[Backport][5.15] Support KP950 for velinux-5.15

Documentation/admin-guide/perf/hisi-pcie-pmu.rst

@@ -28,7 +28,9 @@ The "identifier" sysfs file allows users to identify the version of the
 PMU hardware device.
 
 The "bus" sysfs file allows users to get the bus number of Root Ports
-monitored by PMU.
+monitored by PMU. Furthermore users can get the Root Ports range in
+[bdf_min, bdf_max] from "bdf_min" and "bdf_max" sysfs attributes
+respectively.
 
 Example usage of perf::
 

Documentation/admin-guide/perf/hisi-pmu.rst

@@ -36,7 +36,10 @@ e.g. hisi_sccl1_hha0/rx_operations is RX_OPERATIONS event of HHA index #0 in
 SCCL ID #1.
 
 The driver also provides a "cpumask" sysfs attribute, which shows the CPU core
-ID used to count the uncore PMU event.
+ID used to count the uncore PMU event. An "associated_cpus" sysfs attribute is
+also provided to show the CPUs associated with this PMU. The "cpumask" indicates
+the CPUs to open the events, usually as a hint for userspaces tools like perf.
+It only contains one associated CPU from the "associated_cpus".
 
 Example usage of perf::
 
@@ -98,6 +101,17 @@ CCL/ICL-ID. For I/O die, the ICL-ID is followed by:
 5'b00011: HAC_ICL;
 5'b10000: PCIe_ICL;
 
+6. ch: NoC PMU supports filtering the event counts of certain transaction
+channel with this option. The current supported channels are as follows:
+
+- 3'b010: Request channel
+- 3'b100: Snoop channel
+- 3'b110: Response channel
+- 3'b111: Data channel
+
+7. tt_en: NoC PMU supports counting only transactions that have tracetag set
+if this option is set. See the 2nd list for more information about tracetag.
+
 Users could configure IDs to count data come from specific CCL/ICL, by setting
 srcid_cmd & srcid_msk, and data desitined for specific CCL/ICL by setting
 tgtid_cmd & tgtid_msk. A set bit in srcid_msk/tgtid_msk means the PMU will not

Documentation/admin-guide/pm/cpufreq.rst

@@ -248,6 +248,20 @@ are the following:
 	If that frequency cannot be determined, this attribute should not
 	be present.
 
+``cpuinfo_avg_freq``
+        An average frequency (in KHz) of all CPUs belonging to a given policy,
+        derived from a hardware provided feedback and reported on a time frame
+        spanning at most few milliseconds.
+
+        This is expected to be based on the frequency the hardware actually runs
+        at and, as such, might require specialised hardware support (such as AMU
+        extension on ARM). If one cannot be determined, this attribute should
+        not be present.
+
+        Note, that failed attempt to retrieve current frequency for a given
+        CPU(s) will result in an appropriate error, i.e: EAGAIN for CPU that
+        remains idle (raised on ARM).
+
 ``cpuinfo_max_freq``
 	Maximum possible operating frequency the CPUs belonging to this policy
 	can run at (in kHz).
@@ -289,7 +303,8 @@ are the following:
 	Some architectures (e.g. ``x86``) may attempt to provide information
 	more precisely reflecting the current CPU frequency through this
 	attribute, but that still may not be the exact current CPU frequency as
-	seen by the hardware at the moment.
+	seen by the hardware at the moment. This behavior though, is only
+	available via c:macro:``CPUFREQ_ARCH_CUR_FREQ`` option.
 
 ``scaling_driver``
 	The scaling driver currently in use.

arch/arm/include/asm/topology.h

@@ -13,6 +13,7 @@
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
 #endif
 
 /* Replace task scheduler's default cpu-invariant accounting */
@@ -24,6 +25,7 @@
 /* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
 #define arch_set_thermal_pressure   topology_set_thermal_pressure
+#define arch_update_thermal_pressure	topology_update_thermal_pressure
 
 #else
 

arch/arm/kernel/perf_event_v7.c

@@ -1072,8 +1072,10 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 {
 	unsigned long config_base = 0;
 
-	if (attr->exclude_idle)
-		return -EPERM;
+	if (attr->exclude_idle) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 	if (attr->exclude_user)
 		config_base |= ARMV7_EXCLUDE_USER;
 	if (attr->exclude_kernel)

arch/arm64/Kconfig

@@ -30,6 +30,7 @@ config ARM64
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS
@@ -203,6 +204,7 @@ config ARM64
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_GENERIC_VDSO
+	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
@@ -1944,6 +1946,22 @@ config ARM64_EPAN
 
 	 The feature is detected at runtime, and will remain disabled
 	 if the cpu does not implement the feature.
+
+config ARM64_HAFT
+	bool "Support for Hardware managed Access Flag for Table Descriptors"
+	depends on ARM64_HW_AFDBM
+	default y
+	help
+	  The ARMv8.9/ARMv9.5 introduces the feature Hardware managed Access
+	  Flag for Table descriptors. When enabled an architectural executed
+	  memory access will update the Access Flag in each Table descriptor
+	  which is accessed during the translation table walk and for which
+	  the Access Flag is 0. The Access Flag of the Table descriptor use
+	  the same bit of PTE_AF.
+
+	  The feature will only be enabled if all the CPUs in the system
+	  support this feature. If unsure, say Y.
+
 endmenu
 
 config ARM64_SVE

arch/arm64/include/asm/assembler.h

@@ -479,9 +479,10 @@ alternative_endif
  */
 	.macro	reset_pmuserenr_el0, tmpreg
 	mrs	\tmpreg, id_aa64dfr0_el1
-	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4
-	cmp	\tmpreg, #1			// Skip if no PMU present
-	b.lt	9000f
+	ubfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	9000f				// Skip if no PMU present or IMP_DEF
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
 9000:
 	.endm

arch/arm64/include/asm/cpufeature.h

@@ -11,7 +11,7 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
-#define MAX_CPU_FEATURES	64
+#define MAX_CPU_FEATURES	128
 #define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
@@ -808,6 +808,12 @@ static inline bool system_supports_tlb_range(void)
 		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
 }
 
+static inline bool system_supports_haft(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_HAFT) &&
+		cpus_have_final_cap(ARM64_HAFT);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 

arch/arm64/include/asm/cputype.h

@@ -113,7 +113,8 @@
 
 #define HISI_CPU_PART_TSV110		0xD01
 #define HISI_CPU_PART_TSV200		0xD02
-#define HISI_CPU_PART_LINXICORE9100    0xD02
+#define HISI_CPU_PART_LINXICORE9100	0xD02
+#define HISI_CPU_PART_HIP12		0xD06
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
@@ -162,6 +163,7 @@
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
 #define MIDR_HISI_TSV200 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV200)
 #define MIDR_HISI_LINXICORE9100 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_LINXICORE9100)
+#define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)

arch/arm64/include/asm/el2_setup.h

@@ -22,6 +22,15 @@
 	isb
 .endm
 
+.macro __init_el2_hcrx
+	mrs	x0, id_aa64mmfr1_el1
+	ubfx	x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
+	cbz	x0, .Lskip_hcrx_\@
+	mov_q	x0, HCRX_HOST_FLAGS
+	msr_s	SYS_HCRX_EL2, x0
+.Lskip_hcrx_\@:
+.endm
+
 /*
  * Allow Non-secure EL1 and EL0 to access physical timer and counter.
  * This is not necessary for VHE, since the host kernel runs in EL2,
@@ -40,13 +49,14 @@
 
 .macro __init_el2_debug
 	mrs	x1, id_aa64dfr0_el1
-	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
-	cmp	x0, #1
-	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
+	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x0, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	x0, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	.Lskip_pmu_\@			// Skip if no PMU present or IMP_DEF
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
 .Lskip_pmu_\@:
-	csel	x2, xzr, x0, lt			// all PMU counters from EL1
+	csel	x2, xzr, x0, eq			// all PMU counters from EL1
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
@@ -187,6 +197,7 @@
  */
 .macro init_el2_state
 	__init_el2_sctlr
+	__init_el2_hcrx
 	__init_el2_timers
 	__init_el2_debug
 	__init_el2_lor

arch/arm64/include/asm/hwcap.h

@@ -85,7 +85,7 @@
 #define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
 #define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
 
-#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 64)
 #define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
 #define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
 #define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
@@ -108,6 +108,7 @@
 #define KERNEL_HWCAP_ECV		__khwcap2_feature(ECV)
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
+#define KERNEL_HWCAP_HBC		__khwcap2_feature(HBC)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_arm.h

@@ -63,6 +63,8 @@
 #define HCR_VM		(UL(1) << 0)
 #define HCR_RES0	((UL(1) << 48) | (UL(1) << 39))
 
+#define HCRX_EL2_TCR2En	(UL(1) << 14)
+
 /*
  * The bits we set in HCR:
  * TLOR:	Trap LORegion register accesses
@@ -89,6 +91,7 @@
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+#define HCRX_HOST_FLAGS (HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */
 #define TCR_EL2_RES1		((1U << 31) | (1 << 23))

arch/arm64/include/asm/module.h

@@ -65,4 +65,19 @@ static inline bool plt_entry_is_initialized(const struct plt_entry *e)
 	return e->adrp || e->add || e->br;
 }
 
+static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
+{
+	const Elf_Shdr *s, *se;
+	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
+	}
+
+	return NULL;
+}
+
 #endif /* __ASM_MODULE_H */

arch/arm64/include/asm/pgalloc.h

@@ -27,7 +27,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
 {
-	pudval_t pudval = PUD_TYPE_TABLE;
+	pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_AF;
 
 	pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN;
 	__pud_populate(pudp, __pa(pmdp), pudval);
@@ -48,7 +48,7 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 
 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
 {
-	p4dval_t p4dval = P4D_TYPE_TABLE;
+	p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_AF;
 
 	p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
 	__p4d_populate(p4dp, __pa(pudp), p4dval);
@@ -77,14 +77,16 @@ static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 {
 	VM_BUG_ON(mm && mm != &init_mm);
-	__pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
+	__pmd_populate(pmdp, __pa(ptep),
+		       PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_UXN);
 }
 
 static inline void
 pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 {
 	VM_BUG_ON(mm == &init_mm);
-	__pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN);
+	__pmd_populate(pmdp, page_to_phys(ptep),
+		       PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_PXN);
 }
 
 #endif

arch/arm64/include/asm/pgtable-hwdef.h

@@ -94,6 +94,7 @@
 #define P4D_TYPE_MASK		(_AT(p4dval_t, 3) << 0)
 #define P4D_TYPE_SECT		(_AT(p4dval_t, 1) << 0)
 #define P4D_SECT_RDONLY		(_AT(p4dval_t, 1) << 7)		/* AP[2] */
+#define P4D_TABLE_AF		(_AT(p4dval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 #define P4D_TABLE_PXN		(_AT(p4dval_t, 1) << 59)
 #define P4D_TABLE_UXN		(_AT(p4dval_t, 1) << 60)
 
@@ -105,6 +106,7 @@
 #define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
 #define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
+#define PUD_TABLE_AF		(_AT(pudval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 #define PUD_TABLE_PXN		(_AT(pudval_t, 1) << 59)
 #define PUD_TABLE_UXN		(_AT(pudval_t, 1) << 60)
 
@@ -115,6 +117,7 @@
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
 #define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
+#define PMD_TABLE_AF		(_AT(pmdval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 
 /*
  * Section

arch/arm64/include/asm/pgtable.h

@@ -852,15 +852,17 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 	return young;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
 					    pmd_t *pmdp)
 {
+	/* Operation applies to PMD table entry only if FEAT_HAFT is enabled */
+	VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft());
 	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -1013,6 +1015,10 @@ static inline bool arch_faults_on_old_pte(void)
 }
 #define arch_faults_on_old_pte		arch_faults_on_old_pte
 
+#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+#define arch_has_hw_nonleaf_pmd_young	system_supports_haft
+#endif
+
 /*
  * Experimentally, it's cheap to set the access flag in hardware and we
  * benefit from prefaulting mappings as 'old' to start with.