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
  ...

5 files changed, 35 insertions, 30 deletions

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 5bfcc50c1a68..ee863566910b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -11,11 +11,11 @@
 #include <linux/err.h>
 #include <linux/pgtable.h>
 #include <linux/bitfield.h>
+#include <asm/access-regs.h>
 #include <asm/fault.h>
 #include <asm/gmap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
-#include <asm/switch_to.h>
 
 union asce {
 	unsigned long val;
@@ -391,7 +391,8 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar,
 	if (ar >= NUM_ACRS)
 		return -EINVAL;
 
-	save_access_regs(vcpu->run->s.regs.acrs);
+	if (vcpu->arch.acrs_loaded)
+		save_access_regs(vcpu->run->s.regs.acrs);
 	alet.val = vcpu->run->s.regs.acrs[ar];
 
 	if (ar == 0 || alet.val == 0) {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fc4007cc067a..dc721d50a942 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -19,13 +19,13 @@
 #include <linux/slab.h>
 #include <linux/bitmap.h>
 #include <linux/vmalloc.h>
+#include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/dis.h>
 #include <linux/uaccess.h>
 #include <asm/sclp.h>
 #include <asm/isc.h>
 #include <asm/gmap.h>
-#include <asm/switch_to.h>
 #include <asm/nmi.h>
 #include <asm/airq.h>
 #include <asm/tpi.h>
@@ -584,7 +584,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 
 	mci.val = mchk->mcic;
 	/* take care of lazy register loading */
-	save_fpu_regs();
+	kvm_s390_fpu_store(vcpu->run);
 	save_access_regs(vcpu->run->s.regs.acrs);
 	if (MACHINE_HAS_GS && vcpu->arch.gs_enabled)
 		save_gs_cb(current->thread.gs_cb);
@@ -648,7 +648,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	}
 	rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA,
 			     vcpu->run->s.regs.gprs, 128);
-	rc |= put_guest_lc(vcpu, current->thread.fpu.fpc,
+	rc |= put_guest_lc(vcpu, vcpu->run->s.regs.fpc,
 			   (u32 __user *) __LC_FP_CREG_SAVE_AREA);
 	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr,
 			   (u32 __user *) __LC_TOD_PROGREG_SAVE_AREA);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ea63ac769889..b11bb8e780a1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -33,19 +33,19 @@
 #include <linux/pgtable.h>
 #include <linux/mmu_notifier.h>
 
+#include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/stp.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
-#include <asm/switch_to.h>
 #include <asm/isc.h>
 #include <asm/sclp.h>
 #include <asm/cpacf.h>
 #include <asm/timex.h>
+#include <asm/fpu.h>
 #include <asm/ap.h>
 #include <asm/uv.h>
-#include <asm/fpu/api.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "pci.h"
@@ -3951,6 +3951,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT |
 				    KVM_SYNC_DIAG318;
+	vcpu->arch.acrs_loaded = false;
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
@@ -4829,8 +4830,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			       vcpu->run->s.regs.gprs,
 			       sizeof(sie_page->pv_grregs));
 		}
-		if (test_cpu_flag(CIF_FPU))
-			load_fpu_regs();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
 		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
@@ -4951,16 +4950,8 @@ static void sync_regs(struct kvm_vcpu *vcpu)
 	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
-	/* save host (userspace) fprs/vrs */
-	save_fpu_regs();
-	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
-	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
-	if (cpu_has_vx())
-		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
-	else
-		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
-	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-
+	vcpu->arch.acrs_loaded = true;
+	kvm_s390_fpu_load(vcpu->run);
 	/* Sync fmt2 only data */
 	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
 		sync_regs_fmt2(vcpu);
@@ -5021,12 +5012,8 @@ static void store_regs(struct kvm_vcpu *vcpu)
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
-	/* Save guest register state */
-	save_fpu_regs();
-	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	/* Restore will be done lazily at return */
-	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
-	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
+	vcpu->arch.acrs_loaded = false;
+	kvm_s390_fpu_store(vcpu->run);
 	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu)))
 		store_regs_fmt2(vcpu);
 }
@@ -5034,6 +5021,7 @@ static void store_regs(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
+	DECLARE_KERNEL_FPU_ONSTACK32(fpu);
 	int rc;
 
 	/*
@@ -5075,6 +5063,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR);
 	sync_regs(vcpu);
 	enable_cpu_timer_accounting(vcpu);
 
@@ -5098,6 +5087,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	disable_cpu_timer_accounting(vcpu);
 	store_regs(vcpu);
+	kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR);
 
 	kvm_sigset_deactivate(vcpu);
 
@@ -5172,8 +5162,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * switch in the run ioctl. Let's update our copies before we save
 	 * it into the save area
 	 */
-	save_fpu_regs();
-	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
+	kvm_s390_fpu_store(vcpu->run);
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a7ea80cfa445..111eb5c74784 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -20,6 +20,24 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
+static inline void kvm_s390_fpu_store(struct kvm_run *run)
+{
+	fpu_stfpc(&run->s.regs.fpc);
+	if (cpu_has_vx())
+		save_vx_regs((__vector128 *)&run->s.regs.vrs);
+	else
+		save_fp_regs((freg_t *)&run->s.regs.fprs);
+}
+
+static inline void kvm_s390_fpu_load(struct kvm_run *run)
+{
+	fpu_lfpc_safe(&run->s.regs.fpc);
+	if (cpu_has_vx())
+		load_vx_regs((__vector128 *)&run->s.regs.vrs);
+	else
+		load_fp_regs((freg_t *)&run->s.regs.fprs);
+}
+
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & ECB_TE))
 #define TDB_FORMAT1		1
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 3af3bd20ac7b..b2c9f010f0fe 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -18,7 +18,6 @@
 #include <asm/sclp.h>
 #include <asm/nmi.h>
 #include <asm/dis.h>
-#include <asm/fpu/api.h>
 #include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -1149,8 +1148,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	 */
 	vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
 	barrier();
-	if (test_cpu_flag(CIF_FPU))
-		load_fpu_regs();
 	if (!kvm_s390_vcpu_sie_inhibited(vcpu))
 		rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
 	barrier();