Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 43a81d0..0023b78 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -920,7 +920,7 @@
config APPLDATA_BASE
def_bool n
prompt "Linux - VM Monitor Stream, base infrastructure"
- depends on PROC_FS
+ depends on PROC_SYSCTL
help
This provides a kernel interface for creating and updating z/VM APPLDATA
monitor records. The monitor records are updated at certain time
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 478b645..2faaf45 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -69,7 +69,7 @@
#
cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
-ifeq ($(call cc-option-yn,-mpacked-stack),y)
+ifeq ($(call cc-option-yn,-mpacked-stack -mbackchain -msoft-float),y)
cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK
aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK
endif
@@ -146,7 +146,7 @@
#KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
KBUILD_IMAGE := $(boot)/bzImage
-install: vmlinux
+install:
$(Q)$(MAKE) $(build)=$(boot) $@
bzImage: vmlinux
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index e2c47d3..0ff9261 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -70,7 +70,7 @@
$(obj)/startup.a: $(OBJECTS) FORCE
$(call if_changed,ar)
-install: $(CONFIGURE) $(obj)/bzImage
+install:
sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
System.map "$(INSTALL_PATH)"
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 4b86a8d..e6bf5f4 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -360,22 +360,23 @@
# the save area and does disabled wait with a faulty address.
#
ENTRY(startup_pgm_check_handler)
- stmg %r0,%r15,__LC_SAVE_AREA_SYNC
- la %r1,4095
- stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1)
- mvc __LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC
- mvc __LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW
+ stmg %r8,%r15,__LC_SAVE_AREA_SYNC
+ la %r8,4095
+ stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r8)
+ stmg %r0,%r7,__LC_GPREGS_SAVE_AREA-4095(%r8)
+ mvc __LC_GPREGS_SAVE_AREA-4095+64(64,%r8),__LC_SAVE_AREA_SYNC
+ mvc __LC_PSW_SAVE_AREA-4095(16,%r8),__LC_PGM_OLD_PSW
mvc __LC_RETURN_PSW(16),__LC_PGM_OLD_PSW
ni __LC_RETURN_PSW,0xfc # remove IO and EX bits
ni __LC_RETURN_PSW+1,0xfb # remove MCHK bit
oi __LC_RETURN_PSW+1,0x2 # set wait state bit
- larl %r2,.Lold_psw_disabled_wait
- stg %r2,__LC_PGM_NEW_PSW+8
- l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2)
+ larl %r9,.Lold_psw_disabled_wait
+ stg %r9,__LC_PGM_NEW_PSW+8
+ l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r9)
brasl %r14,print_pgm_check_info
.Lold_psw_disabled_wait:
- la %r1,4095
- lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
+ la %r8,4095
+ lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)
lpswe __LC_RETURN_PSW # disabled wait
.Ldump_info_stack:
.long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 24ef67e..75905b5 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -27,22 +27,25 @@
register unsigned long _addr asm("0") = (unsigned long)addr;
register unsigned long _rc asm("1") = 0;
unsigned long reg1, reg2;
- psw_t old = S390_lowcore.program_new_psw;
+ psw_t old;
asm volatile(
+ " mvc 0(16,%[psw_old]),0(%[psw_pgm])\n"
" epsw %0,%1\n"
- " st %0,%[psw_pgm]\n"
- " st %1,%[psw_pgm]+4\n"
+ " st %0,0(%[psw_pgm])\n"
+ " st %1,4(%[psw_pgm])\n"
" larl %0,1f\n"
- " stg %0,%[psw_pgm]+8\n"
+ " stg %0,8(%[psw_pgm])\n"
" diag %[addr],%[subcode],0x308\n"
- "1: nopr %%r7\n"
+ "1: mvc 0(16,%[psw_pgm]),0(%[psw_old])\n"
: "=&d" (reg1), "=&a" (reg2),
- [psw_pgm] "=Q" (S390_lowcore.program_new_psw),
+ "+Q" (S390_lowcore.program_new_psw),
+ "=Q" (old),
[addr] "+d" (_addr), "+d" (_rc)
- : [subcode] "d" (subcode)
+ : [subcode] "d" (subcode),
+ [psw_old] "a" (&old),
+ [psw_pgm] "a" (&S390_lowcore.program_new_psw)
: "cc", "memory");
- S390_lowcore.program_new_psw = old;
return _rc;
}
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index 5d12352..5591243 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -75,7 +75,7 @@
*(unsigned long *) prng.parm_block ^= seed;
for (i = 0; i < 16; i++) {
cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
- (char *) entropy, (char *) entropy,
+ (u8 *) entropy, (u8 *) entropy,
sizeof(entropy));
memcpy(prng.parm_block, entropy, sizeof(entropy));
}
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 62e7c13..8504954 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -70,24 +70,27 @@
register unsigned long _ry asm("4") = 0x10; /* storage configuration */
int rc = -1; /* fail */
unsigned long reg1, reg2;
- psw_t old = S390_lowcore.program_new_psw;
+ psw_t old;
asm volatile(
+ " mvc 0(16,%[psw_old]),0(%[psw_pgm])\n"
" epsw %0,%1\n"
- " st %0,%[psw_pgm]\n"
- " st %1,%[psw_pgm]+4\n"
+ " st %0,0(%[psw_pgm])\n"
+ " st %1,4(%[psw_pgm])\n"
" larl %0,1f\n"
- " stg %0,%[psw_pgm]+8\n"
+ " stg %0,8(%[psw_pgm])\n"
" diag %[rx],%[ry],0x260\n"
" ipm %[rc]\n"
" srl %[rc],28\n"
- "1:\n"
+ "1: mvc 0(16,%[psw_pgm]),0(%[psw_old])\n"
: "=&d" (reg1), "=&a" (reg2),
- [psw_pgm] "=Q" (S390_lowcore.program_new_psw),
+ "+Q" (S390_lowcore.program_new_psw),
+ "=Q" (old),
[rc] "+&d" (rc), [ry] "+d" (_ry)
- : [rx] "d" (_rx1), "d" (_rx2)
+ : [rx] "d" (_rx1), "d" (_rx2),
+ [psw_old] "a" (&old),
+ [psw_pgm] "a" (&S390_lowcore.program_new_psw)
: "cc", "memory");
- S390_lowcore.program_new_psw = old;
return rc == 0 ? _ry : -1;
}
@@ -112,24 +115,30 @@
static int tprot(unsigned long addr)
{
- unsigned long pgm_addr;
+ unsigned long reg1, reg2;
int rc = -EFAULT;
- psw_t old = S390_lowcore.program_new_psw;
+ psw_t old;
- S390_lowcore.program_new_psw.mask = __extract_psw();
asm volatile(
- " larl %[pgm_addr],1f\n"
- " stg %[pgm_addr],%[psw_pgm_addr]\n"
+ " mvc 0(16,%[psw_old]),0(%[psw_pgm])\n"
+ " epsw %[reg1],%[reg2]\n"
+ " st %[reg1],0(%[psw_pgm])\n"
+ " st %[reg2],4(%[psw_pgm])\n"
+ " larl %[reg1],1f\n"
+ " stg %[reg1],8(%[psw_pgm])\n"
" tprot 0(%[addr]),0\n"
" ipm %[rc]\n"
" srl %[rc],28\n"
- "1:\n"
- : [pgm_addr] "=&d"(pgm_addr),
- [psw_pgm_addr] "=Q"(S390_lowcore.program_new_psw.addr),
- [rc] "+&d"(rc)
- : [addr] "a"(addr)
+ "1: mvc 0(16,%[psw_pgm]),0(%[psw_old])\n"
+ : [reg1] "=&d" (reg1),
+ [reg2] "=&a" (reg2),
+ [rc] "+&d" (rc),
+ "=Q" (S390_lowcore.program_new_psw.addr),
+ "=Q" (old)
+ : [psw_old] "a" (&old),
+ [psw_pgm] "a" (&S390_lowcore.program_new_psw),
+ [addr] "a" (addr)
: "cc", "memory");
- S390_lowcore.program_new_psw = old;
return rc;
}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 5367950..fa01502 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -170,6 +170,11 @@
handle_relocs(__kaslr_offset);
if (__kaslr_offset) {
+ /*
+ * Save KASLR offset for early dumps, before vmcore_info is set.
+ * Mark as uneven to distinguish from real vmcore_info pointer.
+ */
+ S390_lowcore.vmcore_info = __kaslr_offset | 0x1UL;
/* Clear non-relocated kernel */
if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
memset(img, 0, vmlinux.image_size);
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S
index 9715715..ea93314 100644
--- a/arch/s390/boot/text_dma.S
+++ b/arch/s390/boot/text_dma.S
@@ -9,16 +9,6 @@
#include <asm/errno.h>
#include <asm/sigp.h>
-#ifdef CC_USING_EXPOLINE
- .pushsection .dma.text.__s390_indirect_jump_r14,"axG"
-__dma__s390_indirect_jump_r14:
- larl %r1,0f
- ex 0,0(%r1)
- j .
-0: br %r14
- .popsection
-#endif
-
.section .dma.text,"ax"
/*
* Simplified version of expoline thunk. The normal thunks can not be used here,
@@ -27,11 +17,10 @@
* affects a few functions that are not performance-relevant.
*/
.macro BR_EX_DMA_r14
-#ifdef CC_USING_EXPOLINE
- jg __dma__s390_indirect_jump_r14
-#else
- br %r14
-#endif
+ larl %r1,0f
+ ex 0,0(%r1)
+ j .
+0: br %r14
.endm
/*
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index ed007f4..3f50115 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -15,7 +15,8 @@
if (!test_facility(158))
return;
- if (uv_call(0, (uint64_t)&uvcb))
+ /* rc==0x100 means that there is additional data we do not process */
+ if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100)
return;
if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index dd95cdb..4cbb4b6 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -53,6 +53,10 @@
bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
{
+ /* max hunk is ARCH_RNG_BUF_SIZE */
+ if (nbytes > ARCH_RNG_BUF_SIZE)
+ return false;
+
/* lock rng buffer */
if (!spin_trylock(&arch_rng_lock))
return false;
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index d39e0f0..686fe7a 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -74,14 +74,17 @@
struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
unsigned int bsize = crypto_shash_blocksize(desc->tfm);
u64 bits;
- unsigned int n, mbl_offset;
+ unsigned int n;
+ int mbl_offset;
n = ctx->count % bsize;
bits = ctx->count * 8;
- mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+ mbl_offset = s390_crypto_shash_parmsize(ctx->func);
if (mbl_offset < 0)
return -EINVAL;
+ mbl_offset = mbl_offset / sizeof(u32);
+
/* set total msg bit length (mbl) in CPACF parmblock */
switch (ctx->func) {
case CPACF_KLMD_SHA_1:
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 68d362f..c72c179 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -27,6 +27,7 @@
extern char ftrace_graph_caller_end;
extern unsigned long ftrace_plt;
+extern void *ftrace_func;
struct dyn_arch_ftrace { };
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index abe6026..4d59d11 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -31,12 +31,12 @@
#define KVM_USER_MEM_SLOTS 32
/*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
*/
#define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
#define KVM_HALT_POLL_NS_DEFAULT 50000
/* s390-specific vcpu->requests bit members */
@@ -873,6 +873,7 @@
atomic64_t cmma_dirty_pages;
/* subset of available cpu features enabled by user space */
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+ /* indexed by vcpu_idx */
DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
struct kvm_s390_gisa_interrupt gisa_int;
};
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 237ee0c..612ed3c 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -141,7 +141,9 @@
/* br %r1 trampoline */
__u16 br_r1_trampoline; /* 0x0400 */
- __u8 pad_0x0402[0x0e00-0x0402]; /* 0x0402 */
+ __u32 return_lpswe; /* 0x0402 */
+ __u32 return_mcck_lpswe; /* 0x0406 */
+ __u8 pad_0x040a[0x0e00-0x040a]; /* 0x040a */
/*
* 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
index 35f8cbe..c759dcf 100644
--- a/arch/s390/include/asm/numa.h
+++ b/arch/s390/include/asm/numa.h
@@ -17,7 +17,6 @@
void numa_setup(void);
int numa_pfn_to_nid(unsigned long pfn);
-int __node_distance(int a, int b);
void numa_update_cpu_topology(void);
extern cpumask_t node_to_cpumask_map[MAX_NUMNODES];
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c..e399102 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -33,6 +33,8 @@
#define ARCH_HAS_PREPARE_HUGEPAGE
#define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+
#include <asm/setup.h>
#ifndef __ASSEMBLY__
@@ -40,7 +42,7 @@
static inline void storage_key_init_range(unsigned long start, unsigned long end)
{
- if (PAGE_DEFAULT_KEY)
+ if (PAGE_DEFAULT_KEY != 0)
__storage_key_init_range(start, end);
}
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index a2399ef..6087a4e 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -183,7 +183,7 @@
/* CLP */
int clp_scan_pci_devices(void);
int clp_rescan_pci_devices(void);
-int clp_rescan_pci_devices_simple(void);
+int clp_rescan_pci_devices_simple(u32 *fid);
int clp_add_pci_device(u32, u32, int);
int clp_enable_fh(struct zpci_dev *, u8);
int clp_disable_fh(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cd060b5..e4dc64c 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,6 +8,10 @@
#include <linux/slab.h>
#include <asm/pci_insn.h>
+/* I/O size constraints */
+#define ZPCI_MAX_READ_SIZE 8
+#define ZPCI_MAX_WRITE_SIZE 128
+
/* I/O Map */
#define ZPCI_IOMAP_SHIFT 48
#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL
@@ -140,7 +144,8 @@
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) src,
- (u64) dst, n, 8);
+ (u64) dst, n,
+ ZPCI_MAX_READ_SIZE);
rc = zpci_read_single(dst, src, size);
if (rc)
break;
@@ -161,7 +166,8 @@
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) dst,
- (u64) src, n, 128);
+ (u64) src, n,
+ ZPCI_MAX_WRITE_SIZE);
if (size > 8) /* main path */
rc = zpci_write_block(dst, src, size);
else
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 50b4ce8..918f0ba 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -29,7 +29,7 @@
typedef typeof(pcp) pcp_op_T__; \
pcp_op_T__ old__, new__, prev__; \
pcp_op_T__ *ptr__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
prev__ = *ptr__; \
do { \
@@ -37,7 +37,7 @@
new__ = old__ op (val); \
prev__ = cmpxchg(ptr__, old__, new__); \
} while (prev__ != old__); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
new__; \
})
@@ -68,7 +68,7 @@
typedef typeof(pcp) pcp_op_T__; \
pcp_op_T__ val__ = (val); \
pcp_op_T__ old__, *ptr__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
if (__builtin_constant_p(val__) && \
((szcast)val__ > -129) && ((szcast)val__ < 128)) { \
@@ -84,7 +84,7 @@
: [val__] "d" (val__) \
: "cc"); \
} \
- preempt_enable(); \
+ preempt_enable_notrace(); \
}
#define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
@@ -95,14 +95,14 @@
typedef typeof(pcp) pcp_op_T__; \
pcp_op_T__ val__ = (val); \
pcp_op_T__ old__, *ptr__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
asm volatile( \
op " %[old__],%[val__],%[ptr__]\n" \
: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \
: [val__] "d" (val__) \
: "cc"); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
old__ + val__; \
})
@@ -114,14 +114,14 @@
typedef typeof(pcp) pcp_op_T__; \
pcp_op_T__ val__ = (val); \
pcp_op_T__ old__, *ptr__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
asm volatile( \
op " %[old__],%[val__],%[ptr__]\n" \
: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \
: [val__] "d" (val__) \
: "cc"); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
}
#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan")
@@ -136,10 +136,10 @@
typedef typeof(pcp) pcp_op_T__; \
pcp_op_T__ ret__; \
pcp_op_T__ *ptr__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
ret__ = cmpxchg(ptr__, oval, nval); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
ret__; \
})
@@ -152,10 +152,10 @@
({ \
typeof(pcp) *ptr__; \
typeof(pcp) ret__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
ret__ = xchg(ptr__, nval); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
ret__; \
})
@@ -171,11 +171,11 @@
typeof(pcp1) *p1__; \
typeof(pcp2) *p2__; \
int ret__; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
p1__ = raw_cpu_ptr(&(pcp1)); \
p2__ = raw_cpu_ptr(&(pcp2)); \
ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
ret__; \
})
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index bccb8f4..77606c4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,7 +56,12 @@
crst_table_init(table, _REGION2_ENTRY_EMPTY);
return (p4d_t *) table;
}
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+ if (!mm_p4d_folded(mm))
+ crst_table_free(mm, (unsigned long *) p4d);
+}
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
{
@@ -65,7 +70,12 @@
crst_table_init(table, _REGION3_ENTRY_EMPTY);
return (pud_t *) table;
}
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+ if (!mm_pud_folded(mm))
+ crst_table_free(mm, (unsigned long *) pud);
+}
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
{
@@ -83,6 +93,8 @@
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
+ if (mm_pmd_folded(mm))
+ return;
pgtable_pmd_page_dtor(virt_to_page(pmd));
crst_table_free(mm, (unsigned long *) pmd);
}
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ff98d7..5ce5869 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -756,6 +756,12 @@
return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
static inline int pmd_dirty(pmd_t pmd)
{
int dirty = 1;
@@ -1173,8 +1179,6 @@
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
- if (!MACHINE_HAS_NX)
- pte_val(entry) &= ~_PAGE_NOEXEC;
if (pte_present(entry))
pte_val(entry) &= ~_PAGE_UNUSED;
if (mm_has_pgste(mm))
@@ -1191,6 +1195,8 @@
{
pte_t __pte;
pte_val(__pte) = physpage + pgprot_val(pgprot);
+ if (!MACHINE_HAS_NX)
+ pte_val(__pte) &= ~_PAGE_NOEXEC;
return pte_mkyoung(__pte);
}
@@ -1241,26 +1247,46 @@
#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
{
- if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
- return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
- return (p4d_t *) pgd;
+ if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+ return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+ return (p4d_t *) pgdp;
+}
+#define p4d_offset_lockless p4d_offset_lockless
+
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
+{
+ return p4d_offset_lockless(pgdp, *pgdp, address);
}
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
{
- if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
- return (pud_t *) p4d_deref(*p4d) + pud_index(address);
- return (pud_t *) p4d;
+ if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+ return (pud_t *) p4d_deref(p4d) + pud_index(address);
+ return (pud_t *) p4dp;
}
+#define pud_offset_lockless pud_offset_lockless
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
{
- if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
- return (pmd_t *) pud_deref(*pud) + pmd_index(address);
- return (pmd_t *) pud;
+ return pud_offset_lockless(p4dp, *p4dp, address);
}
+#define pud_offset pud_offset
+
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
+{
+ if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+ return (pmd_t *) pud_deref(pud) + pmd_index(address);
+ return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
+{
+ return pmd_offset_lockless(pudp, *pudp, address);
+}
+#define pmd_offset pmd_offset
static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
{
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 51a0e4a..48d6ccd 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -162,6 +162,7 @@
#define INIT_THREAD { \
.ksp = sizeof(init_stack) + (unsigned long) &init_stack, \
.fpu.regs = (void *) init_task.thread.fpu.fprs, \
+ .last_break = 1, \
}
/*
@@ -214,7 +215,7 @@
return sp;
}
-static __no_kasan_or_inline unsigned short stap(void)
+static __always_inline unsigned short stap(void)
{
unsigned short cpu_address;
@@ -253,7 +254,7 @@
* Set PSW mask to specified value, while leaving the
* PSW addr pointing to the next instruction.
*/
-static __no_kasan_or_inline void __load_psw_mask(unsigned long mask)
+static __always_inline void __load_psw_mask(unsigned long mask)
{
unsigned long addr;
psw_t psw;
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e3f238e..4f35b10 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -227,7 +227,7 @@
* @sbal: absolute SBAL address
*/
struct sl_element {
- unsigned long sbal;
+ u64 sbal;
} __attribute__ ((packed));
/**
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 6dc6c4f..e6a5007 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -8,6 +8,7 @@
#include <linux/bits.h>
#include <uapi/asm/setup.h>
+#include <linux/build_bug.h>
#define EP_OFFSET 0x10008
#define EP_STRING "S390EP"
@@ -38,6 +39,7 @@
#define MACHINE_FLAG_NX BIT(15)
#define MACHINE_FLAG_GS BIT(16)
#define MACHINE_FLAG_SCC BIT(17)
+#define MACHINE_FLAG_PCI_MIO BIT(18)
#define LPP_MAGIC BIT(31)
#define LPP_PID_MASK _AC(0xffffffff, UL)
@@ -105,6 +107,7 @@
#define MACHINE_HAS_NX (S390_lowcore.machine_flags & MACHINE_FLAG_NX)
#define MACHINE_HAS_GS (S390_lowcore.machine_flags & MACHINE_FLAG_GS)
#define MACHINE_HAS_SCC (S390_lowcore.machine_flags & MACHINE_FLAG_SCC)
+#define MACHINE_HAS_PCI_MIO (S390_lowcore.machine_flags & MACHINE_FLAG_PCI_MIO)
/*
* Console mode. Override with conmode=
@@ -157,6 +160,12 @@
return __kaslr_offset;
}
+static inline u32 gen_lpswe(unsigned long addr)
+{
+ BUILD_BUG_ON(addr > 0xfff);
+ return 0xb2b20000 | addr;
+}
+
#else /* __ASSEMBLY__ */
#define IPL_DEVICE (IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 0ae4bbf..e192681 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -79,12 +79,16 @@
CALL_ARGS_4(arg1, arg2, arg3, arg4); \
register unsigned long r4 asm("6") = (unsigned long)(arg5)
-#define CALL_FMT_0 "=&d" (r2) :
-#define CALL_FMT_1 "+&d" (r2) :
-#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
-#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
-#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
-#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
+/*
+ * To keep this simple mark register 2-6 as being changed (volatile)
+ * by the called function, even though register 6 is saved/nonvolatile.
+ */
+#define CALL_FMT_0 "=&d" (r2)
+#define CALL_FMT_1 "+&d" (r2)
+#define CALL_FMT_2 CALL_FMT_1, "+&d" (r3)
+#define CALL_FMT_3 CALL_FMT_2, "+&d" (r4)
+#define CALL_FMT_4 CALL_FMT_3, "+&d" (r5)
+#define CALL_FMT_5 CALL_FMT_4, "+&d" (r6)
#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
#define CALL_CLOBBER_4 CALL_CLOBBER_5
@@ -105,10 +109,118 @@
" brasl 14,%[_fn]\n" \
" la 15,0(%[_prev])\n" \
: [_prev] "=&a" (prev), CALL_FMT_##nr \
- [_stack] "a" (stack), \
+ : [_stack] "a" (stack), \
[_bc] "i" (offsetof(struct stack_frame, back_chain)), \
[_fn] "X" (fn) : CALL_CLOBBER_##nr); \
r2; \
})
+#define CALL_LARGS_0(...) \
+ long dummy = 0
+#define CALL_LARGS_1(t1, a1) \
+ long arg1 = (long)(t1)(a1)
+#define CALL_LARGS_2(t1, a1, t2, a2) \
+ CALL_LARGS_1(t1, a1); \
+ long arg2 = (long)(t2)(a2)
+#define CALL_LARGS_3(t1, a1, t2, a2, t3, a3) \
+ CALL_LARGS_2(t1, a1, t2, a2); \
+ long arg3 = (long)(t3)(a3)
+#define CALL_LARGS_4(t1, a1, t2, a2, t3, a3, t4, a4) \
+ CALL_LARGS_3(t1, a1, t2, a2, t3, a3); \
+ long arg4 = (long)(t4)(a4)
+#define CALL_LARGS_5(t1, a1, t2, a2, t3, a3, t4, a4, t5, a5) \
+ CALL_LARGS_4(t1, a1, t2, a2, t3, a3, t4, a4); \
+ long arg5 = (long)(t5)(a5)
+
+#define CALL_REGS_0 \
+ register long r2 asm("2") = dummy
+#define CALL_REGS_1 \
+ register long r2 asm("2") = arg1
+#define CALL_REGS_2 \
+ CALL_REGS_1; \
+ register long r3 asm("3") = arg2
+#define CALL_REGS_3 \
+ CALL_REGS_2; \
+ register long r4 asm("4") = arg3
+#define CALL_REGS_4 \
+ CALL_REGS_3; \
+ register long r5 asm("5") = arg4
+#define CALL_REGS_5 \
+ CALL_REGS_4; \
+ register long r6 asm("6") = arg5
+
+#define CALL_TYPECHECK_0(...)
+#define CALL_TYPECHECK_1(t, a, ...) \
+ typecheck(t, a)
+#define CALL_TYPECHECK_2(t, a, ...) \
+ CALL_TYPECHECK_1(__VA_ARGS__); \
+ typecheck(t, a)
+#define CALL_TYPECHECK_3(t, a, ...) \
+ CALL_TYPECHECK_2(__VA_ARGS__); \
+ typecheck(t, a)
+#define CALL_TYPECHECK_4(t, a, ...) \
+ CALL_TYPECHECK_3(__VA_ARGS__); \
+ typecheck(t, a)
+#define CALL_TYPECHECK_5(t, a, ...) \
+ CALL_TYPECHECK_4(__VA_ARGS__); \
+ typecheck(t, a)
+
+#define CALL_PARM_0(...) void
+#define CALL_PARM_1(t, a, ...) t
+#define CALL_PARM_2(t, a, ...) t, CALL_PARM_1(__VA_ARGS__)
+#define CALL_PARM_3(t, a, ...) t, CALL_PARM_2(__VA_ARGS__)
+#define CALL_PARM_4(t, a, ...) t, CALL_PARM_3(__VA_ARGS__)
+#define CALL_PARM_5(t, a, ...) t, CALL_PARM_4(__VA_ARGS__)
+#define CALL_PARM_6(t, a, ...) t, CALL_PARM_5(__VA_ARGS__)
+
+/*
+ * Use call_on_stack() to call a function switching to a specified
+ * stack. Proper sign and zero extension of function arguments is
+ * done. Usage:
+ *
+ * rc = call_on_stack(nr, stack, rettype, fn, t1, a1, t2, a2, ...)
+ *
+ * - nr specifies the number of function arguments of fn.
+ * - stack specifies the stack to be used.
+ * - fn is the function to be called.
+ * - rettype is the return type of fn.
+ * - t1, a1, ... are pairs, where t1 must match the type of the first
+ * argument of fn, t2 the second, etc. a1 is the corresponding
+ * first function argument (not name), etc.
+ */
+#define call_on_stack(nr, stack, rettype, fn, ...) \
+({ \
+ rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = fn; \
+ unsigned long frame = current_frame_address(); \
+ unsigned long __stack = stack; \
+ unsigned long prev; \
+ CALL_LARGS_##nr(__VA_ARGS__); \
+ CALL_REGS_##nr; \
+ \
+ CALL_TYPECHECK_##nr(__VA_ARGS__); \
+ asm volatile( \
+ " lgr %[_prev],15\n" \
+ " lg 15,%[_stack]\n" \
+ " stg %[_frame],%[_bc](15)\n" \
+ " brasl 14,%[_fn]\n" \
+ " lgr 15,%[_prev]\n" \
+ : [_prev] "=&d" (prev), CALL_FMT_##nr \
+ : [_stack] "R" (__stack), \
+ [_bc] "i" (offsetof(struct stack_frame, back_chain)), \
+ [_frame] "d" (frame), \
+ [_fn] "X" (__fn) : CALL_CLOBBER_##nr); \
+ (rettype)r2; \
+})
+
+#define CALL_ON_STACK_NORETURN(fn, stack) \
+({ \
+ asm volatile( \
+ " la 15,0(%[_stack])\n" \
+ " xc %[_bc](8,15),%[_bc](15)\n" \
+ " brasl 14,%[_fn]\n" \
+ ::[_bc] "i" (offsetof(struct stack_frame, back_chain)), \
+ [_stack] "a" (stack), [_fn] "X" (fn)); \
+ BUG(); \
+})
+
#endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index f073292..d9d5de0 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -33,7 +33,17 @@
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
- return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
+ unsigned long error = regs->gprs[2];
+#ifdef CONFIG_COMPAT
+ if (test_tsk_thread_flag(task, TIF_31BIT)) {
+ /*
+ * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+ * and will match correctly in comparisons.
+ */
+ error = (long)(int)error;
+ }
+#endif
+ return IS_ERR_VALUE(error) ? error : 0;
}
static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 64539c2..b6a4ce9 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,8 +10,9 @@
#ifndef _ASM_S390_TIMEX_H
#define _ASM_S390_TIMEX_H
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
#include <linux/time64.h>
+#include <asm/lowcore.h>
/* The value of the TOD clock for 1.1.1970. */
#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -154,7 +155,7 @@
static inline unsigned long long get_tod_clock(void)
{
- unsigned char clk[STORE_CLOCK_EXT_SIZE];
+ char clk[STORE_CLOCK_EXT_SIZE];
get_tod_clock_ext(clk);
return *((unsigned long long *)&clk[1]);
@@ -186,15 +187,18 @@
/**
* get_clock_monotonic - returns current time in clock rate units
*
- * The caller must ensure that preemption is disabled.
* The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
*/
static inline unsigned long long get_tod_clock_monotonic(void)
{
- return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+ unsigned long long tod;
+
+ preempt_disable_notrace();
+ tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+ preempt_enable_notrace();
+ return tod;
}
/**
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index cca406f..ef9dd25 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -83,8 +83,6 @@
#define pcibus_to_node(bus) __pcibus_to_node(bus)
-#define node_distance(a, b) __node_distance(a, b)
-
#else /* !CONFIG_NUMA */
#define numa_node_id numa_node_id
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index a470f1f..3244388 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -276,6 +276,6 @@
}
int copy_to_user_real(void __user *dest, void *src, unsigned long count);
-void s390_kernel_write(void *dst, const void *src, size_t size);
+void *s390_kernel_write(void *dst, const void *src, size_t size);
#endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 169d760..f3ba84f 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -36,6 +36,7 @@
__u32 tk_shift; /* Shift used for xtime_nsec 0x60 */
__u32 ts_dir; /* TOD steering direction 0x64 */
__u64 ts_end; /* TOD steering end 0x68 */
+ __u32 hrtimer_res; /* hrtimer resolution 0x70 */
};
struct vdso_per_cpu_data {
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 41ac4ad..a65cb49 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -76,6 +76,7 @@
OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
OFFSET(__VDSO_TS_END, vdso_data, ts_end);
+ OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr);
@@ -87,7 +88,6 @@
DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
- DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
BLANK();
/* idle data offsets */
@@ -125,6 +125,8 @@
OFFSET(__LC_EXT_DAMAGE_CODE, lowcore, external_damage_code);
OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address);
OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr);
+ OFFSET(__LC_RETURN_LPSWE, lowcore, return_lpswe);
+ OFFSET(__LC_RETURN_MCCK_LPSWE, lowcore, return_mcck_lpswe);
OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw);
OFFSET(__LC_EXT_OLD_PSW, lowcore, external_old_psw);
OFFSET(__LC_SVC_OLD_PSW, lowcore, svc_old_psw);
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index af013b4..2da0273 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -37,10 +37,12 @@
static int diag8_response(int cmdlen, char *response, int *rlen)
{
+ unsigned long _cmdlen = cmdlen | 0x40000000L;
+ unsigned long _rlen = *rlen;
register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
register unsigned long reg3 asm ("3") = (addr_t) response;
- register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
- register unsigned long reg5 asm ("5") = *rlen;
+ register unsigned long reg4 asm ("4") = _cmdlen;
+ register unsigned long reg5 asm ("5") = _rlen;
asm volatile(
" diag %2,%0,0x8\n"
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 6d321f5..b1aadc3 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -198,9 +198,10 @@
if (!areas)
goto fail_malloc_areas;
for (i = 0; i < nr_areas; i++) {
+ /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */
areas[i] = kmalloc_array(pages_per_area,
sizeof(debug_entry_t *),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (!areas[i])
goto fail_malloc_areas2;
for (j = 0; j < pages_per_area; j++) {
@@ -326,24 +327,6 @@
goto out;
rc->mode = mode & ~S_IFMT;
-
- /* create root directory */
- rc->debugfs_root_entry = debugfs_create_dir(rc->name,
- debug_debugfs_root_entry);
-
- /* append new element to linked list */
- if (!debug_area_first) {
- /* first element in list */
- debug_area_first = rc;
- rc->prev = NULL;
- } else {
- /* append element to end of list */
- debug_area_last->next = rc;
- rc->prev = debug_area_last;
- }
- debug_area_last = rc;
- rc->next = NULL;
-
refcount_set(&rc->ref_count, 1);
out:
return rc;
@@ -403,27 +386,10 @@
*/
static void debug_info_put(debug_info_t *db_info)
{
- int i;
-
if (!db_info)
return;
- if (refcount_dec_and_test(&db_info->ref_count)) {
- for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
- if (!db_info->views[i])
- continue;
- debugfs_remove(db_info->debugfs_entries[i]);
- }
- debugfs_remove(db_info->debugfs_root_entry);
- if (db_info == debug_area_first)
- debug_area_first = db_info->next;
- if (db_info == debug_area_last)
- debug_area_last = db_info->prev;
- if (db_info->prev)
- db_info->prev->next = db_info->next;
- if (db_info->next)
- db_info->next->prev = db_info->prev;
+ if (refcount_dec_and_test(&db_info->ref_count))
debug_info_free(db_info);
- }
}
/*
@@ -647,6 +613,31 @@
return 0; /* success */
}
+/* Create debugfs entries and add to internal list. */
+static void _debug_register(debug_info_t *id)
+{
+ /* create root directory */
+ id->debugfs_root_entry = debugfs_create_dir(id->name,
+ debug_debugfs_root_entry);
+
+ /* append new element to linked list */
+ if (!debug_area_first) {
+ /* first element in list */
+ debug_area_first = id;
+ id->prev = NULL;
+ } else {
+ /* append element to end of list */
+ debug_area_last->next = id;
+ id->prev = debug_area_last;
+ }
+ debug_area_last = id;
+ id->next = NULL;
+
+ debug_register_view(id, &debug_level_view);
+ debug_register_view(id, &debug_flush_view);
+ debug_register_view(id, &debug_pages_view);
+}
+
/**
* debug_register_mode() - creates and initializes debug area.
*
@@ -676,19 +667,16 @@
if ((uid != 0) || (gid != 0))
pr_warn("Root becomes the owner of all s390dbf files in sysfs\n");
BUG_ON(!initialized);
- mutex_lock(&debug_mutex);
/* create new debug_info */
rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode);
- if (!rc)
- goto out;
- debug_register_view(rc, &debug_level_view);
- debug_register_view(rc, &debug_flush_view);
- debug_register_view(rc, &debug_pages_view);
-out:
- if (!rc)
+ if (rc) {
+ mutex_lock(&debug_mutex);
+ _debug_register(rc);
+ mutex_unlock(&debug_mutex);
+ } else {
pr_err("Registering debug feature %s failed\n", name);
- mutex_unlock(&debug_mutex);
+ }
return rc;
}
EXPORT_SYMBOL(debug_register_mode);
@@ -717,6 +705,27 @@
}
EXPORT_SYMBOL(debug_register);
+/* Remove debugfs entries and remove from internal list. */
+static void _debug_unregister(debug_info_t *id)
+{
+ int i;
+
+ for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+ if (!id->views[i])
+ continue;
+ debugfs_remove(id->debugfs_entries[i]);
+ }
+ debugfs_remove(id->debugfs_root_entry);
+ if (id == debug_area_first)
+ debug_area_first = id->next;
+ if (id == debug_area_last)
+ debug_area_last = id->prev;
+ if (id->prev)
+ id->prev->next = id->next;
+ if (id->next)
+ id->next->prev = id->prev;
+}
+
/**
* debug_unregister() - give back debug area.
*
@@ -730,8 +739,10 @@
if (!id)
return;
mutex_lock(&debug_mutex);
- debug_info_put(id);
+ _debug_unregister(id);
mutex_unlock(&debug_mutex);
+
+ debug_info_put(id);
}
EXPORT_SYMBOL(debug_unregister);
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index e9dac9a..ccba63a 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -84,7 +84,7 @@
static void *show_diag_stat_start(struct seq_file *m, loff_t *pos)
{
- return *pos <= nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL;
+ return *pos <= NR_DIAG_STAT ? (void *)((unsigned long) *pos + 1) : NULL;
}
static void *show_diag_stat_next(struct seq_file *m, void *v, loff_t *pos)
@@ -133,7 +133,7 @@
}
EXPORT_SYMBOL(diag_stat_inc);
-void diag_stat_inc_norecursion(enum diag_stat_enum nr)
+void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr)
{
this_cpu_inc(diag_stat.counter[nr]);
trace_s390_diagnose_norecursion(diag_map[nr].code);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 7abe6ae..03e35b3 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -461,10 +461,11 @@
ptr += sprintf(ptr, "%%c%i", value);
else if (operand->flags & OPERAND_VR)
ptr += sprintf(ptr, "%%v%i", value);
- else if (operand->flags & OPERAND_PCREL)
- ptr += sprintf(ptr, "%lx", (signed int) value
- + addr);
- else if (operand->flags & OPERAND_SIGNED)
+ else if (operand->flags & OPERAND_PCREL) {
+ void *pcrel = (void *)((int)value + addr);
+
+ ptr += sprintf(ptr, "%px", pcrel);
+ } else if (operand->flags & OPERAND_SIGNED)
ptr += sprintf(ptr, "%i", value);
else
ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@
else
*ptr++ = ' ';
addr = regs->psw.addr + start - 32;
- ptr += sprintf(ptr, "%016lx: ", addr);
+ ptr += sprintf(ptr, "%px: ", (void *)addr);
if (start + opsize >= end)
break;
for (i = 0; i < opsize; i++)
@@ -556,7 +557,7 @@
void print_fn_code(unsigned char *code, unsigned long len)
{
- char buffer[64], *ptr;
+ char buffer[128], *ptr;
int opsize, i;
while (len) {
@@ -564,7 +565,7 @@
opsize = insn_length(*code);
if (opsize > len)
break;
- ptr += sprintf(ptr, "%p: ", code);
+ ptr += sprintf(ptr, "%px: ", code);
for (i = 0; i < opsize; i++)
ptr += sprintf(ptr, "%02x", code[i]);
*ptr++ = '\t';
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63..eb89cb0 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -169,6 +169,8 @@
psw_t psw;
psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+ if (IS_ENABLED(CONFIG_KASAN))
+ psw.mask |= PSW_MASK_DAT;
psw.addr = (unsigned long) s390_base_ext_handler;
S390_lowcore.external_new_psw = psw;
psw.addr = (unsigned long) s390_base_pgm_handler;
@@ -250,6 +252,10 @@
clock_comparator_max = -1ULL >> 1;
__ctl_set_bit(0, 53);
}
+ if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) {
+ S390_lowcore.machine_flags |= MACHINE_FLAG_PCI_MIO;
+ /* the control bit is set during PCI initialization */
+ }
}
static inline void save_vector_registers(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 270d1d1..5cba181 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -115,26 +115,29 @@
.macro SWITCH_ASYNC savearea,timer
tmhh %r8,0x0001 # interrupting from user ?
- jnz 1f
+ jnz 2f
lgr %r14,%r9
+ cghi %r14,__LC_RETURN_LPSWE
+ je 0f
slg %r14,BASED(.Lcritical_start)
clg %r14,BASED(.Lcritical_length)
- jhe 0f
+ jhe 1f
+0:
lghi %r11,\savearea # inside critical section, do cleanup
brasl %r14,cleanup_critical
tmhh %r8,0x0001 # retest problem state after cleanup
- jnz 1f
-0: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
+ jnz 2f
+1: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
slgr %r14,%r15
srag %r14,%r14,STACK_SHIFT
- jnz 2f
+ jnz 3f
CHECK_STACK \savearea
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- j 3f
-1: UPDATE_VTIME %r14,%r15,\timer
+ j 4f
+2: UPDATE_VTIME %r14,%r15,\timer
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
-2: lg %r15,__LC_ASYNC_STACK # load async stack
-3: la %r11,STACK_FRAME_OVERHEAD(%r15)
+3: lg %r15,__LC_ASYNC_STACK # load async stack
+4: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
.macro UPDATE_VTIME w1,w2,enter_timer
@@ -365,9 +368,9 @@
jnz .Lsysc_nr_ok
# svc 0: system call number in %r1
llgfr %r1,%r1 # clear high word in r1
+ sth %r1,__PT_INT_CODE+2(%r11)
cghi %r1,NR_syscalls
jnl .Lsysc_nr_ok
- sth %r1,__PT_INT_CODE+2(%r11)
slag %r8,%r1,3
.Lsysc_nr_ok:
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
@@ -401,7 +404,7 @@
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_PSW
+ b __LC_RETURN_LPSWE(%r0)
.Lsysc_done:
#
@@ -608,43 +611,50 @@
BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r10,__LC_LAST_BREAK
- lg %r12,__LC_CURRENT
+ srag %r11,%r10,12
+ jnz 0f
+ /* if __LC_LAST_BREAK is < 4096, it contains one of
+ * the lpswe addresses in lowcore. Set it to 1 (initial state)
+ * to prevent leaking that address to userspace.
+ */
+ lghi %r10,1
+0: lg %r12,__LC_CURRENT
lghi %r11,0
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_PGM_OLD_PSW
tmhh %r8,0x0001 # test problem state bit
- jnz 2f # -> fault in user space
+ jnz 3f # -> fault in user space
#if IS_ENABLED(CONFIG_KVM)
# cleanup critical section for program checks in sie64a
lgr %r14,%r9
slg %r14,BASED(.Lsie_critical_start)
clg %r14,BASED(.Lsie_critical_length)
- jhe 0f
+ jhe 1f
lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
lghi %r11,_PIF_GUEST_FAULT
#endif
-0: tmhh %r8,0x4000 # PER bit set in old PSW ?
- jnz 1f # -> enabled, can't be a double fault
+1: tmhh %r8,0x4000 # PER bit set in old PSW ?
+ jnz 2f # -> enabled, can't be a double fault
tm __LC_PGM_ILC+3,0x80 # check for per exception
jnz .Lpgm_svcper # -> single stepped svc
-1: CHECK_STACK __LC_SAVE_AREA_SYNC
+2: CHECK_STACK __LC_SAVE_AREA_SYNC
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- # CHECK_VMAP_STACK branches to stack_overflow or 4f
- CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f
-2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+ # CHECK_VMAP_STACK branches to stack_overflow or 5f
+ CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,5f
+3: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
aghi %r14,__TASK_thread # pointer to thread_struct
lghi %r13,__LC_PGM_TDB
tm __LC_PGM_ILC+2,0x02 # check for transaction abort
- jz 3f
+ jz 4f
mvc __THREAD_trap_tdb(256,%r14),0(%r13)
-3: stg %r10,__THREAD_last_break(%r14)
-4: lgr %r13,%r11
+4: stg %r10,__THREAD_last_break(%r14)
+5: lgr %r13,%r11
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
@@ -663,14 +673,14 @@
stg %r13,__PT_FLAGS(%r11)
stg %r10,__PT_ARGS(%r11)
tm __LC_PGM_ILC+3,0x80 # check for per exception
- jz 5f
+ jz 6f
tmhh %r8,0x0001 # kernel per event ?
jz .Lpgm_kprobe
oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP
mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS
mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE
mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-5: REENABLE_IRQS
+6: REENABLE_IRQS
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
larl %r1,pgm_check_table
llgh %r10,__PT_INT_CODE+2(%r11)
@@ -775,7 +785,7 @@
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
.Lio_exit_kernel:
lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_PSW
+ b __LC_RETURN_LPSWE(%r0)
.Lio_done:
#
@@ -983,6 +993,7 @@
* Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
*/
ENTRY(psw_idle)
+ stg %r14,(__SF_GPRS+8*8)(%r15)
stg %r3,__SF_EMPTY(%r15)
larl %r1,.Lpsw_idle_lpsw+4
stg %r1,__SF_EMPTY+8(%r15)
@@ -1214,7 +1225,7 @@
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
0: lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_MCCK_PSW
+ b __LC_RETURN_MCCK_LPSWE
.Lmcck_panic:
lg %r15,__LC_NODAT_STACK
@@ -1271,6 +1282,8 @@
#endif
ENTRY(cleanup_critical)
+ cghi %r9,__LC_RETURN_LPSWE
+ je .Lcleanup_lpswe
#if IS_ENABLED(CONFIG_KVM)
clg %r9,BASED(.Lcleanup_table_sie) # .Lsie_gmap
jl 0f
@@ -1424,6 +1437,7 @@
mvc __LC_RETURN_PSW(16),__PT_PSW(%r9)
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
+.Lcleanup_lpswe:
1: lmg %r8,%r9,__LC_RETURN_PSW
BR_EX %r14,%r11
.Lcleanup_sysc_restore_insn:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1bb85f6..7df6b26 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -57,6 +57,7 @@
* > brasl %r0,ftrace_caller # offset 0
*/
+void *ftrace_func __read_mostly = ftrace_stub;
unsigned long ftrace_plt;
static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
@@ -166,6 +167,7 @@
int ftrace_update_ftrace_func(ftrace_func_t func)
{
+ ftrace_func = func;
return 0;
}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 8371855..da550cb 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -294,11 +294,6 @@
return IRQ_HANDLED;
}
-static struct irqaction external_interrupt = {
- .name = "EXT",
- .handler = do_ext_interrupt,
-};
-
void __init init_ext_interrupts(void)
{
int idx;
@@ -308,7 +303,8 @@
irq_set_chip_and_handler(EXT_INTERRUPT,
&dummy_irq_chip, handle_percpu_irq);
- setup_irq(EXT_INTERRUPT, &external_interrupt);
+ if (request_irq(EXT_INTERRUPT, do_ext_interrupt, 0, "EXT", NULL))
+ panic("Failed to register EXT interrupt\n");
}
static DEFINE_SPINLOCK(irq_subclass_lock);
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index ab584e8..9156653 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -36,7 +36,7 @@
unsigned char *ipe = (unsigned char *)expected;
unsigned char *ipn = (unsigned char *)new;
- pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
+ pr_emerg("Jump label code mismatch at %pS [%px]\n", ipc, ipc);
pr_emerg("Found: %6ph\n", ipc);
pr_emerg("Expected: %6ph\n", ipe);
pr_emerg("New: %6ph\n", ipn);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 444a191..cb8b1cc 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -164,7 +164,9 @@
#ifdef CONFIG_CRASH_DUMP
int rc;
+ preempt_disable();
rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image);
+ preempt_enable();
return rc == 0;
#else
return false;
@@ -254,10 +256,10 @@
VMCOREINFO_SYMBOL(lowcore_ptr);
VMCOREINFO_SYMBOL(high_memory);
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
- mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
vmcoreinfo_append_str("EDMA=%lx\n", __edma);
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+ mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
}
void machine_shutdown(void)
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 8415ae7..f9e4baa 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -151,7 +151,7 @@
buf.mem += crashk_res.start;
buf.memsz = buf.bufsz;
- data->parm->initrd_start = buf.mem;
+ data->parm->initrd_start = data->memsz;
data->parm->initrd_size = buf.memsz;
data->memsz += buf.memsz;
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index d5035de..b7182ce 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -28,6 +28,7 @@
break;
case R_390_64: /* Direct 64 bit. */
case R_390_GLOB_DAT:
+ case R_390_JMP_SLOT:
*(u64 *)loc = val;
break;
case R_390_PC16: /* PC relative 16 bit. */
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 9e1660a..14bad57 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -26,6 +26,12 @@
#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
+#ifdef __PACK_STACK
+/* allocate just enough for r14, r15 and backchain */
+#define TRACED_FUNC_FRAME_SIZE 24
+#else
+#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD
+#endif
ENTRY(_mcount)
BR_EX %r14
@@ -35,25 +41,33 @@
ENTRY(ftrace_caller)
.globl ftrace_regs_caller
.set ftrace_regs_caller,ftrace_caller
+ stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller
lgr %r1,%r15
#if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT))
aghi %r0,MCOUNT_RETURN_FIXUP
#endif
- aghi %r15,-STACK_FRAME_SIZE
+ # allocate stack frame for ftrace_caller to contain traced function
+ aghi %r15,-TRACED_FUNC_FRAME_SIZE
stg %r1,__SF_BACKCHAIN(%r15)
+ stg %r0,(__SF_GPRS+8*8)(%r15)
+ stg %r15,(__SF_GPRS+9*8)(%r15)
+ # allocate pt_regs and stack frame for ftrace_trace_function
+ aghi %r15,-STACK_FRAME_SIZE
stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+ aghi %r1,-TRACED_FUNC_FRAME_SIZE
+ stg %r1,__SF_BACKCHAIN(%r15)
stg %r0,(STACK_PTREGS_PSW+8)(%r15)
stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
aghik %r2,%r0,-MCOUNT_INSN_SIZE
lgrl %r4,function_trace_op
- lgrl %r1,ftrace_trace_function
+ lgrl %r1,ftrace_func
#else
lgr %r2,%r0
aghi %r2,-MCOUNT_INSN_SIZE
larl %r4,function_trace_op
lg %r4,0(%r4)
- larl %r1,ftrace_trace_function
+ larl %r1,ftrace_func
lg %r1,0(%r1)
#endif
lgr %r3,%r14
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 48d48b6..0eb1d1c 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -199,7 +199,7 @@
[PERF_COUNT_HW_BUS_CYCLES] = -1,
};
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
{
struct perf_event_attr *attr = &event->attr;
struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@
int err = 0;
u64 ev;
- switch (attr->type) {
+ switch (type) {
case PERF_TYPE_RAW:
/* Raw events are used to access counters directly,
* hence do not permit excludes */
@@ -294,17 +294,16 @@
static int cpumf_pmu_event_init(struct perf_event *event)
{
+ unsigned int type = event->attr.type;
int err;
- switch (event->attr.type) {
- case PERF_TYPE_HARDWARE:
- case PERF_TYPE_HW_CACHE:
- case PERF_TYPE_RAW:
- err = __hw_perf_event_init(event);
- break;
- default:
+ if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+ err = __hw_perf_event_init(event, type);
+ else if (event->pmu->type == type)
+ /* Registered as unknown PMU */
+ err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+ else
return -ENOENT;
- }
if (unlikely(err) && event->destroy)
event->destroy(event);
@@ -553,7 +552,7 @@
return -ENODEV;
cpumf_pmu.attr_groups = cpumf_cf_event_group();
- rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+ rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
if (rc)
pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
return rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2654e34..e949ab8 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -243,13 +243,13 @@
int err = -ENOENT;
debug_sprintf_event(cf_diag_dbg, 5,
- "%s event %p cpu %d config %#llx "
+ "%s event %p cpu %d config %#llx type:%u "
"sample_type %#llx cf_diag_events %d\n", __func__,
- event, event->cpu, attr->config, attr->sample_type,
- atomic_read(&cf_diag_events));
+ event, event->cpu, attr->config, event->pmu->type,
+ attr->sample_type, atomic_read(&cf_diag_events));
if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
- event->attr.type != PERF_TYPE_RAW)
+ event->attr.type != event->pmu->type)
goto out;
/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@
}
debug_register_view(cf_diag_dbg, &debug_sprintf_view);
- rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+ rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
if (rc) {
debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
debug_unregister(cf_diag_dbg);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8b12a..b83bddf 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -193,7 +193,7 @@
unsigned long num_sdb, gfp_t gfp_flags)
{
int i, rc;
- unsigned long *new, *tail;
+ unsigned long *new, *tail, *tail_prev = NULL;
if (!sfb->sdbt || !sfb->tail)
return -EINVAL;
@@ -232,6 +232,7 @@
sfb->num_sdbt++;
/* Link current page to tail of chain */
*tail = (unsigned long)(void *) new + 1;
+ tail_prev = tail;
tail = new;
}
@@ -241,10 +242,22 @@
* issue, a new realloc call (if required) might succeed.
*/
rc = alloc_sample_data_block(tail, gfp_flags);
- if (rc)
+ if (rc) {
+ /* Undo last SDBT. An SDBT with no SDB at its first
+ * entry but with an SDBT entry instead can not be
+ * handled by the interrupt handler code.
+ * Avoid this situation.
+ */
+ if (tail_prev) {
+ sfb->num_sdbt--;
+ free_page((unsigned long) new);
+ tail = tail_prev;
+ }
break;
+ }
sfb->num_sdb++;
tail++;
+ tail_prev = new = NULL; /* Allocated at least one SBD */
}
/* Link sampling buffer to its origin */
@@ -1300,18 +1313,28 @@
*/
if (flush_all && done)
break;
-
- /* If an event overflow happened, discard samples by
- * processing any remaining sample-data-blocks.
- */
- if (event_overflow)
- flush_all = 1;
}
/* Account sample overflows in the event hardware structure */
if (sampl_overflow)
OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
sampl_overflow, 1 + num_sdb);
+
+ /* Perf_event_overflow() and perf_event_account_interrupt() limit
+ * the interrupt rate to an upper limit. Roughly 1000 samples per
+ * task tick.
+ * Hitting this limit results in a large number
+ * of throttled REF_REPORT_THROTTLE entries and the samples
+ * are dropped.
+ * Slightly increase the interval to avoid hitting this limit.
+ */
+ if (event_overflow) {
+ SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+ debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n",
+ __func__,
+ DIV_ROUND_UP(SAMPL_RATE(hwc), 10));
+ }
+
if (sampl_overflow || event_overflow)
debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
"overflow stats: sample=%llu event=%llu\n",
@@ -1406,8 +1429,8 @@
idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
- te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK;
+ te->flags &= ~(SDB_TE_BUFFER_FULL_MASK |
+ SDB_TE_ALERT_REQ_MASK);
te->overflow = 0;
}
/* Save the position of empty SDBs */
@@ -1454,8 +1477,7 @@
te = aux_sdb_trailer(aux, alert_index);
do {
orig_flags = te->flags;
- orig_overflow = te->overflow;
- *overflow = orig_overflow;
+ *overflow = orig_overflow = te->overflow;
if (orig_flags & SDB_TE_BUFFER_FULL_MASK) {
/*
* SDB is already set by hardware.
@@ -1566,6 +1588,7 @@
perf_aux_output_end(handle, size);
num_sdb = aux->sfb.num_sdb;
+ num_sdb = aux->sfb.num_sdb;
while (!done) {
/* Get an output handle */
aux = perf_aux_output_begin(handle, cpuhw->event);
@@ -1688,7 +1711,7 @@
}
/* Allocate aux_buffer struct for the event */
- aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL);
+ aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL);
if (!aux)
goto no_aux;
sfb = &aux->sfb;
@@ -2194,4 +2217,4 @@
}
arch_initcall(init_cpum_sampling_pmu);
-core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index fcb6c2e..1e75cc9 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,9 +224,13 @@
struct pt_regs *regs)
{
struct unwind_state state;
+ unsigned long addr;
- unwind_for_each_frame(&state, current, regs, 0)
- perf_callchain_store(entry, state.ip);
+ unwind_for_each_frame(&state, current, regs, 0) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || perf_callchain_store(entry, addr))
+ return;
+ }
}
/* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b0afec6..4e6299e 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -105,6 +105,7 @@
p->thread.system_timer = 0;
p->thread.hardirq_timer = 0;
p->thread.softirq_timer = 0;
+ p->thread.last_break = 1;
frame->sf.back_chain = 0;
/* new return point is ret_from_fork */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 6ebc211..91b9b3f 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -165,8 +165,9 @@
static int show_cpuinfo(struct seq_file *m, void *v)
{
unsigned long n = (unsigned long) v - 1;
+ unsigned long first = cpumask_first(cpu_online_mask);
- if (!n)
+ if (n == first)
show_cpu_summary(m, v);
if (!machine_has_cpu_mhz)
return 0;
@@ -179,6 +180,8 @@
{
if (*pos)
*pos = cpumask_next(*pos - 1, cpu_online_mask);
+ else
+ *pos = cpumask_first(cpu_online_mask);
return *pos < nr_cpu_ids ? (void *)*pos + 1 : NULL;
}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ad71132..ad74472 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -324,6 +324,25 @@
child->thread.per_user.end = data;
}
+static void fixup_int_code(struct task_struct *child, addr_t data)
+{
+ struct pt_regs *regs = task_pt_regs(child);
+ int ilc = regs->int_code >> 16;
+ u16 insn;
+
+ if (ilc > 6)
+ return;
+
+ if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
+ &insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
+ return;
+
+ /* double check that tracee stopped on svc instruction */
+ if ((insn >> 8) != 0xa)
+ return;
+
+ regs->int_code = 0x20000 | (data & 0xffff);
+}
/*
* Write a word to the user area of a process at location addr. This
* operation does have an additional problem compared to peek_user.
@@ -335,7 +354,9 @@
struct user *dummy = NULL;
addr_t offset;
+
if (addr < (addr_t) &dummy->regs.acrs) {
+ struct pt_regs *regs = task_pt_regs(child);
/*
* psw and gprs are stored on the stack
*/
@@ -353,7 +374,11 @@
/* Invalid addressing mode bits */
return -EINVAL;
}
- *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+ if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+ addr == offsetof(struct user, regs.gprs[2]))
+ fixup_int_code(child, data);
+ *(addr_t *)((addr_t) ®s->psw + addr) = data;
} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
/*
@@ -719,6 +744,10 @@
regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
(__u64)(tmp & PSW32_ADDR_AMODE);
} else {
+
+ if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+ addr == offsetof(struct compat_user, regs.gprs[2]))
+ fixup_int_code(child, data);
/* gpr 0-15 */
*(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp;
}
@@ -838,40 +867,45 @@
asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
{
unsigned long mask = -1UL;
+ long ret = -1;
/*
* The sysc_tracesys code in entry.S stored the system
* call number to gprs[2].
*/
if (test_thread_flag(TIF_SYSCALL_TRACE) &&
- (tracehook_report_syscall_entry(regs) ||
- regs->gprs[2] >= NR_syscalls)) {
+ tracehook_report_syscall_entry(regs)) {
/*
- * Tracing decided this syscall should not happen or the
- * debugger stored an invalid system call number. Skip
+ * Tracing decided this syscall should not happen. Skip
* the system call and the system call restart handling.
*/
- clear_pt_regs_flag(regs, PIF_SYSCALL);
- return -1;
+ goto skip;
}
/* Do the secure computing check after ptrace. */
if (secure_computing(NULL)) {
/* seccomp failures shouldn't expose any additional code. */
- return -1;
+ goto skip;
}
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_enter(regs, regs->gprs[2]);
+ trace_sys_enter(regs, regs->int_code & 0xffff);
if (is_compat_task())
mask = 0xffffffff;
- audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask,
+ audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask,
regs->gprs[3] &mask, regs->gprs[4] &mask,
regs->gprs[5] &mask);
+ if ((signed long)regs->gprs[2] >= NR_syscalls) {
+ regs->gprs[2] = -ENOSYS;
+ ret = -ENOSYS;
+ }
return regs->gprs[2];
+skip:
+ clear_pt_regs_flag(regs, PIF_SYSCALL);
+ return ret;
}
asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
@@ -1256,7 +1290,6 @@
cb->pc == 1 &&
cb->qc == 0 &&
cb->reserved2 == 0 &&
- cb->key == PAGE_DEFAULT_KEY &&
cb->reserved3 == 0 &&
cb->reserved4 == 0 &&
cb->reserved5 == 0 &&
@@ -1320,7 +1353,11 @@
kfree(data);
return -EINVAL;
}
-
+ /*
+ * Override access key in any case, since user space should
+ * not be able to set it, nor should it care about it.
+ */
+ ri_cb.key = PAGE_DEFAULT_KEY >> 4;
preempt_disable();
if (!target->thread.ri_cb)
target->thread.ri_cb = data;
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 125c7f6..1788a54 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -57,7 +57,7 @@
cb->k = 1;
cb->ps = 1;
cb->pc = 1;
- cb->key = PAGE_DEFAULT_KEY;
+ cb->key = PAGE_DEFAULT_KEY >> 4;
cb->v = 1;
}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3ff291b..f661f17 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -73,6 +73,7 @@
#include <asm/nospec-branch.h>
#include <asm/mem_detect.h>
#include <asm/uv.h>
+#include <asm/asm-offsets.h>
#include "entry.h"
/*
@@ -161,7 +162,7 @@
else if (CONSOLE_IS_3270)
add_preferred_console("tty3270", 0, NULL);
else if (CONSOLE_IS_VT220)
- add_preferred_console("ttyS", 1, NULL);
+ add_preferred_console("ttysclp", 0, NULL);
else if (CONSOLE_IS_HVC)
add_preferred_console("hvc", 0, NULL);
}
@@ -355,7 +356,6 @@
void __init arch_call_rest_init(void)
{
- struct stack_frame *frame;
unsigned long stack;
stack = stack_alloc();
@@ -368,13 +368,7 @@
set_task_stack_end_magic(current);
stack += STACK_INIT_OFFSET;
S390_lowcore.kernel_stack = stack;
- frame = (struct stack_frame *) stack;
- memset(frame, 0, sizeof(*frame));
- /* Branch to rest_init on the new stack, never returns */
- asm volatile(
- " la 15,0(%[_frame])\n"
- " jg rest_init\n"
- : : [_frame] "a" (frame));
+ CALL_ON_STACK_NORETURN(rest_init, stack);
}
static void __init setup_lowcore_dat_off(void)
@@ -457,6 +451,8 @@
lc->spinlock_index = 0;
arch_spin_lock_setup(0);
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
+ lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+ lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
set_prefix((u32)(unsigned long) lc);
lowcore_ptr[0] = lc;
@@ -631,7 +627,7 @@
/*
* Make sure that the area behind memory_end is protected
*/
-static void reserve_memory_end(void)
+static void __init reserve_memory_end(void)
{
if (memory_end_set)
memblock_reserve(memory_end, ULONG_MAX);
@@ -640,7 +636,7 @@
/*
* Make sure that oldmem, where the dump is stored, is protected
*/
-static void reserve_oldmem(void)
+static void __init reserve_oldmem(void)
{
#ifdef CONFIG_CRASH_DUMP
if (OLDMEM_BASE)
@@ -652,7 +648,7 @@
/*
* Make sure that oldmem, where the dump is stored, is protected
*/
-static void remove_oldmem(void)
+static void __init remove_oldmem(void)
{
#ifdef CONFIG_CRASH_DUMP
if (OLDMEM_BASE)
@@ -926,9 +922,9 @@
if (MACHINE_HAS_VX) {
elf_hwcap |= HWCAP_S390_VXRS;
if (test_facility(134))
- elf_hwcap |= HWCAP_S390_VXRS_EXT;
- if (test_facility(135))
elf_hwcap |= HWCAP_S390_VXRS_BCD;
+ if (test_facility(135))
+ elf_hwcap |= HWCAP_S390_VXRS_EXT;
if (test_facility(148))
elf_hwcap |= HWCAP_S390_VXRS_EXT2;
if (test_facility(152))
@@ -1059,7 +1055,7 @@
if (!early_ipl_comp_list_addr)
return;
- if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+ if (ipl_block.hdr.flags & IPL_PL_FLAG_SIPL)
pr_info("Linux is running with Secure-IPL enabled\n");
else
pr_info("Linux is running with Secure-IPL disabled\n");
@@ -1117,6 +1113,7 @@
if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
nospec_auto_detect();
+ jump_label_init();
parse_early_param();
#ifdef CONFIG_CRASH_DUMP
/* Deactivate elfcorehdr= kernel parameter */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 4497465..8c51462 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -212,6 +212,8 @@
lc->spinlock_lockval = arch_spin_lockval(cpu);
lc->spinlock_index = 0;
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
+ lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+ lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
if (nmi_alloc_per_cpu(lc))
goto out_async;
if (vdso_alloc_per_cpu(lc))
@@ -262,10 +264,13 @@
lc->spinlock_index = 0;
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
+ lc->user_asce = S390_lowcore.kernel_asce;
lc->machine_flags = S390_lowcore.machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
+ lc->cregs_save_area[1] = lc->kernel_asce;
+ lc->cregs_save_area[7] = lc->vdso_asce;
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
sizeof(lc->stfle_fac_list));
@@ -398,7 +403,7 @@
return -1;
}
-bool arch_vcpu_is_preempted(int cpu)
+bool notrace arch_vcpu_is_preempted(int cpu)
{
if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
return false;
@@ -408,7 +413,7 @@
}
EXPORT_SYMBOL(arch_vcpu_is_preempted);
-void smp_yield_cpu(int cpu)
+void notrace smp_yield_cpu(int cpu)
{
if (MACHINE_HAS_DIAG9C) {
diag_stat_inc_norecursion(DIAG_STAT_X09C);
@@ -724,39 +729,67 @@
static int smp_add_present_cpu(int cpu);
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+ bool configured, bool early)
{
struct pcpu *pcpu;
- cpumask_t avail;
- int cpu, nr, i, j;
+ int cpu, nr, i;
u16 address;
nr = 0;
- cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
- cpu = cpumask_first(&avail);
- for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
- if (sclp.has_core_type && info->core[i].type != boot_core_type)
+ if (sclp.has_core_type && core->type != boot_core_type)
+ return nr;
+ cpu = cpumask_first(avail);
+ address = core->core_id << smp_cpu_mt_shift;
+ for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+ if (pcpu_find_address(cpu_present_mask, address + i))
continue;
- address = info->core[i].core_id << smp_cpu_mt_shift;
- for (j = 0; j <= smp_cpu_mtid; j++) {
- if (pcpu_find_address(cpu_present_mask, address + j))
- continue;
- pcpu = pcpu_devices + cpu;
- pcpu->address = address + j;
- pcpu->state =
- (cpu >= info->configured*(smp_cpu_mtid + 1)) ?
- CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
- smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
- set_cpu_present(cpu, true);
- if (sysfs_add && smp_add_present_cpu(cpu) != 0)
- set_cpu_present(cpu, false);
- else
- nr++;
- cpu = cpumask_next(cpu, &avail);
- if (cpu >= nr_cpu_ids)
+ pcpu = pcpu_devices + cpu;
+ pcpu->address = address + i;
+ if (configured)
+ pcpu->state = CPU_STATE_CONFIGURED;
+ else
+ pcpu->state = CPU_STATE_STANDBY;
+ smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+ set_cpu_present(cpu, true);
+ if (!early && smp_add_present_cpu(cpu) != 0)
+ set_cpu_present(cpu, false);
+ else
+ nr++;
+ cpumask_clear_cpu(cpu, avail);
+ cpu = cpumask_next(cpu, avail);
+ }
+ return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+ struct sclp_core_entry *core;
+ static cpumask_t avail;
+ bool configured;
+ u16 core_id;
+ int nr, i;
+
+ nr = 0;
+ cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+ /*
+ * Add IPL core first (which got logical CPU number 0) to make sure
+ * that all SMT threads get subsequent logical CPU numbers.
+ */
+ if (early) {
+ core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+ for (i = 0; i < info->configured; i++) {
+ core = &info->core[i];
+ if (core->core_id == core_id) {
+ nr += smp_add_core(core, &avail, true, early);
break;
+ }
}
}
+ for (i = 0; i < info->combined; i++) {
+ configured = i < info->configured;
+ nr += smp_add_core(&info->core[i], &avail, configured, early);
+ }
return nr;
}
@@ -805,18 +838,21 @@
/* Add CPUs present at boot */
get_online_cpus();
- __smp_rescan_cpus(info, 0);
+ __smp_rescan_cpus(info, true);
put_online_cpus();
memblock_free_early((unsigned long)info, sizeof(*info));
}
static void smp_init_secondary(void)
{
- int cpu = smp_processor_id();
+ int cpu = raw_smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
restore_access_regs(S390_lowcore.access_regs_save_area);
+ set_cpu_flag(CIF_ASCE_PRIMARY);
+ set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
+ rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
@@ -843,30 +879,18 @@
S390_lowcore.restart_source = -1UL;
__ctl_load(S390_lowcore.cregs_save_area, 0, 15);
__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
- CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0);
+ CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack);
}
/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
- struct pcpu *pcpu;
- int base, i, rc;
+ struct pcpu *pcpu = pcpu_devices + cpu;
+ int rc;
- pcpu = pcpu_devices + cpu;
if (pcpu->state != CPU_STATE_CONFIGURED)
return -EIO;
- base = smp_get_base_cpu(cpu);
- for (i = 0; i <= smp_cpu_mtid; i++) {
- if (base + i < nr_cpu_ids)
- if (cpu_online(base + i))
- break;
- }
- /*
- * If this is the first CPU of the core to get online
- * do an initial CPU reset.
- */
- if (i > smp_cpu_mtid &&
- pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) !=
+ if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) !=
SIGP_CC_ORDER_CODE_ACCEPTED)
return -EIO;
@@ -1148,7 +1172,7 @@
smp_get_core_info(info, 0);
get_online_cpus();
mutex_lock(&smp_cpu_state_mutex);
- nr = __smp_rescan_cpus(info, 1);
+ nr = __smp_rescan_cpus(info, false);
mutex_unlock(&smp_cpu_state_mutex);
put_online_cpus();
kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766be..11c32b2 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -310,6 +310,7 @@
vdso_data->tk_mult = tk->tkr_mono.mult;
vdso_data->tk_shift = tk->tkr_mono.shift;
+ vdso_data->hrtimer_res = hrtimer_resolution;
smp_wmb();
++vdso_data->tb_update_count;
}
@@ -353,8 +354,9 @@
static DEFINE_MUTEX(clock_sync_mutex);
static unsigned long clock_sync_flags;
-#define CLOCK_SYNC_HAS_STP 0
-#define CLOCK_SYNC_STP 1
+#define CLOCK_SYNC_HAS_STP 0
+#define CLOCK_SYNC_STP 1
+#define CLOCK_SYNC_STPINFO_VALID 2
/*
* The get_clock function for the physical clock. It will get the current
@@ -591,6 +593,22 @@
queue_work(time_sync_wq, &stp_work);
}
+static int __store_stpinfo(void)
+{
+ int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+
+ if (rc)
+ clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+ else
+ set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+ return rc;
+}
+
+static int stpinfo_valid(void)
+{
+ return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+}
+
static int stp_sync_clock(void *data)
{
struct clock_sync_data *sync = data;
@@ -612,8 +630,7 @@
if (rc == 0) {
sync->clock_delta = clock_delta;
clock_sync_global(clock_delta);
- rc = chsc_sstpi(stp_page, &stp_info,
- sizeof(struct stp_sstpi));
+ rc = __store_stpinfo();
if (rc == 0 && stp_info.tmd != 2)
rc = -EAGAIN;
}
@@ -658,7 +675,7 @@
if (rc)
goto out_unlock;
- rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+ rc = __store_stpinfo();
if (rc || stp_info.c == 0)
goto out_unlock;
@@ -695,10 +712,14 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%016llx\n",
- *(unsigned long long *) stp_info.ctnid);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%016llx\n",
+ *(unsigned long long *) stp_info.ctnid);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
@@ -707,9 +728,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.ctn);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.ctn);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
@@ -718,9 +743,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x2000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x2000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
@@ -729,9 +758,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x8000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x8000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
@@ -740,9 +773,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL);
@@ -751,9 +788,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x0800))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int) stp_info.tto);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x0800))
+ ret = sprintf(buf, "%i\n", (int) stp_info.tto);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
@@ -762,9 +803,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x4000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x4000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(time_zone_offset, 0400,
@@ -774,9 +819,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.tmd);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.tmd);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
@@ -785,9 +834,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.tst);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.tst);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 490b52e..11a669f 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -14,7 +14,7 @@
static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth);
-void trace_s390_diagnose_norecursion(int diag_nr)
+void notrace trace_s390_diagnose_norecursion(int diag_nr)
{
unsigned long flags;
unsigned int *depth;
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index a8204f9..6e609b1 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -60,6 +60,11 @@
ip = READ_ONCE_NOCHECK(sf->gprs[8]);
reliable = false;
regs = NULL;
+ if (!__kernel_text_address(ip)) {
+ /* skip bogus %r14 */
+ state->regs = NULL;
+ return unwind_next_frame(state);
+ }
} else {
sf = (struct stack_frame *) state->sp;
sp = READ_ONCE_NOCHECK(sf->back_chain);
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index bec19e7..4a66a1c 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -18,8 +18,8 @@
KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
- -Wl,--hash-style=both
+ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+ --hash-style=both --build-id -T
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -37,8 +37,8 @@
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
- $(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE
+ $(call if_changed,ld)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -50,8 +50,6 @@
$(call if_changed_dep,vdso64as)
# actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
quiet_cmd_vdso64as = VDSO64A $@
cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 0814353..0c79caa 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -17,12 +17,14 @@
.type __kernel_clock_getres,@function
__kernel_clock_getres:
CFI_STARTPROC
- larl %r1,4f
+ larl %r1,3f
+ lg %r0,0(%r1)
cghi %r2,__CLOCK_REALTIME_COARSE
je 0f
cghi %r2,__CLOCK_MONOTONIC_COARSE
je 0f
- larl %r1,3f
+ larl %r1,_vdso_data
+ llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1)
cghi %r2,__CLOCK_REALTIME
je 0f
cghi %r2,__CLOCK_MONOTONIC
@@ -36,7 +38,6 @@
jz 2f
0: ltgr %r3,%r3
jz 1f /* res == NULL */
- lg %r0,0(%r1)
xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */
stg %r0,8(%r3) /* store tp->tv_usec */
1: lghi %r2,0
@@ -45,6 +46,5 @@
svc 0
br %r14
CFI_ENDPROC
-3: .quad __CLOCK_REALTIME_RES
-4: .quad __CLOCK_COARSE_RES
+3: .quad __CLOCK_COARSE_RES
.size __kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c475ca4..6e60cc2 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -136,7 +136,8 @@
" stck %1" /* Store current tod clock value */
#endif
: "=Q" (S390_lowcore.last_update_timer),
- "=Q" (S390_lowcore.last_update_clock));
+ "=Q" (S390_lowcore.last_update_clock)
+ : : "cc");
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
@@ -216,7 +217,7 @@
avg_steal = S390_lowcore.avg_steal_timer / 2;
if ((s64) steal > 0) {
S390_lowcore.steal_timer = 0;
- account_steal_time(steal);
+ account_steal_time(cputime_to_nsecs(steal));
avg_steal += steal;
}
S390_lowcore.avg_steal_timer = avg_steal;
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index f4c5175..4c56de5 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -18,6 +18,23 @@
/**
* kvm_s390_real_to_abs - convert guest real address to guest absolute address
+ * @prefix - guest prefix
+ * @gra - guest real address
+ *
+ * Returns the guest absolute address that corresponds to the passed guest real
+ * address @gra of by applying the given prefix.
+ */
+static inline unsigned long _kvm_s390_real_to_abs(u32 prefix, unsigned long gra)
+{
+ if (gra < 2 * PAGE_SIZE)
+ gra += prefix;
+ else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE)
+ gra -= prefix;
+ return gra;
+}
+
+/**
+ * kvm_s390_real_to_abs - convert guest real address to guest absolute address
* @vcpu - guest virtual cpu
* @gra - guest real address
*
@@ -27,13 +44,30 @@
static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
unsigned long gra)
{
- unsigned long prefix = kvm_s390_get_prefix(vcpu);
+ return _kvm_s390_real_to_abs(kvm_s390_get_prefix(vcpu), gra);
+}
- if (gra < 2 * PAGE_SIZE)
- gra += prefix;
- else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE)
- gra -= prefix;
- return gra;
+/**
+ * _kvm_s390_logical_to_effective - convert guest logical to effective address
+ * @psw: psw of the guest
+ * @ga: guest logical address
+ *
+ * Convert a guest logical address to an effective address by applying the
+ * rules of the addressing mode defined by bits 31 and 32 of the given PSW
+ * (extendended/basic addressing mode).
+ *
+ * Depending on the addressing mode, the upper 40 bits (24 bit addressing
+ * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing
+ * mode) of @ga will be zeroed and the remaining bits will be returned.
+ */
+static inline unsigned long _kvm_s390_logical_to_effective(psw_t *psw,
+ unsigned long ga)
+{
+ if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT)
+ return ga;
+ if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT)
+ return ga & ((1UL << 31) - 1);
+ return ga & ((1UL << 24) - 1);
}
/**
@@ -52,13 +86,7 @@
static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu,
unsigned long ga)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
-
- if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT)
- return ga;
- if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT)
- return ga & ((1UL << 31) - 1);
- return ga & ((1UL << 24) - 1);
+ return _kvm_s390_logical_to_effective(&vcpu->arch.sie_block->gpsw, ga);
}
/*
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index d1ccc16..fa9483a 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -408,13 +408,13 @@
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
- set_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
+ set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
- clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
+ clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
@@ -2191,7 +2191,7 @@
return -EINVAL;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
mutex_lock(&fi->ais_lock);
ais.simm = fi->simm;
@@ -2500,7 +2500,7 @@
int ret = 0;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
return -EFAULT;
@@ -2580,7 +2580,7 @@
struct kvm_s390_ais_all ais;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais)))
return -EFAULT;
@@ -2984,18 +2984,18 @@
static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
{
- int vcpu_id, online_vcpus = atomic_read(&kvm->online_vcpus);
+ int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_vcpu *vcpu;
- for_each_set_bit(vcpu_id, kvm->arch.idle_mask, online_vcpus) {
- vcpu = kvm_get_vcpu(kvm, vcpu_id);
+ for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
+ vcpu = kvm_get_vcpu(kvm, vcpu_idx);
if (psw_ioint_disabled(vcpu))
continue;
deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
if (deliverable_mask) {
/* lately kicked but not yet running */
- if (test_and_set_bit(vcpu_id, gi->kicked_mask))
+ if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
return;
kvm_s390_vcpu_wakeup(vcpu);
return;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d047e84..9ed2fee 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -318,31 +318,31 @@
static inline int plo_test_bit(unsigned char nr)
{
- register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
+ unsigned long function = (unsigned long)nr | 0x100;
int cc;
asm volatile(
+ " lgr 0,%[function]\n"
/* Parameter registers are ignored for "test bit" */
" plo 0,0,0,0(0)\n"
" ipm %0\n"
" srl %0,28\n"
: "=d" (cc)
- : "d" (r0)
- : "cc");
+ : [function] "d" (function)
+ : "cc", "0");
return cc == 0;
}
static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
{
- register unsigned long r0 asm("0") = 0; /* query function */
- register unsigned long r1 asm("1") = (unsigned long) query;
-
asm volatile(
- /* Parameter regs are ignored */
+ " lghi 0,0\n"
+ " lgr 1,%[query]\n"
+ /* Parameter registers are ignored */
" .insn rrf,%[opc] << 16,2,4,6,0\n"
:
- : "d" (r0), "a" (r1), [opc] "i" (opcode)
- : "cc", "memory");
+ : [query] "d" ((unsigned long)query), [opc] "i" (opcode)
+ : "cc", "memory", "0", "1");
}
#define INSN_SORTL 0xb938
@@ -1932,6 +1932,9 @@
start = slot + 1;
}
+ if (start >= slots->used_slots)
+ return slots->used_slots - 1;
+
if (gfn >= memslots[start].base_gfn &&
gfn < memslots[start].base_gfn + memslots[start].npages) {
atomic_set(&slots->lru_slot, start);
@@ -2863,9 +2866,7 @@
vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 |
CR14_UNUSED_33 |
CR14_EXTERNAL_DAMAGE_SUBMASK;
- /* make sure the new fpc will be lazily loaded */
- save_fpu_regs();
- current->thread.fpu.fpc = 0;
+ vcpu->run->s.regs.fpc = 0;
vcpu->arch.sie_block->gbea = 1;
vcpu->arch.sie_block->pp = 0;
vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
@@ -3725,7 +3726,7 @@
kvm_s390_patch_guest_per_regs(vcpu);
}
- clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.gisa_int.kicked_mask);
+ clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask);
vcpu->arch.sie_block->icptcode = 0;
cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
@@ -3979,16 +3980,16 @@
current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
if (MACHINE_HAS_GS) {
+ preempt_disable();
__ctl_set_bit(2, 4);
if (vcpu->arch.gs_enabled)
save_gs_cb(current->thread.gs_cb);
- preempt_disable();
current->thread.gs_cb = vcpu->arch.host_gscb;
restore_gs_cb(vcpu->arch.host_gscb);
- preempt_enable();
if (!vcpu->arch.host_gscb)
__ctl_clear_bit(2, 4);
vcpu->arch.host_gscb = NULL;
+ preempt_enable();
}
/* SIE will save etoken directly into SDNX and therefore kvm_run */
}
@@ -4354,7 +4355,7 @@
switch (ioctl) {
case KVM_S390_STORE_STATUS:
idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = kvm_s390_vcpu_store_status(vcpu, arg);
+ r = kvm_s390_store_status_unloaded(vcpu, arg);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
case KVM_S390_SET_INITIAL_PSW: {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 6d9448d..63d94a5 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -67,7 +67,7 @@
static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
{
- return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
+ return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ed52ffa..560310e 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -626,10 +626,12 @@
* available for the guest are AQIC and TAPQ with the t bit set
* since we do not set IC.3 (FIII) we currently will only intercept
* the AQIC function code.
+ * Note: running nested under z/VM can result in intercepts for other
+ * function codes, e.g. PQAP(QCI). We do not support this and bail out.
*/
reg0 = vcpu->run->s.regs.gprs[0];
fc = (reg0 >> 24) & 0xff;
- if (WARN_ON_ONCE(fc != 0x03))
+ if (fc != 0x03)
return -EOPNOTSUPP;
/* PQAP instruction is allowed for guest kernel only */
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 076090f..4f6c22d 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1202,6 +1202,7 @@
scb_s->iprcc = PGM_ADDRESSING;
scb_s->pgmilc = 4;
scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
+ rc = 1;
}
return rc;
}
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index c4f8039..0267405 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -64,10 +64,13 @@
{
mm_segment_t old_fs;
unsigned long asce, cr;
+ unsigned long flags;
old_fs = current->thread.mm_segment;
if (old_fs & 1)
return old_fs;
+ /* protect against a concurrent page table upgrade */
+ local_irq_save(flags);
current->thread.mm_segment |= 1;
asce = S390_lowcore.kernel_asce;
if (likely(old_fs == USER_DS)) {
@@ -83,6 +86,7 @@
__ctl_load(asce, 7, 7);
set_cpu_flag(CIF_ASCE_SECONDARY);
}
+ local_irq_restore(flags);
return old_fs;
}
EXPORT_SYMBOL(enable_sacf_uaccess);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index edcdca9..4fa7a56 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -787,14 +787,18 @@
static inline unsigned long *gmap_table_walk(struct gmap *gmap,
unsigned long gaddr, int level)
{
+ const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
unsigned long *table;
if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
return NULL;
if (gmap_is_shadow(gmap) && gmap->removed)
return NULL;
- if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+
+ if (asce_type != _ASCE_TYPE_REGION1 &&
+ gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
return NULL;
+
table = gmap->table;
switch (gmap->asce & _ASCE_TYPE_MASK) {
case _ASCE_TYPE_REGION1:
@@ -1840,6 +1844,7 @@
goto out_free;
} else if (*table & _REGION_ENTRY_ORIGIN) {
rc = -EAGAIN; /* Race with shadow */
+ goto out_free;
}
crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
/* mark as invalid as long as the parent table is not protected */
@@ -2480,23 +2485,36 @@
}
EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct vm_area_struct *vma = walk->vma;
+
+ split_huge_pmd(vma, pmd, addr);
+ return 0;
+}
+
+static const struct mm_walk_ops thp_split_walk_ops = {
+ .pmd_entry = thp_split_walk_pmd_entry,
+};
+
static inline void thp_split_mm(struct mm_struct *mm)
{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct vm_area_struct *vma;
- unsigned long addr;
for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
- for (addr = vma->vm_start;
- addr < vma->vm_end;
- addr += PAGE_SIZE)
- follow_page(vma, addr, FOLL_SPLIT);
vma->vm_flags &= ~VM_HUGEPAGE;
vma->vm_flags |= VM_NOHUGEPAGE;
+ walk_page_vma(vma, &thp_split_walk_ops, NULL);
}
mm->def_flags |= VM_NOHUGEPAGE;
-#endif
}
+#else
+static inline void thp_split_mm(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
* Remove all empty zero pages from the mapping for lazy refaulting
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index b0246c7..ff8234b 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -2,7 +2,7 @@
/*
* IBM System z Huge TLB Page Support for Kernel.
*
- * Copyright IBM Corp. 2007,2016
+ * Copyright IBM Corp. 2007,2020
* Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
*/
@@ -11,6 +11,9 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/security.h>
/*
* If the bit selected by single-bit bitmask "a" is set within "x", move
@@ -114,7 +117,7 @@
_PAGE_YOUNG);
#ifdef CONFIG_MEM_SOFT_DIRTY
pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
- _PAGE_DIRTY);
+ _PAGE_SOFT_DIRTY);
#endif
pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
_PAGE_NOEXEC);
@@ -156,10 +159,13 @@
rste &= ~_SEGMENT_ENTRY_NOEXEC;
/* Set correct table type for 2G hugepages */
- if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
- rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
- else
+ if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+ if (likely(pte_present(pte)))
+ rste |= _REGION3_ENTRY_LARGE;
+ rste |= _REGION_ENTRY_TYPE_R3;
+ } else if (likely(pte_present(pte)))
rste |= _SEGMENT_ENTRY_LARGE;
+
clear_huge_pte_skeys(mm, rste);
pte_val(*ptep) = rste;
}
@@ -267,3 +273,98 @@
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
+
+static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
+ unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ struct hstate *h = hstate_file(file);
+ struct vm_unmapped_area_info info;
+
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = current->mm->mmap_base;
+ info.high_limit = TASK_SIZE;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+ return vm_unmapped_area(&info);
+}
+
+static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
+ unsigned long addr0, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ struct hstate *h = hstate_file(file);
+ struct vm_unmapped_area_info info;
+ unsigned long addr;
+
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+ info.high_limit = current->mm->mmap_base;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+ addr = vm_unmapped_area(&info);
+
+ /*
+ * A failed mmap() very likely causes application failure,
+ * so fall back to the bottom-up function here. This scenario
+ * can happen with large stack limits and large mmap()
+ * allocations.
+ */
+ if (addr & ~PAGE_MASK) {
+ VM_BUG_ON(addr != -ENOMEM);
+ info.flags = 0;
+ info.low_limit = TASK_UNMAPPED_BASE;
+ info.high_limit = TASK_SIZE;
+ addr = vm_unmapped_area(&info);
+ }
+
+ return addr;
+}
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct hstate *h = hstate_file(file);
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int rc;
+
+ if (len & ~huge_page_mask(h))
+ return -EINVAL;
+ if (len > TASK_SIZE - mmap_min_addr)
+ return -ENOMEM;
+
+ if (flags & MAP_FIXED) {
+ if (prepare_hugepage_range(file, addr, len))
+ return -EINVAL;
+ goto check_asce_limit;
+ }
+
+ if (addr) {
+ addr = ALIGN(addr, huge_page_size(h));
+ vma = find_vma(mm, addr);
+ if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
+ (!vma || addr + len <= vm_start_gap(vma)))
+ goto check_asce_limit;
+ }
+
+ if (mm->get_unmapped_area == arch_get_unmapped_area)
+ addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
+ pgoff, flags);
+ else
+ addr = hugetlb_get_unmapped_area_topdown(file, addr, len,
+ pgoff, flags);
+ if (addr & ~PAGE_MASK)
+ return addr;
+
+check_asce_limit:
+ if (addr + len > current->mm->context.asce_limit &&
+ addr + len <= TASK_SIZE) {
+ rc = crst_table_upgrade(mm, addr + len);
+ if (rc)
+ return (unsigned long) rc;
+ }
+ return addr;
+}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index a124f19..5521f59 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -168,9 +168,9 @@
return;
/* make sure bounce buffers are shared */
+ swiotlb_force = SWIOTLB_FORCE;
swiotlb_init(1);
swiotlb_update_mem_attributes();
- swiotlb_force = SWIOTLB_FORCE;
}
void __init mem_init(void)
@@ -291,10 +291,8 @@
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c
index 460f255..5182e08 100644
--- a/arch/s390/mm/kasan_init.c
+++ b/arch/s390/mm/kasan_init.c
@@ -101,6 +101,9 @@
pgt_prot = pgprot_val(PAGE_KERNEL_EXEC);
sgt_prot = pgprot_val(SEGMENT_KERNEL_EXEC);
+ /*
+ * The first 1MB of 1:1 mapping is mapped with 4KB pages
+ */
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
@@ -146,30 +149,26 @@
pm_dir = pmd_offset(pu_dir, address);
if (pmd_none(*pm_dir)) {
- if (mode == POPULATE_ZERO_SHADOW &&
- IS_ALIGNED(address, PMD_SIZE) &&
+ if (IS_ALIGNED(address, PMD_SIZE) &&
end - address >= PMD_SIZE) {
- pmd_populate(&init_mm, pm_dir,
- kasan_early_shadow_pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- continue;
- }
- /* the first megabyte of 1:1 is mapped with 4k pages */
- if (has_edat && address && end - address >= PMD_SIZE &&
- mode != POPULATE_ZERO_SHADOW) {
- void *page;
+ if (mode == POPULATE_ZERO_SHADOW) {
+ pmd_populate(&init_mm, pm_dir, kasan_early_shadow_pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
+ } else if (has_edat && address) {
+ void *page;
- if (mode == POPULATE_ONE2ONE) {
- page = (void *)address;
- } else {
- page = kasan_early_alloc_segment();
- memset(page, 0, _SEGMENT_SIZE);
+ if (mode == POPULATE_ONE2ONE) {
+ page = (void *)address;
+ } else {
+ page = kasan_early_alloc_segment();
+ memset(page, 0, _SEGMENT_SIZE);
+ }
+ pmd_val(*pm_dir) = __pa(page) | sgt_prot;
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
}
- pmd_val(*pm_dir) = __pa(page) | sgt_prot;
- address = (address + PMD_SIZE) & PMD_MASK;
- continue;
}
-
pt_dir = kasan_early_pte_alloc();
pmd_populate(&init_mm, pm_dir, pt_dir);
} else if (pmd_large(*pm_dir)) {
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1864a8b..1d17413 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -55,22 +55,29 @@
*/
static DEFINE_SPINLOCK(s390_kernel_write_lock);
-void notrace s390_kernel_write(void *dst, const void *src, size_t size)
+notrace void *s390_kernel_write(void *dst, const void *src, size_t size)
{
+ void *tmp = dst;
unsigned long flags;
long copied;
spin_lock_irqsave(&s390_kernel_write_lock, flags);
- while (size) {
- copied = s390_kernel_write_odd(dst, src, size);
- dst += copied;
- src += copied;
- size -= copied;
+ if (!(flags & PSW_MASK_DAT)) {
+ memcpy(dst, src, size);
+ } else {
+ while (size) {
+ copied = s390_kernel_write_odd(tmp, src, size);
+ tmp += copied;
+ src += copied;
+ size -= copied;
+ }
}
spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
+
+ return dst;
}
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
{
register unsigned long _dest asm("2") = (unsigned long) dest;
register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +98,23 @@
return rc;
}
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
- unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+ unsigned long src,
+ unsigned long count)
{
int irqs_disabled, rc;
unsigned long flags;
if (!count)
return 0;
- flags = __arch_local_irq_stnsm(0xf8UL);
+ flags = arch_local_irq_save();
irqs_disabled = arch_irqs_disabled_flags(flags);
if (!irqs_disabled)
trace_hardirqs_off();
+ __arch_local_irq_stnsm(0xf8); // disable DAT
rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+ if (flags & PSW_MASK_DAT)
+ __arch_local_irq_stosm(0x04); // enable DAT
if (!irqs_disabled)
trace_hardirqs_on();
__arch_local_irq_ssm(flags);
@@ -115,9 +126,15 @@
*/
int memcpy_real(void *dest, void *src, size_t count)
{
- if (S390_lowcore.nodat_stack != 0)
- return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack,
- 3, dest, src, count);
+ int rc;
+
+ if (S390_lowcore.nodat_stack != 0) {
+ preempt_disable();
+ rc = CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, 3,
+ dest, src, count);
+ preempt_enable();
+ return rc;
+ }
/*
* This is a really early memcpy_real call, the stacks are
* not set up yet. Just call _memcpy_real on the early boot
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 3dd253f..46071be 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -70,8 +70,20 @@
{
struct mm_struct *mm = arg;
- if (current->active_mm == mm)
- set_user_asce(mm);
+ /* we must change all active ASCEs to avoid the creation of new TLBs */
+ if (current->active_mm == mm) {
+ S390_lowcore.user_asce = mm->context.asce;
+ if (current->thread.mm_segment == USER_DS) {
+ __ctl_load(S390_lowcore.user_asce, 1, 1);
+ /* Mark user-ASCE present in CR1 */
+ clear_cpu_flag(CIF_ASCE_PRIMARY);
+ }
+ if (current->thread.mm_segment == USER_DS_SACF) {
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
+ /* enable_sacf_uaccess does all or nothing */
+ WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
+ }
+ }
__tlb_flush_local();
}
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b403fa1..f810930 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -415,6 +415,10 @@
SET_MEMORY_RO | SET_MEMORY_X);
__set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
+
+ /* we need lowcore executable for our LPSWE instructions */
+ set_memory_x(0, 1);
+
pr_info("Write protected kernel read-only data: %luk\n",
(unsigned long)(__end_rodata - _stext) >> 10);
}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index ce88211..2d29966 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -23,6 +23,7 @@
#include <linux/filter.h>
#include <linux/init.h>
#include <linux/bpf.h>
+#include <linux/mm.h>
#include <asm/cacheflush.h>
#include <asm/dis.h>
#include <asm/facility.h>
@@ -113,7 +114,7 @@
{
u32 r1 = reg2hex[b1];
- if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15)
+ if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1])
jit->seen_reg[r1] = 1;
}
@@ -568,10 +569,10 @@
EMIT4(0xb9080000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_ADD | BPF_K: /* dst = (u32) dst + (u32) imm */
- if (!imm)
- break;
- /* alfi %dst,imm */
- EMIT6_IMM(0xc20b0000, dst_reg, imm);
+ if (imm != 0) {
+ /* alfi %dst,imm */
+ EMIT6_IMM(0xc20b0000, dst_reg, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_ADD | BPF_K: /* dst = dst + imm */
@@ -593,17 +594,22 @@
EMIT4(0xb9090000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_SUB | BPF_K: /* dst = (u32) dst - (u32) imm */
- if (!imm)
- break;
- /* alfi %dst,-imm */
- EMIT6_IMM(0xc20b0000, dst_reg, -imm);
+ if (imm != 0) {
+ /* alfi %dst,-imm */
+ EMIT6_IMM(0xc20b0000, dst_reg, -imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */
if (!imm)
break;
- /* agfi %dst,-imm */
- EMIT6_IMM(0xc2080000, dst_reg, -imm);
+ if (imm == -0x80000000) {
+ /* algfi %dst,0x80000000 */
+ EMIT6_IMM(0xc20a0000, dst_reg, 0x80000000);
+ } else {
+ /* agfi %dst,-imm */
+ EMIT6_IMM(0xc2080000, dst_reg, -imm);
+ }
break;
/*
* BPF_MUL
@@ -618,10 +624,10 @@
EMIT4(0xb90c0000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_MUL | BPF_K: /* dst = (u32) dst * (u32) imm */
- if (imm == 1)
- break;
- /* msfi %r5,imm */
- EMIT6_IMM(0xc2010000, dst_reg, imm);
+ if (imm != 1) {
+ /* msfi %r5,imm */
+ EMIT6_IMM(0xc2010000, dst_reg, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_MUL | BPF_K: /* dst = dst * imm */
@@ -674,6 +680,8 @@
if (BPF_OP(insn->code) == BPF_MOD)
/* lhgi %dst,0 */
EMIT4_IMM(0xa7090000, dst_reg, 0);
+ else
+ EMIT_ZERO(dst_reg);
break;
}
/* lhi %w0,0 */
@@ -768,10 +776,10 @@
EMIT4(0xb9820000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_XOR | BPF_K: /* dst = (u32) dst ^ (u32) imm */
- if (!imm)
- break;
- /* xilf %dst,imm */
- EMIT6_IMM(0xc0070000, dst_reg, imm);
+ if (imm != 0) {
+ /* xilf %dst,imm */
+ EMIT6_IMM(0xc0070000, dst_reg, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */
@@ -792,10 +800,10 @@
EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU | BPF_LSH | BPF_K: /* dst = (u32) dst << (u32) imm */
- if (imm == 0)
- break;
- /* sll %dst,imm(%r0) */
- EMIT4_DISP(0x89000000, dst_reg, REG_0, imm);
+ if (imm != 0) {
+ /* sll %dst,imm(%r0) */
+ EMIT4_DISP(0x89000000, dst_reg, REG_0, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_LSH | BPF_K: /* dst = dst << imm */
@@ -817,10 +825,10 @@
EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU | BPF_RSH | BPF_K: /* dst = (u32) dst >> (u32) imm */
- if (imm == 0)
- break;
- /* srl %dst,imm(%r0) */
- EMIT4_DISP(0x88000000, dst_reg, REG_0, imm);
+ if (imm != 0) {
+ /* srl %dst,imm(%r0) */
+ EMIT4_DISP(0x88000000, dst_reg, REG_0, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_RSH | BPF_K: /* dst = dst >> imm */
@@ -842,10 +850,10 @@
EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */
- if (imm == 0)
- break;
- /* sra %dst,imm(%r0) */
- EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm);
+ if (imm != 0) {
+ /* sra %dst,imm(%r0) */
+ EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm);
+ }
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */
@@ -913,6 +921,11 @@
}
break;
/*
+ * BPF_NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */
@@ -1369,7 +1382,7 @@
}
memset(&jit, 0, sizeof(jit));
- jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
+ jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
if (jit.addrs == NULL) {
fp = orig_fp;
goto out;
@@ -1422,7 +1435,7 @@
if (!fp->is_func || extra_pass) {
bpf_prog_fill_jited_linfo(fp, jit.addrs + 1);
free_addrs:
- kfree(jit.addrs);
+ kvfree(jit.addrs);
kfree(jit_data);
fp->aux->jit_data = NULL;
}
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index d2910fa..8386c58 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -49,12 +49,6 @@
mode->update_cpu_topology();
}
-int __node_distance(int a, int b)
-{
- return mode->distance ? mode->distance(a, b) : 0;
-}
-EXPORT_SYMBOL(__node_distance);
-
int numa_debug_enabled;
/*
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index c7fea9b..b8ddacf 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -423,7 +423,7 @@
if (zpci_use_mio(zdev))
pdev->resource[i].start =
- (resource_size_t __force) zdev->bars[i].mio_wb;
+ (resource_size_t __force) zdev->bars[i].mio_wt;
else
pdev->resource[i].start = (resource_size_t __force)
pci_iomap_range_fh(pdev, i, 0, 0);
@@ -530,7 +530,7 @@
flags |= IORESOURCE_MEM_64;
if (zpci_use_mio(zdev))
- addr = (unsigned long) zdev->bars[i].mio_wb;
+ addr = (unsigned long) zdev->bars[i].mio_wt;
else
addr = ZPCI_ADDR(entry);
size = 1UL << zdev->bars[i].size;
@@ -854,7 +854,6 @@
}
static unsigned int s390_pci_probe __initdata = 1;
-static unsigned int s390_pci_no_mio __initdata;
unsigned int s390_pci_force_floating __initdata;
static unsigned int s390_pci_initialized;
@@ -865,7 +864,7 @@
return NULL;
}
if (!strcmp(str, "nomio")) {
- s390_pci_no_mio = 1;
+ S390_lowcore.machine_flags &= ~MACHINE_FLAG_PCI_MIO;
return NULL;
}
if (!strcmp(str, "force_floating")) {
@@ -890,7 +889,7 @@
if (!test_facility(69) || !test_facility(71))
return 0;
- if (test_facility(153) && !s390_pci_no_mio) {
+ if (MACHINE_HAS_PCI_MIO) {
static_branch_enable(&have_mio);
ctl_set_bit(2, 5);
}
@@ -934,5 +933,5 @@
void zpci_rescan(void)
{
if (zpci_is_enabled())
- clp_rescan_pci_devices_simple();
+ clp_rescan_pci_devices_simple(NULL);
}
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index e585a62..20e093f 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -240,12 +240,14 @@
}
/*
- * Enable/Disable a given PCI function defined by its function handle.
+ * Enable/Disable a given PCI function and update its function handle if
+ * necessary
*/
-static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
+static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
{
struct clp_req_rsp_set_pci *rrb;
int rc, retries = 100;
+ u32 fid = zdev->fid;
rrb = clp_alloc_block(GFP_KERNEL);
if (!rrb)
@@ -256,7 +258,7 @@
rrb->request.hdr.len = sizeof(rrb->request);
rrb->request.hdr.cmd = CLP_SET_PCI_FN;
rrb->response.hdr.len = sizeof(rrb->response);
- rrb->request.fh = *fh;
+ rrb->request.fh = zdev->fh;
rrb->request.oc = command;
rrb->request.ndas = nr_dma_as;
@@ -269,12 +271,17 @@
}
} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
- if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
- *fh = rrb->response.fh;
- else {
+ if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
zpci_err("Set PCI FN:\n");
zpci_err_clp(rrb->response.hdr.rsp, rc);
- rc = -EIO;
+ }
+
+ if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+ zdev->fh = rrb->response.fh;
+ } else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY &&
+ rrb->response.fh == 0) {
+ /* Function is already in desired state - update handle */
+ rc = clp_rescan_pci_devices_simple(&fid);
}
clp_free_block(rrb);
return rc;
@@ -282,18 +289,17 @@
int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
{
- u32 fh = zdev->fh;
int rc;
- rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
- zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+ rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+ zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
if (rc)
goto out;
- zdev->fh = fh;
if (zpci_use_mio(zdev)) {
- rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO);
- zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+ rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_MIO);
+ zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n",
+ zdev->fid, zdev->fh, rc);
if (rc)
clp_disable_fh(zdev);
}
@@ -303,17 +309,13 @@
int clp_disable_fh(struct zpci_dev *zdev)
{
- u32 fh = zdev->fh;
int rc;
if (!zdev_enabled(zdev))
return 0;
- rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
- zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
- if (!rc)
- zdev->fh = fh;
-
+ rc = clp_set_pci_fn(zdev, 0, CLP_SET_DISABLE_PCI_FN);
+ zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
return rc;
}
@@ -370,10 +372,14 @@
static void __clp_update(struct clp_fh_list_entry *entry, void *data)
{
struct zpci_dev *zdev;
+ u32 *fid = data;
if (!entry->vendor_id)
return;
+ if (fid && *fid != entry->fid)
+ return;
+
zdev = get_zdev_by_fid(entry->fid);
if (!zdev)
return;
@@ -413,7 +419,10 @@
return rc;
}
-int clp_rescan_pci_devices_simple(void)
+/* Rescan PCI functions and refresh function handles. If fid is non-NULL only
+ * refresh the handle of the function matching @fid
+ */
+int clp_rescan_pci_devices_simple(u32 *fid)
{
struct clp_req_rsp_list_pci *rrb;
int rc;
@@ -422,7 +431,7 @@
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, NULL, __clp_update);
+ rc = clp_list_pci(rrb, fid, __clp_update);
clp_free_block(rrb);
return rc;
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index fbe97ab..743f257 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -115,7 +115,6 @@
.name = "PCI-MSI",
.irq_unmask = pci_msi_unmask_irq,
.irq_mask = pci_msi_mask_irq,
- .irq_set_affinity = zpci_set_irq_affinity,
};
static void zpci_handle_cpu_local_irq(bool rescan)
@@ -276,7 +275,9 @@
rc = -EIO;
if (hwirq - bit >= msi_vecs)
break;
- irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+ irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
+ (irq_delivery == DIRECTED) ?
+ msi->affinity : NULL);
if (irq < 0)
return -ENOMEM;
rc = irq_set_msi_desc(irq, msi);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 7d42a87..020a2c5 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -11,6 +11,113 @@
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/pci.h>
+#include <asm/pci_io.h>
+#include <asm/pci_debug.h>
+
+static inline void zpci_err_mmio(u8 cc, u8 status, u64 offset)
+{
+ struct {
+ u64 offset;
+ u8 cc;
+ u8 status;
+ } data = {offset, cc, status};
+
+ zpci_err_hex(&data, sizeof(data));
+}
+
+static inline int __pcistb_mio_inuser(
+ void __iomem *ioaddr, const void __user *src,
+ u64 len, u8 *status)
+{
+ int cc = -ENXIO;
+
+ asm volatile (
+ " sacf 256\n"
+ "0: .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n"
+ "1: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "2: sacf 768\n"
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+ : [cc] "+d" (cc), [len] "+d" (len)
+ : [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src))
+ : "cc", "memory");
+ *status = len >> 24 & 0xff;
+ return cc;
+}
+
+static inline int __pcistg_mio_inuser(
+ void __iomem *ioaddr, const void __user *src,
+ u64 ulen, u8 *status)
+{
+ register u64 addr asm("2") = (u64 __force) ioaddr;
+ register u64 len asm("3") = ulen;
+ int cc = -ENXIO;
+ u64 val = 0;
+ u64 cnt = ulen;
+ u8 tmp;
+
+ /*
+ * copy 0 < @len <= 8 bytes from @src into the right most bytes of
+ * a register, then store it to PCI at @ioaddr while in secondary
+ * address space. pcistg then uses the user mappings.
+ */
+ asm volatile (
+ " sacf 256\n"
+ "0: llgc %[tmp],0(%[src])\n"
+ " sllg %[val],%[val],8\n"
+ " aghi %[src],1\n"
+ " ogr %[val],%[tmp]\n"
+ " brctg %[cnt],0b\n"
+ "1: .insn rre,0xb9d40000,%[val],%[ioaddr]\n"
+ "2: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "3: sacf 768\n"
+ EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+ :
+ [src] "+a" (src), [cnt] "+d" (cnt),
+ [val] "+d" (val), [tmp] "=d" (tmp),
+ [len] "+d" (len), [cc] "+d" (cc),
+ [ioaddr] "+a" (addr)
+ :: "cc", "memory");
+ *status = len >> 24 & 0xff;
+
+ /* did we read everything from user memory? */
+ if (!cc && cnt != 0)
+ cc = -EFAULT;
+
+ return cc;
+}
+
+static inline int __memcpy_toio_inuser(void __iomem *dst,
+ const void __user *src, size_t n)
+{
+ int size, rc = 0;
+ u8 status = 0;
+ mm_segment_t old_fs;
+
+ if (!src)
+ return -EINVAL;
+
+ old_fs = enable_sacf_uaccess();
+ while (n > 0) {
+ size = zpci_get_max_write_size((u64 __force) dst,
+ (u64 __force) src, n,
+ ZPCI_MAX_WRITE_SIZE);
+ if (size > 8) /* main path */
+ rc = __pcistb_mio_inuser(dst, src, size, &status);
+ else
+ rc = __pcistg_mio_inuser(dst, src, size, &status);
+ if (rc)
+ break;
+ src += size;
+ dst += size;
+ n -= size;
+ }
+ disable_sacf_uaccess(old_fs);
+ if (rc)
+ zpci_err_mmio(rc, status, (__force u64) dst);
+ return rc;
+}
static long get_pfn(unsigned long user_addr, unsigned long access,
unsigned long *pfn)
@@ -46,6 +153,20 @@
if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
return -EINVAL;
+
+ /*
+ * Only support read access to MIO capable devices on a MIO enabled
+ * system. Otherwise we would have to check for every address if it is
+ * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+ * don't need for MIO capable devices.
+ */
+ if (static_branch_likely(&have_mio)) {
+ ret = __memcpy_toio_inuser((void __iomem *) mmio_addr,
+ user_buffer,
+ length);
+ return ret;
+ }
+
if (length > 64) {
buf = kmalloc(length, GFP_KERNEL);
if (!buf)
@@ -56,7 +177,8 @@
ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
if (ret)
goto out;
- io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+ io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
+ (mmio_addr & ~PAGE_MASK));
ret = -EFAULT;
if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
@@ -72,6 +194,78 @@
return ret;
}
+static inline int __pcilg_mio_inuser(
+ void __user *dst, const void __iomem *ioaddr,
+ u64 ulen, u8 *status)
+{
+ register u64 addr asm("2") = (u64 __force) ioaddr;
+ register u64 len asm("3") = ulen;
+ u64 cnt = ulen;
+ int shift = ulen * 8;
+ int cc = -ENXIO;
+ u64 val, tmp;
+
+ /*
+ * read 0 < @len <= 8 bytes from the PCI memory mapped at @ioaddr (in
+ * user space) into a register using pcilg then store these bytes at
+ * user address @dst
+ */
+ asm volatile (
+ " sacf 256\n"
+ "0: .insn rre,0xb9d60000,%[val],%[ioaddr]\n"
+ "1: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ " ltr %[cc],%[cc]\n"
+ " jne 4f\n"
+ "2: ahi %[shift],-8\n"
+ " srlg %[tmp],%[val],0(%[shift])\n"
+ "3: stc %[tmp],0(%[dst])\n"
+ " aghi %[dst],1\n"
+ " brctg %[cnt],2b\n"
+ "4: sacf 768\n"
+ EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+ :
+ [cc] "+d" (cc), [val] "=d" (val), [len] "+d" (len),
+ [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp),
+ [shift] "+d" (shift)
+ :
+ [ioaddr] "a" (addr)
+ : "cc", "memory");
+
+ /* did we write everything to the user space buffer? */
+ if (!cc && cnt != 0)
+ cc = -EFAULT;
+
+ *status = len >> 24 & 0xff;
+ return cc;
+}
+
+static inline int __memcpy_fromio_inuser(void __user *dst,
+ const void __iomem *src,
+ unsigned long n)
+{
+ int size, rc = 0;
+ u8 status;
+ mm_segment_t old_fs;
+
+ old_fs = enable_sacf_uaccess();
+ while (n > 0) {
+ size = zpci_get_max_write_size((u64 __force) src,
+ (u64 __force) dst, n,
+ ZPCI_MAX_READ_SIZE);
+ rc = __pcilg_mio_inuser(dst, src, size, &status);
+ if (rc)
+ break;
+ src += size;
+ dst += size;
+ n -= size;
+ }
+ disable_sacf_uaccess(old_fs);
+ if (rc)
+ zpci_err_mmio(rc, status, (__force u64) dst);
+ return rc;
+}
+
SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
void __user *, user_buffer, size_t, length)
{
@@ -86,12 +280,27 @@
if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
return -EINVAL;
+
+ /*
+ * Only support write access to MIO capable devices on a MIO enabled
+ * system. Otherwise we would have to check for every address if it is
+ * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+ * don't need for MIO capable devices.
+ */
+ if (static_branch_likely(&have_mio)) {
+ ret = __memcpy_fromio_inuser(
+ user_buffer, (const void __iomem *)mmio_addr,
+ length);
+ return ret;
+ }
+
if (length > 64) {
buf = kmalloc(length, GFP_KERNEL);
if (!buf)
return -ENOMEM;
- } else
+ } else {
buf = local_buf;
+ }
ret = get_pfn(mmio_addr, VM_READ, &pfn);
if (ret)
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index a433ba0..215f174 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -13,6 +13,8 @@
#include <linux/stat.h>
#include <linux/pci.h>
+#include "../../../drivers/pci/pci.h"
+
#include <asm/sclp.h>
#define zpci_attr(name, fmt, member) \
@@ -49,31 +51,50 @@
static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
+ struct kernfs_node *kn;
struct pci_dev *pdev = to_pci_dev(dev);
struct zpci_dev *zdev = to_zpci(pdev);
- int ret;
+ int ret = 0;
- if (!device_remove_file_self(dev, attr))
- return count;
+ /* Can't use device_remove_self() here as that would lead us to lock
+ * the pci_rescan_remove_lock while holding the device' kernfs lock.
+ * This would create a possible deadlock with disable_slot() which is
+ * not directly protected by the device' kernfs lock but takes it
+ * during the device removal which happens under
+ * pci_rescan_remove_lock.
+ *
+ * This is analogous to sdev_store_delete() in
+ * drivers/scsi/scsi_sysfs.c
+ */
+ kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+ WARN_ON_ONCE(!kn);
+ /* device_remove_file() serializes concurrent calls ignoring all but
+ * the first
+ */
+ device_remove_file(dev, attr);
+ /* A concurrent call to recover_store() may slip between
+ * sysfs_break_active_protection() and the sysfs file removal.
+ * Once it unblocks from pci_lock_rescan_remove() the original pdev
+ * will already be removed.
+ */
pci_lock_rescan_remove();
- pci_stop_and_remove_bus_device(pdev);
- ret = zpci_disable_device(zdev);
- if (ret)
- goto error;
+ if (pci_dev_is_added(pdev)) {
+ pci_stop_and_remove_bus_device(pdev);
+ ret = zpci_disable_device(zdev);
+ if (ret)
+ goto out;
- ret = zpci_enable_device(zdev);
- if (ret)
- goto error;
-
- pci_rescan_bus(zdev->bus);
+ ret = zpci_enable_device(zdev);
+ if (ret)
+ goto out;
+ pci_rescan_bus(zdev->bus);
+ }
+out:
pci_unlock_rescan_remove();
-
- return count;
-
-error:
- pci_unlock_rescan_remove();
- return ret;
+ if (kn)
+ sysfs_unbreak_active_protection(kn);
+ return ret ? ret : count;
}
static DEVICE_ATTR_WO(recover);
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bc0d7a0..9de5606 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -15,8 +15,10 @@
$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
$(call if_changed_rule,as_o_S)
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
- $(call if_changed_rule,cc_o_c)
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 5a10ce3..3d1c31e 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -62,14 +62,15 @@
jh 10b
.endm
-.macro START_NEXT_KERNEL base
+.macro START_NEXT_KERNEL base subcode
lg %r4,kernel_entry-\base(%r13)
lg %r5,load_psw_mask-\base(%r13)
ogr %r4,%r5
stg %r4,0(%r0)
xgr %r0,%r0
- diag %r0,%r0,0x308
+ lghi %r1,\subcode
+ diag %r0,%r1,0x308
.endm
.text
@@ -123,7 +124,7 @@
je .start_crash_kernel
/* start normal kernel */
- START_NEXT_KERNEL .base_crash
+ START_NEXT_KERNEL .base_crash 0
.return_old_kernel:
lmg %r6,%r15,gprregs-.base_crash(%r13)
@@ -227,7 +228,7 @@
MEMCPY %r9,%r10,%r11
/* start crash kernel */
- START_NEXT_KERNEL .base_dst
+ START_NEXT_KERNEL .base_dst 1
load_psw_mask:
diff --git a/arch/s390/purgatory/string.c b/arch/s390/purgatory/string.c
new file mode 100644
index 0000000..c98c22a
--- /dev/null
+++ b/arch/s390/purgatory/string.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define __HAVE_ARCH_MEMCMP /* arch function */
+#include "../lib/string.c"