Automatic merge of 'next' into merge (2024-09-06 20:41)

arch/powerpc/Kconfig

@@ -853,8 +853,8 @@ config DATA_SHIFT_BOOL
 	bool "Set custom data alignment"
 	depends on ADVANCED_OPTIONS
 	depends on STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE
-	depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) || \
-		   PPC_85xx
+	depends on (PPC_8xx && !PIN_TLB_DATA && (!STRICT_KERNEL_RWX || !PIN_TLB_TEXT)) || \
+		   PPC_BOOK3S_32 || PPC_85xx
 	help
 	  This option allows you to set the kernel data alignment. When
 	  RAM is mapped by blocks, the alignment needs to fit the size and
@@ -870,9 +870,9 @@ config DATA_SHIFT
 	range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_85xx
 	default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
 	default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
-	default 23 if STRICT_KERNEL_RWX && PPC_8xx
-	default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA
-	default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
+	default 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && \
+		      (PIN_TLB_DATA || PIN_TLB_TEXT)
+	default 19 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
 	default 24 if STRICT_KERNEL_RWX && PPC_85xx
 	default PAGE_SHIFT
 	help
@@ -1269,8 +1269,27 @@ config TASK_SIZE_BOOL
 config TASK_SIZE
 	hex "Size of user task space" if TASK_SIZE_BOOL
 	default "0x80000000" if PPC_8xx
-	default "0xb0000000" if PPC_BOOK3S_32
+	default "0xb0000000" if PPC_BOOK3S_32 && EXECMEM
 	default "0xc0000000"
+
+config MODULES_SIZE_BOOL
+	bool "Set custom size for modules/execmem area"
+	depends on EXECMEM && ADVANCED_OPTIONS
+	help
+	  This option allows you to set the size of kernel virtual address
+	  space dedicated for modules/execmem.
+	  For the time being it is only for 8xx and book3s/32. Other
+	  platform share it with vmalloc space.
+
+	  Say N here unless you know what you are doing.
+
+config MODULES_SIZE
+	int "Size of modules/execmem area (In Mbytes)" if MODULES_SIZE_BOOL
+	range 1 256 if EXECMEM
+	default 64 if EXECMEM && PPC_BOOK3S_32
+	default 32 if EXECMEM && PPC_8xx
+	default 0
+
 endmenu
 
 if PPC64

arch/powerpc/configs/ppc64_defconfig

@@ -93,6 +93,7 @@ CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_MEM_SOFT_DIRTY=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_ZONE_DEVICE=y
 CONFIG_NET=y
 CONFIG_PACKET=y

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -196,7 +196,8 @@ void unmap_kernel_page(unsigned long va);
 #endif
 
 #define MODULES_END	ALIGN_DOWN(PAGE_OFFSET, SZ_256M)
-#define MODULES_VADDR	(MODULES_END - SZ_256M)
+#define MODULES_SIZE	(CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR	(MODULES_END - MODULES_SIZE)
 
 #ifndef __ASSEMBLY__
 #include <linux/sched.h>

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -74,6 +74,26 @@
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
 
+/*
+ * With 4K page size the real_pte machinery is all nops.
+ */
+#define __real_pte(e, p, o)		((real_pte_t){(e)})
+#define __rpte_to_pte(r)	((r).pte)
+#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
+
 /*
  * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
  * a matter of returning the PTE bits that need to be modified. On 64K PTE,

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -330,32 +330,6 @@ static inline unsigned long pud_leaf_size(pud_t pud)
 
 #ifndef __ASSEMBLY__
 
-/*
- * This is the default implementation of various PTE accessors, it's
- * used in all cases except Book3S with 64K pages where we have a
- * concept of sub-pages
- */
-#ifndef __real_pte
-
-#define __real_pte(e, p, o)		((real_pte_t){(e)})
-#define __rpte_to_pte(r)	((r).pte)
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
-
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
-	do {							         \
-		index = 0;					         \
-		shift = mmu_psize_defs[psize].shift;		         \
-
-#define pte_iterate_hashed_end() } while(0)
-
-/*
- * We expect this to be called only for user addresses or kernel virtual
- * addresses other than the linear mapping.
- */
-#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
-
-#endif /* __real_pte */
-
 static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr,
 				       pte_t *ptep, unsigned long clr,
 				       unsigned long set, int huge)

arch/powerpc/include/asm/mmu_context.h

@@ -116,9 +116,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
 }
 #endif
 
-extern int use_cop(unsigned long acop, struct mm_struct *mm);
-extern void drop_cop(unsigned long acop, struct mm_struct *mm);
-
 #ifdef CONFIG_PPC_BOOK3S_64
 static inline void inc_mm_active_cpus(struct mm_struct *mm)
 {

arch/powerpc/include/asm/nohash/32/mmu-8xx.h

@@ -170,8 +170,9 @@
 
 #define mmu_linear_psize	MMU_PAGE_8M
 
-#define MODULES_VADDR	(PAGE_OFFSET - SZ_256M)
 #define MODULES_END	PAGE_OFFSET
+#define MODULES_SIZE	(CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR	(MODULES_END - MODULES_SIZE)
 
 #ifndef __ASSEMBLY__
 

arch/powerpc/include/asm/nohash/pgalloc.h

@@ -19,8 +19,14 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+	pgd_t *pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
 			pgtable_gfp_flags(mm, GFP_KERNEL));
+
+#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_BOOK3S_603)
+	memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD,
+	       (MAX_PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+#endif
+	return pgd;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)

arch/powerpc/include/asm/thread_info.h

@@ -226,6 +226,10 @@ static inline int arch_within_stack_frames(const void * const stack,
 	return BAD_STACK;
 }
 
+#ifdef CONFIG_PPC32
+extern void *emergency_ctx[];
+#endif
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

arch/powerpc/kernel/head_8xx.S

@@ -40,16 +40,6 @@
 
 #include "head_32.h"
 
-.macro compare_to_kernel_boundary scratch, addr
-#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
-/* By simply checking Address >= 0x80000000, we know if its a kernel address */
-	not.	\scratch, \addr
-#else
-	rlwinm	\scratch, \addr, 16, 0xfff8
-	cmpli	cr0, \scratch, PAGE_OFFSET@h
-#endif
-.endm
-
 #define PAGE_SHIFT_512K		19
 #define PAGE_SHIFT_8M		23
 
@@ -199,18 +189,7 @@ instruction_counter:
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 	INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
 	mtspr	SPRN_MD_EPN, r10
-#ifdef CONFIG_EXECMEM
-	mfcr	r11
-	compare_to_kernel_boundary r10, r10
-#endif
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
-#ifdef CONFIG_EXECMEM
-	blt+	3f
-	rlwinm	r10, r10, 0, 20, 31
-	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
-	mtcr	r11
-#endif
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
 	mfspr	r10, SPRN_MD_TWC
@@ -248,19 +227,12 @@ instruction_counter:
 	START_EXCEPTION(INTERRUPT_DATA_TLB_MISS_8xx, DataStoreTLBMiss)
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mtspr	SPRN_M_TW, r11
-	mfcr	r11
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
 	mfspr	r10, SPRN_MD_EPN
-	compare_to_kernel_boundary r10, r10
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
-	blt+	3f
-	rlwinm	r10, r10, 0, 20, 31
-	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
-	mtcr	r11
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
 
 	mtspr	SPRN_MD_TWC, r11
@@ -332,15 +304,19 @@ instruction_counter:
 	cmpwi	cr1, r11, RPN_PATTERN
 	beq-	cr1, FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
+	mfspr	r11, SPRN_DSISR
+	rlwinm	r11, r11, 0, DSISR_NOHPTE
+	cmpwi	cr1, r11, 0
+	beq+	cr1, .Ldtlbie
+	mfspr	r11, SPRN_DAR
+	tlbie	r11
+	rlwinm	r11, r11, 16, 0xffff
+	cmplwi	cr1, r11, TASK_SIZE@h
+	bge-	cr1, FixupPGD
+.Ldtlbie:
 	EXCEPTION_PROLOG_1
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataTLBError handle_dar_dsisr=1
-	lwz	r4, _DAR(r11)
-	lwz	r5, _DSISR(r11)
-	andis.	r10,r5,DSISR_NOHPTE@h
-	beq+	.Ldtlbie
-	tlbie	r4
-.Ldtlbie:
 	prepare_transfer_to_handler
 	bl	do_page_fault
 	b	interrupt_return
@@ -394,6 +370,30 @@ DARFixed:/* Return from dcbx instruction bug workaround */
 	__HEAD
 	. = 0x2000
 
+FixupPGD:
+	mtspr	SPRN_M_TW, r10
+	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_MD_EPN, r10
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
+	lwz	r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	cmpwi	cr1, r10, 0
+	bne	cr1, 1f
+
+	rlwinm	r10, r11, 0, 20, 31
+	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
+	lwz	r10, (swapper_pg_dir - PAGE_OFFSET)@l(r10)	/* Get the level 1 entry */
+	cmpwi	cr1, r10, 0
+	beq	cr1, 1f
+	stw	r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11)	/* Set the level 1 entry */
+	mfspr	r10, SPRN_M_TW
+	mtcr	r10
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+1:
+	mfspr	r10, SPRN_M_TW
+	b	.Ldtlbie
+
 /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
  * by decoding the registers used by the dcbx instruction and adding them.
  * DAR is set to the calculated address.
@@ -404,7 +404,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mfspr	r10, SPRN_SRR0
 	mtspr	SPRN_MD_EPN, r10
 	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr1, r11, PAGE_OFFSET@h
+	cmpli	cr1, r11, TASK_SIZE@h
 	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
 	blt+	cr1, 3f
 
@@ -587,6 +587,10 @@ start_here:
 	lis	r0, (MD_TWAM | MD_RSV4I)@h
 	mtspr	SPRN_MD_CTR, r0
 #endif
+#ifndef CONFIG_PIN_TLB_TEXT
+	li	r0, 0
+	mtspr	SPRN_MI_CTR, r0
+#endif
 #if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR)
 	lis	r0, MD_TWAM@h
 	mtspr	SPRN_MD_CTR, r0
@@ -683,6 +687,7 @@ SYM_FUNC_START_LOCAL(initial_mmu)
 	blr
 SYM_FUNC_END(initial_mmu)
 
+#ifdef CONFIG_PIN_TLB
 _GLOBAL(mmu_pin_tlb)
 	lis	r9, (1f - PAGE_OFFSET)@h
 	ori	r9, r9, (1f - PAGE_OFFSET)@l
@@ -704,6 +709,7 @@ _GLOBAL(mmu_pin_tlb)
 	mtspr	SPRN_MD_CTR, r6
 	tlbia
 
+#ifdef CONFIG_PIN_TLB_TEXT
 	LOAD_REG_IMMEDIATE(r5, 28 << 8)
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
 	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
@@ -724,6 +730,7 @@ _GLOBAL(mmu_pin_tlb)
 	bdnzt	lt, 2b
 	lis	r0, MI_RSV4I@h
 	mtspr	SPRN_MI_CTR, r0
+#endif
 
 	LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
 #ifdef CONFIG_PIN_TLB_DATA
@@ -783,3 +790,4 @@ _GLOBAL(mmu_pin_tlb)
 	mtspr	SPRN_SRR1, r10
 	mtspr	SPRN_SRR0, r11
 	rfi
+#endif