Merge tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:

 - Various virtual vs physical address usage fixes

 - Fix error handling in Processor Activity Instrumentation device
   driver, and export number of counters with a sysfs file

 - Allow for multiple events when Processor Activity Instrumentation
   counters are monitored in system wide sampling

 - Change multiplier and shift values of the Time-of-Day clock source to
   improve steering precision

 - Remove a couple of unneeded GFP_DMA flags from allocations

 - Disable mmap alignment if randomize_va_space is also disabled, to
   avoid a too small heap

 - Various changes to allow s390 to be compiled with LLVM=1, since
   ld.lld and llvm-objcopy will have proper s390 support witch clang 19

 - Add __uninitialized macro to Compiler Attributes. This is helpful
   with s390's FPU code where some users have up to 520 byte stack
   frames. Clearing such stack frames (if INIT_STACK_ALL_PATTERN or
   INIT_STACK_ALL_ZERO is enabled) before they are used contradicts the
   intention (performance improvement) of such code sections.

 - Convert switch_to() to an out-of-line function, and use the generic
   switch_to header file

 - Replace the usage of s390's debug feature with pr_debug() calls
   within the zcrypt device driver

 - Improve hotplug support of the Adjunct Processor device driver

 - Improve retry handling in the zcrypt device driver

 - Various changes to the in-kernel FPU code:

     - Make in-kernel FPU sections preemptible

     - Convert various larger inline assemblies and assembler files to
       C, mainly by using singe instruction inline assemblies. This
       increases readability, but also allows makes it easier to add
       proper instrumentation hooks

     - Cleanup of the header files

 - Provide fast variants of csum_partial() and
   csum_partial_copy_nocheck() based on vector instructions

 - Introduce and use a lock to synchronize accesses to zpci device data
   structures to avoid inconsistent states caused by concurrent accesses

 - Compile the kernel without -fPIE. This addresses the following
   problems if the kernel is compiled with -fPIE:

     - It uses dynamic symbols (.dynsym), for which the linker refuses
       to allow more than 64k sections. This can break features which
       use '-ffunction-sections' and '-fdata-sections', including
       kpatch-build and function granular KASLR

     - It unnecessarily uses GOT relocations, adding an extra layer of
       indirection for many memory accesses

 - Fix shared_cpu_list for CPU private L2 caches, which incorrectly were
   reported as globally shared

* tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (117 commits)
  s390/tools: handle rela R_390_GOTPCDBL/R_390_GOTOFF64
  s390/cache: prevent rebuild of shared_cpu_list
  s390/crypto: remove retry loop with sleep from PAES pkey invocation
  s390/pkey: improve pkey retry behavior
  s390/zcrypt: improve zcrypt retry behavior
  s390/zcrypt: introduce retries on in-kernel send CPRB functions
  s390/ap: introduce mutex to lock the AP bus scan
  s390/ap: rework ap_scan_bus() to return true on config change
  s390/ap: clarify AP scan bus related functions and variables
  s390/ap: rearm APQNs bindings complete completion
  s390/configs: increase number of LOCKDEP_BITS
  s390/vfio-ap: handle hardware checkstop state on queue reset operation
  s390/pai: change sampling event assignment for PMU device driver
  s390/boot: fix minor comment style damages
  s390/boot: do not check for zero-termination relocation entry
  s390/boot: make type of __vmlinux_relocs_64_start|end consistent
  s390/boot: sanitize kaslr_adjust_relocs() function prototype
  s390/boot: simplify GOT handling
  s390: vmlinux.lds.S: fix .got.plt assertion
  s390/boot: workaround current 'llvm-objdump -t -j ...' behavior
  ...

1 files changed, 13 insertions, 49 deletions

diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index cd0b9e95f499..863e2d320938 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -12,15 +12,14 @@
  */
 
 #include <linux/raid/pq.h>
-#include <asm/fpu/api.h>
-#include <asm/vx-insn.h>
+#include <asm/fpu.h>
 
 #define NSIZE 16
 
-static inline void LOAD_CONST(void)
+static __always_inline void LOAD_CONST(void)
 {
-	asm volatile("VREPIB %v24,7");
-	asm volatile("VREPIB %v25,0x1d");
+	fpu_vrepib(24, 0x07);
+	fpu_vrepib(25, 0x1d);
 }
 
 /*
@@ -28,10 +27,7 @@ static inline void LOAD_CONST(void)
  * vector register y left by 1 bit and stores the result in
  * vector register x.
  */
-static inline void SHLBYTE(int x, int y)
-{
-	asm volatile ("VAB %0,%1,%1" : : "i" (x), "i" (y));
-}
+#define SHLBYTE(x, y)		fpu_vab(x, y, y)
 
 /*
  * For each of the 16 bytes in the vector register y the MASK()
@@ -39,49 +35,17 @@ static inline void SHLBYTE(int x, int y)
  * or 0x00 if the high bit is 0. The result is stored in vector
  * register x.
  */
-static inline void MASK(int x, int y)
-{
-	asm volatile ("VESRAVB	%0,%1,24" : : "i" (x), "i" (y));
-}
-
-static inline void AND(int x, int y, int z)
-{
-	asm volatile ("VN %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
-}
-
-static inline void XOR(int x, int y, int z)
-{
-	asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
-}
+#define MASK(x, y)		fpu_vesravb(x, y, 24)
 
-static inline void LOAD_DATA(int x, u8 *ptr)
-{
-	typedef struct { u8 _[16 * $#]; } addrtype;
-	register addrtype *__ptr asm("1") = (addrtype *) ptr;
-
-	asm volatile ("VLM %2,%3,0,%1"
-		      : : "m" (*__ptr), "a" (__ptr), "i" (x),
-			  "i" (x + $# - 1));
-}
-
-static inline void STORE_DATA(int x, u8 *ptr)
-{
-	typedef struct { u8 _[16 * $#]; } addrtype;
-	register addrtype *__ptr asm("1") = (addrtype *) ptr;
-
-	asm volatile ("VSTM %2,%3,0,1"
-		      : "=m" (*__ptr) : "a" (__ptr), "i" (x),
-			"i" (x + $# - 1));
-}
-
-static inline void COPY_VEC(int x, int y)
-{
-	asm volatile ("VLR %0,%1" : : "i" (x), "i" (y));
-}
+#define AND(x, y, z)		fpu_vn(x, y, z)
+#define XOR(x, y, z)		fpu_vx(x, y, z)
+#define LOAD_DATA(x, ptr)	fpu_vlm(x, x + $# - 1, ptr)
+#define STORE_DATA(x, ptr)	fpu_vstm(x, x + $# - 1, ptr)
+#define COPY_VEC(x, y)		fpu_vlr(x, y)
 
 static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 {
-	struct kernel_fpu vxstate;
+	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
 	u8 **dptr, *p, *q;
 	int d, z, z0;
 
@@ -114,7 +78,7 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 					size_t bytes, void **ptrs)
 {
-	struct kernel_fpu vxstate;
+	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
 	u8 **dptr, *p, *q;
 	int d, z, z0;