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL) ||
+	     rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))) {
 		r->mon.mbm_cntr_assignable = true;
 		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
 		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1f71cc135e9a..e88eacb1b5bb 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -825,6 +825,9 @@ void fpu__clear_user_states(struct fpu *fpu)
 	    !fpregs_state_valid(fpu, smp_processor_id()))
 		os_xrstor_supervisor(fpu->fpstate);
 
+	/* Ensure XFD state is in sync before reloading XSTATE */
+	xfd_update_state(fpu->fpstate);
+
 	/* Reset user states in registers. */
 	restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE);