Merge tag 's390-6.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Alexander Gordeev:

 - Refactor SCLP memory hotplug code

 - Introduce common boot_panic() decompressor helper macro and use it to
   get rid of nearly few identical implementations

 - Take into account additional key generation flags and forward it to
   the ep11 implementation. With that allow users to modify the key
   generation process, e.g. provide valid combinations of XCP_BLOB_*
   flags

 - Replace kmalloc() + copy_from_user() with memdup_user_nul() in s390
   debug facility and HMC driver

 - Add DAX support for DCSS memory block devices

 - Make the compiler statement attribute "assume" available with a new
   __assume macro

 - Rework ffs() and fls() family bitops functions, including source code
   improvements and generated code optimizations. Use the newly
   introduced __assume macro for that

 - Enable additional network features in default configurations

 - Use __GFP_ACCOUNT flag for user page table allocations to add missing
   kmemcg accounting

 - Add WQ_PERCPU flag to explicitly request the use of the per-CPU
   workqueue for 3590 tape driver

 - Switch power reading to the per-CPU and the Hiperdispatch to the
   default workqueue

 - Add memory allocation profiling hooks to allow better profiling data
   and the /proc/allocinfo output similar to other architectures

* tag 's390-6.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (21 commits)
  s390/mm: Add memory allocation profiling hooks
  s390: Replace use of system_wq with system_dfl_wq
  s390/diag324: Replace use of system_wq with system_percpu_wq
  s390/tape: Add WQ_PERCPU to alloc_workqueue users
  s390/bitops: Switch to generic ffs() if supported by compiler
  s390/bitops: Switch to generic fls(), fls64(), etc.
  s390/mm: Use __GFP_ACCOUNT for user page table allocations
  s390/configs: Enable additional network features
  s390/bitops: Cleanup __flogr()
  s390/bitops: Use __assume() for __flogr() inline assembly return value
  compiler_types: Add __assume macro
  s390/bitops: Limit return value range of __flogr()
  s390/dcssblk: Add DAX support
  s390/hmcdrv: Replace kmalloc() + copy_from_user() with memdup_user_nul()
  s390/debug: Replace kmalloc() + copy_from_user() with memdup_user_nul()
  s390/pkey: Forward keygenflags to ep11_unwrapkey
  s390/boot: Add common boot_panic() code
  s390/bitops: Optimize inlining
  s390/bitops: Slightly optimize ffs() and fls64()
  s390/sclp: Move memory hotplug code for better modularity
  ...

2 files changed, 46 insertions, 72 deletions

diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index fbcc3e1cc776..ec945fb60c02 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -122,6 +122,8 @@ static inline bool test_bit_inv(unsigned long nr,
 	return test_bit(nr ^ (BITS_PER_LONG - 1), ptr);
 }
 
+#ifndef CONFIG_CC_HAS_BUILTIN_FFS
+
 /**
  * __flogr - find leftmost one
  * @word - The word to search
@@ -130,11 +132,12 @@ static inline bool test_bit_inv(unsigned long nr,
  * where the most significant bit has bit number 0.
  * If no bit is set this function returns 64.
  */
-static inline unsigned char __flogr(unsigned long word)
+static __always_inline __attribute_const__ unsigned long __flogr(unsigned long word)
 {
-	if (__builtin_constant_p(word)) {
-		unsigned long bit = 0;
+	unsigned long bit;
 
+	if (__builtin_constant_p(word)) {
+		bit = 0;
 		if (!word)
 			return 64;
 		if (!(word & 0xffffffff00000000UL)) {
@@ -163,86 +166,49 @@ static inline unsigned char __flogr(unsigned long word)
 		}
 		return bit;
 	} else {
-		union register_pair rp;
+		union register_pair rp __uninitialized;
 
 		rp.even = word;
-		asm volatile(
-			"       flogr   %[rp],%[rp]\n"
-			: [rp] "+d" (rp.pair) : : "cc");
-		return rp.even;
+		asm("flogr	%[rp],%[rp]"
+		    : [rp] "+d" (rp.pair) : : "cc");
+		bit = rp.even;
+		/*
+		 * The result of the flogr instruction is a value in the range
+		 * of 0..64. Let the compiler know that the AND operation can
+		 * be optimized away.
+		 */
+		__assume(bit <= 64);
+		return bit & 127;
 	}
 }
 
 /**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static inline __attribute_const__ unsigned long __ffs(unsigned long word)
-{
-	return __flogr(-word & word) ^ (BITS_PER_LONG - 1);
-}
-
-/**
  * ffs - find first bit set
  * @word: the word to search
  *
  * This is defined the same way as the libc and
  * compiler builtin ffs routines (man ffs).
  */
-static inline __attribute_const__ int ffs(int word)
+static __always_inline __flatten __attribute_const__ int ffs(int word)
 {
-	unsigned long mask = 2 * BITS_PER_LONG - 1;
 	unsigned int val = (unsigned int)word;
 
-	return (1 + (__flogr(-val & val) ^ (BITS_PER_LONG - 1))) & mask;
-}
-
-/**
- * __fls - find last (most-significant) set bit in a long word
- * @word: the word to search
- *
- * Undefined if no set bit exists, so code should check against 0 first.
- */
-static inline __attribute_const__ unsigned long __fls(unsigned long word)
-{
-	return __flogr(word) ^ (BITS_PER_LONG - 1);
+	return BITS_PER_LONG - __flogr(-val & val);
 }
 
-/**
- * fls64 - find last set bit in a 64-bit word
- * @word: the word to search
- *
- * This is defined in a similar way as the libc and compiler builtin
- * ffsll, but returns the position of the most significant set bit.
- *
- * fls64(value) returns 0 if value is 0 or the position of the last
- * set bit if value is nonzero. The last (most significant) bit is
- * at position 64.
- */
-static inline __attribute_const__ int fls64(unsigned long word)
-{
-	unsigned long mask = 2 * BITS_PER_LONG - 1;
+#else /* CONFIG_CC_HAS_BUILTIN_FFS */
 
-	return (1 + (__flogr(word) ^ (BITS_PER_LONG - 1))) & mask;
-}
+#include <asm-generic/bitops/builtin-ffs.h>
 
-/**
- * fls - find last (most-significant) bit set
- * @word: the word to search
- *
- * This is defined the same way as ffs.
- * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
- */
-static inline __attribute_const__ int fls(unsigned int word)
-{
-	return fls64(word);
-}
+#endif /* CONFIG_CC_HAS_BUILTIN_FFS */
 
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-fls.h>
+#include <asm-generic/bitops/fls64.h>
 #include <asm/arch_hweight.h>
 #include <asm-generic/bitops/const_hweight.h>
-#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 5345398df653..a16e65072371 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -19,12 +19,16 @@
 
 #define CRST_ALLOC_ORDER 2
 
-unsigned long *crst_table_alloc(struct mm_struct *);
+unsigned long *crst_table_alloc_noprof(struct mm_struct *);
+#define crst_table_alloc(...)	alloc_hooks(crst_table_alloc_noprof(__VA_ARGS__))
 void crst_table_free(struct mm_struct *, unsigned long *);
 
-unsigned long *page_table_alloc(struct mm_struct *);
-struct ptdesc *page_table_alloc_pgste(struct mm_struct *mm);
+unsigned long *page_table_alloc_noprof(struct mm_struct *);
+#define page_table_alloc(...)	alloc_hooks(page_table_alloc_noprof(__VA_ARGS__))
 void page_table_free(struct mm_struct *, unsigned long *);
+
+struct ptdesc *page_table_alloc_pgste_noprof(struct mm_struct *mm);
+#define page_table_alloc_pgste(...)	alloc_hooks(page_table_alloc_pgste_noprof(__VA_ARGS__))
 void page_table_free_pgste(struct ptdesc *ptdesc);
 
 static inline void crst_table_init(unsigned long *crst, unsigned long entry)
@@ -48,9 +52,9 @@ static inline unsigned long check_asce_limit(struct mm_struct *mm, unsigned long
 	return addr;
 }
 
-static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
+static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long address)
 {
-	unsigned long *table = crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc_noprof(mm);
 
 	if (!table)
 		return NULL;
@@ -59,6 +63,7 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	return (p4d_t *) table;
 }
+#define p4d_alloc_one(...)	alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__))
 
 static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 {
@@ -69,9 +74,9 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 	crst_table_free(mm, (unsigned long *) p4d);
 }
 
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
+static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long address)
 {
-	unsigned long *table = crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc_noprof(mm);
 
 	if (!table)
 		return NULL;
@@ -80,6 +85,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	return (pud_t *) table;
 }
+#define pud_alloc_one(...)	alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
@@ -90,9 +96,9 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 	crst_table_free(mm, (unsigned long *) pud);
 }
 
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
+static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *table = crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc_noprof(mm);
 
 	if (!table)
 		return NULL;
@@ -103,6 +109,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 	}
 	return (pmd_t *) table;
 }
+#define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
@@ -127,9 +134,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 	set_pud(pud, __pud(_REGION3_ENTRY | __pa(pmd)));
 }
 
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+static inline pgd_t *pgd_alloc_noprof(struct mm_struct *mm)
 {
-	unsigned long *table = crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc_noprof(mm);
 
 	if (!table)
 		return NULL;
@@ -137,6 +144,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	return (pgd_t *) table;
 }
+#define pgd_alloc(...)	alloc_hooks(pgd_alloc_noprof(__VA_ARGS__))
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {