Merge pull request #12 from sched-ext/merge_latest

v6.7.5-scx1

Makefile

@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 7
-SUBLEVEL = 4
-EXTRAVERSION = -scx2
+SUBLEVEL = 5
+EXTRAVERSION = -scx1
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*

arch/arc/include/asm/cacheflush.h

@@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 /* TBD: optimize this */
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */

arch/arm/include/asm/cacheflush.h

@@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		dsb(ishst);
 }
 
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 	if (!cache_is_vipt_nonaliasing())

arch/csky/abiv1/inc/abi/cacheflush.h

@@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
  */
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)		cache_wbinv_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)

arch/csky/abiv2/inc/abi/cacheflush.h

@@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm,
 void flush_icache_deferred(struct mm_struct *mm);
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \

arch/m68k/include/asm/cacheflush_mm.h

@@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len);
 #define flush_cache_all() __flush_cache_all()
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 static inline void flush_cache_mm(struct mm_struct *mm)

arch/mips/include/asm/cacheflush.h

@@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		__flush_cache_vmap();
 }
 
+#define flush_cache_vmap_early(start, end)     do { } while (0)
+
 extern void (*__flush_cache_vunmap)(void);
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)

arch/nios2/include/asm/cacheflush.h

@@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 #define flush_icache_pages flush_icache_pages
 
 #define flush_cache_vmap(start, end)		flush_dcache_range(start, end)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_dcache_range(start, end)
 
 extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,

arch/parisc/include/asm/cacheflush.h

@@ -41,6 +41,7 @@ void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);

arch/riscv/include/asm/cacheflush.h

@@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)	flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 
 #ifndef CONFIG_SMP

arch/riscv/include/asm/hugetlb.h

@@ -11,6 +11,9 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 }
 #define arch_clear_hugepage_flags arch_clear_hugepage_flags
 
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 void huge_pte_clear(struct mm_struct *mm, unsigned long addr,

arch/riscv/include/asm/stacktrace.h

@@ -21,4 +21,9 @@ static inline bool on_thread_stack(void)
 	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
 }
 
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
 #endif /* _ASM_RISCV_STACKTRACE_H */

arch/riscv/include/asm/tlb.h

@@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 #ifdef CONFIG_MMU
-	if (tlb->fullmm || tlb->need_flush_all)
+	if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
 		flush_tlb_mm(tlb->mm);
 	else
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,

arch/riscv/include/asm/tlbflush.h

@@ -41,6 +41,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
 void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -66,6 +67,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */

arch/riscv/mm/hugetlbpage.c

@@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return pte;
 }
 
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		return P4D_SIZE - PUD_SIZE;
+#endif
+	case PMD_SIZE:
+		return PUD_SIZE - PMD_SIZE;
+	case napot_cont_size(NAPOT_CONT64KB_ORDER):
+		return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+	default:
+		break;
+	}
+
+	return 0UL;
+}
+
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
@@ -177,13 +197,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	return entry;
 }
 
+static void clear_flush(struct mm_struct *mm,
+			unsigned long addr,
+			pte_t *ptep,
+			unsigned long pgsize,
+			unsigned long ncontig)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		ptep_get_and_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift;
+	unsigned long hugepage_shift, pgsize;
 	int i, pte_num;
 
 	if (sz >= PGDIR_SIZE)
@@ -198,7 +241,22 @@ void set_huge_pte_at(struct mm_struct *mm,
 		hugepage_shift = PAGE_SHIFT;
 
 	pte_num = sz >> hugepage_shift;
-	for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
+	pgsize = 1 << hugepage_shift;
+
+	if (!pte_present(pte)) {
+		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+			set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	if (!pte_napot(pte)) {
+		set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+	for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
 		set_pte_at(mm, addr, ptep, pte);
 }
 
@@ -306,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		pte_clear(mm, addr, ptep);
 }
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	unsigned long order;
 
@@ -334,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init);
 
 #else
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	return false;
 }
@@ -351,7 +409,7 @@ int pmd_huge(pmd_t pmd)
 	return pmd_leaf(pmd);
 }
 
-bool __init arch_hugetlb_valid_size(unsigned long size)
+static bool __hugetlb_valid_size(unsigned long size)
 {
 	if (size == HPAGE_SIZE)
 		return true;
@@ -363,6 +421,16 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 		return false;
 }
 
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	return __hugetlb_valid_size(size);
+}
+
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	return __hugetlb_valid_size(huge_page_size(h));
+}
+
 #ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {

arch/riscv/mm/init.c

@@ -1385,6 +1385,10 @@ void __init misc_mem_init(void)
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 	arch_numa_init();
 	sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* The entire VMEMMAP region has been populated. Flush TLB for this region */
+	local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
 	zone_sizes_init();
 	arch_reserve_crashkernel();
 	memblock_dump_all();

arch/riscv/mm/tlbflush.c

@@ -66,6 +66,12 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+/* Flush a range of kernel pages without broadcasting */
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 static void __ipi_flush_tlb_all(void *info)
 {
 	local_flush_tlb_all();

arch/sh/include/asm/cacheflush.h

@@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma,
 	unsigned long len);
 
 #define flush_cache_vmap(start, end)		local_flush_cache_all(NULL)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		local_flush_cache_all(NULL)
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)

arch/sparc/include/asm/cacheflush_32.h

@@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 /* When a context switch happens we must flush all user windows so that

arch/sparc/include/asm/cacheflush_64.h

@@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *,
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #endif /* !__ASSEMBLY__ */

arch/x86/boot/header.S

@@ -106,8 +106,7 @@ extra_header_fields:
 	.word	0				# MinorSubsystemVersion
 	.long	0				# Win32VersionValue
 
-	.long	setup_size + ZO__end + pecompat_vsize
-						# SizeOfImage
+	.long	setup_size + ZO__end		# SizeOfImage
 
 	.long	salign				# SizeOfHeaders
 	.long	0				# CheckSum
@@ -143,7 +142,7 @@ section_table:
 	.ascii	".setup"
 	.byte	0
 	.byte	0
-	.long	setup_size - salign 		# VirtualSize
+	.long	pecompat_fstart - salign 	# VirtualSize
 	.long	salign				# VirtualAddress
 	.long	pecompat_fstart - salign	# SizeOfRawData
 	.long	salign				# PointerToRawData
@@ -156,8 +155,8 @@ section_table:
 #ifdef CONFIG_EFI_MIXED
 	.asciz	".compat"
 
-	.long	8				# VirtualSize
-	.long	setup_size + ZO__end		# VirtualAddress
+	.long	pecompat_fsize			# VirtualSize
+	.long	pecompat_fstart			# VirtualAddress
 	.long	pecompat_fsize			# SizeOfRawData
 	.long	pecompat_fstart			# PointerToRawData
 
@@ -172,17 +171,16 @@ section_table:
 	 * modes this image supports.
 	 */
 	.pushsection ".pecompat", "a", @progbits
-	.balign	falign
-	.set	pecompat_vsize, salign
+	.balign	salign
 	.globl	pecompat_fstart
 pecompat_fstart:
 	.byte	0x1				# Version
 	.byte	8				# Size
 	.word	IMAGE_FILE_MACHINE_I386		# PE machine type
 	.long	setup_size + ZO_efi32_pe_entry	# Entrypoint
+	.byte	0x0				# Sentinel
 	.popsection
 #else
-	.set	pecompat_vsize, 0
 	.set	pecompat_fstart, setup_size
 #endif
 	.ascii	".text"

arch/x86/boot/setup.ld

@@ -24,6 +24,9 @@ SECTIONS
 	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }
 
+	.pecompat	: { *(.pecompat) }
+	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
 	. = ALIGN(16);
 	.rodata		: { *(.rodata*) }
 
@@ -36,9 +39,6 @@ SECTIONS
 	. = ALIGN(16);
 	.data		: { *(.data*) }
 
-	.pecompat	: { *(.pecompat) }
-	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
 	.signature	: {
 		setup_sig = .;
 		LONG(0x5a5aaa55)