[PATCH V6 0/4] Add support for 4PB virtual address space on hash

[PATCH V6 0/4] Add support for 4PB virtual address space on hash

[Aneesh Kumar K.V]

This patch series extended the max virtual address space value from 512TB
to 4PB with 64K page size. We do that by allocating one vsid context for
each 512TB range. More details of that is explained in patch 3.

Changes from V5:
* Fix for loop segmentation fault.
* updates from Michael

Changes from V4:
* Move context allocation to mmap time instead of SLB miss time
* Address review comments 

Changes from V3:
* move extended_id to be a union with mm_context_t id. This reduce some
 array index complexity.
* Add addr_limit check when handling slb miss for extended context

Changes from V2:
* Rebased on top of slice_mask series from Nick Piggin
* Fixed segfault when mmap with 512TB hint address


Aneesh Kumar K.V (4):
  powerpc/mm/slice: Consolidate return path in slice_get_unmapped_area()
  powerpc/mm: Add support for handling > 512TB address in SLB miss
  powerpc/mm/hash64: Increase the VA range
  powerpc/mm/hash: Don't memset pgd table if not needed

 arch/powerpc/include/asm/book3s/64/hash-4k.h  |   6 ++
 arch/powerpc/include/asm/book3s/64/hash-64k.h |   8 +-
 arch/powerpc/include/asm/book3s/64/mmu.h      |  33 +++++++-
 arch/powerpc/include/asm/book3s/64/pgalloc.h  |  12 ++-
 arch/powerpc/include/asm/mmu_context.h        |  39 ++++++++++
 arch/powerpc/include/asm/processor.h          |  15 +++-
 arch/powerpc/kernel/exceptions-64s.S          |  11 ++-
 arch/powerpc/kernel/traps.c                   |  12 ---
 arch/powerpc/mm/copro_fault.c                 |   2 +-
 arch/powerpc/mm/hash_utils_64.c               |   4 +-
 arch/powerpc/mm/init_64.c                     |   6 --
 arch/powerpc/mm/mmu_context_book3s64.c        |  15 +++-
 arch/powerpc/mm/pgtable-hash64.c              |   6 +-
 arch/powerpc/mm/pgtable_64.c                  |   5 --
 arch/powerpc/mm/slb.c                         | 108 ++++++++++++++++++++++++++
 arch/powerpc/mm/slb_low.S                     |  11 ++-
 arch/powerpc/mm/slice.c                       |  49 ++++++++----
 arch/powerpc/mm/tlb_hash64.c                  |   2 +-
 18 files changed, 288 insertions(+), 56 deletions(-)

-- 
2.14.3

[PATCH V6 1/4] powerpc/mm/slice: Consolidate return path in slice_get_unmapped_area()

[Aneesh Kumar K.V]

In a following patch, on finding a free area we will need to do
allocatinon of extra contexts as needed. Consolidating the return path
for slice_get_unmapped_area() will make that easier.

Split into a separate patch to make review easy.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/mm/slice.c | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 1297b3ad7dd2..09ac1a709d0c 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -574,7 +574,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 		 */
 		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
 			slice_dbg(" fits good !\n");
-			return addr;
+			newaddr = addr;
+			goto return_addr;
 		}
 	} else {
 		/* Now let's see if we can find something in the existing
@@ -587,7 +588,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 			 * we thus return directly
 			 */
 			slice_dbg(" found area at 0x%lx\n", newaddr);
-			return newaddr;
+			goto return_addr;
 		}
 	}
 	/*
@@ -601,6 +602,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	if (addr != 0 || fixed) {
 		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
 			slice_dbg(" fits potential !\n");
+			newaddr = addr;
 			goto convert;
 		}
 	}
@@ -615,34 +617,34 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * anywhere in the good area.
 	 */
 	if (addr) {
-		addr = slice_find_area(mm, len, &good_mask,
-				       psize, topdown, high_limit);
-		if (addr != -ENOMEM) {
-			slice_dbg(" found area at 0x%lx\n", addr);
-			return addr;
+		newaddr = slice_find_area(mm, len, &good_mask,
+					  psize, topdown, high_limit);
+		if (newaddr != -ENOMEM) {
+			slice_dbg(" found area at 0x%lx\n", newaddr);
+			goto return_addr;
 		}
 	}
 
 	/* Now let's see if we can find something in the existing slices
 	 * for that size plus free slices
 	 */
-	addr = slice_find_area(mm, len, &potential_mask,
-			       psize, topdown, high_limit);
+	newaddr = slice_find_area(mm, len, &potential_mask,
+				  psize, topdown, high_limit);
 
 #ifdef CONFIG_PPC_64K_PAGES
-	if (addr == -ENOMEM && psize == MMU_PAGE_64K) {
+	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
 		/* retry the search with 4k-page slices included */
 		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
-		addr = slice_find_area(mm, len, &potential_mask,
-				       psize, topdown, high_limit);
+		newaddr = slice_find_area(mm, len, &potential_mask,
+					  psize, topdown, high_limit);
 	}
 #endif
 
-	if (addr == -ENOMEM)
+	if (newaddr == -ENOMEM)
 		return -ENOMEM;
 
-	slice_range_to_mask(addr, len, &potential_mask);
-	slice_dbg(" found potential area at 0x%lx\n", addr);
+	slice_range_to_mask(newaddr, len, &potential_mask);
+	slice_dbg(" found potential area at 0x%lx\n", newaddr);
 	slice_print_mask(" mask", &potential_mask);
 
  convert:
@@ -656,7 +658,9 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
 	}
-	return addr;
+
+return_addr:
+	return newaddr;
 
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
-- 
2.14.3

[PATCH V6 2/4] powerpc/mm: Add support for handling > 512TB address in SLB miss

[Aneesh Kumar K.V]

For addresses above 512TB we allocate additional mmu contexts. To make
it all easy, addresses above 512TB are handled with IR/DR=1 and with
stack frame setup.

The mmu_context_t is also updated to track the new extended_ids. To
support upto 4PB we need a total 8 contexts.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Minor formatting tweaks and comment wording, switch BUG to WARN
      in get_ea_context().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  |   6 ++
 arch/powerpc/include/asm/book3s/64/hash-64k.h |   6 ++
 arch/powerpc/include/asm/book3s/64/mmu.h      |  33 +++++++-
 arch/powerpc/include/asm/mmu_context.h        |  39 ++++++++++
 arch/powerpc/include/asm/processor.h          |   6 ++
 arch/powerpc/kernel/exceptions-64s.S          |  11 ++-
 arch/powerpc/kernel/traps.c                   |  12 ---
 arch/powerpc/mm/copro_fault.c                 |   2 +-
 arch/powerpc/mm/hash_utils_64.c               |   4 +-
 arch/powerpc/mm/mmu_context_book3s64.c        |  15 +++-
 arch/powerpc/mm/pgtable-hash64.c              |   2 +-
 arch/powerpc/mm/slb.c                         | 108 ++++++++++++++++++++++++++
 arch/powerpc/mm/slb_low.S                     |  11 ++-
 arch/powerpc/mm/slice.c                       |  15 +++-
 arch/powerpc/mm/tlb_hash64.c                  |   2 +-
 15 files changed, 245 insertions(+), 27 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 67c5475311ee..1a35eb944481 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -11,6 +11,12 @@
 #define H_PUD_INDEX_SIZE  9
 #define H_PGD_INDEX_SIZE  9
 
+/*
+ * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB
+ * Hence also limit max EA bits to 64TB.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		46
+
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
 #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 3bcf269f8f55..8d0cbbb31023 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -7,6 +7,12 @@
 #define H_PUD_INDEX_SIZE  7
 #define H_PGD_INDEX_SIZE  8
 
+/*
+ * Each context is 512TB size. SLB miss for first context/default context
+ * is handled in the hotpath.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		49
+
 /*
  * 64k aligned address free up few of the lower bits of RPN for us
  * We steal that here. For more deatils look at pte_pfn/pfn_pte()
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index c8c836e8ad1b..5094696eecd6 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -91,7 +91,18 @@ struct slice_mask {
 };
 
 typedef struct {
-	mm_context_id_t id;
+	union {
+		/*
+		 * We use id as the PIDR content for radix. On hash we can use
+		 * more than one id. The extended ids are used when we start
+		 * having address above 512TB. We allocate one extended id
+		 * for each 512TB. The new id is then used with the 49 bit
+		 * EA to build a new VA. We always use ESID_BITS_1T_MASK bits
+		 * from EA and new context ids to build the new VAs.
+		 */
+		mm_context_id_t id;
+		mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE];
+	};
 	u16 user_psize;		/* page size index */
 
 	/* Number of bits in the mm_cpumask */
@@ -196,5 +207,25 @@ extern void radix_init_pseries(void);
 static inline void radix_init_pseries(void) { };
 #endif
 
+static inline int get_ea_context(mm_context_t *ctx, unsigned long ea)
+{
+	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
+
+	if (likely(index < ARRAY_SIZE(ctx->extended_id)))
+		return ctx->extended_id[index];
+
+	/* should never happen */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline unsigned long get_user_vsid(mm_context_t *ctx,
+					  unsigned long ea, int ssize)
+{
+	unsigned long context = get_ea_context(ctx, ea);
+
+	return get_vsid(context, ea, ssize);
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 3a15b6db9501..1835ca1505d6 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -60,12 +60,51 @@ extern int hash__alloc_context_id(void);
 extern void hash__reserve_context_id(int id);
 extern void __destroy_context(int context_id);
 static inline void mmu_context_init(void) { }
+
+static inline int alloc_extended_context(struct mm_struct *mm,
+					 unsigned long ea)
+{
+	int context_id;
+
+	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
+
+	context_id = hash__alloc_context_id();
+	if (context_id < 0)
+		return context_id;
+
+	VM_WARN_ON(mm->context.extended_id[index]);
+	mm->context.extended_id[index] = context_id;
+	return context_id;
+}
+
+static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
+{
+	int context_id;
+
+	context_id = get_ea_context(&mm->context, ea);
+	if (!context_id)
+		return true;
+	return false;
+}
+
 #else
 extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
 			       struct task_struct *tsk);
 extern unsigned long __init_new_context(void);
 extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
+static inline int alloc_extended_context(struct mm_struct *mm,
+					 unsigned long ea)
+{
+	/* non book3s_64 should never find this called */
+	WARN_ON(1);
+	return -ENOMEM;
+}
+
+static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
+{
+	return false;
+}
 #endif
 
 #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 01299cdc9806..75b084486ce1 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -119,9 +119,15 @@ void release_thread(struct task_struct *);
  */
 #define TASK_SIZE_USER64		TASK_SIZE_512TB
 #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
+#define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
 #else
 #define TASK_SIZE_USER64		TASK_SIZE_64TB
 #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
+/*
+ * We don't need to allocate extended context ids for 4K page size, because
+ * we limit the max effective address on this config to 64TB.
+ */
+#define TASK_CONTEXT_SIZE		TASK_SIZE_64TB
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6bee20c43feb..1a0aa70bcb2b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -621,7 +621,10 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
 	mtlr	r10
 
-	beq-	8f		/* if bad address, make full stack frame */
+	/*
+	 * Large address, check whether we have to allocate new contexts.
+	 */
+	beq-	8f
 
 	bne-	cr5,2f		/* if unrecoverable exception, oops */
 
@@ -685,7 +688,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mr	r3,r12
 	mfspr	r11,SPRN_SRR0
 	mfspr	r12,SPRN_SRR1
-	LOAD_HANDLER(r10,bad_addr_slb)
+	LOAD_HANDLER(r10, large_addr_slb)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
@@ -700,7 +703,7 @@ EXC_COMMON_BEGIN(unrecov_slb)
 	bl	unrecoverable_exception
 	b	1b
 
-EXC_COMMON_BEGIN(bad_addr_slb)
+EXC_COMMON_BEGIN(large_addr_slb)
 	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r3, PACA_EXSLB+EX_DAR(r13)
@@ -710,7 +713,7 @@ EXC_COMMON_BEGIN(bad_addr_slb)
 	std	r10, _TRAP(r1)
 2:	bl	save_nvgprs
 	addi	r3, r1, STACK_FRAME_OVERHEAD
-	bl	slb_miss_bad_addr
+	bl	slb_miss_large_addr
 	b	ret_from_except
 
 EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1e48d157196a..f200bfd98b17 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1495,18 +1495,6 @@ void alignment_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void slb_miss_bad_addr(struct pt_regs *regs)
-{
-	enum ctx_state prev_state = exception_enter();
-
-	if (user_mode(regs))
-		_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
-	else
-		bad_page_fault(regs, regs->dar, SIGSEGV);
-
-	exception_exit(prev_state);
-}
-
 void StackOverflow(struct pt_regs *regs)
 {
 	printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n",
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 697b70ad1195..7d0945bd3a61 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -112,7 +112,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 			return 1;
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		vsidkey = SLB_VSID_USER;
 		break;
 	case VMALLOC_REGION_ID:
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index b578148d89e6..f62325d4f5f5 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1261,7 +1261,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		}
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		break;
 	case VMALLOC_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
@@ -1526,7 +1526,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 
 	/* Get VSID */
 	ssize = user_segment_size(ea);
-	vsid = get_vsid(mm->context.id, ea, ssize);
+	vsid = get_user_vsid(&mm->context, ea, ssize);
 	if (!vsid)
 		return;
 	/*
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 422be81bf69f..b75194dff64c 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -179,6 +179,19 @@ void __destroy_context(int context_id)
 }
 EXPORT_SYMBOL_GPL(__destroy_context);
 
+static void destroy_contexts(mm_context_t *ctx)
+{
+	int index, context_id;
+
+	spin_lock(&mmu_context_lock);
+	for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) {
+		context_id = ctx->extended_id[index];
+		if (context_id)
+			ida_remove(&mmu_context_ida, context_id);
+	}
+	spin_unlock(&mmu_context_lock);
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 static void destroy_pagetable_page(struct mm_struct *mm)
 {
@@ -217,7 +230,7 @@ void destroy_context(struct mm_struct *mm)
 	else
 		subpage_prot_free(mm);
 	destroy_pagetable_page(mm);
-	__destroy_context(mm->context.id);
+	destroy_contexts(&mm->context);
 	mm->context.id = MMU_NO_CONTEXT;
 }
 
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index 469808e77e58..a87b18cf6749 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -320,7 +320,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 		WARN_ON(vsid == 0);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 13cfe413b40d..66577cc66dc9 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
 #include <linux/compiler.h>
+#include <linux/context_tracking.h>
 #include <linux/mm_types.h>
 
 #include <asm/udbg.h>
@@ -340,3 +341,110 @@ void slb_initialize(void)
 
 	asm volatile("isync":::"memory");
 }
+
+static void insert_slb_entry(unsigned long vsid, unsigned long ea,
+			     int bpsize, int ssize)
+{
+	unsigned long flags, vsid_data, esid_data;
+	enum slb_index index;
+	int slb_cache_index;
+
+	/*
+	 * We are irq disabled, hence should be safe to access PACA.
+	 */
+	index = get_paca()->stab_rr;
+
+	/*
+	 * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
+	 */
+	if (index < (mmu_slb_size - 1))
+		index++;
+	else
+		index = SLB_NUM_BOLTED;
+
+	get_paca()->stab_rr = index;
+
+	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
+	vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
+		    ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
+	esid_data = mk_esid_data(ea, ssize, index);
+
+	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
+		     : "memory");
+
+	/*
+	 * Now update slb cache entries
+	 */
+	slb_cache_index = get_paca()->slb_cache_ptr;
+	if (slb_cache_index < SLB_CACHE_ENTRIES) {
+		/*
+		 * We have space in slb cache for optimized switch_slb().
+		 * Top 36 bits from esid_data as per ISA
+		 */
+		get_paca()->slb_cache[slb_cache_index++] = esid_data >> 28;
+		get_paca()->slb_cache_ptr++;
+	} else {
+		/*
+		 * Our cache is full and the current cache content strictly
+		 * doesn't indicate the active SLB conents. Bump the ptr
+		 * so that switch_slb() will ignore the cache.
+		 */
+		get_paca()->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
+	}
+}
+
+static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long vsid;
+	int bpsize;
+
+	/*
+	 * We are always above 1TB, hence use high user segment size.
+	 */
+	vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
+	bpsize = get_slice_psize(mm, ea);
+	insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
+}
+
+void slb_miss_large_addr(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+	unsigned long ea = regs->dar;
+	int context;
+
+	if (REGION_ID(ea) != USER_REGION_ID)
+		goto slb_bad_addr;
+
+	/*
+	 * Are we beyound what the page table layout supports ?
+	 */
+	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
+		goto slb_bad_addr;
+
+	/* Lower address should have been handled by asm code */
+	if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
+		goto slb_bad_addr;
+
+	/*
+	 * consider this as bad access if we take a SLB miss
+	 * on an address above addr limit.
+	 */
+	if (ea >= current->mm->context.slb_addr_limit)
+		goto slb_bad_addr;
+
+	context = get_ea_context(&current->mm->context, ea);
+	if (!context)
+		goto slb_bad_addr;
+
+	handle_multi_context_slb_miss(context, ea);
+	exception_exit(prev_state);
+	return;
+
+slb_bad_addr:
+	if (user_mode(regs))
+		_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+	else
+		bad_page_fault(regs, ea, SIGSEGV);
+	exception_exit(prev_state);
+}
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 2c7c717fd2ea..a83fbd2a4a24 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -75,10 +75,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
  */
 _GLOBAL(slb_allocate)
 	/*
-	 * check for bad kernel/user address
-	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+	 * Check if the address falls within the range of the first context, or
+	 * if we may need to handle multi context. For the first context we
+	 * allocate the slb entry via the fast path below. For large address we
+	 * branch out to C-code and see if additional contexts have been
+	 * allocated.
+	 * The test here is:
+	 *   (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
 	 */
-	rldicr. r9,r3,4,(63 - H_PGTABLE_EADDR_SIZE - 4)
+	rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
 	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 09ac1a709d0c..9cd87d11fe4e 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -648,6 +648,15 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	slice_print_mask(" mask", &potential_mask);
 
  convert:
+	/*
+	 * Try to allocate the context before we do slice convert
+	 * so that we handle the context allocation failure gracefully.
+	 */
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+
 	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
 	if (compat_maskp && !fixed)
 		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
@@ -658,10 +667,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
 	}
+	return newaddr;
 
 return_addr:
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
 	return newaddr;
-
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 9b23f12e863c..87d71dd25441 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -89,7 +89,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	/* Build full vaddr */
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;
-- 
2.14.3

[PATCH V6 3/4] powerpc/mm/hash64: Increase the VA range

[Aneesh Kumar K.V]

This patch increases the max virtual (effective) address value to 4PB.
With 4K page size config we continue to limit ourself to 64TB.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Keep the H_PGTABLE_RANGE test, update it to work]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 2 +-
 arch/powerpc/include/asm/processor.h          | 9 ++++++++-
 arch/powerpc/mm/init_64.c                     | 6 ------
 arch/powerpc/mm/pgtable-hash64.c              | 4 ++++
 arch/powerpc/mm/pgtable_64.c                  | 5 -----
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 8d0cbbb31023..55d5cd64cdb3 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -4,7 +4,7 @@
 
 #define H_PTE_INDEX_SIZE  8
 #define H_PMD_INDEX_SIZE  10
-#define H_PUD_INDEX_SIZE  7
+#define H_PUD_INDEX_SIZE  10
 #define H_PGD_INDEX_SIZE  8
 
 /*
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 75b084486ce1..bb9cb25ffb20 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -109,6 +109,13 @@ void release_thread(struct task_struct *);
 #define TASK_SIZE_64TB  (0x0000400000000000UL)
 #define TASK_SIZE_128TB (0x0000800000000000UL)
 #define TASK_SIZE_512TB (0x0002000000000000UL)
+#define TASK_SIZE_1PB   (0x0004000000000000UL)
+#define TASK_SIZE_2PB   (0x0008000000000000UL)
+/*
+ * With 52 bits in the address we can support
+ * upto 4PB of range.
+ */
+#define TASK_SIZE_4PB   (0x0010000000000000UL)
 
 /*
  * For now 512TB is only supported with book3s and 64K linux page size.
@@ -117,7 +124,7 @@ void release_thread(struct task_struct *);
 /*
  * Max value currently used:
  */
-#define TASK_SIZE_USER64		TASK_SIZE_512TB
+#define TASK_SIZE_USER64		TASK_SIZE_4PB
 #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
 #define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
 #else
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index fdb424a29f03..63470b06c502 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -68,12 +68,6 @@
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if H_PGTABLE_RANGE > USER_VSID_RANGE
-#warning Limited user VSID range means pagetable space is wasted
-#endif
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
 phys_addr_t memstart_addr = ~0;
 EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index a87b18cf6749..199bfda5f0d9 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -24,6 +24,10 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
 
+#if H_PGTABLE_RANGE > (USER_VSID_RANGE * (TASK_SIZE_USER64 / TASK_CONTEXT_SIZE))
+#warning Limited user VSID range means pagetable space is wasted
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * vmemmap is the starting address of the virtual address space where
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index adf469f312f2..9bf659d5078c 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -57,11 +57,6 @@
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT))
-#error TASK_SIZE_USER64 exceeds user VSID range
-#endif
-#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /*
-- 
2.14.3

[PATCH V6 4/4] powerpc/mm/hash: Don't memset pgd table if not needed

[Aneesh Kumar K.V]

We need to zero-out pgd table only if we share the slab cache with
pud/pmd level caches. With the support of 4PB, we don't share the slab
cache anymore. Instead of removing the code completely hide it within
an #ifdef. We don't need to do this with any other page table level,
because they all allocate table of double the size and we take of
initializing the first half corrrectly during page table zap.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Consolidate multiple #if / #ifdef into one]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/pgalloc.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 4746bc68d446..558a159600ad 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -80,8 +80,18 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
 			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	/*
+	 * With hugetlb, we don't clear the second half of the page table.
+	 * If we share the same slab cache with the pmd or pud level table,
+	 * we need to make sure we zero out the full table on alloc.
+	 * With 4K we don't store slot in the second half. Hence we don't
+	 * need to do this for 4k.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \
+	((H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX) ||		     \
+	 (H_PGD_INDEX_SIZE == H_PMD_CACHE_INDEX))
 	memset(pgd, 0, PGD_TABLE_SIZE);
-
+#endif
 	return pgd;
 }
 
-- 
2.14.3

Re: [V6, 1/4] powerpc/mm/slice: Consolidate return path in slice_get_unmapped_area()

[Michael Ellerman]

On Mon, 2018-03-26 at 10:04:47 UTC, "Aneesh Kumar K.V" wrote:
> In a following patch, on finding a free area we will need to do
> allocatinon of extra contexts as needed. Consolidating the return path
> for slice_get_unmapped_area() will make that easier.
> 
> Split into a separate patch to make review easy.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Series applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/0dea04b288c06654b0de3563c5b8cd

cheers

Re: [PATCH V6 2/4] powerpc/mm: Add support for handling > 512TB address in SLB miss

[Christophe LEROY]

Le 26/03/2018 à 12:04, Aneesh Kumar K.V a écrit :
> For addresses above 512TB we allocate additional mmu contexts. To make
> it all easy, addresses above 512TB are handled with IR/DR=1 and with
> stack frame setup.
> 
> The mmu_context_t is also updated to track the new extended_ids. To
> support upto 4PB we need a total 8 contexts.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> [mpe: Minor formatting tweaks and comment wording, switch BUG to WARN
>        in get_ea_context().]
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Compilation fails on mpc885_ads_defconfig + CONFIG_HUGETLBFS :

   CC      arch/powerpc/mm/slice.o
arch/powerpc/mm/slice.c: In function 'slice_get_unmapped_area':
arch/powerpc/mm/slice.c:655:2: error: implicit declaration of function 
'need_extra_context' [-Werror=implicit-function-declaration]
arch/powerpc/mm/slice.c:656:3: error: implicit declaration of function 
'alloc_extended_context' [-Werror=implicit-function-declaration]
cc1: all warnings being treated as errors
make[1]: *** [arch/powerpc/mm/slice.o] Error 1
make: *** [arch/powerpc/mm] Error 2

Christophe

> ---
>   arch/powerpc/include/asm/book3s/64/hash-4k.h  |   6 ++
>   arch/powerpc/include/asm/book3s/64/hash-64k.h |   6 ++
>   arch/powerpc/include/asm/book3s/64/mmu.h      |  33 +++++++-
>   arch/powerpc/include/asm/mmu_context.h        |  39 ++++++++++
>   arch/powerpc/include/asm/processor.h          |   6 ++
>   arch/powerpc/kernel/exceptions-64s.S          |  11 ++-
>   arch/powerpc/kernel/traps.c                   |  12 ---
>   arch/powerpc/mm/copro_fault.c                 |   2 +-
>   arch/powerpc/mm/hash_utils_64.c               |   4 +-
>   arch/powerpc/mm/mmu_context_book3s64.c        |  15 +++-
>   arch/powerpc/mm/pgtable-hash64.c              |   2 +-
>   arch/powerpc/mm/slb.c                         | 108 ++++++++++++++++++++++++++
>   arch/powerpc/mm/slb_low.S                     |  11 ++-
>   arch/powerpc/mm/slice.c                       |  15 +++-
>   arch/powerpc/mm/tlb_hash64.c                  |   2 +-
>   15 files changed, 245 insertions(+), 27 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
> index 67c5475311ee..1a35eb944481 100644
> --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
> +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
> @@ -11,6 +11,12 @@
>   #define H_PUD_INDEX_SIZE  9
>   #define H_PGD_INDEX_SIZE  9
>   
> +/*
> + * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB
> + * Hence also limit max EA bits to 64TB.
> + */
> +#define MAX_EA_BITS_PER_CONTEXT		46
> +
>   #ifndef __ASSEMBLY__
>   #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
>   #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
> diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> index 3bcf269f8f55..8d0cbbb31023 100644
> --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
> +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> @@ -7,6 +7,12 @@
>   #define H_PUD_INDEX_SIZE  7
>   #define H_PGD_INDEX_SIZE  8
>   
> +/*
> + * Each context is 512TB size. SLB miss for first context/default context
> + * is handled in the hotpath.
> + */
> +#define MAX_EA_BITS_PER_CONTEXT		49
> +
>   /*
>    * 64k aligned address free up few of the lower bits of RPN for us
>    * We steal that here. For more deatils look at pte_pfn/pfn_pte()
> diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> index c8c836e8ad1b..5094696eecd6 100644
> --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> @@ -91,7 +91,18 @@ struct slice_mask {
>   };
>   
>   typedef struct {
> -	mm_context_id_t id;
> +	union {
> +		/*
> +		 * We use id as the PIDR content for radix. On hash we can use
> +		 * more than one id. The extended ids are used when we start
> +		 * having address above 512TB. We allocate one extended id
> +		 * for each 512TB. The new id is then used with the 49 bit
> +		 * EA to build a new VA. We always use ESID_BITS_1T_MASK bits
> +		 * from EA and new context ids to build the new VAs.
> +		 */
> +		mm_context_id_t id;
> +		mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE];
> +	};
>   	u16 user_psize;		/* page size index */
>   
>   	/* Number of bits in the mm_cpumask */
> @@ -196,5 +207,25 @@ extern void radix_init_pseries(void);
>   static inline void radix_init_pseries(void) { };
>   #endif
>   
> +static inline int get_ea_context(mm_context_t *ctx, unsigned long ea)
> +{
> +	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
> +
> +	if (likely(index < ARRAY_SIZE(ctx->extended_id)))
> +		return ctx->extended_id[index];
> +
> +	/* should never happen */
> +	WARN_ON(1);
> +	return 0;
> +}
> +
> +static inline unsigned long get_user_vsid(mm_context_t *ctx,
> +					  unsigned long ea, int ssize)
> +{
> +	unsigned long context = get_ea_context(ctx, ea);
> +
> +	return get_vsid(context, ea, ssize);
> +}
> +
>   #endif /* __ASSEMBLY__ */
>   #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 3a15b6db9501..1835ca1505d6 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -60,12 +60,51 @@ extern int hash__alloc_context_id(void);
>   extern void hash__reserve_context_id(int id);
>   extern void __destroy_context(int context_id);
>   static inline void mmu_context_init(void) { }
> +
> +static inline int alloc_extended_context(struct mm_struct *mm,
> +					 unsigned long ea)
> +{
> +	int context_id;
> +
> +	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
> +
> +	context_id = hash__alloc_context_id();
> +	if (context_id < 0)
> +		return context_id;
> +
> +	VM_WARN_ON(mm->context.extended_id[index]);
> +	mm->context.extended_id[index] = context_id;
> +	return context_id;
> +}
> +
> +static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
> +{
> +	int context_id;
> +
> +	context_id = get_ea_context(&mm->context, ea);
> +	if (!context_id)
> +		return true;
> +	return false;
> +}
> +
>   #else
>   extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
>   			       struct task_struct *tsk);
>   extern unsigned long __init_new_context(void);
>   extern void __destroy_context(unsigned long context_id);
>   extern void mmu_context_init(void);
> +static inline int alloc_extended_context(struct mm_struct *mm,
> +					 unsigned long ea)
> +{
> +	/* non book3s_64 should never find this called */
> +	WARN_ON(1);
> +	return -ENOMEM;
> +}
> +
> +static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
> +{
> +	return false;
> +}
>   #endif
>   
>   #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
> diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
> index 01299cdc9806..75b084486ce1 100644
> --- a/arch/powerpc/include/asm/processor.h
> +++ b/arch/powerpc/include/asm/processor.h
> @@ -119,9 +119,15 @@ void release_thread(struct task_struct *);
>    */
>   #define TASK_SIZE_USER64		TASK_SIZE_512TB
>   #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
> +#define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
>   #else
>   #define TASK_SIZE_USER64		TASK_SIZE_64TB
>   #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
> +/*
> + * We don't need to allocate extended context ids for 4K page size, because
> + * we limit the max effective address on this config to 64TB.
> + */
> +#define TASK_CONTEXT_SIZE		TASK_SIZE_64TB
>   #endif
>   
>   /*
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 6bee20c43feb..1a0aa70bcb2b 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -621,7 +621,10 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
>   	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
>   	mtlr	r10
>   
> -	beq-	8f		/* if bad address, make full stack frame */
> +	/*
> +	 * Large address, check whether we have to allocate new contexts.
> +	 */
> +	beq-	8f
>   
>   	bne-	cr5,2f		/* if unrecoverable exception, oops */
>   
> @@ -685,7 +688,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
>   	mr	r3,r12
>   	mfspr	r11,SPRN_SRR0
>   	mfspr	r12,SPRN_SRR1
> -	LOAD_HANDLER(r10,bad_addr_slb)
> +	LOAD_HANDLER(r10, large_addr_slb)
>   	mtspr	SPRN_SRR0,r10
>   	ld	r10,PACAKMSR(r13)
>   	mtspr	SPRN_SRR1,r10
> @@ -700,7 +703,7 @@ EXC_COMMON_BEGIN(unrecov_slb)
>   	bl	unrecoverable_exception
>   	b	1b
>   
> -EXC_COMMON_BEGIN(bad_addr_slb)
> +EXC_COMMON_BEGIN(large_addr_slb)
>   	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
>   	RECONCILE_IRQ_STATE(r10, r11)
>   	ld	r3, PACA_EXSLB+EX_DAR(r13)
> @@ -710,7 +713,7 @@ EXC_COMMON_BEGIN(bad_addr_slb)
>   	std	r10, _TRAP(r1)
>   2:	bl	save_nvgprs
>   	addi	r3, r1, STACK_FRAME_OVERHEAD
> -	bl	slb_miss_bad_addr
> +	bl	slb_miss_large_addr
>   	b	ret_from_except
>   
>   EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
> diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
> index 1e48d157196a..f200bfd98b17 100644
> --- a/arch/powerpc/kernel/traps.c
> +++ b/arch/powerpc/kernel/traps.c
> @@ -1495,18 +1495,6 @@ void alignment_exception(struct pt_regs *regs)
>   	exception_exit(prev_state);
>   }
>   
> -void slb_miss_bad_addr(struct pt_regs *regs)
> -{
> -	enum ctx_state prev_state = exception_enter();
> -
> -	if (user_mode(regs))
> -		_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
> -	else
> -		bad_page_fault(regs, regs->dar, SIGSEGV);
> -
> -	exception_exit(prev_state);
> -}
> -
>   void StackOverflow(struct pt_regs *regs)
>   {
>   	printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n",
> diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
> index 697b70ad1195..7d0945bd3a61 100644
> --- a/arch/powerpc/mm/copro_fault.c
> +++ b/arch/powerpc/mm/copro_fault.c
> @@ -112,7 +112,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
>   			return 1;
>   		psize = get_slice_psize(mm, ea);
>   		ssize = user_segment_size(ea);
> -		vsid = get_vsid(mm->context.id, ea, ssize);
> +		vsid = get_user_vsid(&mm->context, ea, ssize);
>   		vsidkey = SLB_VSID_USER;
>   		break;
>   	case VMALLOC_REGION_ID:
> diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
> index b578148d89e6..f62325d4f5f5 100644
> --- a/arch/powerpc/mm/hash_utils_64.c
> +++ b/arch/powerpc/mm/hash_utils_64.c
> @@ -1261,7 +1261,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
>   		}
>   		psize = get_slice_psize(mm, ea);
>   		ssize = user_segment_size(ea);
> -		vsid = get_vsid(mm->context.id, ea, ssize);
> +		vsid = get_user_vsid(&mm->context, ea, ssize);
>   		break;
>   	case VMALLOC_REGION_ID:
>   		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
> @@ -1526,7 +1526,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
>   
>   	/* Get VSID */
>   	ssize = user_segment_size(ea);
> -	vsid = get_vsid(mm->context.id, ea, ssize);
> +	vsid = get_user_vsid(&mm->context, ea, ssize);
>   	if (!vsid)
>   		return;
>   	/*
> diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
> index 422be81bf69f..b75194dff64c 100644
> --- a/arch/powerpc/mm/mmu_context_book3s64.c
> +++ b/arch/powerpc/mm/mmu_context_book3s64.c
> @@ -179,6 +179,19 @@ void __destroy_context(int context_id)
>   }
>   EXPORT_SYMBOL_GPL(__destroy_context);
>   
> +static void destroy_contexts(mm_context_t *ctx)
> +{
> +	int index, context_id;
> +
> +	spin_lock(&mmu_context_lock);
> +	for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) {
> +		context_id = ctx->extended_id[index];
> +		if (context_id)
> +			ida_remove(&mmu_context_ida, context_id);
> +	}
> +	spin_unlock(&mmu_context_lock);
> +}
> +
>   #ifdef CONFIG_PPC_64K_PAGES
>   static void destroy_pagetable_page(struct mm_struct *mm)
>   {
> @@ -217,7 +230,7 @@ void destroy_context(struct mm_struct *mm)
>   	else
>   		subpage_prot_free(mm);
>   	destroy_pagetable_page(mm);
> -	__destroy_context(mm->context.id);
> +	destroy_contexts(&mm->context);
>   	mm->context.id = MMU_NO_CONTEXT;
>   }
>   
> diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
> index 469808e77e58..a87b18cf6749 100644
> --- a/arch/powerpc/mm/pgtable-hash64.c
> +++ b/arch/powerpc/mm/pgtable-hash64.c
> @@ -320,7 +320,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
>   
>   	if (!is_kernel_addr(addr)) {
>   		ssize = user_segment_size(addr);
> -		vsid = get_vsid(mm->context.id, addr, ssize);
> +		vsid = get_user_vsid(&mm->context, addr, ssize);
>   		WARN_ON(vsid == 0);
>   	} else {
>   		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
> diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
> index 13cfe413b40d..66577cc66dc9 100644
> --- a/arch/powerpc/mm/slb.c
> +++ b/arch/powerpc/mm/slb.c
> @@ -22,6 +22,7 @@
>   #include <asm/cacheflush.h>
>   #include <asm/smp.h>
>   #include <linux/compiler.h>
> +#include <linux/context_tracking.h>
>   #include <linux/mm_types.h>
>   
>   #include <asm/udbg.h>
> @@ -340,3 +341,110 @@ void slb_initialize(void)
>   
>   	asm volatile("isync":::"memory");
>   }
> +
> +static void insert_slb_entry(unsigned long vsid, unsigned long ea,
> +			     int bpsize, int ssize)
> +{
> +	unsigned long flags, vsid_data, esid_data;
> +	enum slb_index index;
> +	int slb_cache_index;
> +
> +	/*
> +	 * We are irq disabled, hence should be safe to access PACA.
> +	 */
> +	index = get_paca()->stab_rr;
> +
> +	/*
> +	 * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
> +	 */
> +	if (index < (mmu_slb_size - 1))
> +		index++;
> +	else
> +		index = SLB_NUM_BOLTED;
> +
> +	get_paca()->stab_rr = index;
> +
> +	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
> +	vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
> +		    ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
> +	esid_data = mk_esid_data(ea, ssize, index);
> +
> +	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
> +		     : "memory");
> +
> +	/*
> +	 * Now update slb cache entries
> +	 */
> +	slb_cache_index = get_paca()->slb_cache_ptr;
> +	if (slb_cache_index < SLB_CACHE_ENTRIES) {
> +		/*
> +		 * We have space in slb cache for optimized switch_slb().
> +		 * Top 36 bits from esid_data as per ISA
> +		 */
> +		get_paca()->slb_cache[slb_cache_index++] = esid_data >> 28;
> +		get_paca()->slb_cache_ptr++;
> +	} else {
> +		/*
> +		 * Our cache is full and the current cache content strictly
> +		 * doesn't indicate the active SLB conents. Bump the ptr
> +		 * so that switch_slb() will ignore the cache.
> +		 */
> +		get_paca()->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
> +	}
> +}
> +
> +static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
> +{
> +	struct mm_struct *mm = current->mm;
> +	unsigned long vsid;
> +	int bpsize;
> +
> +	/*
> +	 * We are always above 1TB, hence use high user segment size.
> +	 */
> +	vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
> +	bpsize = get_slice_psize(mm, ea);
> +	insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
> +}
> +
> +void slb_miss_large_addr(struct pt_regs *regs)
> +{
> +	enum ctx_state prev_state = exception_enter();
> +	unsigned long ea = regs->dar;
> +	int context;
> +
> +	if (REGION_ID(ea) != USER_REGION_ID)
> +		goto slb_bad_addr;
> +
> +	/*
> +	 * Are we beyound what the page table layout supports ?
> +	 */
> +	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
> +		goto slb_bad_addr;
> +
> +	/* Lower address should have been handled by asm code */
> +	if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
> +		goto slb_bad_addr;
> +
> +	/*
> +	 * consider this as bad access if we take a SLB miss
> +	 * on an address above addr limit.
> +	 */
> +	if (ea >= current->mm->context.slb_addr_limit)
> +		goto slb_bad_addr;
> +
> +	context = get_ea_context(&current->mm->context, ea);
> +	if (!context)
> +		goto slb_bad_addr;
> +
> +	handle_multi_context_slb_miss(context, ea);
> +	exception_exit(prev_state);
> +	return;
> +
> +slb_bad_addr:
> +	if (user_mode(regs))
> +		_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
> +	else
> +		bad_page_fault(regs, ea, SIGSEGV);
> +	exception_exit(prev_state);
> +}
> diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
> index 2c7c717fd2ea..a83fbd2a4a24 100644
> --- a/arch/powerpc/mm/slb_low.S
> +++ b/arch/powerpc/mm/slb_low.S
> @@ -75,10 +75,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
>    */
>   _GLOBAL(slb_allocate)
>   	/*
> -	 * check for bad kernel/user address
> -	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
> +	 * Check if the address falls within the range of the first context, or
> +	 * if we may need to handle multi context. For the first context we
> +	 * allocate the slb entry via the fast path below. For large address we
> +	 * branch out to C-code and see if additional contexts have been
> +	 * allocated.
> +	 * The test here is:
> +	 *   (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
>   	 */
> -	rldicr. r9,r3,4,(63 - H_PGTABLE_EADDR_SIZE - 4)
> +	rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
>   	bne-	8f
>   
>   	srdi	r9,r3,60		/* get region */
> diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
> index 09ac1a709d0c..9cd87d11fe4e 100644
> --- a/arch/powerpc/mm/slice.c
> +++ b/arch/powerpc/mm/slice.c
> @@ -648,6 +648,15 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
>   	slice_print_mask(" mask", &potential_mask);
>   
>    convert:
> +	/*
> +	 * Try to allocate the context before we do slice convert
> +	 * so that we handle the context allocation failure gracefully.
> +	 */
> +	if (need_extra_context(mm, newaddr)) {
> +		if (alloc_extended_context(mm, newaddr) < 0)
> +			return -ENOMEM;
> +	}
> +
>   	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
>   	if (compat_maskp && !fixed)
>   		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
> @@ -658,10 +667,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
>   		if (psize > MMU_PAGE_BASE)
>   			on_each_cpu(slice_flush_segments, mm, 1);
>   	}
> +	return newaddr;
>   
>   return_addr:
> +	if (need_extra_context(mm, newaddr)) {
> +		if (alloc_extended_context(mm, newaddr) < 0)
> +			return -ENOMEM;
> +	}
>   	return newaddr;
> -
>   }
>   EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
>   
> diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
> index 9b23f12e863c..87d71dd25441 100644
> --- a/arch/powerpc/mm/tlb_hash64.c
> +++ b/arch/powerpc/mm/tlb_hash64.c
> @@ -89,7 +89,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
>   	/* Build full vaddr */
>   	if (!is_kernel_addr(addr)) {
>   		ssize = user_segment_size(addr);
> -		vsid = get_vsid(mm->context.id, addr, ssize);
> +		vsid = get_user_vsid(&mm->context, addr, ssize);
>   	} else {
>   		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
>   		ssize = mmu_kernel_ssize;
> 

Re: [PATCH V6 2/4] powerpc/mm: Add support for handling > 512TB address in SLB miss

[Aneesh Kumar K.V]

On 04/09/2018 12:49 PM, Christophe LEROY wrote:
> 
> 
> Le 26/03/2018 à 12:04, Aneesh Kumar K.V a écrit :
>> For addresses above 512TB we allocate additional mmu contexts. To make
>> it all easy, addresses above 512TB are handled with IR/DR=1 and with
>> stack frame setup.
>>
>> The mmu_context_t is also updated to track the new extended_ids. To
>> support upto 4PB we need a total 8 contexts.
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>> [mpe: Minor formatting tweaks and comment wording, switch BUG to WARN
>>        in get_ea_context().]
>> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
> 
> Compilation fails on mpc885_ads_defconfig + CONFIG_HUGETLBFS :
> 
>    CC      arch/powerpc/mm/slice.o
> arch/powerpc/mm/slice.c: In function 'slice_get_unmapped_area':
> arch/powerpc/mm/slice.c:655:2: error: implicit declaration of function 
> 'need_extra_context' [-Werror=implicit-function-declaration]
> arch/powerpc/mm/slice.c:656:3: error: implicit declaration of function 
> 'alloc_extended_context' [-Werror=implicit-function-declaration]
> cc1: all warnings being treated as errors
> make[1]: *** [arch/powerpc/mm/slice.o] Error 1
> make: *** [arch/powerpc/mm] Error 2


something like below?

diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 9cd87d1..205fe55 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -35,6 +35,7 @@
  #include <asm/mmu.h>
  #include <asm/copro.h>
  #include <asm/hugetlb.h>
+#include <asm/mmu_context.h>

  static DEFINE_SPINLOCK(slice_convert_lock);


PPC64 was including that header via include/linux/pkeys.h

-aneesh

Re: [PATCH V6 2/4] powerpc/mm: Add support for handling > 512TB address in SLB miss

[Christophe LEROY]

Le 09/04/2018 à 10:33, Aneesh Kumar K.V a écrit :
> On 04/09/2018 12:49 PM, Christophe LEROY wrote:
>>
>>
>> Le 26/03/2018 à 12:04, Aneesh Kumar K.V a écrit :
>>> For addresses above 512TB we allocate additional mmu contexts. To make
>>> it all easy, addresses above 512TB are handled with IR/DR=1 and with
>>> stack frame setup.
>>>
>>> The mmu_context_t is also updated to track the new extended_ids. To
>>> support upto 4PB we need a total 8 contexts.
>>>
>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>>> [mpe: Minor formatting tweaks and comment wording, switch BUG to WARN
>>>        in get_ea_context().]
>>> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
>>
>> Compilation fails on mpc885_ads_defconfig + CONFIG_HUGETLBFS :
>>
>>    CC      arch/powerpc/mm/slice.o
>> arch/powerpc/mm/slice.c: In function 'slice_get_unmapped_area':
>> arch/powerpc/mm/slice.c:655:2: error: implicit declaration of function 
>> 'need_extra_context' [-Werror=implicit-function-declaration]
>> arch/powerpc/mm/slice.c:656:3: error: implicit declaration of function 
>> 'alloc_extended_context' [-Werror=implicit-function-declaration]
>> cc1: all warnings being treated as errors
>> make[1]: *** [arch/powerpc/mm/slice.o] Error 1
>> make: *** [arch/powerpc/mm] Error 2
> 
> 
> something like below?
> 
> diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
> index 9cd87d1..205fe55 100644
> --- a/arch/powerpc/mm/slice.c
> +++ b/arch/powerpc/mm/slice.c
> @@ -35,6 +35,7 @@
>   #include <asm/mmu.h>
>   #include <asm/copro.h>
>   #include <asm/hugetlb.h>
> +#include <asm/mmu_context.h>
> 
>   static DEFINE_SPINLOCK(slice_convert_lock);
> 
> 
> PPC64 was including that header via include/linux/pkeys.h

Yes compilation OK now.

Christophe

> 
> -aneesh