[PATCH v3 4/4] RISC-V: Allow booting kernel from any 4KB aligned address

[Anup Patel <Anup.Patel@wdc.com>]

Currently, we have to boot RISCV64 kernel from a 2MB aligned physical
address and RISCV32 kernel from a 4MB aligned physical address. This
constraint is because initial pagetable setup (i.e. setup_vm()) maps
entire RAM using hugepages (i.e. 2MB for 3-level pagetable and 4MB for
2-level pagetable).

Further, the above booting contraint also results in memory wastage
because if we boot kernel from some <xyz> address (which is not same as
RAM start address) then RISCV kernel will map PAGE_OFFSET virtual address
lineraly to <xyz> physical address and memory between RAM start and <xyz>
will be reserved/unusable.

For example, RISCV64 kernel booted from 0x80200000 will waste 2MB of RAM
and RISCV32 kernel booted from 0x80400000 will waste 4MB of RAM.

This patch re-writes the initial pagetable setup code to allow booting
RISV32 and RISCV64 kernel from any 4KB (i.e. PAGE_SIZE) aligned address.

To achieve this:
1. We add kconfig option BOOT_PAGE_ALIGNED. When it is enabled we use
   4KB mappings in initial page table setup otherwise we use 2MB/4MB
   mappings.
2. We map kernel and dtb (few MBs) in setup_vm() (called from head.S)
3. Once we reach paging_init() (called from setup_arch()) after
   memblock setup, we map all available memory banks.

With this patch in-place, the booting constraint for RISCV32 and RISCV64
kernel is much more relaxed when CONFIG_BOOT_PAGE_ALIGNED=y and we can
now boot kernel very close to RAM start thereby minimizng memory wastage.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 arch/riscv/Kconfig                  |  12 +
 arch/riscv/include/asm/fixmap.h     |   5 +
 arch/riscv/include/asm/pgtable-64.h |   5 +
 arch/riscv/include/asm/pgtable.h    |   5 +
 arch/riscv/kernel/head.S            |   1 +
 arch/riscv/kernel/setup.c           |   4 +-
 arch/riscv/mm/init.c                | 351 ++++++++++++++++++++++++----
 7 files changed, 335 insertions(+), 48 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index eb56c82d8aa1..d7812b1f7c7e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -172,6 +172,18 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config BOOT_PAGE_ALIGNED
+	bool "Allow booting from page aligned address"
+	default n
+	help
+	  This enables support for booting the kernel from any page aligned
+	  address (i.e. 4KB aligned). This option is particularly useful on
+	  systems with a very small RAM (few MBs) as we can boot the kernel
+	  closer to the RAM start address, thereby reducing the amount of
+	  unusable RAM below the kernel.
+
+	  If you don't know what to do here, say N.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index c207f6634b91..9c66033c3a54 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -21,6 +21,11 @@
  */
 enum fixed_addresses {
 	FIX_HOLE,
+#define FIX_FDT_SIZE	SZ_1M
+	FIX_FDT_END,
+	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+	FIX_PTE,
+	FIX_PMD,
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_fixed_addresses
 };
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 7aa0ea9bd8bb..56ecc3dc939d 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -78,6 +78,11 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
 	return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
 }
 
+static inline unsigned long _pmd_pfn(pmd_t pmd)
+{
+	return pmd_val(pmd) >> _PAGE_PFN_SHIFT;
+}
+
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 1141364d990e..c4968b47c37d 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -127,6 +127,11 @@ static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
 	return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
 }
 
+static inline unsigned long _pgd_pfn(pgd_t pgd)
+{
+	return pgd_val(pgd) >> _PAGE_PFN_SHIFT;
+}
+
 #define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
 
 /* Locate an entry in the page global directory */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 3449671ec867..61e253ae38b4 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -62,6 +62,7 @@ clear_bss_done:
 
 	/* Initialize page tables and relocate to virtual addresses */
 	la sp, init_thread_union + THREAD_SIZE
+	mv a0, s1
 	call setup_vm
 	call relocate
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 540a331d1376..79670458527d 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -30,6 +30,7 @@
 #include <linux/sched/task.h>
 #include <linux/swiotlb.h>
 
+#include <asm/fixmap.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -54,7 +55,8 @@ unsigned long boot_cpu_hartid;
 
 void __init parse_dtb(unsigned int hartid, void *dtb)
 {
-	if (early_init_dt_scan(__va(dtb)))
+	dtb = (void *)fix_to_virt(FIX_FDT) + ((uintptr_t)dtb & ~PAGE_MASK);
+	if (early_init_dt_scan(dtb))
 		return;
 
 	pr_err("No DTB passed to the kernel\n");
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f9add4381c73..56970dab3727 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1,14 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2012 Regents of the University of California
- *
- *   This program is free software; you can redistribute it and/or
- *   modify it under the terms of the GNU General Public License
- *   as published by the Free Software Foundation, version 2.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
  */
 
 #include <linux/init.h>
@@ -49,13 +42,6 @@ void setup_zero_page(void)
 	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 }
 
-void __init paging_init(void)
-{
-	setup_zero_page();
-	local_flush_tlb_all();
-	zone_sizes_init();
-}
-
 void __init mem_init(void)
 {
 #ifdef CONFIG_FLATMEM
@@ -152,16 +138,28 @@ EXPORT_SYMBOL(va_pa_offset);
 unsigned long pfn_base;
 EXPORT_SYMBOL(pfn_base);
 
+#define MAX_EARLY_MAPPING_SIZE	SZ_128M
+
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 
 #ifndef __PAGETABLE_PMD_FOLDED
-#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
-pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
+#if MAX_EARLY_MAPPING_SIZE < PGDIR_SIZE
+#define NUM_SWAPPER_PMDS	1UL
+#else
+#define NUM_SWAPPER_PMDS	(MAX_EARLY_MAPPING_SIZE/PGDIR_SIZE)
+#endif
+pmd_t swapper_pmd[PTRS_PER_PMD*NUM_SWAPPER_PMDS] __page_aligned_bss;
 pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
+#define NUM_SWAPPER_PTES	(MAX_EARLY_MAPPING_SIZE/PMD_SIZE)
+#else
+#define NUM_SWAPPER_PTES	(MAX_EARLY_MAPPING_SIZE/PGDIR_SIZE)
 #endif
 
+pte_t swapper_pte[PTRS_PER_PTE*NUM_SWAPPER_PTES] __page_aligned_bss;
 pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
 
+static uintptr_t map_size;
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 {
 	unsigned long addr = __fix_to_virt(idx);
@@ -179,6 +177,201 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 	}
 }
 
+struct mapping_ops {
+	pte_t *(*get_pte_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pte)(uintptr_t va);
+	pmd_t *(*get_pmd_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pmd)(uintptr_t va);
+};
+
+static phys_addr_t __init final_alloc_pgtable(void)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static pte_t *__init early_get_pte_virt(phys_addr_t pa)
+{
+	return (pte_t *)((uintptr_t)pa);
+}
+
+static pte_t *__init final_get_pte_virt(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PTE);
+
+	return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
+}
+
+static phys_addr_t __init early_alloc_pte(uintptr_t va)
+{
+	pte_t *base = swapper_pte;
+	uintptr_t pte_num = ((va - PAGE_OFFSET) >> PMD_SHIFT);
+
+	BUG_ON(pte_num >= NUM_SWAPPER_PTES);
+
+	return (uintptr_t)&base[pte_num * PTRS_PER_PTE];
+}
+
+static phys_addr_t __init final_alloc_pte(uintptr_t va)
+{
+	return final_alloc_pgtable();
+}
+
+static void __init create_pte_mapping(pte_t *ptep,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	uintptr_t pte_index = pte_index(va);
+
+	BUG_ON(sz != PAGE_SIZE);
+
+	if (pte_none(ptep[pte_index]))
+		ptep[pte_index] = pfn_pte(PFN_DOWN(pa), prot);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static pmd_t *__init early_get_pmd_virt(phys_addr_t pa)
+{
+	return (pmd_t *)((uintptr_t)pa);
+}
+
+static pmd_t *__init final_get_pmd_virt(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PMD);
+
+	return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
+}
+
+static phys_addr_t __init early_alloc_pmd(uintptr_t va)
+{
+	pmd_t *base = swapper_pmd;
+	uintptr_t pmd_num = (va - PAGE_OFFSET) >> PGDIR_SHIFT;
+
+	BUG_ON(pmd_num >= NUM_SWAPPER_PMDS);
+
+	return (uintptr_t)&base[pmd_num * PTRS_PER_PMD];
+}
+
+static phys_addr_t __init final_alloc_pmd(uintptr_t va)
+{
+	return final_alloc_pgtable();
+}
+
+static void __init create_pmd_mapping(pmd_t *pmdp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot,
+				      struct mapping_ops *ops)
+{
+	pte_t *ptep;
+	phys_addr_t pte_phys;
+	uintptr_t pmd_index = pmd_index(va);
+
+	if (sz == PMD_SIZE) {
+		if (pmd_none(pmdp[pmd_index]))
+			pmdp[pmd_index] = pfn_pmd(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pmd_none(pmdp[pmd_index])) {
+		pte_phys = ops->alloc_pte(va);
+		pmdp[pmd_index] = pfn_pmd(PFN_DOWN(pte_phys),
+					  __pgprot(_PAGE_TABLE));
+		ptep = ops->get_pte_virt(pte_phys);
+		memset(ptep, 0, PAGE_SIZE);
+	} else {
+		pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_index]));
+		ptep = ops->get_pte_virt(pte_phys);
+	}
+
+	create_pte_mapping(ptep, va, pa, sz, prot);
+}
+
+
+static void __init create_pgd_mapping(pgd_t *pgdp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot,
+				      struct mapping_ops *ops)
+{
+	pmd_t *pmdp;
+	phys_addr_t pmd_phys;
+	uintptr_t pgd_index = pgd_index(va);
+
+	if (sz == PGDIR_SIZE) {
+		if (pgd_val(pgdp[pgd_index]) == 0)
+			pgdp[pgd_index] = pfn_pgd(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pgd_val(pgdp[pgd_index]) == 0) {
+		pmd_phys = ops->alloc_pmd(va);
+		pgdp[pgd_index] = pfn_pgd(PFN_DOWN(pmd_phys),
+					  __pgprot(_PAGE_TABLE));
+		pmdp = ops->get_pmd_virt(pmd_phys);
+		memset(pmdp, 0, PAGE_SIZE);
+	} else {
+		pmd_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_index]));
+		pmdp = ops->get_pmd_virt(pmd_phys);
+	}
+
+	create_pmd_mapping(pmdp, va, pa, sz, prot, ops);
+}
+#else
+static void __init create_pgd_mapping(pgd_t *pgdp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot,
+				      struct mapping_ops *ops)
+{
+	pte_t *ptep;
+	phys_addr_t pte_phys;
+	uintptr_t pgd_index = pgd_index(va);
+
+	if (sz == PGDIR_SIZE) {
+		if (pgd_val(pgdp[pgd_index]) == 0)
+			pgdp[pgd_index] = pfn_pgd(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pgd_val(pgdp[pgd_index]) == 0) {
+		pte_phys = ops->alloc_pte(va);
+		pgdp[pgd_index] = pfn_pgd(PFN_DOWN(pte_phys),
+					  __pgprot(_PAGE_TABLE));
+		ptep = ops->get_pte_virt(pte_phys);
+		memset(ptep, 0, PAGE_SIZE);
+	} else {
+		pte_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_index]));
+		ptep = ops->get_pte_virt(pte_phys);
+	}
+
+	create_pte_mapping(ptep, va, pa, sz, prot);
+}
+#endif
+
+static uintptr_t __init best_map_size(uintptr_t load_pa, phys_addr_t size)
+{
+#ifdef CONFIG_BOOT_PAGE_ALIGNED
+	uintptr_t map_sz = PAGE_SIZE;
+#else
+#ifndef __PAGETABLE_PMD_FOLDED
+	uintptr_t map_sz = PMD_SIZE;
+#else
+	uintptr_t map_sz = PGDIR_SIZE;
+#endif
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+	if (!(load_pa & (PMD_SIZE - 1)) &&
+	    (size >= PMD_SIZE) &&
+	    (map_sz < PMD_SIZE))
+		map_sz = PMD_SIZE;
+#endif
+
+	if (!(load_pa & (PGDIR_SIZE - 1)) &&
+	    (size >= PGDIR_SIZE) &&
+	    (map_sz < PGDIR_SIZE))
+		map_sz = PGDIR_SIZE;
+
+	return map_sz;
+}
+
 /*
  * The setup_vm() is called from head.S with MMU-off.
  *
@@ -192,46 +385,110 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
  * Currently, the above requirements are honoured by using custom CFLAGS
  * for init.o in mm/Makefile.
  */
-asmlinkage void __init setup_vm(void)
+asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
-	uintptr_t i;
-	uintptr_t pa = (uintptr_t) &_start;
+	uintptr_t va, end_va;
+	uintptr_t load_pa = (uintptr_t)(&_start);
+	uintptr_t load_sz = (uintptr_t)(&_end) - load_pa;
+	pgprot_t tableprot = __pgprot(_PAGE_TABLE);
 	pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
+	struct mapping_ops ops;
 
-	va_pa_offset = PAGE_OFFSET - pa;
-	pfn_base = PFN_DOWN(pa);
+	va_pa_offset = PAGE_OFFSET - load_pa;
+	pfn_base = PFN_DOWN(load_pa);
+	map_size = best_map_size(load_pa, PGDIR_SIZE);
 
 	/* Sanity check alignment and size */
 	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
-	BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
+	BUG_ON((load_pa % map_size) != 0);
+	BUG_ON(load_sz > MAX_EARLY_MAPPING_SIZE);
+
+	/* Setup swapper ops */
+	ops.get_pte_virt = early_get_pte_virt;
+	ops.alloc_pte = early_alloc_pte;
+	ops.get_pmd_virt = NULL;
+	ops.alloc_pmd = NULL;
 
 #ifndef __PAGETABLE_PMD_FOLDED
-	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
-		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+	/* Update mapping ops for PMD */
+	ops.get_pmd_virt = early_get_pmd_virt;
+	ops.alloc_pmd = early_alloc_pmd;
+
+	/* Setup swapper PGD and PMD for fixmap */
+	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+			   (uintptr_t)fixmap_pmd, PGDIR_SIZE, tableprot, &ops);
+	create_pmd_mapping(fixmap_pmd, FIXADDR_START,
+			   (uintptr_t)fixmap_pte, PMD_SIZE, tableprot, &ops);
+#else
+	/* Setup swapper PGD for fixmap */
+	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+			   (uintptr_t)fixmap_pte, PGDIR_SIZE, tableprot, &ops);
+#endif
 
-		swapper_pg_dir[o] =
-			pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
-				__pgprot(_PAGE_TABLE));
-	}
-	for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
-		swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
-
-	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
-		pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pmd),
-				__pgprot(_PAGE_TABLE));
-	fixmap_pmd[(FIXADDR_START >> PMD_SHIFT) % PTRS_PER_PMD] =
-		pfn_pmd(PFN_DOWN((uintptr_t)fixmap_pte),
-				__pgprot(_PAGE_TABLE));
+	/*
+	 * Setup swapper PGD covering entire kernel which will allows
+	 * us to reach paging_init(). We map all memory banks later in
+	 * setup_vm_final() below.
+	 */
+	end_va = PAGE_OFFSET + load_sz;
+	for (va = PAGE_OFFSET; va < end_va; va += map_size)
+		create_pgd_mapping(swapper_pg_dir, va,
+				   load_pa + (va - PAGE_OFFSET),
+				   map_size, prot, &ops);
+
+	/* Create fixed mapping for early FDT parsing */
+	end_va = __fix_to_virt(FIX_FDT) + FIX_FDT_SIZE;
+	for (va = __fix_to_virt(FIX_FDT); va < end_va; va += PAGE_SIZE)
+		create_pte_mapping(fixmap_pte, va,
+				   dtb_pa + (va - __fix_to_virt(FIX_FDT)),
+				   PAGE_SIZE, prot);
+}
+
+static void __init setup_vm_final(void)
+{
+	phys_addr_t pa, start, end;
+	struct memblock_region *reg;
+	struct mapping_ops ops;
+	pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
+
+	/* Setup mapping ops */
+	ops.get_pte_virt = final_get_pte_virt;
+	ops.alloc_pte = final_alloc_pte;
+#ifndef __PAGETABLE_PMD_FOLDED
+	ops.get_pmd_virt = final_get_pmd_virt;
+	ops.alloc_pmd = final_alloc_pmd;
 #else
-	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
-		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+	ops.get_pmd_virt = NULL;
+	ops.alloc_pmd = NULL;
+#endif
 
-		swapper_pg_dir[o] =
-			pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
+	/* Map all memory banks */
+	for_each_memblock(memory, reg) {
+		start = reg->base;
+		end = start + reg->size;
+
+		if (start >= end)
+			break;
+		if (memblock_is_nomap(reg))
+			continue;
+		if (start <= __pa(PAGE_OFFSET) &&
+		    __pa(PAGE_OFFSET) < end)
+			start = __pa(PAGE_OFFSET);
+
+		for (pa = start; pa < end; pa += map_size)
+			create_pgd_mapping(swapper_pg_dir,
+					   (uintptr_t)__va(pa), pa,
+					   map_size, prot, &ops);
 	}
 
-	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
-		pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pte),
-				__pgprot(_PAGE_TABLE));
-#endif
+	clear_fixmap(FIX_PTE);
+	clear_fixmap(FIX_PMD);
+}
+
+void __init paging_init(void)
+{
+	setup_vm_final();
+	setup_zero_page();
+	local_flush_tlb_all();
+	zone_sizes_init();
 }
-- 
2.17.1