s390/kvm: support collaborative memory management

This patch enables Collaborative Memory Management (CMM) for kvm
on s390. CMM allows the guest to inform the host about page usage
(see arch/s390/mm/cmm.c). The host uses this information to avoid
swapping in unused pages in the page fault handler. Further, a CPU
provided list of unused invalid pages is processed to reclaim swap
space of not yet accessed unused pages.

[ Martin Schwidefsky: patch reordering and cleanup ]

Signed-off-by: Konstantin Weitz <konstantin.weitz@gmail.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

3 files changed, 68 insertions, 0 deletions

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f390d57..10b5db3c9bc4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -68,6 +68,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
         { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
         { "instruction_stsch", VCPU_STAT(instruction_stsch) },
         { "instruction_chsc", VCPU_STAT(instruction_chsc) },
+        { "instruction_essa", VCPU_STAT(instruction_essa) },
         { "instruction_stsi", VCPU_STAT(instruction_stsi) },
         { "instruction_stfl", VCPU_STAT(instruction_stfl) },
         { "instruction_tprot", VCPU_STAT(instruction_tprot) },
@@ -283,7 +284,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
         if (kvm_is_ucontrol(vcpu->kvm))
                 gmap_free(vcpu->arch.gmap);
 
+        if (vcpu->arch.sie_block->cbrlo)
+                __free_page(__pfn_to_page(
+                                vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT));
         free_page((unsigned long)(vcpu->arch.sie_block));
+
         kvm_vcpu_uninit(vcpu);
         kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
@@ -390,6 +395,8 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+        struct page *cbrl;
+
         atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
                                                     CPUSTAT_SM |
                                                     CPUSTAT_STOPPED |
@@ -401,6 +408,14 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
         vcpu->arch.sie_block->ecb2  = 8;
         vcpu->arch.sie_block->eca   = 0xC1002001U;
         vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
+        if (kvm_enabled_cmma()) {
+                cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO);
+                if (cbrl) {
+                        vcpu->arch.sie_block->ecb2 |= 0x80;
+                        vcpu->arch.sie_block->ecb2 &= ~0x08;
+                        vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl);
+                }
+        }
         hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
         tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
                      (unsigned long) vcpu);
@@ -761,6 +776,16 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
         return rc;
 }
 
+bool kvm_enabled_cmma(void)
+{
+        if (!MACHINE_IS_LPAR)
+                return false;
+        /* only enable for z10 and later */
+        if (!MACHINE_HAS_EDAT1)
+                return false;
+        return true;
+}
+
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
         int rc, exit_reason;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index f9559b0bd620..564514f410f4 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -156,6 +156,8 @@ void s390_vcpu_block(struct kvm_vcpu *vcpu);
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
 void exit_sie_sync(struct kvm_vcpu *vcpu);
+/* are we going to support cmma? */
+bool kvm_enabled_cmma(void);
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 75beea632a10..aacb6b129914 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -636,8 +636,49 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
         return 0;
 }
 
+static int handle_essa(struct kvm_vcpu *vcpu)
+{
+        /* entries expected to be 1FF */
+        int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
+        unsigned long *cbrlo, cbrle;
+        struct gmap *gmap;
+        int i;
+
+        VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
+        gmap = vcpu->arch.gmap;
+        vcpu->stat.instruction_essa++;
+        if (!kvm_enabled_cmma() || !vcpu->arch.sie_block->cbrlo)
+                return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+        if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+                return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+        if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
+                return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+        /* Rewind PSW to repeat the ESSA instruction */
+        vcpu->arch.sie_block->gpsw.addr =
+                __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+        vcpu->arch.sie_block->cbrlo &= PAGE_MASK;       /* reset nceo */
+        cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
+        down_read(&gmap->mm->mmap_sem);
+        for (i = 0; i < entries; ++i) {
+                cbrle = cbrlo[i];
+                if (unlikely(cbrle & ~PAGE_MASK || cbrle < 2 * PAGE_SIZE))
+                        /* invalid entry */
+                        break;
+                /* try to free backing */
+                __gmap_zap(cbrle, gmap);
+        }
+        up_read(&gmap->mm->mmap_sem);
+        if (i < entries)
+                return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+        return 0;
+}
+
 static const intercept_handler_t b9_handlers[256] = {
         [0x8d] = handle_epsw,
+        [0xab] = handle_essa,
         [0xaf] = handle_pfmf,
 };