Merge 7.2-rc3 into usb-next

We need the USB fixes in here as well to build on top of.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

9 files changed, 45 insertions, 106 deletions

diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h
index 6297631532e5..767f35ea62b3 100644
--- a/arch/arm64/include/asm/tlbbatch.h
+++ b/arch/arm64/include/asm/tlbbatch.h
@@ -2,17 +2,11 @@
 #ifndef _ARCH_ARM64_TLBBATCH_H
 #define _ARCH_ARM64_TLBBATCH_H
 
-#include <linux/cpumask.h>
-
 struct arch_tlbflush_unmap_batch {
-#ifdef CONFIG_ARM64_ERRATUM_4193714
 	/*
-	 * Track CPUs that need SME DVMSync on completion of this batch.
-	 * Otherwise, the arm64 HW can do tlb shootdown, so we don't need to
-	 * record cpumask for sending IPI
+	 * For arm64, HW can do TLB shootdown, so we don't need to record a
+	 * cpumask for sending IPIs.
 	 */
-	cpumask_var_t cpumask;
-#endif
 };
 
 #endif /* _ARCH_ARM64_TLBBATCH_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index d52ac8c17190..e0e84332f51b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -82,6 +82,8 @@ static inline unsigned long get_trans_granule(void)
 
 #ifdef CONFIG_ARM64_ERRATUM_4193714
 
+extern cpumask_t sme_active_cpus;
+
 void sme_do_dvmsync(const struct cpumask *mask);
 
 static inline void sme_dvmsync(struct mm_struct *mm)
@@ -92,42 +94,12 @@ static inline void sme_dvmsync(struct mm_struct *mm)
 	sme_do_dvmsync(mm_cpumask(mm));
 }
 
-static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					   struct mm_struct *mm)
+static inline void sme_dvmsync_batch(void)
 {
 	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
 		return;
 
-	/*
-	 * Order the mm_cpumask() read after the hardware DVMSync.
-	 */
-	dsb(ish);
-	if (cpumask_empty(mm_cpumask(mm)))
-		return;
-
-	/*
-	 * Allocate the batch cpumask on first use. Fall back to an immediate
-	 * IPI for this mm in case of failure.
-	 */
-	if (!cpumask_available(batch->cpumask) &&
-	    !zalloc_cpumask_var(&batch->cpumask, GFP_ATOMIC)) {
-		sme_do_dvmsync(mm_cpumask(mm));
-		return;
-	}
-
-	cpumask_or(batch->cpumask, batch->cpumask, mm_cpumask(mm));
-}
-
-static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
-{
-	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
-		return;
-
-	if (!cpumask_available(batch->cpumask))
-		return;
-
-	sme_do_dvmsync(batch->cpumask);
-	cpumask_clear(batch->cpumask);
+	sme_do_dvmsync(&sme_active_cpus);
 }
 
 #else
@@ -135,11 +107,7 @@ static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
 static inline void sme_dvmsync(struct mm_struct *mm)
 {
 }
-static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					   struct mm_struct *mm)
-{
-}
-static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
+static inline void sme_dvmsync_batch(void)
 {
 }
 
@@ -285,11 +253,11 @@ static inline void __tlbi_sync_s1ish(struct mm_struct *mm)
 	sme_dvmsync(mm);
 }
 
-static inline void __tlbi_sync_s1ish_batch(struct arch_tlbflush_unmap_batch *batch)
+static inline void __tlbi_sync_s1ish_batch(void)
 {
 	dsb(ish);
 	__repeat_tlbi_sync(vale1is, 0);
-	sme_dvmsync_batch(batch);
+	sme_dvmsync_batch();
 }
 
 static inline void __tlbi_sync_s1ish_kernel(void)
@@ -434,7 +402,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
  */
 static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	__tlbi_sync_s1ish_batch(batch);
+	__tlbi_sync_s1ish_batch();
 }
 
 /*
@@ -722,7 +690,6 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 
 	__flush_tlb_range(&vma, start, end, PAGE_SIZE, 3,
 			  TLBF_NOWALKCACHE | TLBF_NOSYNC);
-	sme_dvmsync_add_pending(batch, mm);
 }
 
 static inline bool __pte_flags_need_flush(ptval_t oldval, ptval_t newval)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 5891f92c2035..681aa2bbc399 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -448,12 +448,14 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 apci_id,
 		return *pcpu;
 	}
 
+	set_cpu_present(*pcpu, true);
 	return 0;
 }
 EXPORT_SYMBOL(acpi_map_cpu);
 
 int acpi_unmap_cpu(int cpu)
 {
+	set_cpu_present(cpu, false);
 	return 0;
 }
 EXPORT_SYMBOL(acpi_unmap_cpu);
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 25dc5afe9ba0..e7f1682a3059 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1355,6 +1355,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs)
  * SME/CME erratum handling.
  */
 static cpumask_t sme_dvmsync_cpus;
+cpumask_t sme_active_cpus;
 
 /*
  * These helpers are only called from non-preemptible contexts, so
@@ -1368,13 +1369,15 @@ void sme_set_active(void)
 		return;
 
 	cpumask_set_cpu(cpu, mm_cpumask(current->mm));
+	cpumask_set_cpu(cpu, &sme_active_cpus);
 
 	/*
 	 * A subsequent (post ERET) SME access may use a stale address
 	 * translation. On C1-Pro, a TLBI+DSB on a different CPU will wait for
-	 * the completion of cpumask_set_cpu() above as it appears in program
-	 * order before the SME access. The post-TLBI+DSB read of mm_cpumask()
-	 * will lead to the IPI being issued.
+	 * the completion of the cpumask_set_cpu() operations above as they
+	 * appear in program order before the SME access. The post-TLBI+DSB
+	 * read of mm_cpumask() or sme_active_cpus will lead to the IPI being
+	 * issued.
 	 *
 	 * https://lore.kernel.org/r/ablEXwhfKyJW1i7l@J2N7QTR9R3
 	 */
@@ -1392,6 +1395,7 @@ void sme_clear_active(void)
 	 * completed on entering EL1.
 	 */
 	cpumask_clear_cpu(cpu, mm_cpumask(current->mm));
+	cpumask_clear_cpu(cpu, &sme_active_cpus);
 }
 
 static void sme_dvmsync_ipi(void *unused)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 033643cd4e5e..581f80e9b9b7 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -341,41 +341,8 @@ void flush_thread(void)
 	flush_gcs();
 }
 
-#ifdef CONFIG_ARM64_ERRATUM_4193714
-
-static void arch_dup_tlbbatch_mask(struct task_struct *dst)
-{
-	/*
-	 * Clear the inherited cpumask with memset() to cover both cases where
-	 * cpumask_var_t is a pointer or an array. It will be allocated lazily
-	 * in sme_dvmsync_add_pending() if CPUMASK_OFFSTACK=y.
-	 */
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
-		memset(&dst->tlb_ubc.arch.cpumask, 0,
-		       sizeof(dst->tlb_ubc.arch.cpumask));
-}
-
-static void arch_release_tlbbatch_mask(struct task_struct *tsk)
-{
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
-		free_cpumask_var(tsk->tlb_ubc.arch.cpumask);
-}
-
-#else
-
-static void arch_dup_tlbbatch_mask(struct task_struct *dst)
-{
-}
-
-static void arch_release_tlbbatch_mask(struct task_struct *tsk)
-{
-}
-
-#endif /* CONFIG_ARM64_ERRATUM_4193714 */
-
 void arch_release_task_struct(struct task_struct *tsk)
 {
-	arch_release_tlbbatch_mask(tsk);
 	fpsimd_release_task(tsk);
 }
 
@@ -391,8 +358,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	*dst = *src;
 
-	arch_dup_tlbbatch_mask(dst);
-
 	/*
 	 * Drop stale reference to src's sve_state and convert dst to
 	 * non-streaming FPSIMD mode.
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d46022f72075..cdcdd160e5b6 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -535,23 +535,13 @@ void arch_unregister_cpu(int cpu)
 {
 	acpi_handle acpi_handle = acpi_get_processor_handle(cpu);
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
-	acpi_status status;
 	unsigned long long sta;
-
-	if (!acpi_handle) {
-		pr_err_once("Removing a CPU without associated ACPI handle\n");
-		return;
-	}
+	acpi_status status;
 
 	status = acpi_evaluate_integer(acpi_handle, "_STA", NULL, &sta);
-	if (ACPI_FAILURE(status))
-		return;
-
-	/* For now do not allow anything that looks like physical CPU HP */
-	if (cpu_present(cpu) && !(sta & ACPI_STA_DEVICE_PRESENT)) {
+	if (!ACPI_FAILURE(status) &&
+	    cpu_present(cpu) && !(sta & ACPI_STA_DEVICE_PRESENT))
 		pr_err_once("Changing CPU present bit is not supported\n");
-		return;
-	}
 
 	unregister_cpu(c);
 }
@@ -566,6 +556,11 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
 }
 EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc);
 
+static bool acpi_cpu_is_present(int cpu)
+{
+	return acpi_cpu_get_madt_gicc(cpu)->flags & ACPI_MADT_ENABLED;
+}
+
 /*
  * acpi_map_gic_cpu_interface - parse processor MADT entry
  *
@@ -670,6 +665,10 @@ static void __init acpi_parse_and_init_cpus(void)
 		early_map_cpu_to_node(i, acpi_numa_get_nid(i));
 }
 #else
+static bool acpi_cpu_is_present(int cpu)
+{
+	return false;
+}
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
 #endif
 
@@ -814,7 +813,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (err)
 			continue;
 
-		set_cpu_present(cpu, true);
+		if (acpi_disabled || acpi_cpu_is_present(cpu))
+			set_cpu_present(cpu, true);
 		numa_store_cpu_info(cpu);
 	}
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f2be501468ce..a25d8beacc83 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1515,7 +1515,13 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
 			if (free_mapped) {
 				/* CONT blocks are not supported in the vmemmap */
 				WARN_ON(pmd_cont(pmd));
-				flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+				/*
+				 * Invalidating a block entry requires just
+				 * a single overlapping TLB invalidation,
+				 * so limit the range of the flush to a single
+				 * page.
+				 */
+				flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 				free_hotplug_page_range(pmd_page(pmd),
 							PMD_SIZE, altmap);
 			}
@@ -1545,7 +1551,8 @@ static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
 		if (pud_leaf(pud)) {
 			pud_clear(pudp);
 			if (free_mapped) {
-				flush_tlb_kernel_range(addr, addr + PUD_SIZE);
+				/* See comment in unmap_hotplug_pmd_range(). */
+				flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 				free_hotplug_page_range(pud_page(pud),
 							PUD_SIZE, altmap);
 			}
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f6bcc0e1a950..b0075ece4a6e 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2177,7 +2177,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
 					      sizeof(u64), &header, &image_ptr,
-					      jit_fill_hole);
+					      jit_fill_hole, was_classic);
 	if (!ro_header)
 		goto out_off;
 
@@ -2870,7 +2870,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, jit_fill_hole);
+	return bpf_prog_pack_alloc(size, jit_fill_hole, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index bc1788b1662b..7cb61aca3797 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1806,7 +1806,7 @@ Res0	15:8
 UnsignedEnum	7:4	BWE
 	0b0000	NI
 	0b0001	FEAT_BWE
-	0b0002	FEAT_BWE2
+	0b0010	FEAT_BWE2
 EndEnum
 UnsignedEnum	3:0	STEP
 	0b0000	NI