powerpc: Update kernel VSID range

This patch change the kernel VSID range so that we limit VSID_BITS to 37.
This enables us to support 64TB with 65 bit VA (37+28). Without this patch
we have boot hangs on platforms that only support 65 bit VA.

With this patch we now have proto vsid generated as below:

We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
from mmu context id and effective segment id of the address.

For user processes max context id is limited to ((1ul << 19) - 5)
for kernel space, we use the top 4 context ids to map address as below
0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ]
0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ]
0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ]
0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ]

Acked-by: Paul Mackerras <[e-mail]>
Signed-off-by: Aneesh Kumar K.V <[e-mail]>
Tested-by: Geoff Levand <[e-mail]>
Signed-off-by: Benjamin Herrenschmidt <[e-mail]>
CC: <[e-mail]> [v3.8]

arch/powerpc/include/asm/mmu-hash64.h

···
 /*
  * VSID allocation (256MB segment)
  *
- * We first generate a 38-bit "proto-VSID".  For kernel addresses this
- * is equal to the ESID | 1 << 37, for user addresses it is:
- *	(context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1)
+ * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
+ * from mmu context id and effective segment id of the address.
  *
- * This splits the proto-VSID into the below range
- *  0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range
- *  2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range
- *
- * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1
- * That is, we assign half of the space to user processes and half
- * to the kernel.
+ * For user processes max context id is limited to ((1ul << 19) - 5)
+ * for kernel space, we use the top 4 context ids to map address as below
+ * NOTE: each context only support 64TB now.
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  *
  * The proto-VSIDs are then scrambled into real VSIDs with the
  * multiplicative hash:
···
  * VSID_MULTIPLIER is prime, so in particular it is
  * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
  * Because the modulus is 2^n-1 we can compute it efficiently without
- * a divide or extra multiply (see below).
+ * a divide or extra multiply (see below). The scramble function gives
+ * robust scattering in the hash table (at least based on some initial
+ * results).
  *
- * This scheme has several advantages over older methods:
+ * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
+ * bad address. This enables us to consolidate bad address handling in
+ * hash_page.
  *
- *	- We have VSIDs allocated for every kernel address
- * (i.e. everything above 0xC000000000000000), except the very top
- * segment, which simplifies several things.
- *
- *	- We allow for USER_ESID_BITS significant bits of ESID and
- * CONTEXT_BITS  bits of context for user addresses.
- *  i.e. 64T (46 bits) of address space for up to half a million contexts.
- *
- *	- The scramble function gives robust scattering in the hash
- * table (at least based on some initial results).  The previous
- * method was more susceptible to pathological cases giving excessive
- * hash collisions.
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble. But the vmemmap
+ * (which is what uses region 0xf) will never be close to 64TB in size
+ * (it's 56 bytes per page of system memory).
  */
 
 #define CONTEXT_BITS		19
···
 #define USER_ESID_BITS_1T	6
 
 /*
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
+ * available for user + kernel mapping. The top 4 contexts are used for
+ * kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
+ * (19 == 37 + 28 - 46).
+ */
+#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 5)
+
+/*
  * This should be computed such that protovosid * vsid_mulitplier
  * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
  */
 #define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_256M		(CONTEXT_BITS + USER_ESID_BITS + 1)
+#define VSID_BITS_256M		(CONTEXT_BITS + USER_ESID_BITS)
 #define VSID_MODULUS_256M	((1UL<<VSID_BITS_256M)-1)
 
 #define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_1T		(CONTEXT_BITS + USER_ESID_BITS_1T + 1)
+#define VSID_BITS_1T		(CONTEXT_BITS + USER_ESID_BITS_1T)
 #define VSID_MODULUS_1T		((1UL<<VSID_BITS_1T)-1)
 
 
···
 	srdi	rx,rt,VSID_BITS_##size;					\
 	clrldi	rt,rt,(64-VSID_BITS_##size);				\
 	add	rt,rt,rx;		/* add high and low bits */	\
-	/* Now, r3 == VSID (mod 2^36-1), and lies between 0 and		\
+	/* NOTE: explanation based on VSID_BITS_##size = 36		\
+	 * Now, r3 == VSID (mod 2^36-1), and lies between 0 and		\
 	 * 2^36-1+2^28-1.  That in particular means that if r3 >=	\
 	 * 2^36-1, then r3+1 has the 2^36 bit set.  So, if r3+1 has	\
 	 * the bit clear, r3 already has the answer we want, if it	\
···
 	})
 #endif /* 1 */
 
-/*
- * This is only valid for addresses >= PAGE_OFFSET
- * The proto-VSID space is divided into two class
- * User:   0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1
- * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1
- *
- * With KERNEL_START at 0xc000000000000000, the proto vsid for
- * the kernel ends up with 0xc00000000 (36 bits). With 64TB
- * support we need to have kernel proto-VSID in the
- * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS.
- */
-static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
-{
-	unsigned long proto_vsid;
-	/*
-	 * We need to make sure proto_vsid for the kernel is
-	 * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T])
-	 */
-	if (ssize == MMU_SEGSIZE_256M) {
-		proto_vsid = ea >> SID_SHIFT;
-		proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS));
-		return vsid_scramble(proto_vsid, 256M);
-	}
-	proto_vsid = ea >> SID_SHIFT_1T;
-	proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T));
-	return vsid_scramble(proto_vsid, 1T);
-}
-
 /* Returns the segment size indicator for a user address */
 static inline int user_segment_size(unsigned long addr)
 {
···
 	return MMU_SEGSIZE_256M;
 }
 
-/* This is only valid for user addresses (which are below 2^44) */
 static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
 				     int ssize)
 {
+	/*
+	 * Bad address. We return VSID 0 for that
+	 */
+	if ((ea & ~REGION_MASK) >= PGTABLE_RANGE)
+		return 0;
+
 	if (ssize == MMU_SEGSIZE_256M)
 		return vsid_scramble((context << USER_ESID_BITS)
 				     | (ea >> SID_SHIFT), 256M);
···
 			     | (ea >> SID_SHIFT_1T), 1T);
 }
 
+/*
+ * This is only valid for addresses >= PAGE_OFFSET
+ *
+ * For kernel space, we use the top 4 context ids to map address as below
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ */
+static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
+{
+	unsigned long context;
+
+	/*
+	 * kernel take the top 4 context from the available range
+	 */
+	context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+	return get_vsid(context, ea, ssize);
+}
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_HASH64_H_ */

arch/powerpc/kernel/exceptions-64s.S

···
 _GLOBAL(do_stab_bolted)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
+	mfspr	r11,SPRN_DAR			/* ea */
 
+	/*
+	 * check for bad kernel/user address
+	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+	 */
+	rldicr. r9,r11,4,(63 - 46 - 4)
+	li	r9,0	/* VSID = 0 for bad address */
+	bne-	0f
+
+	/*
+	 * Calculate VSID:
+	 * This is the kernel vsid, we take the top for context from
+	 * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+	 * Here we know that (ea >> 60) == 0xc
+	 */
+	lis	r9,(MAX_USER_CONTEXT + 1)@ha
+	addi	r9,r9,(MAX_USER_CONTEXT + 1)@l
+
+	srdi	r10,r11,SID_SHIFT
+	rldimi  r10,r9,USER_ESID_BITS,0 /* proto vsid */
+	ASM_VSID_SCRAMBLE(r10, r9, 256M)
+	rldic	r9,r10,12,16	/* r9 = vsid << 12 */
+
+0:
 	/* Hash to the primary group */
 	ld	r10,PACASTABVIRT(r13)
-	mfspr	r11,SPRN_DAR
-	srdi	r11,r11,28
+	srdi	r11,r11,SID_SHIFT
 	rldimi	r10,r11,7,52	/* r10 = first ste of the group */
-
-	/* Calculate VSID */
-	/* This is a kernel address, so protovsid = ESID | 1 << 37 */
-	li	r9,0x1
-	rldimi  r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0
-	ASM_VSID_SCRAMBLE(r11, r9, 256M)
-	rldic	r9,r11,12,16	/* r9 = vsid << 12 */
 
 	/* Search the primary group for a free entry */
 1:	ld	r11,0(r10)	/* Test valid bit of the current ste	*/

arch/powerpc/mm/hash_utils_64.c

···
 		unsigned long vpn  = hpt_vpn(vaddr, vsid, ssize);
 		unsigned long tprot = prot;
 
+		/*
+		 * If we hit a bad address return error.
+		 */
+		if (!vsid)
+			return -1;
 		/* Make kernel text executable */
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
···
 	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
 		ea, access, trap);
 
-	if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) {
-		DBG_LOW(" out of pgtable range !\n");
- 		return 1;
-	}
-
 	/* Get region & vsid */
  	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
···
 	}
 	DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);
 
+	/* Bad address. */
+	if (!vsid) {
+		DBG_LOW("Bad address!\n");
+		return 1;
+	}
 	/* Get pgdir */
 	pgdir = mm->pgd;
 	if (pgdir == NULL)
···
 	/* Get VSID */
 	ssize = user_segment_size(ea);
 	vsid = get_vsid(mm->context.id, ea, ssize);
+	if (!vsid)
+		return;
 
 	/* Hash doesn't like irqs */
 	local_irq_save(flags);
···
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
 	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
+	/* Don't create HPTE entries for bad address */
+	if (!vsid)
+		return;
 	ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr),
 				 mode, HPTE_V_BOLTED,
 				 mmu_linear_psize, mmu_kernel_ssize);

arch/powerpc/mm/mmu_context_hash64.c

···
 static DEFINE_SPINLOCK(mmu_context_lock);
 static DEFINE_IDA(mmu_context_ida);
 
-/*
- * 256MB segment
- * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
- * available for user mappings. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
- */
-#define MAX_CONTEXT	((1UL << CONTEXT_BITS) - 1)
-
 int __init_new_context(void)
 {
 	int index;
···
 	else if (err)
 		return err;
 
-	if (index > MAX_CONTEXT) {
+	if (index > MAX_USER_CONTEXT) {
 		spin_lock(&mmu_context_lock);
 		ida_remove(&mmu_context_ida, index);
 		spin_unlock(&mmu_context_lock);

arch/powerpc/mm/slb_low.S

···
  * No other registers are examined or changed.
  */
 _GLOBAL(slb_allocate_realmode)
-	/* r3 = faulting address */
+	/*
+	 * check for bad kernel/user address
+	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+	 */
+	rldicr. r9,r3,4,(63 - 46 - 4)
+	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
-	srdi	r10,r3,28		/* get esid */
+	srdi	r10,r3,SID_SHIFT	/* get esid */
 	cmpldi	cr7,r9,0xc		/* cmp PAGE_OFFSET for later use */
 
 	/* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
···
 	 */
 _GLOBAL(slb_miss_kernel_load_linear)
 	li	r11,0
-	li	r9,0x1
 	/*
-	 * for 1T we shift 12 bits more.  slb_finish_load_1T will do
-	 * the necessary adjustment
+	 * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+	 * r9 = region id.
 	 */
-	rldimi  r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
+	addis	r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
+	addi	r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+
+
 BEGIN_FTR_SECTION
 	b	slb_finish_load
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
···
 	_GLOBAL(slb_miss_kernel_load_io)
 	li	r11,0
 6:
-	li	r9,0x1
 	/*
-	 * for 1T we shift 12 bits more.  slb_finish_load_1T will do
-	 * the necessary adjustment
+	 * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+	 * r9 = region id.
 	 */
-	rldimi  r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
+	addis	r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
+	addi	r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+
 BEGIN_FTR_SECTION
 	b	slb_finish_load
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
-0:	/* user address: proto-VSID = context << 15 | ESID. First check
-	 * if the address is within the boundaries of the user region
-	 */
-	srdi.	r9,r10,USER_ESID_BITS
-	bne-	8f			/* invalid ea bits set */
-
-
+0:
 	/* when using slices, we extract the psize off the slice bitmaps
 	 * and then we need to get the sllp encoding off the mmu_psize_defs
 	 * array.
···
 	ld	r9,PACACONTEXTID(r13)
 BEGIN_FTR_SECTION
 	cmpldi	r10,0x1000
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-	rldimi	r10,r9,USER_ESID_BITS,0
-BEGIN_FTR_SECTION
 	bge	slb_finish_load_1T
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load
 
 8:	/* invalid EA */
 	li	r10,0			/* BAD_VSID */
+	li	r9,0			/* BAD_VSID */
 	li	r11,SLB_VSID_USER	/* flags don't much matter */
 	b	slb_finish_load
 
···
 
 	/* get context to calculate proto-VSID */
 	ld	r9,PACACONTEXTID(r13)
-	rldimi	r10,r9,USER_ESID_BITS,0
-
 	/* fall through slb_finish_load */
 
 #endif /* __DISABLED__ */
···
 /*
  * Finish loading of an SLB entry and return
  *
- * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
+ * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
  */
 slb_finish_load:
+	rldimi  r10,r9,USER_ESID_BITS,0
 	ASM_VSID_SCRAMBLE(r10,r9,256M)
 	/*
 	 * bits above VSID_BITS_256M need to be ignored from r10
···
 /*
  * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
  *
- * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9
+ * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9
  */
 slb_finish_load_1T:
-	srdi	r10,r10,40-28		/* get 1T ESID */
+	srdi	r10,r10,(SID_SHIFT_1T - SID_SHIFT)	/* get 1T ESID */
+	rldimi  r10,r9,USER_ESID_BITS_1T,0
 	ASM_VSID_SCRAMBLE(r10,r9,1T)
 	/*
 	 * bits above VSID_BITS_1T need to be ignored from r10

arch/powerpc/mm/tlb_hash64.c

···
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
 		vsid = get_vsid(mm->context.id, addr, ssize);
-		WARN_ON(vsid == 0);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;
 	}
+	WARN_ON(vsid == 0);
 	vpn = hpt_vpn(addr, vsid, ssize);
 	rpte = __real_pte(__pte(pte), ptep);