powerpc/mm: Add addr_limit to mm_context and use it to derive max slice index

In the followup patch, we will increase the slice array size to handle
512TB range, but will limit the max addr to 128TB. Avoid doing
unnecessary computation and avoid doing slice mask related operation
above address limit.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -598,6 +598,7 @@ extern void slb_set_size(u16 size);
 
 /* 4 bits per slice and we have one slice per 1TB */
 #define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
+#define TASK_SLICE_ARRAY_SZ(x)	((x)->context.addr_limit >> 41)
 
 #ifndef __ASSEMBLY__
 

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

@@ -82,6 +82,7 @@ typedef struct {
 #ifdef CONFIG_PPC_MM_SLICES
 	u64 low_slices_psize;	/* SLB page size encodings */
 	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+	unsigned long addr_limit;
 #else
 	u16 sllp;		/* SLB page size encoding */
 #endif

arch/powerpc/kernel/paca.c

@@ -253,9 +253,10 @@ void copy_mm_to_paca(struct mm_struct *mm)
 
 	get_paca()->mm_ctx_id = context->id;
 #ifdef CONFIG_PPC_MM_SLICES
+	VM_BUG_ON(!mm->context.addr_limit);
 	get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
 	memcpy(&get_paca()->mm_ctx_high_slices_psize,
-	       &context->high_slices_psize, SLICE_ARRAY_SIZE);
+	       &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
 #else /* CONFIG_PPC_MM_SLICES */
 	get_paca()->mm_ctx_user_psize = context->user_psize;
 	get_paca()->mm_ctx_sllp = context->sllp;

arch/powerpc/kernel/setup-common.c

@@ -920,6 +920,15 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_code = (unsigned long) _etext;
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
+
+#ifdef CONFIG_PPC_MM_SLICES
+#ifdef CONFIG_PPC64
+	init_mm.context.addr_limit = TASK_SIZE_USER64;
+#else
+#error	"context.addr_limit not initialized."
+#endif
+#endif
+
 #ifdef CONFIG_PPC_64K_PAGES
 	init_mm.context.pte_frag = NULL;
 #endif

arch/powerpc/mm/mmu_context_book3s64.c

@@ -78,6 +78,13 @@ static int hash__init_new_context(struct mm_struct *mm)
 	if (index < 0)
 		return index;
 
+	/*
+	 * We do switch_slb() early in fork, even before we setup the
+	 * mm->context.addr_limit. Default to max task size so that we copy the
+	 * default values to paca which will help us to handle slb miss early.
+	 */
+	mm->context.addr_limit = TASK_SIZE_USER64;
+
 	/*
 	 * The old code would re-promote on fork, we don't do that when using
 	 * slices as it could cause problem promoting slices that have been

arch/powerpc/mm/slice.c

@@ -136,7 +136,7 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret)
 	if (mm->task_size <= SLICE_LOW_TOP)
 		return;
 
-	for (i = 0; i < SLICE_NUM_HIGH; i++)
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++)
 		if (!slice_high_has_vma(mm, i))
 			__set_bit(i, ret->high_slices);
 }
@@ -157,7 +157,7 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
 			ret->low_slices |= 1u << i;
 
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < SLICE_NUM_HIGH; i++) {
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) {
 		mask_index = i & 0x1;
 		index = i >> 1;
 		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
@@ -165,15 +165,17 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
 	}
 }
 
-static int slice_check_fit(struct slice_mask mask, struct slice_mask available)
+static int slice_check_fit(struct mm_struct *mm,
+			   struct slice_mask mask, struct slice_mask available)
 {
 	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.addr_limit);
 
 	bitmap_and(result, mask.high_slices,
-		   available.high_slices, SLICE_NUM_HIGH);
+		   available.high_slices, slice_count);
 
 	return (mask.low_slices & available.low_slices) == mask.low_slices &&
-		bitmap_equal(result, mask.high_slices, SLICE_NUM_HIGH);
+		bitmap_equal(result, mask.high_slices, slice_count);
 }
 
 static void slice_flush_segments(void *parm)
@@ -217,7 +219,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
 	mm->context.low_slices_psize = lpsizes;
 
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < SLICE_NUM_HIGH; i++) {
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) {
 		mask_index = i & 0x1;
 		index = i >> 1;
 		if (test_bit(i, mask.high_slices))
@@ -484,7 +486,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 		/* Check if we fit in the good mask. If we do, we just return,
 		 * nothing else to do
 		 */
-		if (slice_check_fit(mask, good_mask)) {
+		if (slice_check_fit(mm, mask, good_mask)) {
 			slice_dbg(" fits good !\n");
 			return addr;
 		}
@@ -509,7 +511,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	slice_or_mask(&potential_mask, &good_mask);
 	slice_print_mask(" potential", potential_mask);
 
-	if ((addr != 0 || fixed) && slice_check_fit(mask, potential_mask)) {
+	if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) {
 		slice_dbg(" fits potential !\n");
 		goto convert;
 	}
@@ -734,6 +736,6 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 	slice_print_mask(" mask", mask);
 	slice_print_mask(" available", available);
 #endif
-	return !slice_check_fit(mask, available);
+	return !slice_check_fit(mm, mask, available);
 }
 #endif