Merge tag 'riscv-for-linus-5.12-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "A handful of new RISC-V related patches for this merge window:

   - A check to ensure drivers are properly using uaccess. This isn't
     manifesting with any of the drivers I'm currently using, but may
     catch errors in new drivers.

   - Some preliminary support for the FU740, along with the HiFive
     Unleashed it will appear on.

   - NUMA support for RISC-V, which involves making the arm64 code
     generic.

   - Support for kasan on the vmalloc region.

   - A handful of new drivers for the Kendryte K210, along with the DT
     plumbing required to boot on a handful of K210-based boards.

   - Support for allocating ASIDs.

   - Preliminary support for kernels larger than 128MiB.

   - Various other improvements to our KASAN support, including the
     utilization of huge pages when allocating the KASAN regions.

  We may have already found a bug with the KASAN_VMALLOC code, but it's
  passing my tests. There's a fix in the works, but that will probably
  miss the merge window.

* tag 'riscv-for-linus-5.12-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (75 commits)
  riscv: Improve kasan population by using hugepages when possible
  riscv: Improve kasan population function
  riscv: Use KASAN_SHADOW_INIT define for kasan memory initialization
  riscv: Improve kasan definitions
  riscv: Get rid of MAX_EARLY_MAPPING_SIZE
  soc: canaan: Sort the Makefile alphabetically
  riscv: Disable KSAN_SANITIZE for vDSO
  riscv: Remove unnecessary declaration
  riscv: Add Canaan Kendryte K210 SD card defconfig
  riscv: Update Canaan Kendryte K210 defconfig
  riscv: Add Kendryte KD233 board device tree
  riscv: Add SiPeed MAIXDUINO board device tree
  riscv: Add SiPeed MAIX GO board device tree
  riscv: Add SiPeed MAIX DOCK board device tree
  riscv: Add SiPeed MAIX BiT board device tree
  riscv: Update Canaan Kendryte K210 device tree
  dt-bindings: add resets property to dw-apb-timer
  dt-bindings: fix sifive gpio properties
  dt-bindings: update sifive uart compatible string
  dt-bindings: update sifive clint compatible string
  ...

1 files changed, 145 insertions, 31 deletions

diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index a8a2ffd9114a..3fc18f469efb 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -9,6 +9,19 @@
 #include <linux/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
+#include <asm/pgalloc.h>
+
+static __init void *early_alloc(size_t size, int node)
+{
+	void *ptr = memblock_alloc_try_nid(size, size,
+		__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, node);
+
+	if (!ptr)
+		panic("%pS: Failed to allocate %zu bytes align=%zx nid=%d from=%llx\n",
+			__func__, size, size, node, (u64)__pa(MAX_DMA_ADDRESS));
+
+	return ptr;
+}
 
 extern pgd_t early_pg_dir[PTRS_PER_PGD];
 asmlinkage void __init kasan_early_init(void)
@@ -47,40 +60,133 @@ asmlinkage void __init kasan_early_init(void)
 	local_flush_tlb_all();
 }
 
-static void __init populate(void *start, void *end)
+static void kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pte_t *ptep, *base_pte;
+
+	if (pmd_none(*pmd))
+		base_pte = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+	else
+		base_pte = (pte_t *)pmd_page_vaddr(*pmd);
+
+	ptep = base_pte + pte_index(vaddr);
+
+	do {
+		if (pte_none(*ptep)) {
+			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
+		}
+	} while (ptep++, vaddr += PAGE_SIZE, vaddr != end);
+
+	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE));
+}
+
+static void kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pmd_t *pmdp, *base_pmd;
+	unsigned long next;
+
+	base_pmd = (pmd_t *)pgd_page_vaddr(*pgd);
+	if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+		base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+
+	pmdp = base_pmd + pmd_index(vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
+			if (phys_addr) {
+				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				continue;
+			}
+		}
+
+		kasan_populate_pte(pmdp, vaddr, next);
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole PGD to be populated before setting the PGD in
+	 * the page table, otherwise, if we did set the PGD before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+}
+
+static void kasan_populate_pgd(unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pgd_t *pgdp = pgd_offset_k(vaddr);
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		/*
+		 * pgdp can't be none since kasan_early_init initialized all KASAN
+		 * shadow region with kasan_early_shadow_pmd: if this is stillthe case,
+		 * that means we can try to allocate a hugepage as a replacement.
+		 */
+		if (pgd_page_vaddr(*pgdp) == (unsigned long)lm_alias(kasan_early_shadow_pmd) &&
+		    IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
+			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+			if (phys_addr) {
+				set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				continue;
+			}
+		}
+
+		kasan_populate_pmd(pgdp, vaddr, next);
+	} while (pgdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_populate(void *start, void *end)
 {
-	unsigned long i, offset;
 	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
 	unsigned long vend = PAGE_ALIGN((unsigned long)end);
-	unsigned long n_pages = (vend - vaddr) / PAGE_SIZE;
-	unsigned long n_ptes =
-	    ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE;
-	unsigned long n_pmds =
-	    ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD;
-
-	pte_t *pte =
-	    memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
-	pmd_t *pmd =
-	    memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
-	pgd_t *pgd = pgd_offset_k(vaddr);
-
-	for (i = 0; i < n_pages; i++) {
-		phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
-		set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
-	}
-
-	for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE)
-		set_pmd(&pmd[i],
-			pfn_pmd(PFN_DOWN(__pa(&pte[offset])),
-				__pgprot(_PAGE_TABLE)));
 
-	for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD)
-		set_pgd(&pgd[i],
-			pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
-				__pgprot(_PAGE_TABLE)));
+	kasan_populate_pgd(vaddr, vend);
 
 	local_flush_tlb_all();
-	memset(start, 0, end - start);
+	memset(start, KASAN_SHADOW_INIT, end - start);
+}
+
+void __init kasan_shallow_populate(void *start, void *end)
+{
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+	unsigned long pfn;
+	int index;
+	void *p;
+	pud_t *pud_dir, *pud_k;
+	pgd_t *pgd_dir, *pgd_k;
+	p4d_t *p4d_dir, *p4d_k;
+
+	while (vaddr < vend) {
+		index = pgd_index(vaddr);
+		pfn = csr_read(CSR_SATP) & SATP_PPN;
+		pgd_dir = (pgd_t *)pfn_to_virt(pfn) + index;
+		pgd_k = init_mm.pgd + index;
+		pgd_dir = pgd_offset_k(vaddr);
+		set_pgd(pgd_dir, *pgd_k);
+
+		p4d_dir = p4d_offset(pgd_dir, vaddr);
+		p4d_k  = p4d_offset(pgd_k, vaddr);
+
+		vaddr = (vaddr + PUD_SIZE) & PUD_MASK;
+		pud_dir = pud_offset(p4d_dir, vaddr);
+		pud_k = pud_offset(p4d_k, vaddr);
+
+		if (pud_present(*pud_dir)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
+			pud_populate(&init_mm, pud_dir, p);
+		}
+		vaddr += PAGE_SIZE;
+	}
 }
 
 void __init kasan_init(void)
@@ -90,7 +196,15 @@ void __init kasan_init(void)
 
 	kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
 				    (void *)kasan_mem_to_shadow((void *)
-								VMALLOC_END));
+								VMEMMAP_END));
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_shallow_populate(
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+	else
+		kasan_populate_early_shadow(
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
 
 	for_each_mem_range(i, &_start, &_end) {
 		void *start = (void *)__va(_start);
@@ -99,7 +213,7 @@ void __init kasan_init(void)
 		if (start >= end)
 			break;
 
-		populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
+		kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
 	};
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
@@ -108,6 +222,6 @@ void __init kasan_init(void)
 			       __pgprot(_PAGE_PRESENT | _PAGE_READ |
 					_PAGE_ACCESSED)));
 
-	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
 	init_task.kasan_depth = 0;
 }