Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 56 insertions, 27 deletions

diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 55a34f2020..bc61ee5975 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -82,12 +82,12 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_MMU
-void flush_icache_pte(pte_t pte)
+void flush_icache_pte(struct mm_struct *mm, pte_t pte)
 {
 	struct folio *folio = page_folio(pte_page(pte));
 
 	if (!test_bit(PG_dcache_clean, &folio->flags)) {
-		flush_icache_all();
+		flush_icache_mm(mm, false);
 		set_bit(PG_dcache_clean, &folio->flags);
 	}
 }
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 217fd4de61..ba8eb39446 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -323,6 +323,8 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	if (unlikely(prev == next))
 		return;
 
+	membarrier_arch_switch_mm(prev, next, task);
+
 	/*
 	 * Mark the current MM context as inactive, and the next as
 	 * active.  This is at least used by the icache flushing
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 0c00efc756..46b4ad418f 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -29,7 +29,6 @@
 #include <asm/io.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
-#include <asm/ptdump.h>
 #include <asm/sections.h>
 #include <asm/soc.h>
 #include <asm/tlbflush.h>
@@ -236,18 +235,19 @@ static void __init setup_bootmem(void)
 		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
 
 	/*
-	 * memblock allocator is not aware of the fact that last 4K bytes of
-	 * the addressable memory can not be mapped because of IS_ERR_VALUE
-	 * macro. Make sure that last 4k bytes are not usable by memblock
-	 * if end of dram is equal to maximum addressable memory.  For 64-bit
-	 * kernel, this problem can't happen here as the end of the virtual
-	 * address space is occupied by the kernel mapping then this check must
-	 * be done as soon as the kernel mapping base address is determined.
+	 * Reserve physical address space that would be mapped to virtual
+	 * addresses greater than (void *)(-PAGE_SIZE) because:
+	 *  - This memory would overlap with ERR_PTR
+	 *  - This memory belongs to high memory, which is not supported
+	 *
+	 * This is not applicable to 64-bit kernel, because virtual addresses
+	 * after (void *)(-PAGE_SIZE) are not linearly mapped: they are
+	 * occupied by kernel mapping. Also it is unrealistic for high memory
+	 * to exist on 64-bit platforms.
 	 */
 	if (!IS_ENABLED(CONFIG_64BIT)) {
-		max_mapped_addr = __pa(~(ulong)0);
-		if (max_mapped_addr == (phys_ram_end - 1))
-			memblock_set_current_limit(max_mapped_addr - 4096);
+		max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE);
+		memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr);
 	}
 
 	min_low_pfn = PFN_UP(phys_ram_base);
@@ -669,6 +669,9 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va,
 				      phys_addr_t size)
 {
+	if (debug_pagealloc_enabled())
+		return PAGE_SIZE;
+
 	if (pgtable_l5_enabled &&
 	    !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
 		return P4D_SIZE;
@@ -723,8 +726,6 @@ void mark_rodata_ro(void)
 	if (IS_ENABLED(CONFIG_64BIT))
 		set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data),
 				  set_memory_ro);
-
-	debug_checkwx();
 }
 #else
 static __init pgprot_t pgprot_from_va(uintptr_t va)
@@ -767,6 +768,11 @@ static int __init print_no5lvl(char *p)
 }
 early_param("no5lvl", print_no5lvl);
 
+static void __init set_mmap_rnd_bits_max(void)
+{
+	mmap_rnd_bits_max = MMAP_VA_BITS - PAGE_SHIFT - 3;
+}
+
 /*
  * There is a simple way to determine if 4-level is supported by the
  * underlying hardware: establish 1:1 mapping in 4-level page table mode
@@ -1081,6 +1087,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 #if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
 	set_satp_mode(dtb_pa);
+	set_mmap_rnd_bits_max();
 #endif
 
 	/*
@@ -1358,7 +1365,7 @@ static void __init arch_reserve_crashkernel(void)
 	bool high = false;
 	int ret;
 
-	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
 	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 410056a50a..271d01a5ba 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -387,17 +387,33 @@ int set_direct_map_default_noflush(struct page *page)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
+static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data)
+{
+	int enable = *(int *)data;
+
+	unsigned long val = pte_val(ptep_get(pte));
+
+	if (enable)
+		val |= _PAGE_PRESENT;
+	else
+		val &= ~_PAGE_PRESENT;
+
+	set_pte(pte, __pte(val));
+
+	return 0;
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!debug_pagealloc_enabled())
 		return;
 
-	if (enable)
-		__set_memory((unsigned long)page_address(page), numpages,
-			     __pgprot(_PAGE_PRESENT), __pgprot(0));
-	else
-		__set_memory((unsigned long)page_address(page), numpages,
-			     __pgprot(0), __pgprot(_PAGE_PRESENT));
+	unsigned long start = (unsigned long)page_address(page);
+	unsigned long size = PAGE_SIZE * numpages;
+
+	apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable);
+
+	flush_tlb_kernel_range(start, start + size);
 }
 #endif
 
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index ef887efcb6..533ec9055f 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -10,7 +10,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  pte_t entry, int dirty)
 {
 	if (!pte_same(ptep_get(ptep), entry))
-		__set_pte_at(ptep, entry);
+		__set_pte_at(vma->vm_mm, ptep, entry);
 	/*
 	 * update_mmu_cache will unconditionally execute, handling both
 	 * the case that the PTE changed and the spurious fault case.
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 657c27bc07..1289cc6d37 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -9,7 +9,6 @@
 #include <linux/seq_file.h>
 #include <linux/ptdump.h>
 
-#include <asm/ptdump.h>
 #include <linux/pgtable.h>
 #include <asm/kasan.h>
 
@@ -336,7 +335,7 @@ static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
 	ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL);
 }
 
-void ptdump_check_wx(void)
+bool ptdump_check_wx(void)
 {
 	struct pg_state st = {
 		.seq = NULL,
@@ -357,11 +356,16 @@ void ptdump_check_wx(void)
 
 	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 
-	if (st.wx_pages)
+	if (st.wx_pages) {
 		pr_warn("Checked W+X mappings: failed, %lu W+X pages found\n",
 			st.wx_pages);
-	else
+
+		return false;
+	} else {
 		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+
+		return true;
+	}
 }
 
 static int ptdump_show(struct seq_file *m, void *v)