Merge pull request #100 from truenas/NAS-123310-cobia

NAS-123310 / 23.10 / Update Linux kernel to v6.1.42 for Cobia

Documentation/accounting/psi.rst

@@ -105,6 +105,10 @@ prevent overly frequent polling. Max limit is chosen as a high enough number
 after which monitors are most likely not needed and psi averages can be used
 instead.
 
+Unprivileged users can also create monitors, with the only limitation that the
+window size must be a multiple of 2s, in order to prevent excessive resource
+usage.
+
 When activated, psi monitor stays active for at least the duration of one
 tracking window to avoid repeated activations/deactivations when system is
 bouncing in and out of the stall state.

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 1
-SUBLEVEL = 40
+SUBLEVEL = 42
 NAME = Curry Ramen
 
 ifndef EXTRAVERSION

arch/arm64/kernel/fpsimd.c

@@ -803,6 +803,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 			  unsigned long vl, unsigned long flags)
 {
+	bool free_sme = false;
+
 	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
 				     PR_SVE_SET_VL_ONEXEC))
 		return -EINVAL;
@@ -851,21 +853,36 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
-	if (system_supports_sme() && type == ARM64_VEC_SME) {
-		task->thread.svcr &= ~(SVCR_SM_MASK |
-				       SVCR_ZA_MASK);
-		clear_thread_flag(TIF_SME);
+	if (system_supports_sme()) {
+		if (type == ARM64_VEC_SME ||
+		    !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) {
+			/*
+			 * We are changing the SME VL or weren't using
+			 * SME anyway, discard the state and force a
+			 * reallocation.
+			 */
+			task->thread.svcr &= ~(SVCR_SM_MASK |
+					       SVCR_ZA_MASK);
+			clear_thread_flag(TIF_SME);
+			free_sme = true;
+		}
 	}
 
 	if (task == current)
 		put_cpu_fpsimd_context();
 
 	/*
-	 * Force reallocation of task SVE and SME state to the correct
-	 * size on next use:
+	 * Free the changed states if they are not in use, SME will be
+	 * reallocated to the correct size on next use and we just
+	 * allocate SVE now in case it is needed for use in streaming
+	 * mode.
 	 */
-	sve_free(task);
-	if (system_supports_sme() && type == ARM64_VEC_SME)
+	if (system_supports_sve()) {
+		sve_free(task);
+		sve_alloc(task, true);
+	}
+
+	if (free_sme)
 		sme_free(task);
 
 	task_set_vl(task, type, vl);

arch/arm64/net/bpf_jit_comp.c

@@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
-	emit_bti(A64_BTI_C, ctx);
+	/* bpf function may be invoked by 3 instruction types:
+	 * 1. bl, attached via freplace to bpf prog via short jump
+	 * 2. br, attached via freplace to bpf prog via long jump
+	 * 3. blr, working as a function pointer, used by emit_call.
+	 * So BTI_JC should used here to support both br and blr.
+	 */
+	emit_bti(A64_BTI_JC, ctx);
 
 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);

arch/mips/include/asm/dec/prom.h

@@ -70,7 +70,7 @@ static inline bool prom_is_rex(u32 magic)
  */
 typedef struct {
 	int pagesize;
-	unsigned char bitmap[0];
+	unsigned char bitmap[];
 } memmap;
 
 

arch/x86/include/asm/microcode.h

@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 #include <linux/earlycpio.h>
 #include <linux/initrd.h>
+#include <asm/microcode_amd.h>
 
 struct ucode_patch {
 	struct list_head plist;

arch/x86/include/asm/microcode_amd.h

@@ -48,11 +48,13 @@ extern void __init load_ucode_amd_bsp(unsigned int family);
 extern void load_ucode_amd_ap(unsigned int family);
 extern int __init save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
+extern void amd_check_microcode(void);
 #else
 static inline void __init load_ucode_amd_bsp(unsigned int family) {}
 static inline void load_ucode_amd_ap(unsigned int family) {}
 static inline int __init
 save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) {}
+static inline void amd_check_microcode(void) {}
 #endif
 #endif /* _ASM_X86_MICROCODE_AMD_H */

arch/x86/include/asm/msr-index.h

@@ -543,6 +543,7 @@
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)
+#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9
 
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030

arch/x86/kernel/cpu/amd.c

@@ -27,18 +27,85 @@
 
 #include "cpu.h"
 
-static const int amd_erratum_383[];
-static const int amd_erratum_400[];
-static const int amd_erratum_1054[];
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
-
 /*
  * nodes_per_socket: Stores the number of nodes per socket.
  * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
  * Node Identifiers[10:8]
  */
 static u32 nodes_per_socket = 1;
 
+/*
+ * AMD errata checking
+ *
+ * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
+ * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
+ * have an OSVW id assigned, which it takes as first argument. Both take a
+ * variable number of family-specific model-stepping ranges created by
+ * AMD_MODEL_RANGE().
+ *
+ * Example:
+ *
+ * const int amd_erratum_319[] =
+ *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
+ *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
+ *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
+ */
+
+#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
+#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
+#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
+	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
+#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
+#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
+#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
+
+static const int amd_erratum_400[] =
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
+
+static const int amd_erratum_383[] =
+	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
+static const int amd_zenbleed[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
+{
+	int osvw_id = *erratum++;
+	u32 range;
+	u32 ms;
+
+	if (osvw_id >= 0 && osvw_id < 65536 &&
+	    cpu_has(cpu, X86_FEATURE_OSVW)) {
+		u64 osvw_len;
+
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
+		if (osvw_id < osvw_len) {
+			u64 osvw_bits;
+
+			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
+			    osvw_bits);
+			return osvw_bits & (1ULL << (osvw_id & 0x3f));
+		}
+	}
+
+	/* OSVW unavailable or ID unknown, match family-model-stepping range */
+	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
+	while ((range = *erratum++))
+		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
+		    (ms >= AMD_MODEL_RANGE_START(range)) &&
+		    (ms <= AMD_MODEL_RANGE_END(range)))
+			return true;
+
+	return false;
+}
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -916,6 +983,47 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 	}
 }
 
+static bool cpu_has_zenbleed_microcode(void)
+{
+	u32 good_rev = 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case 0x30 ... 0x3f: good_rev = 0x0830107a; break;
+	case 0x60 ... 0x67: good_rev = 0x0860010b; break;
+	case 0x68 ... 0x6f: good_rev = 0x08608105; break;
+	case 0x70 ... 0x7f: good_rev = 0x08701032; break;
+	case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
+
+	default:
+		return false;
+		break;
+	}
+
+	if (boot_cpu_data.microcode < good_rev)
+		return false;
+
+	return true;
+}
+
+static void zenbleed_check(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has_amd_erratum(c, amd_zenbleed))
+		return;
+
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (!cpu_has(c, X86_FEATURE_AVX))
+		return;
+
+	if (!cpu_has_zenbleed_microcode()) {
+		pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n");
+		msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+	} else {
+		msr_clear_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+	}
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd(c);
@@ -1005,6 +1113,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
+
+	zenbleed_check(c);
 }
 
 #ifdef CONFIG_X86_32
@@ -1100,73 +1210,6 @@ static const struct cpu_dev amd_cpu_dev = {
 
 cpu_dev_register(amd_cpu_dev);
 
-/*
- * AMD errata checking
- *
- * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
- * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
- * have an OSVW id assigned, which it takes as first argument. Both take a
- * variable number of family-specific model-stepping ranges created by
- * AMD_MODEL_RANGE().
- *
- * Example:
- *
- * const int amd_erratum_319[] =
- *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
- *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
- *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
- */
-
-#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
-#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
-#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
-	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
-#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
-#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
-#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
-
-static const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
-			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
-
-static const int amd_erratum_383[] =
-	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
-
-/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
-static const int amd_erratum_1054[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
-{
-	int osvw_id = *erratum++;
-	u32 range;
-	u32 ms;
-
-	if (osvw_id >= 0 && osvw_id < 65536 &&
-	    cpu_has(cpu, X86_FEATURE_OSVW)) {
-		u64 osvw_len;
-
-		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
-		if (osvw_id < osvw_len) {
-			u64 osvw_bits;
-
-			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
-			    osvw_bits);
-			return osvw_bits & (1ULL << (osvw_id & 0x3f));
-		}
-	}
-
-	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
-	while ((range = *erratum++))
-		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
-		    (ms >= AMD_MODEL_RANGE_START(range)) &&
-		    (ms <= AMD_MODEL_RANGE_END(range)))
-			return true;
-
-	return false;
-}
-
 void set_dr_addr_mask(unsigned long mask, int dr)
 {
 	if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -1201,3 +1244,15 @@ u32 amd_get_highest_perf(void)
 	return 255;
 }
 EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+
+static void zenbleed_check_cpu(void *unused)
+{
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+
+	zenbleed_check(c);
+}
+
+void amd_check_microcode(void)
+{
+	on_each_cpu(zenbleed_check_cpu, NULL, 1);
+}

arch/x86/kernel/cpu/common.c

@@ -2346,6 +2346,8 @@ void microcode_check(struct cpuinfo_x86 *prev_info)
 
 	perf_check_microcode();
 
+	amd_check_microcode();
+
 	store_cpu_caps(&curr_info);
 
 	if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability,

drivers/acpi/video_detect.c

@@ -510,6 +510,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"),
 		},
 	},
+	{
+	 .callback = video_detect_force_native,
+	 /* Dell Studio 1569 */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1569"),
+		},
+	},
 	{
 	 .callback = video_detect_force_native,
 	 /* Acer Aspire 3830TG */