Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 66 insertions, 62 deletions

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 2fdb47a19efd..b59e06f507ea 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -343,17 +343,16 @@ extern void slb_set_size(u16 size);
 /*
  * 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:
@@ -363,41 +362,49 @@ extern void slb_set_size(u16 size);
  * 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).
- *
- * This scheme has several advantages over older methods:
- *
- *	- We have VSIDs allocated for every kernel address
- * (i.e. everything above 0xC000000000000000), except the very top
- * segment, which simplifies several things.
+ * a divide or extra multiply (see below). The scramble function gives
+ * robust scattering in the hash table (at least based on some initial
+ * results).
  *
- *	- 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.
+ * 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.
  *
- *	- 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 ESID_BITS		18
+#define ESID_BITS_1T		6
+
+/*
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + 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		38
+#define VSID_BITS_256M		(CONTEXT_BITS + 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		26
+#define VSID_BITS_1T		(CONTEXT_BITS + ESID_BITS_1T)
 #define VSID_MODULUS_1T		((1UL<<VSID_BITS_1T)-1)
 
-#define CONTEXT_BITS		19
-#define USER_ESID_BITS		18
-#define USER_ESID_BITS_1T	6
 
-#define USER_VSID_RANGE	(1UL << (USER_ESID_BITS + SID_SHIFT))
+#define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
 
 /*
  * This macro generates asm code to compute the VSID scramble
@@ -421,7 +428,8 @@ extern void slb_set_size(u16 size);
 	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	\
@@ -513,34 +521,6 @@ typedef struct {
 	})
 #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)
 {
@@ -550,17 +530,41 @@ 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)
+		return vsid_scramble((context << ESID_BITS)
 				     | (ea >> SID_SHIFT), 256M);
-	return vsid_scramble((context << USER_ESID_BITS_1T)
+	return vsid_scramble((context << ESID_BITS_1T)
 			     | (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_ */