FAILED: patch "[PATCH] LoongArch: Use accessors to page table entries instead of" failed to apply to 6.6-stable tree

PATCH Superseded [email protected] 2 participants 6 messages Sep 10, 2024 – Sep 13, 2024 2 messages not in the archive

Subsystems (5)

Stable branch LoongArch KASAN KVM LoongArch +1 more subsystems

lore

Share & tools

lore

[email protected]

author maintainer

2024-09-10 08:55 UTC #0 lore raw

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 4574815abf43e2bf05643e1b3f7a2e5d6df894f0
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2024091028-stinking-mourner-56f5@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..

Possible dependencies:

4574815abf43 ("LoongArch: Use accessors to page table entries instead of direct dereference") 752e2cd7b4fb ("LoongArch: KVM: Implement kvm mmu operations")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 4574815abf43e2bf05643e1b3f7a2e5d6df894f0 Mon Sep 17 00:00:00 2001
From: Huacai Chen <[email protected]>
Date: Wed, 7 Aug 2024 17:37:11 +0800
Subject: [PATCH] LoongArch: Use accessors to page table entries instead of
direct dereference

As very well explained in commit 20a004e7b017cce282 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables"), an architecture whose page table walker can modify the PTE in parallel must use READ_ONCE()/ WRITE_ONCE() macro to avoid any compiler transformation.

So apply that to LoongArch which is such an architecture, in order to avoid potential problems.

Similar to commit edf955647269422e ("riscv: Use accessors to page table entries instead of direct dereference").

Signed-off-by Huacai Chen <[email protected]>

arch/loongarch/include/asm/hugetlb.h +2 -2

index aa44b3fe43dd..5da32c00d483 100644
@@ -34,7 +34,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
 	pte_t clear;
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 
 	pte_val(clear) = (unsigned long)invalid_pte_table;
 	set_pte_at(mm, addr, ptep, clear);

@@ -65,7 +65,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     pte_t *ptep, pte_t pte,
 					     int dirty)
 {
-	int changed = !pte_same(*ptep, pte);
+	int changed = !pte_same(ptep_get(ptep), pte);
 
 	if (changed) {
 		set_pte_at(vma->vm_mm, addr, ptep, pte);

arch/loongarch/include/asm/kfence.h +3 -3

index 92636e82957c..da9e93024626 100644
@@ -53,13 +53,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *pte = virt_to_kpte(addr);
 
-	if (WARN_ON(!pte) || pte_none(*pte))
+	if (WARN_ON(!pte) || pte_none(ptep_get(pte)))
 		return false;
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT)));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT)));
 
 	preempt_disable();
 	local_flush_tlb_one(addr);

arch/loongarch/include/asm/pgtable.h +30 ~~-20~~

112 lines not on this page · raw message

arch/loongarch/kvm/mmu.c +4 -4

index 2634a9e8d82c..28681dfb4b85 100644
@@ -714,19 +714,19 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	 * value) and then p*d_offset() walks into the target huge page instead
 	 * of the old page table (sees the new value).
 	 */
-	pgd = READ_ONCE(*pgd_offset(kvm->mm, hva));
+	pgd = pgdp_get(pgd_offset(kvm->mm, hva));
 	if (pgd_none(pgd))
 		goto out;
 
-	p4d = READ_ONCE(*p4d_offset(&pgd, hva));
+	p4d = p4dp_get(p4d_offset(&pgd, hva));
 	if (p4d_none(p4d) || !p4d_present(p4d))
 		goto out;
 
-	pud = READ_ONCE(*pud_offset(&p4d, hva));
+	pud = pudp_get(pud_offset(&p4d, hva));
 	if (pud_none(pud) || !pud_present(pud))
 		goto out;
 
-	pmd = READ_ONCE(*pmd_offset(&pud, hva));
+	pmd = pmdp_get(pmd_offset(&pud, hva));
 	if (pmd_none(pmd) || !pmd_present(pmd))
 		goto out;

arch/loongarch/mm/hugetlbpage.c +3 -3

index 12222c56cb59..e4068906143b 100644
@@ -39,11 +39,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
+	if (pgd_present(pgdp_get(pgd))) {
 		p4d = p4d_offset(pgd, addr);
-		if (p4d_present(*p4d)) {
+		if (p4d_present(p4dp_get(p4d))) {
 			pud = pud_offset(p4d, addr);
-			if (pud_present(*pud))
+			if (pud_present(pudp_get(pud)))
 				pmd = pmd_offset(pud, addr);
 		}
 	}

arch/loongarch/mm/init.c +5 -5

index bf789d114c2d..8a87a482c8f4 100644
@@ -141,7 +141,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
 int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
 				unsigned long addr, unsigned long next)
 {
-	int huge = pmd_val(*pmd) & _PAGE_HUGE;
+	int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE;
 
 	if (huge)
 		vmemmap_verify((pte_t *)pmd, node, addr, next);

@@ -173,7 +173,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pud)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -184,7 +184,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pmd)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -195,7 +195,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(pmdp_get(pmd))) {
 		pte_t *pte;
 
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);

@@ -216,7 +216,7 @@ void __init __set_fixmap(enum fixed_addresses idx,
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
 	ptep = populate_kernel_pte(addr);
-	if (!pte_none(*ptep)) {
+	if (!pte_none(ptep_get(ptep))) {
 		pte_ERROR(*ptep);
 		return;
 	}

arch/loongarch/mm/kasan_init.c +5 -5

index c608adc99845..427d6b1aec09 100644
@@ -105,7 +105,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node)
 
 static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early)
 {
-	if (__pmd_none(early, READ_ONCE(*pmdp))) {
+	if (__pmd_none(early, pmdp_get(pmdp))) {
 		phys_addr_t pte_phys = early ?
 				__pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -118,7 +118,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
 
 static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early)
 {
-	if (__pud_none(early, READ_ONCE(*pudp))) {
+	if (__pud_none(early, pudp_get(pudp))) {
 		phys_addr_t pmd_phys = early ?
 				__pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -131,7 +131,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 
 static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early)
 {
-	if (__p4d_none(early, READ_ONCE(*p4dp))) {
+	if (__p4d_none(early, p4dp_get(p4dp))) {
 		phys_addr_t pud_phys = early ?
 			__pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -154,7 +154,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 					      : kasan_alloc_zeroed_page(node);
 		next = addr + PAGE_SIZE;
 		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep)));
+	} while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep)));
 }
 
 static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,

@@ -166,7 +166,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		kasan_pte_populate(pmdp, addr, next, node, early);
-	} while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp)));
+	} while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp)));
 }
 
 static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,

arch/loongarch/mm/pgtable.c +1 -1

index bda018150000..eb6a29b491a7 100644
@@ -128,7 +128,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot)
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 	flush_tlb_all();
 }

He Lugang

2024-09-10 13:01 UTC #1 lore raw

PATCH 1/2 LoongArch: KVM: Implement kvm mmu operations

From: Tianrui Zhao <[email protected]>

commit 752e2cd7b4fb412f3e008493e0195e357bab9773 upstream

Implement LoongArch kvm mmu, it is used to switch gpa to hpa when guest exit because of address translation exception.

This patch implement: allocating gpa page table, searching gpa from it, and flushing guest gpa in the table.

Reviewed-by Bibo Mao <[email protected]>

Tested-by Huacai Chen <[email protected]>

Signed-off-by Tianrui Zhao <[email protected]>

Signed-off-by Huacai Chen <[email protected]>

Signed-off-by He Lugang <[email protected]>

---
 arch/loongarch/include/asm/kvm_mmu.h | 139 ++++
 arch/loongarch/kvm/mmu.c             | 914 +++++++++++++++++++++++++++
 2 files changed, 1053 insertions(+)
 create mode 100644 arch/loongarch/include/asm/kvm_mmu.h
 create mode 100644 arch/loongarch/kvm/mmu.c

arch/loongarch/include/asm/kvm_mmu.h new file +139 -0

new file mode 100644
index 000000000000..099bafc6f797
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_MMU_H__
+#define __ASM_LOONGARCH_KVM_MMU_H__
+
+#include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels
+ * for which pages need to be cached.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	(CONFIG_PGTABLE_LEVELS - 1)
+
+#define _KVM_FLUSH_PGTABLE	0x1
+#define _KVM_HAS_PGMASK		0x2
+#define kvm_pfn_pte(pfn, prot)	(((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
+#define kvm_pte_pfn(x)		((phys_addr_t)((x & _PFN_MASK) >> PFN_PTE_SHIFT))
+
+typedef unsigned long kvm_pte_t;
+typedef struct kvm_ptw_ctx kvm_ptw_ctx;
+typedef int (*kvm_pte_ops)(kvm_pte_t *pte, phys_addr_t addr, kvm_ptw_ctx *ctx);
+
+struct kvm_ptw_ctx {
+	kvm_pte_ops     ops;
+	unsigned long   flag;
+
+	/* for kvm_arch_mmu_enable_log_dirty_pt_masked use */
+	unsigned long   mask;
+	unsigned long   gfn;
+
+	/* page walk mmu info */
+	unsigned int    level;
+	unsigned long   pgtable_shift;
+	unsigned long   invalid_entry;
+	unsigned long   *invalid_ptes;
+	unsigned int    *pte_shifts;
+	void		*opaque;
+
+	/* free pte table page list */
+	struct list_head list;
+};
+
+kvm_pte_t *kvm_pgd_alloc(void);
+
+static inline void kvm_set_pte(kvm_pte_t *ptep, kvm_pte_t val)
+{
+	WRITE_ONCE(*ptep, val);
+}
+
+static inline int kvm_pte_write(kvm_pte_t pte) { return pte & _PAGE_WRITE; }
+static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & _PAGE_DIRTY; }
+static inline int kvm_pte_young(kvm_pte_t pte) { return pte & _PAGE_ACCESSED; }
+static inline int kvm_pte_huge(kvm_pte_t pte) { return pte & _PAGE_HUGE; }
+
+static inline kvm_pte_t kvm_pte_mkyoung(kvm_pte_t pte)
+{
+	return pte | _PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkold(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkdirty(kvm_pte_t pte)
+{
+	return pte | _PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkclean(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkhuge(kvm_pte_t pte)
+{
+	return pte | _PAGE_HUGE;
+}
+
+static inline kvm_pte_t kvm_pte_mksmall(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_HUGE;
+}
+
+static inline int kvm_need_flush(kvm_ptw_ctx *ctx)
+{
+	return ctx->flag & _KVM_FLUSH_PGTABLE;
+}
+
+static inline kvm_pte_t *kvm_pgtable_offset(kvm_ptw_ctx *ctx, kvm_pte_t *table,
+					phys_addr_t addr)
+{
+
+	return table + ((addr >> ctx->pgtable_shift) & (PTRS_PER_PTE - 1));
+}
+
+static inline phys_addr_t kvm_pgtable_addr_end(kvm_ptw_ctx *ctx,
+				phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary, size;
+
+	size = 0x1UL << ctx->pgtable_shift;
+	boundary = (addr + size) & ~(size - 1);
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+static inline int kvm_pte_present(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	if (!ctx || ctx->level == 0)
+		return !!(*entry & _PAGE_PRESENT);
+
+	return *entry != ctx->invalid_entry;
+}
+
+static inline int kvm_pte_none(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	return *entry == ctx->invalid_entry;
+}
+
+static inline void kvm_ptw_enter(kvm_ptw_ctx *ctx)
+{
+	ctx->level--;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+static inline void kvm_ptw_exit(kvm_ptw_ctx *ctx)
+{
+	ctx->level++;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+#endif /* __ASM_LOONGARCH_KVM_MMU_H__ */

arch/loongarch/kvm/mmu.c new file +914 -0

914 lines not on this page · raw message

Signature · 1 line

2.45.2

A message that is not in the archive (sent off-list or not yet received): [email protected]

He Lugang

2024-09-10 13:02 UTC #3 lore raw

PATCH 2/2 LoongArch: Use accessors to page table entries instead of direct dereference

From: Huacai Chen <[email protected]>

commit 4574815abf43e2bf05643e1b3f7a2e5d6df894f0 upstream

So apply that to LoongArch which is such an architecture, in order to avoid potential problems.

Similar to commit edf955647269422e ("riscv: Use accessors to page table entries instead of direct dereference").

Signed-off-by Huacai Chen <[email protected]>

Signed-off-by He Lugang <[email protected]>

---
 arch/loongarch/include/asm/hugetlb.h |  4 +--
 arch/loongarch/include/asm/kfence.h  |  6 ++--
 arch/loongarch/include/asm/pgtable.h | 48 +++++++++++++++++-----------
 arch/loongarch/kvm/mmu.c             |  8 ++---
 arch/loongarch/mm/hugetlbpage.c      |  6 ++--
 arch/loongarch/mm/init.c             | 10 +++---
 arch/loongarch/mm/kasan_init.c       | 10 +++---
 arch/loongarch/mm/pgtable.c          |  2 +-
 8 files changed, 52 insertions(+), 42 deletions(-)

arch/loongarch/include/asm/hugetlb.h +2 -2

index aa44b3fe43dd..5da32c00d483 100644
@@ -34,7 +34,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
 	pte_t clear;
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 
 	pte_val(clear) = (unsigned long)invalid_pte_table;
 	set_pte_at(mm, addr, ptep, clear);

@@ -65,7 +65,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     pte_t *ptep, pte_t pte,
 					     int dirty)
 {
-	int changed = !pte_same(*ptep, pte);
+	int changed = !pte_same(ptep_get(ptep), pte);
 
 	if (changed) {
 		set_pte_at(vma->vm_mm, addr, ptep, pte);

arch/loongarch/include/asm/kfence.h +3 -3

index 6c82aea1c993..2835b41d2a84 100644
@@ -43,13 +43,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *pte = virt_to_kpte(addr);
 
-	if (WARN_ON(!pte) || pte_none(*pte))
+	if (WARN_ON(!pte) || pte_none(ptep_get(pte)))
 		return false;
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT)));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT)));
 
 	preempt_disable();
 	local_flush_tlb_one(addr);

arch/loongarch/include/asm/pgtable.h +29 ~~-19~~

111 lines not on this page · raw message

arch/loongarch/kvm/mmu.c +4 -4

index 80480df5f550..545a824e38b1 100644
@@ -679,19 +679,19 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	 * value) and then p*d_offset() walks into the target huge page instead
 	 * of the old page table (sees the new value).
 	 */
-	pgd = READ_ONCE(*pgd_offset(kvm->mm, hva));
+	pgd = pgdp_get(pgd_offset(kvm->mm, hva));
 	if (pgd_none(pgd))
 		goto out;
 
-	p4d = READ_ONCE(*p4d_offset(&pgd, hva));
+	p4d = p4dp_get(p4d_offset(&pgd, hva));
 	if (p4d_none(p4d) || !p4d_present(p4d))
 		goto out;
 
-	pud = READ_ONCE(*pud_offset(&p4d, hva));
+	pud = pudp_get(pud_offset(&p4d, hva));
 	if (pud_none(pud) || !pud_present(pud))
 		goto out;
 
-	pmd = READ_ONCE(*pmd_offset(&pud, hva));
+	pmd = pmdp_get(pmd_offset(&pud, hva));
 	if (pmd_none(pmd) || !pmd_present(pmd))
 		goto out;

arch/loongarch/mm/hugetlbpage.c +3 -3

index 1e76fcb83093..62ddcea0aa14 100644
@@ -39,11 +39,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
+	if (pgd_present(pgdp_get(pgd))) {
 		p4d = p4d_offset(pgd, addr);
-		if (p4d_present(*p4d)) {
+		if (p4d_present(p4dp_get(p4d))) {
 			pud = pud_offset(p4d, addr);
-			if (pud_present(*pud))
+			if (pud_present(pudp_get(pud)))
 				pmd = pmd_offset(pud, addr);
 		}
 	}

arch/loongarch/mm/init.c +5 -5

index 4dd53427f657..71fa4b773eb3 100644
@@ -140,7 +140,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
 int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
 				unsigned long addr, unsigned long next)
 {
-	int huge = pmd_val(*pmd) & _PAGE_HUGE;
+	int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE;
 
 	if (huge)
 		vmemmap_verify((pte_t *)pmd, node, addr, next);

@@ -172,7 +172,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pud)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -183,7 +183,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pmd)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -194,7 +194,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(pmdp_get(pmd))) {
 		pte_t *pte;
 
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);

@@ -215,7 +215,7 @@ void __init __set_fixmap(enum fixed_addresses idx,
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
 	ptep = populate_kernel_pte(addr);
-	if (!pte_none(*ptep)) {
+	if (!pte_none(ptep_get(ptep))) {
 		pte_ERROR(*ptep);
 		return;
 	}

arch/loongarch/mm/kasan_init.c +5 -5

index c608adc99845..427d6b1aec09 100644
@@ -105,7 +105,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node)
 
 static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early)
 {
-	if (__pmd_none(early, READ_ONCE(*pmdp))) {
+	if (__pmd_none(early, pmdp_get(pmdp))) {
 		phys_addr_t pte_phys = early ?
 				__pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -118,7 +118,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
 
 static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early)
 {
-	if (__pud_none(early, READ_ONCE(*pudp))) {
+	if (__pud_none(early, pudp_get(pudp))) {
 		phys_addr_t pmd_phys = early ?
 				__pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -131,7 +131,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 
 static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early)
 {
-	if (__p4d_none(early, READ_ONCE(*p4dp))) {
+	if (__p4d_none(early, p4dp_get(p4dp))) {
 		phys_addr_t pud_phys = early ?
 			__pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -154,7 +154,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 					      : kasan_alloc_zeroed_page(node);
 		next = addr + PAGE_SIZE;
 		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep)));
+	} while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep)));
 }
 
 static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,

@@ -166,7 +166,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		kasan_pte_populate(pmdp, addr, next, node, early);
-	} while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp)));
+	} while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp)));
 }
 
 static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,

arch/loongarch/mm/pgtable.c +1 -1

index 2aae72e63871..6a038a27373a 100644
@@ -128,7 +128,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot)
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 	flush_tlb_all();
 }

Signature · 1 line

2.45.2

A message that is not in the archive (sent off-list or not yet received): [email protected]

He Lugang

2024-09-10 13:11 UTC #5 lore raw

PATCH RESEND 2/2 LoongArch: Use accessors to page table entries instead of direct dereference

From: Huacai Chen <[email protected]>

commit 4574815abf43e2bf05643e1b3f7a2e5d6df894f0 upstream

So apply that to LoongArch which is such an architecture, in order to avoid potential problems.

Similar to commit edf955647269422e ("riscv: Use accessors to page table entries instead of direct dereference").

Signed-off-by Huacai Chen <[email protected]>

---
 arch/loongarch/include/asm/hugetlb.h |  4 +--
 arch/loongarch/include/asm/kfence.h  |  6 ++--
 arch/loongarch/include/asm/pgtable.h | 48 +++++++++++++++++-----------
 arch/loongarch/kvm/mmu.c             |  8 ++---
 arch/loongarch/mm/hugetlbpage.c      |  6 ++--
 arch/loongarch/mm/init.c             | 10 +++---
 arch/loongarch/mm/kasan_init.c       | 10 +++---
 arch/loongarch/mm/pgtable.c          |  2 +-
 8 files changed, 52 insertions(+), 42 deletions(-)

arch/loongarch/include/asm/hugetlb.h +2 -2

index aa44b3fe43dd..5da32c00d483 100644
@@ -34,7 +34,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
 	pte_t clear;
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 
 	pte_val(clear) = (unsigned long)invalid_pte_table;
 	set_pte_at(mm, addr, ptep, clear);

@@ -65,7 +65,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     pte_t *ptep, pte_t pte,
 					     int dirty)
 {
-	int changed = !pte_same(*ptep, pte);
+	int changed = !pte_same(ptep_get(ptep), pte);
 
 	if (changed) {
 		set_pte_at(vma->vm_mm, addr, ptep, pte);

arch/loongarch/include/asm/kfence.h +3 -3

index 6c82aea1c993..2835b41d2a84 100644
@@ -43,13 +43,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *pte = virt_to_kpte(addr);
 
-	if (WARN_ON(!pte) || pte_none(*pte))
+	if (WARN_ON(!pte) || pte_none(ptep_get(pte)))
 		return false;
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT)));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT)));
 
 	preempt_disable();
 	local_flush_tlb_one(addr);

arch/loongarch/include/asm/pgtable.h +29 ~~-19~~

111 lines not on this page · raw message

arch/loongarch/kvm/mmu.c +4 -4

index 80480df5f550..545a824e38b1 100644
@@ -679,19 +679,19 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	 * value) and then p*d_offset() walks into the target huge page instead
 	 * of the old page table (sees the new value).
 	 */
-	pgd = READ_ONCE(*pgd_offset(kvm->mm, hva));
+	pgd = pgdp_get(pgd_offset(kvm->mm, hva));
 	if (pgd_none(pgd))
 		goto out;
 
-	p4d = READ_ONCE(*p4d_offset(&pgd, hva));
+	p4d = p4dp_get(p4d_offset(&pgd, hva));
 	if (p4d_none(p4d) || !p4d_present(p4d))
 		goto out;
 
-	pud = READ_ONCE(*pud_offset(&p4d, hva));
+	pud = pudp_get(pud_offset(&p4d, hva));
 	if (pud_none(pud) || !pud_present(pud))
 		goto out;
 
-	pmd = READ_ONCE(*pmd_offset(&pud, hva));
+	pmd = pmdp_get(pmd_offset(&pud, hva));
 	if (pmd_none(pmd) || !pmd_present(pmd))
 		goto out;

arch/loongarch/mm/hugetlbpage.c +3 -3

index 1e76fcb83093..62ddcea0aa14 100644
@@ -39,11 +39,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
+	if (pgd_present(pgdp_get(pgd))) {
 		p4d = p4d_offset(pgd, addr);
-		if (p4d_present(*p4d)) {
+		if (p4d_present(p4dp_get(p4d))) {
 			pud = pud_offset(p4d, addr);
-			if (pud_present(*pud))
+			if (pud_present(pudp_get(pud)))
 				pmd = pmd_offset(pud, addr);
 		}
 	}

arch/loongarch/mm/init.c +5 -5

index 4dd53427f657..71fa4b773eb3 100644
@@ -140,7 +140,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
 int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
 				unsigned long addr, unsigned long next)
 {
-	int huge = pmd_val(*pmd) & _PAGE_HUGE;
+	int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE;
 
 	if (huge)
 		vmemmap_verify((pte_t *)pmd, node, addr, next);

@@ -172,7 +172,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pud)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -183,7 +183,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pmd)
 			panic("%s: Failed to allocate memory\n", __func__);

@@ -194,7 +194,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	}
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(pmdp_get(pmd))) {
 		pte_t *pte;
 
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);

@@ -215,7 +215,7 @@ void __init __set_fixmap(enum fixed_addresses idx,
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
 	ptep = populate_kernel_pte(addr);
-	if (!pte_none(*ptep)) {
+	if (!pte_none(ptep_get(ptep))) {
 		pte_ERROR(*ptep);
 		return;
 	}

arch/loongarch/mm/kasan_init.c +5 -5

index c608adc99845..427d6b1aec09 100644
@@ -105,7 +105,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node)
 
 static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early)
 {
-	if (__pmd_none(early, READ_ONCE(*pmdp))) {
+	if (__pmd_none(early, pmdp_get(pmdp))) {
 		phys_addr_t pte_phys = early ?
 				__pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -118,7 +118,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
 
 static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early)
 {
-	if (__pud_none(early, READ_ONCE(*pudp))) {
+	if (__pud_none(early, pudp_get(pudp))) {
 		phys_addr_t pmd_phys = early ?
 				__pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -131,7 +131,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 
 static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early)
 {
-	if (__p4d_none(early, READ_ONCE(*p4dp))) {
+	if (__p4d_none(early, p4dp_get(p4dp))) {
 		phys_addr_t pud_phys = early ?
 			__pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
 		if (!early)

@@ -154,7 +154,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 					      : kasan_alloc_zeroed_page(node);
 		next = addr + PAGE_SIZE;
 		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep)));
+	} while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep)));
 }
 
 static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,

@@ -166,7 +166,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		kasan_pte_populate(pmdp, addr, next, node, early);
-	} while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp)));
+	} while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp)));
 }
 
 static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,

arch/loongarch/mm/pgtable.c +1 -1

index 2aae72e63871..6a038a27373a 100644
@@ -128,7 +128,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot)
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 	flush_tlb_all();
 }

Signature · 1 line

2.45.2

Greg KH

author maintainer

2024-09-13 14:27 UTC #6 lore raw

Re: [PATCH 6.6.y RESEND 2/2] LoongArch: Use accessors to page table entries instead of direct dereference

Quoted 9 lines · He Lugang

From: Huacai Chen <[email protected]>
commit 4574815abf43e2bf05643e1b3f7a2e5d6df894f0 upstream
As very well explained in commit 20a004e7b017cce282 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables"), an architecture whose page table walker can modify the PTE in parallel must use READ_ONCE()/ WRITE_ONCE() macro to avoid any compiler transformation.

Quoted 7 lines

So apply that to LoongArch which is such an architecture, in order to avoid potential problems.
Similar to commit edf955647269422e ("riscv: Use accessors to page table entries instead of direct dereference").
Signed-off-by Huacai Chen <[email protected]>

You did not sign off on this, so I'm dropping it :(

He Lugang

2024-09-10 13:12 UTC #7 lore raw

PATCH RESEND 1/2 LoongArch: KVM: Implement kvm mmu operations

In reply to [email protected]

From: Tianrui Zhao <[email protected]>

commit 752e2cd7b4fb412f3e008493e0195e357bab9773 upstream

Implement LoongArch kvm mmu, it is used to switch gpa to hpa when guest exit because of address translation exception.

This patch implement: allocating gpa page table, searching gpa from it, and flushing guest gpa in the table.

Reviewed-by Bibo Mao <[email protected]>

Tested-by Huacai Chen <[email protected]>

Signed-off-by Tianrui Zhao <[email protected]>

Signed-off-by Huacai Chen <[email protected]>

Signed-off-by He Lugang <[email protected]>

---
 arch/loongarch/include/asm/kvm_mmu.h | 139 ++++
 arch/loongarch/kvm/mmu.c             | 914 +++++++++++++++++++++++++++
 2 files changed, 1053 insertions(+)
 create mode 100644 arch/loongarch/include/asm/kvm_mmu.h
 create mode 100644 arch/loongarch/kvm/mmu.c

arch/loongarch/include/asm/kvm_mmu.h new file +139 -0

new file mode 100644
index 000000000000..099bafc6f797
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_MMU_H__
+#define __ASM_LOONGARCH_KVM_MMU_H__
+
+#include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels
+ * for which pages need to be cached.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	(CONFIG_PGTABLE_LEVELS - 1)
+
+#define _KVM_FLUSH_PGTABLE	0x1
+#define _KVM_HAS_PGMASK		0x2
+#define kvm_pfn_pte(pfn, prot)	(((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
+#define kvm_pte_pfn(x)		((phys_addr_t)((x & _PFN_MASK) >> PFN_PTE_SHIFT))
+
+typedef unsigned long kvm_pte_t;
+typedef struct kvm_ptw_ctx kvm_ptw_ctx;
+typedef int (*kvm_pte_ops)(kvm_pte_t *pte, phys_addr_t addr, kvm_ptw_ctx *ctx);
+
+struct kvm_ptw_ctx {
+	kvm_pte_ops     ops;
+	unsigned long   flag;
+
+	/* for kvm_arch_mmu_enable_log_dirty_pt_masked use */
+	unsigned long   mask;
+	unsigned long   gfn;
+
+	/* page walk mmu info */
+	unsigned int    level;
+	unsigned long   pgtable_shift;
+	unsigned long   invalid_entry;
+	unsigned long   *invalid_ptes;
+	unsigned int    *pte_shifts;
+	void		*opaque;
+
+	/* free pte table page list */
+	struct list_head list;
+};
+
+kvm_pte_t *kvm_pgd_alloc(void);
+
+static inline void kvm_set_pte(kvm_pte_t *ptep, kvm_pte_t val)
+{
+	WRITE_ONCE(*ptep, val);
+}
+
+static inline int kvm_pte_write(kvm_pte_t pte) { return pte & _PAGE_WRITE; }
+static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & _PAGE_DIRTY; }
+static inline int kvm_pte_young(kvm_pte_t pte) { return pte & _PAGE_ACCESSED; }
+static inline int kvm_pte_huge(kvm_pte_t pte) { return pte & _PAGE_HUGE; }
+
+static inline kvm_pte_t kvm_pte_mkyoung(kvm_pte_t pte)
+{
+	return pte | _PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkold(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkdirty(kvm_pte_t pte)
+{
+	return pte | _PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkclean(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkhuge(kvm_pte_t pte)
+{
+	return pte | _PAGE_HUGE;
+}
+
+static inline kvm_pte_t kvm_pte_mksmall(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_HUGE;
+}
+
+static inline int kvm_need_flush(kvm_ptw_ctx *ctx)
+{
+	return ctx->flag & _KVM_FLUSH_PGTABLE;
+}
+
+static inline kvm_pte_t *kvm_pgtable_offset(kvm_ptw_ctx *ctx, kvm_pte_t *table,
+					phys_addr_t addr)
+{
+
+	return table + ((addr >> ctx->pgtable_shift) & (PTRS_PER_PTE - 1));
+}
+
+static inline phys_addr_t kvm_pgtable_addr_end(kvm_ptw_ctx *ctx,
+				phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary, size;
+
+	size = 0x1UL << ctx->pgtable_shift;
+	boundary = (addr + size) & ~(size - 1);
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+static inline int kvm_pte_present(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	if (!ctx || ctx->level == 0)
+		return !!(*entry & _PAGE_PRESENT);
+
+	return *entry != ctx->invalid_entry;
+}
+
+static inline int kvm_pte_none(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	return *entry == ctx->invalid_entry;
+}
+
+static inline void kvm_ptw_enter(kvm_ptw_ctx *ctx)
+{
+	ctx->level--;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+static inline void kvm_ptw_exit(kvm_ptw_ctx *ctx)
+{
+	ctx->level++;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+#endif /* __ASM_LOONGARCH_KVM_MMU_H__ */

arch/loongarch/kvm/mmu.c new file +914 -0

914 lines not on this page · raw message

Signature · 1 line

2.45.2