summaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/boot/startup.c2
-rw-r--r--arch/s390/configs/debug_defconfig3
-rw-r--r--arch/s390/configs/defconfig3
-rw-r--r--arch/s390/configs/zfcpdump_defconfig1
-rw-r--r--arch/s390/include/asm/bitops.h6
-rw-r--r--arch/s390/include/asm/gmap.h1
-rw-r--r--arch/s390/include/asm/hugetlb.h16
-rw-r--r--arch/s390/include/asm/uv.h2
-rw-r--r--arch/s390/kernel/crash_dump.c62
-rw-r--r--arch/s390/kernel/dumpstack.c7
-rw-r--r--arch/s390/kernel/ftrace.c3
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c3
-rw-r--r--arch/s390/kernel/perf_pai_ext.c3
-rw-r--r--arch/s390/kernel/processor.c2
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/s390/kernel/traps.c6
-rw-r--r--arch/s390/kernel/uv.c136
-rw-r--r--arch/s390/kvm/gmap.c103
-rw-r--r--arch/s390/kvm/kvm-s390.c25
-rw-r--r--arch/s390/mm/gmap.c28
-rw-r--r--arch/s390/mm/hugetlbpage.c4
-rw-r--r--arch/s390/pci/pci_bus.c20
-rw-r--r--arch/s390/pci/pci_iov.c56
-rw-r--r--arch/s390/pci/pci_iov.h7
-rw-r--r--arch/s390/purgatory/Makefile4
25 files changed, 282 insertions, 222 deletions
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 885bd1dd2c82..9276e0576d0a 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -86,7 +86,7 @@ static int cmma_test_essa(void)
: [reg1] "=&d" (reg1),
[reg2] "=&a" (reg2),
[rc] "+&d" (rc),
- [tmp] "=&d" (tmp),
+ [tmp] "+&d" (tmp),
"+Q" (get_lowcore()->program_new_psw),
"=Q" (old)
: [psw_old] "a" (&old),
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index d6beec5292a0..80bdfbae6e5b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
# CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=y
@@ -740,7 +741,6 @@ CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
-CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -875,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
CONFIG_LATENCYTOP=y
CONFIG_BOOTTIME_TRACING=y
CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
CONFIG_FPROBE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8cfbfb10bba8..449a0e996b96 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
# CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=y
@@ -725,7 +726,6 @@ CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
-CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_FIPS=y
CONFIG_CRYPTO_USER=m
@@ -826,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
CONFIG_BOOTTIME_TRACING=y
CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
CONFIG_FPROBE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index bcbaa069de96..853b2326a171 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -62,7 +62,6 @@ CONFIG_ZFCP=y
# CONFIG_INOTIFY_USER is not set
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_LSM="yama,loadpin,safesetid,integrity"
# CONFIG_ZLIB_DFLTCC is not set
CONFIG_XZ_DEC_MICROLZMA=y
CONFIG_PRINTK_TIME=y
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d5125296ade2..a5ca0a947691 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -53,7 +53,11 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig
unsigned long mask;
int cc;
- if (__builtin_constant_p(nr)) {
+ /*
+ * With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to
+ * handle __builtin_constant_p() in some cases.
+ */
+ if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) {
addr = (const volatile unsigned char *)ptr;
addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE;
mask = 1UL << (nr & (BITS_PER_BYTE - 1));
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 4e73ef46d4b2..9f2814d0e1e9 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -139,7 +139,6 @@ int s390_replace_asce(struct gmap *gmap);
void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
unsigned long end, bool interruptible);
-int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split);
unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
/**
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f82..663e87220e89 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
#define __HAVE_ARCH_HUGE_PTEP_GET
pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep);
+
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep,
+ unsigned long sz)
+{
+ return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
static inline void arch_clear_hugetlb_flags(struct folio *folio)
{
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
- return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+ return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
}
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
if (changed) {
- huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+ __huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}
return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+ pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
}
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index b11f5b6d0bd1..46fb0ef6f984 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -631,7 +631,7 @@ int uv_pin_shared(unsigned long paddr);
int uv_destroy_folio(struct folio *folio);
int uv_destroy_pte(pte_t pte);
int uv_convert_from_secure_pte(pte_t pte);
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb);
int uv_convert_from_secure(unsigned long paddr);
int uv_convert_from_secure_folio(struct folio *folio);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 276cb4c1e11b..4a981266b483 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -246,15 +246,6 @@ bool is_kdump_kernel(void)
}
EXPORT_SYMBOL_GPL(is_kdump_kernel);
-static const char *nt_name(Elf64_Word type)
-{
- const char *name = "LINUX";
-
- if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
- name = KEXEC_CORE_NOTE_NAME;
- return name;
-}
-
/*
* Initialize ELF note
*/
@@ -279,10 +270,8 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
return PTR_ADD(buf, len);
}
-static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
-{
- return nt_init_name(buf, type, desc, d_len, nt_name(type));
-}
+#define nt_init(buf, type, desc) \
+ nt_init_name(buf, NT_ ## type, &(desc), sizeof(desc), NN_ ## type)
/*
* Calculate the size of ELF note
@@ -298,10 +287,7 @@ static size_t nt_size_name(int d_len, const char *name)
return size;
}
-static inline size_t nt_size(Elf64_Word type, int d_len)
-{
- return nt_size_name(d_len, nt_name(type));
-}
+#define nt_size(type, desc) nt_size_name(sizeof(desc), NN_ ## type)
/*
* Fill ELF notes for one CPU with save area registers
@@ -322,18 +308,16 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
memcpy(&nt_fpregset.fpc, &sa->fpc, sizeof(sa->fpc));
memcpy(&nt_fpregset.fprs, &sa->fprs, sizeof(sa->fprs));
/* Create ELF notes for the CPU */
- ptr = nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus));
- ptr = nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset));
- ptr = nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer));
- ptr = nt_init(ptr, NT_S390_TODCMP, &sa->todcmp, sizeof(sa->todcmp));
- ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg));
- ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs));
- ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix));
+ ptr = nt_init(ptr, PRSTATUS, nt_prstatus);
+ ptr = nt_init(ptr, PRFPREG, nt_fpregset);
+ ptr = nt_init(ptr, S390_TIMER, sa->timer);
+ ptr = nt_init(ptr, S390_TODCMP, sa->todcmp);
+ ptr = nt_init(ptr, S390_TODPREG, sa->todpreg);
+ ptr = nt_init(ptr, S390_CTRS, sa->ctrs);
+ ptr = nt_init(ptr, S390_PREFIX, sa->prefix);
if (cpu_has_vx()) {
- ptr = nt_init(ptr, NT_S390_VXRS_HIGH,
- &sa->vxrs_high, sizeof(sa->vxrs_high));
- ptr = nt_init(ptr, NT_S390_VXRS_LOW,
- &sa->vxrs_low, sizeof(sa->vxrs_low));
+ ptr = nt_init(ptr, S390_VXRS_HIGH, sa->vxrs_high);
+ ptr = nt_init(ptr, S390_VXRS_LOW, sa->vxrs_low);
}
return ptr;
}
@@ -346,16 +330,16 @@ static size_t get_cpu_elf_notes_size(void)
struct save_area *sa = NULL;
size_t size;
- size = nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
- size += nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
- size += nt_size(NT_S390_TIMER, sizeof(sa->timer));
- size += nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
- size += nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
- size += nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
- size += nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+ size = nt_size(PRSTATUS, struct elf_prstatus);
+ size += nt_size(PRFPREG, elf_fpregset_t);
+ size += nt_size(S390_TIMER, sa->timer);
+ size += nt_size(S390_TODCMP, sa->todcmp);
+ size += nt_size(S390_TODPREG, sa->todpreg);
+ size += nt_size(S390_CTRS, sa->ctrs);
+ size += nt_size(S390_PREFIX, sa->prefix);
if (cpu_has_vx()) {
- size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
- size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+ size += nt_size(S390_VXRS_HIGH, sa->vxrs_high);
+ size += nt_size(S390_VXRS_LOW, sa->vxrs_low);
}
return size;
@@ -371,7 +355,7 @@ static void *nt_prpsinfo(void *ptr)
memset(&prpsinfo, 0, sizeof(prpsinfo));
prpsinfo.pr_sname = 'R';
strcpy(prpsinfo.pr_fname, "vmlinux");
- return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo));
+ return nt_init(ptr, PRPSINFO, prpsinfo);
}
/*
@@ -610,7 +594,7 @@ static size_t get_elfcorehdr_size(int phdr_count)
/* PT_NOTES */
size += sizeof(Elf64_Phdr);
/* nt_prpsinfo */
- size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+ size += nt_size(PRPSINFO, struct elf_prpsinfo);
/* regsets */
size += get_cpu_cnt() * get_cpu_elf_notes_size();
/* nt_vmcoreinfo */
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 1ecd0580561f..911b95cd57e5 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -198,13 +198,8 @@ void __noreturn die(struct pt_regs *regs, const char *str)
console_verbose();
spin_lock_irq(&die_lock);
bust_spinlocks(1);
- printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
+ printk("%s: %04x ilc:%d [#%d]", str, regs->int_code & 0xffff,
regs->int_code >> 17, ++die_counter);
-#ifdef CONFIG_PREEMPT
- pr_cont("PREEMPT ");
-#elif defined(CONFIG_PREEMPT_RT)
- pr_cont("PREEMPT_RT ");
-#endif
pr_cont("SMP ");
if (debug_pagealloc_enabled())
pr_cont("DEBUG_PAGEALLOC");
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 63ba6306632e..e540b022ceb2 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -266,12 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+ unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
if (unlikely(ftrace_graph_is_dead()))
return;
if (unlikely(atomic_read(&current->tracing_graph_pause)))
return;
- if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+ if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
*parent = (unsigned long)&return_to_handler;
}
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 10725f5a6f0f..63875270941b 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -518,7 +518,8 @@ static void paicrypt_have_samples(void)
/* Called on schedule-in and schedule-out. No access to event structure,
* but for sampling only event CRYPTO_ALL is allowed.
*/
-static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx,
+ struct task_struct *task, bool sched_in)
{
/* We started with a clean page on event installation. So read out
* results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index a8f0bad99cf0..fd14d5ebccbc 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -542,7 +542,8 @@ static void paiext_have_samples(void)
/* Called on schedule-in and schedule-out. No access to event structure,
* but for sampling only event NNPA_ALL is allowed.
*/
-static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx,
+ struct task_struct *task, bool sched_in)
{
/* We started with a clean page on event installation. So read out
* results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5ce9a795a0fe..745649ad9779 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -72,7 +72,7 @@ void notrace stop_machine_yield(const struct cpumask *cpumask)
this_cpu = smp_processor_id();
if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
__this_cpu_write(cpu_relax_retry, 0);
- cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+ cpu = cpumask_next_wrap(this_cpu, cpumask);
if (cpu >= nr_cpu_ids)
return;
if (arch_vcpu_is_preempted(cpu))
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index e9115b4d8b63..a4569b96ef06 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
464 common getxattrat sys_getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 24fee11b030d..b746213d3110 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -285,10 +285,10 @@ static void __init test_monitor_call(void)
return;
asm volatile(
" mc 0,0\n"
- "0: xgr %0,%0\n"
+ "0: lhi %[val],0\n"
"1:\n"
- EX_TABLE(0b,1b)
- : "+d" (val));
+ EX_TABLE(0b, 1b)
+ : [val] "+d" (val));
if (!val)
panic("Monitor call doesn't work!\n");
}
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 9f05df2da2f7..9a5d5be8acf4 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -206,6 +206,39 @@ int uv_convert_from_secure_pte(pte_t pte)
return uv_convert_from_secure_folio(pfn_folio(pte_pfn(pte)));
}
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+ /*
+ * The misc feature indicates, among other things, that importing a
+ * shared page from a different protected VM will automatically also
+ * transfer its ownership.
+ */
+ if (uv_has_feature(BIT_UV_FEAT_MISC))
+ return false;
+ if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+ return false;
+ return atomic_read(&mm->context.protected_count) > 1;
+}
+
/*
* Calculate the expected ref_count for a folio that would otherwise have no
* further pins. This was cribbed from similar functions in other places in
@@ -228,7 +261,7 @@ static int expected_folio_refs(struct folio *folio)
}
/**
- * make_folio_secure() - make a folio secure
+ * __make_folio_secure() - make a folio secure
* @folio: the folio to make secure
* @uvcb: the uvcb that describes the UVC to be used
*
@@ -237,20 +270,18 @@ static int expected_folio_refs(struct folio *folio)
*
* Return: 0 on success;
* -EBUSY if the folio is in writeback or has too many references;
- * -E2BIG if the folio is large;
* -EAGAIN if the UVC needs to be attempted again;
* -ENXIO if the address is not mapped;
* -EINVAL if the UVC failed for other reasons.
*
* Context: The caller must hold exactly one extra reference on the folio
- * (it's the same logic as split_folio())
+ * (it's the same logic as split_folio()), and the folio must be
+ * locked.
*/
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+static int __make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
{
int expected, cc = 0;
- if (folio_test_large(folio))
- return -E2BIG;
if (folio_test_writeback(folio))
return -EBUSY;
expected = expected_folio_refs(folio) + 1;
@@ -277,7 +308,98 @@ int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
return -EAGAIN;
return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
}
-EXPORT_SYMBOL_GPL(make_folio_secure);
+
+static int make_folio_secure(struct mm_struct *mm, struct folio *folio, struct uv_cb_header *uvcb)
+{
+ int rc;
+
+ if (!folio_trylock(folio))
+ return -EAGAIN;
+ if (should_export_before_import(uvcb, mm))
+ uv_convert_from_secure(folio_to_phys(folio));
+ rc = __make_folio_secure(folio, uvcb);
+ folio_unlock(folio);
+
+ return rc;
+}
+
+/**
+ * s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split.
+ * @mm: the mm containing the folio to work on
+ * @folio: the folio
+ * @split: whether to split a large folio
+ *
+ * Context: Must be called while holding an extra reference to the folio;
+ * the mm lock should not be held.
+ * Return: 0 if the folio was split successfully;
+ * -EAGAIN if the folio was not split successfully but another attempt
+ * can be made, or if @split was set to false;
+ * -EINVAL in case of other errors. See split_folio().
+ */
+static int s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
+{
+ int rc;
+
+ lockdep_assert_not_held(&mm->mmap_lock);
+ folio_wait_writeback(folio);
+ lru_add_drain_all();
+ if (split) {
+ folio_lock(folio);
+ rc = split_folio(folio);
+ folio_unlock(folio);
+
+ if (rc != -EBUSY)
+ return rc;
+ }
+ return -EAGAIN;
+}
+
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb)
+{
+ struct vm_area_struct *vma;
+ struct folio_walk fw;
+ struct folio *folio;
+ int rc;
+
+ mmap_read_lock(mm);
+ vma = vma_lookup(mm, hva);
+ if (!vma) {
+ mmap_read_unlock(mm);
+ return -EFAULT;
+ }
+ folio = folio_walk_start(&fw, vma, hva, 0);
+ if (!folio) {
+ mmap_read_unlock(mm);
+ return -ENXIO;
+ }
+
+ folio_get(folio);
+ /*
+ * Secure pages cannot be huge and userspace should not combine both.
+ * In case userspace does it anyway this will result in an -EFAULT for
+ * the unpack. The guest is thus never reaching secure mode.
+ * If userspace plays dirty tricks and decides to map huge pages at a
+ * later point in time, it will receive a segmentation fault or
+ * KVM_RUN will return -EFAULT.
+ */
+ if (folio_test_hugetlb(folio))
+ rc = -EFAULT;
+ else if (folio_test_large(folio))
+ rc = -E2BIG;
+ else if (!pte_write(fw.pte) || (pte_val(fw.pte) & _PAGE_INVALID))
+ rc = -ENXIO;
+ else
+ rc = make_folio_secure(mm, folio, uvcb);
+ folio_walk_end(&fw, vma);
+ mmap_read_unlock(mm);
+
+ if (rc == -E2BIG || rc == -EBUSY)
+ rc = s390_wiggle_split_folio(mm, folio, rc == -E2BIG);
+ folio_put(folio);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(make_hva_secure);
/*
* To be called with the folio locked or with an extra reference! This will
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 02adf151d4de..6d8944d1b4a0 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -23,116 +23,25 @@
#include "gmap.h"
/**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
-{
- /*
- * The misc feature indicates, among other things, that importing a
- * shared page from a different protected VM will automatically also
- * transfer its ownership.
- */
- if (uv_has_feature(BIT_UV_FEAT_MISC))
- return false;
- if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
- return false;
- return atomic_read(&mm->context.protected_count) > 1;
-}
-
-static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
-{
- struct folio *folio = page_folio(page);
- int rc;
-
- /*
- * Secure pages cannot be huge and userspace should not combine both.
- * In case userspace does it anyway this will result in an -EFAULT for
- * the unpack. The guest is thus never reaching secure mode.
- * If userspace plays dirty tricks and decides to map huge pages at a
- * later point in time, it will receive a segmentation fault or
- * KVM_RUN will return -EFAULT.
- */
- if (folio_test_hugetlb(folio))
- return -EFAULT;
- if (folio_test_large(folio)) {
- mmap_read_unlock(gmap->mm);
- rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
- mmap_read_lock(gmap->mm);
- if (rc)
- return rc;
- folio = page_folio(page);
- }
-
- if (!folio_trylock(folio))
- return -EAGAIN;
- if (should_export_before_import(uvcb, gmap->mm))
- uv_convert_from_secure(folio_to_phys(folio));
- rc = make_folio_secure(folio, uvcb);
- folio_unlock(folio);
-
- /*
- * In theory a race is possible and the folio might have become
- * large again before the folio_trylock() above. In that case, no
- * action is performed and -EAGAIN is returned; the callers will
- * have to try again later.
- * In most cases this implies running the VM again, getting the same
- * exception again, and make another attempt in this function.
- * This is expected to happen extremely rarely.
- */
- if (rc == -E2BIG)
- return -EAGAIN;
- /* The folio has too many references, try to shake some off */
- if (rc == -EBUSY) {
- mmap_read_unlock(gmap->mm);
- kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
- mmap_read_lock(gmap->mm);
- return -EAGAIN;
- }
-
- return rc;
-}
-
-/**
* gmap_make_secure() - make one guest page secure
* @gmap: the guest gmap
* @gaddr: the guest address that needs to be made secure
* @uvcb: the UVCB specifying which operation needs to be performed
*
* Context: needs to be called with kvm->srcu held.
- * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()).
+ * Return: 0 on success, < 0 in case of error.
*/
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
{
struct kvm *kvm = gmap->private;
- struct page *page;
- int rc = 0;
+ unsigned long vmaddr;
lockdep_assert_held(&kvm->srcu);
- page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
- mmap_read_lock(gmap->mm);
- if (page)
- rc = __gmap_make_secure(gmap, page, uvcb);
- kvm_release_page_clean(page);
- mmap_read_unlock(gmap->mm);
-
- return rc;
+ vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr));
+ if (kvm_is_error_hva(vmaddr))
+ return -EFAULT;
+ return make_hva_secure(gmap->mm, vmaddr, uvcb);
}
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ebecb96bacce..020502af7dc9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4952,6 +4952,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
{
unsigned int flags = 0;
unsigned long gaddr;
+ int rc;
gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
if (kvm_s390_cur_gmap_fault_is_write())
@@ -4961,16 +4962,6 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
case 0:
vcpu->stat.exit_null++;
break;
- case PGM_NON_SECURE_STORAGE_ACCESS:
- kvm_s390_assert_primary_as(vcpu);
- /*
- * This is normal operation; a page belonging to a protected
- * guest has not been imported yet. Try to import the page into
- * the protected guest.
- */
- if (gmap_convert_to_secure(vcpu->arch.gmap, gaddr) == -EINVAL)
- send_sig(SIGSEGV, current, 0);
- break;
case PGM_SECURE_STORAGE_ACCESS:
case PGM_SECURE_STORAGE_VIOLATION:
kvm_s390_assert_primary_as(vcpu);
@@ -4995,6 +4986,20 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
send_sig(SIGSEGV, current, 0);
}
break;
+ case PGM_NON_SECURE_STORAGE_ACCESS:
+ kvm_s390_assert_primary_as(vcpu);
+ /*
+ * This is normal operation; a page belonging to a protected
+ * guest has not been imported yet. Try to import the page into
+ * the protected guest.
+ */
+ rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr);
+ if (rc == -EINVAL)
+ send_sig(SIGSEGV, current, 0);
+ if (rc != -ENXIO)
+ break;
+ flags = FAULT_FLAG_WRITE;
+ fallthrough;
case PGM_PROTECTION:
case PGM_SEGMENT_TRANSLATION:
case PGM_PAGE_TRANSLATION:
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 94d927785800..d14b488e7a1f 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2626,31 +2626,3 @@ int s390_replace_asce(struct gmap *gmap)
return 0;
}
EXPORT_SYMBOL_GPL(s390_replace_asce);
-
-/**
- * kvm_s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split
- * @mm: the mm containing the folio to work on
- * @folio: the folio
- * @split: whether to split a large folio
- *
- * Context: Must be called while holding an extra reference to the folio;
- * the mm lock should not be held.
- */
-int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
-{
- int rc;
-
- lockdep_assert_not_held(&mm->mmap_lock);
- folio_wait_writeback(folio);
- lru_add_drain_all();
- if (split) {
- folio_lock(folio);
- rc = split_folio(folio);
- folio_unlock(folio);
-
- if (rc != -EBUSY)
- return rc;
- }
- return -EAGAIN;
-}
-EXPORT_SYMBOL_GPL(kvm_s390_wiggle_split_folio);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de..2e568f175cd4 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
return __rste_to_pte(pte_val(*ptep));
}
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
{
pte_t pte = huge_ptep_get(mm, addr, ptep);
pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 857afbc4828f..39a481ec4a40 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -331,6 +331,17 @@ error:
return rc;
}
+static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev)
+{
+ struct pci_dev *pdev;
+
+ pdev = zpci_iov_find_parent_pf(zbus, zdev);
+ if (!pdev)
+ return true;
+ pci_dev_put(pdev);
+ return false;
+}
+
int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
{
bool topo_is_tid = zdev->tid_avail;
@@ -345,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
topo = topo_is_tid ? zdev->tid : zdev->pchid;
zbus = zpci_bus_get(topo, topo_is_tid);
+ /*
+ * An isolated VF gets its own domain/bus even if there exists
+ * a matching domain/bus already
+ */
+ if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) {
+ zpci_bus_put(zbus);
+ zbus = NULL;
+ }
+
if (!zbus) {
zbus = zpci_bus_alloc(topo, topo_is_tid);
if (!zbus)
diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c
index ead062bf2b41..191e56a623f6 100644
--- a/arch/s390/pci/pci_iov.c
+++ b/arch/s390/pci/pci_iov.c
@@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in
return 0;
}
-int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+/**
+ * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function
+ * @zbus: The bus that the PCI function is on, or would be added on
+ * @zdev: The PCI function
+ *
+ * Finds the parent PF, if it exists and is configured, of the given PCI function
+ * and increments its refcount. Th PF is searched for on the provided bus so the
+ * caller has to ensure that this is the correct bus to search. This function may
+ * be used before adding the PCI function to a zbus.
+ *
+ * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not
+ * found. If the function is not a VF or has no RequesterID information,
+ * NULL is returned as well.
+ */
+struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
{
- int i, cand_devfn;
- struct zpci_dev *zdev;
+ int i, vfid, devfn, cand_devfn;
struct pci_dev *pdev;
- int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
- int rc = 0;
if (!zbus->multifunction)
- return 0;
-
- /* If the parent PF for the given VF is also configured in the
+ return NULL;
+ /* Non-VFs and VFs without RID available don't have a parent */
+ if (!zdev->vfn || !zdev->rid_available)
+ return NULL;
+ /* Linux vfid starts at 0 vfn at 1 */
+ vfid = zdev->vfn - 1;
+ devfn = zdev->rid & ZPCI_RID_MASK_DEVFN;
+ /*
+ * If the parent PF for the given VF is also configured in the
* instance, it must be on the same zbus.
* We can then identify the parent PF by checking what
* devfn the VF would have if it belonged to that PF using the PF's
@@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn
if (!pdev)
continue;
cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
- if (cand_devfn == virtfn->devfn) {
- rc = zpci_iov_link_virtfn(pdev, virtfn, vfid);
- /* balance pci_get_slot() */
- pci_dev_put(pdev);
- break;
- }
+ if (cand_devfn == devfn)
+ return pdev;
/* balance pci_get_slot() */
pci_dev_put(pdev);
}
}
+ return NULL;
+}
+
+int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+{
+ struct zpci_dev *zdev = to_zpci(virtfn);
+ struct pci_dev *pdev_pf;
+ int rc = 0;
+
+ pdev_pf = zpci_iov_find_parent_pf(zbus, zdev);
+ if (pdev_pf) {
+ /* Linux' vfids start at 0 while zdev->vfn starts at 1 */
+ rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1);
+ pci_dev_put(pdev_pf);
+ }
return rc;
}
diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h
index e3fa4e77fc86..d2c2793eb0f3 100644
--- a/arch/s390/pci/pci_iov.h
+++ b/arch/s390/pci/pci_iov.h
@@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev);
int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn);
+struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev);
+
#else /* CONFIG_PCI_IOV */
static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {}
@@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v
{
return 0;
}
+
+static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
+{
+ return NULL;
+}
#endif /* CONFIG_PCI_IOV */
#endif /* __S390_PCI_IOV_h */
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bdcf2a3b6c41..bd39b36e7bd6 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
$(call if_changed_rule,cc_o_c)
-CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
+CFLAGS_sha256.o := -D__NO_FORTIFY
$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
$(call if_changed_rule,as_o_S)
@@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
KBUILD_CFLAGS += -fno-stack-protector
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
KBUILD_CFLAGS += $(CLANG_FLAGS)
KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
# Since we link purgatory with -r unresolved symbols are not checked, so we
# also link a purgatory.chk binary without -r to check for unresolved symbols.