summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--MAINTAINERS2
-rw-r--r--arch/arm64/boot/dts/arm/fvp-base-revc.dts2
-rw-r--r--arch/hexagon/Makefile6
-rw-r--r--arch/s390/boot/startup.c2
-rw-r--r--arch/s390/boot/vmem.c6
-rw-r--r--arch/s390/kernel/ipl.c2
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/static_call.h15
-rw-r--r--arch/x86/include/asm/sync_core.h6
-rw-r--r--arch/x86/include/asm/xen/hypercall.h36
-rw-r--r--arch/x86/kernel/callthunks.c5
-rw-r--r--arch/x86/kernel/cpu/common.c38
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c58
-rw-r--r--arch/x86/kernel/static_call.c9
-rw-r--r--arch/x86/kernel/vmlinux.lds.S4
-rw-r--r--arch/x86/xen/enlighten.c65
-rw-r--r--arch/x86/xen/enlighten_hvm.c13
-rw-r--r--arch/x86/xen/enlighten_pv.c4
-rw-r--r--arch/x86/xen/enlighten_pvh.c7
-rw-r--r--arch/x86/xen/xen-asm.S50
-rw-r--r--arch/x86/xen/xen-head.S107
-rw-r--r--arch/x86/xen/xen-ops.h9
-rw-r--r--drivers/clocksource/hyperv_timer.c14
-rw-r--r--drivers/cxl/core/region.c25
-rw-r--r--drivers/cxl/pci.c6
-rw-r--r--drivers/firmware/arm_ffa/bus.c15
-rw-r--r--drivers/firmware/arm_ffa/driver.c7
-rw-r--r--drivers/firmware/arm_scmi/vendors/imx/Kconfig1
-rw-r--r--drivers/firmware/imx/Kconfig1
-rw-r--r--drivers/hv/hv_balloon.c9
-rw-r--r--drivers/hv/hv_kvp.c10
-rw-r--r--drivers/hv/hv_snapshot.c9
-rw-r--r--drivers/hv/hv_util.c13
-rw-r--r--drivers/hv/hyperv_vmbus.h2
-rw-r--r--drivers/hv/vmbus_drv.c2
-rw-r--r--drivers/net/xen-netfront.c5
-rw-r--r--drivers/platform/x86/dell/alienware-wmi.c24
-rw-r--r--drivers/platform/x86/intel/ifs/core.c1
-rw-r--r--drivers/platform/x86/intel/vsec.c2
-rw-r--r--drivers/platform/x86/p2sb.c77
-rw-r--r--drivers/platform/x86/touchscreen_dmi.c26
-rw-r--r--fs/btrfs/bio.c16
-rw-r--r--fs/btrfs/ctree.h19
-rw-r--r--fs/btrfs/extent-tree.c6
-rw-r--r--fs/btrfs/tree-checker.c27
-rw-r--r--fs/erofs/data.c36
-rw-r--r--fs/erofs/fileio.c9
-rw-r--r--fs/erofs/fscache.c10
-rw-r--r--fs/erofs/internal.h15
-rw-r--r--fs/erofs/super.c78
-rw-r--r--fs/erofs/zdata.c4
-rw-r--r--fs/erofs/zutil.c7
-rw-r--r--include/clocksource/hyperv_timer.h2
-rw-r--r--include/linux/arm_ffa.h13
-rw-r--r--include/linux/compiler.h37
-rw-r--r--include/linux/fortify-string.h14
-rw-r--r--include/linux/hyperv.h1
-rw-r--r--include/linux/static_call.h6
-rw-r--r--include/linux/trace_events.h6
-rw-r--r--kernel/static_call_inline.c2
-rw-r--r--kernel/trace/fgraph.c8
-rw-r--r--kernel/trace/trace.c255
-rw-r--r--kernel/trace/trace.h6
-rw-r--r--kernel/trace/trace_events.c225
-rw-r--r--kernel/trace/trace_functions.c3
-rw-r--r--kernel/trace/trace_output.c6
-rw-r--r--security/selinux/ss/services.c8
-rw-r--r--sound/soc/fsl/Kconfig2
-rw-r--r--tools/hv/.gitignore3
-rw-r--r--tools/hv/hv_fcopy_uio_daemon.c12
-rwxr-xr-xtools/hv/hv_get_dns_info.sh4
-rw-r--r--tools/hv/hv_kvp_daemon.c9
-rwxr-xr-xtools/hv/hv_set_ifconfig.sh2
-rw-r--r--tools/objtool/check.c9
74 files changed, 1014 insertions, 543 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index baf0eeb9a355..7e29c4e86db1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8453,7 +8453,7 @@ F: include/video/s1d13xxxfb.h
EROFS FILE SYSTEM
M: Gao Xiang <xiang@kernel.org>
M: Chao Yu <chao@kernel.org>
-R: Yue Hu <huyue2@coolpad.com>
+R: Yue Hu <zbestahu@gmail.com>
R: Jeffle Xu <jefflexu@linux.alibaba.com>
R: Sandeep Dhavale <dhavale@google.com>
L: linux-erofs@lists.ozlabs.org
diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
index 19973ab4ea6b..9e10d7a6b5a2 100644
--- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts
+++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
@@ -233,7 +233,7 @@
#interrupt-cells = <0x1>;
compatible = "pci-host-ecam-generic";
device_type = "pci";
- bus-range = <0x0 0x1>;
+ bus-range = <0x0 0xff>;
reg = <0x0 0x40000000 0x0 0x10000000>;
ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>;
interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile
index 92d005958dfb..ff172cbe5881 100644
--- a/arch/hexagon/Makefile
+++ b/arch/hexagon/Makefile
@@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y)
TIR_NAME := r19
KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__
KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME)
+
+# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0
+# https://github.com/llvm/llvm-project/issues/99714
+ifneq ($(call clang-min-version, 190100),y)
+KBUILD_CFLAGS += -mllvm -hexagon-cext=false
+endif
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index abe6e6c0ab98..6087d38c7235 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -234,6 +234,8 @@ static unsigned long get_vmem_size(unsigned long identity_size,
vsize = round_up(SZ_2G + max_mappable, rte_size) +
round_up(vmemmap_size, rte_size) +
FIXMAP_SIZE + MODULES_LEN + KASLR_LEN;
+ if (IS_ENABLED(CONFIG_KMSAN))
+ vsize += MODULES_LEN * 2;
return size_add(vsize, vmalloc_size);
}
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 145035f84a0e..3fa28db2fe59 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
pages++;
}
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_4K, pages);
}
@@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
}
pgtable_pte_populate(pmd, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_1M, pages);
}
@@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
}
pgtable_pmd_populate(pud, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_2G, pages);
}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index edbb52ce3f1e..7d12a1305fc9 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
if (len >= sizeof(_value)) \
return -E2BIG; \
len = strscpy(_value, buf, sizeof(_value)); \
- if (len < 0) \
+ if ((ssize_t)len < 0) \
return len; \
strim(_value); \
return len; \
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0975815980c..20e6009381ed 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -230,6 +230,8 @@ static inline unsigned long long l1tf_pfn_limit(void)
return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
}
+void init_cpu_devs(void);
+void get_cpu_vendor(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 125c407e2abe..41502bd2afd6 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -65,4 +65,19 @@
extern bool __static_call_fixup(void *tramp, u8 op, void *dest);
+extern void __static_call_update_early(void *tramp, void *func);
+
+#define static_call_update_early(name, _func) \
+({ \
+ typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \
+ if (static_call_initialized) { \
+ __static_call_update(&STATIC_CALL_KEY(name), \
+ STATIC_CALL_TRAMP_ADDR(name), __F);\
+ } else { \
+ WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \
+ __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\
+ __F); \
+ } \
+})
+
#endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index ab7382f92aff..96bda43538ee 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -8,7 +8,7 @@
#include <asm/special_insns.h>
#ifdef CONFIG_X86_32
-static inline void iret_to_self(void)
+static __always_inline void iret_to_self(void)
{
asm volatile (
"pushfl\n\t"
@@ -19,7 +19,7 @@ static inline void iret_to_self(void)
: ASM_CALL_CONSTRAINT : : "memory");
}
#else
-static inline void iret_to_self(void)
+static __always_inline void iret_to_self(void)
{
unsigned int tmp;
@@ -55,7 +55,7 @@ static inline void iret_to_self(void)
* Like all of Linux's memory ordering operations, this is a
* compiler barrier as well.
*/
-static inline void sync_core(void)
+static __always_inline void sync_core(void)
{
/*
* The SERIALIZE instruction is the most straightforward way to
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a2dd24947eb8..97771b9d33af 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -39,9 +39,11 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/pgtable.h>
+#include <linux/instrumentation.h>
#include <trace/events/xen.h>
+#include <asm/alternative.h>
#include <asm/page.h>
#include <asm/smap.h>
#include <asm/nospec-branch.h>
@@ -86,11 +88,20 @@ struct xen_dm_op_buf;
* there aren't more than 5 arguments...)
*/
-extern struct { char _entry[32]; } hypercall_page[];
+void xen_hypercall_func(void);
+DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func);
-#define __HYPERCALL "call hypercall_page+%c[offset]"
-#define __HYPERCALL_ENTRY(x) \
- [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
+#ifdef MODULE
+#define __ADDRESSABLE_xen_hypercall
+#else
+#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall)
+#endif
+
+#define __HYPERCALL \
+ __ADDRESSABLE_xen_hypercall \
+ "call __SCT__xen_hypercall"
+
+#define __HYPERCALL_ENTRY(x) "a" (x)
#ifdef CONFIG_X86_32
#define __HYPERCALL_RETREG "eax"
@@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_0ARG(); \
asm volatile (__HYPERCALL \
: __HYPERCALL_0PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER0); \
(type)__res; \
})
@@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_1ARG(a1); \
asm volatile (__HYPERCALL \
: __HYPERCALL_1PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER1); \
(type)__res; \
})
@@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_2ARG(a1, a2); \
asm volatile (__HYPERCALL \
: __HYPERCALL_2PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER2); \
(type)__res; \
})
@@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_3ARG(a1, a2, a3); \
asm volatile (__HYPERCALL \
: __HYPERCALL_3PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER3); \
(type)__res; \
})
@@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_4ARG(a1, a2, a3, a4); \
asm volatile (__HYPERCALL \
: __HYPERCALL_4PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER4); \
(type)__res; \
})
@@ -206,12 +217,9 @@ xen_single_call(unsigned int call,
__HYPERCALL_DECLS;
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
- if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
- return -EINVAL;
-
- asm volatile(CALL_NOSPEC
+ asm volatile(__HYPERCALL
: __HYPERCALL_5PARAM
- : [thunk_target] "a" (&hypercall_page[call])
+ : __HYPERCALL_ENTRY(call)
: __HYPERCALL_CLOBBER5);
return (long)__res;
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 465647456753..f17d16607882 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -143,11 +143,6 @@ static bool skip_addr(void *dest)
dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE)
return true;
#endif
-#ifdef CONFIG_XEN
- if (dest >= (void *)hypercall_page &&
- dest < (void*)hypercall_page + PAGE_SIZE)
- return true;
-#endif
return false;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a5c28975c608..3e9037690814 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
}
-static void get_cpu_vendor(struct cpuinfo_x86 *c)
+void get_cpu_vendor(struct cpuinfo_x86 *c)
{
char *v = c->x86_vendor_id;
int i;
@@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
detect_nopl();
}
-void __init early_cpu_init(void)
+void __init init_cpu_devs(void)
{
const struct cpu_dev *const *cdev;
int count = 0;
-#ifdef CONFIG_PROCESSOR_SELECT
- pr_info("KERNEL supported cpus:\n");
-#endif
-
for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
const struct cpu_dev *cpudev = *cdev;
@@ -1665,20 +1661,30 @@ void __init early_cpu_init(void)
break;
cpu_devs[count] = cpudev;
count++;
+ }
+}
+void __init early_cpu_init(void)
+{
#ifdef CONFIG_PROCESSOR_SELECT
- {
- unsigned int j;
-
- for (j = 0; j < 2; j++) {
- if (!cpudev->c_ident[j])
- continue;
- pr_info(" %s %s\n", cpudev->c_vendor,
- cpudev->c_ident[j]);
- }
- }
+ unsigned int i, j;
+
+ pr_info("KERNEL supported cpus:\n");
#endif
+
+ init_cpu_devs();
+
+#ifdef CONFIG_PROCESSOR_SELECT
+ for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) {
+ for (j = 0; j < 2; j++) {
+ if (!cpu_devs[i]->c_ident[j])
+ continue;
+ pr_info(" %s %s\n", cpu_devs[i]->c_vendor,
+ cpu_devs[i]->c_ident[j]);
+ }
}
+#endif
+
early_identify_cpu(&boot_cpu_data);
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index d18078834ded..dc12fe5ef3ca 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
hyperv_cleanup();
}
#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+ hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * Adjust the offsets used by hv tsc clocksource to
+ * account for the time spent before hibernation.
+ * adjusted value = reference counter (time) at suspend
+ * - reference counter (time) now.
+ */
+ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+ old_save_sched_clock_state();
+ save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+ restore_hv_clock_tsc_state();
+ old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+ return;
+
+ old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+ x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 4eefaac64c6c..9eed0c144dad 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
}
EXPORT_SYMBOL_GPL(arch_static_call_transform);
+noinstr void __static_call_update_early(void *tramp, void *func)
+{
+ BUG_ON(system_state != SYSTEM_BOOTING);
+ BUG_ON(!early_boot_irqs_disabled);
+ BUG_ON(static_call_initialized);
+ __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE);
+ sync_core();
+}
+
#ifdef CONFIG_MITIGATION_RETHUNK
/*
* This is called by apply_returns() to fix up static call trampolines,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index fab3ac9a4574..6a17396c8174 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store);
* linker will never mark as relocatable. (Using just ABSOLUTE() is not
* sufficient for that).
*/
-#ifdef CONFIG_XEN
#ifdef CONFIG_XEN_PV
xen_elfnote_entry_value =
ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen);
#endif
-xen_elfnote_hypercall_page_value =
- ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page);
-#endif
#ifdef CONFIG_PVH
xen_elfnote_phys32_entry_value =
ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 84e5adbd0925..43dcd8c7badc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -2,6 +2,7 @@
#include <linux/console.h>
#include <linux/cpu.h>
+#include <linux/instrumentation.h>
#include <linux/kexec.h>
#include <linux/memblock.h>
#include <linux/slab.h>
@@ -21,7 +22,8 @@
#include "xen-ops.h"
-EXPORT_SYMBOL_GPL(hypercall_page);
+DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm);
+EXPORT_STATIC_CALL_TRAMP(xen_hypercall);
/*
* Pointer to the xen_vcpu_info structure or
@@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags);
*/
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
+static __ref void xen_get_vendor(void)
+{
+ init_cpu_devs();
+ cpu_detect(&boot_cpu_data);
+ get_cpu_vendor(&boot_cpu_data);
+}
+
+void xen_hypercall_setfunc(void)
+{
+ if (static_call_query(xen_hypercall) != xen_hypercall_hvm)
+ return;
+
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
+ static_call_update(xen_hypercall, xen_hypercall_amd);
+ else
+ static_call_update(xen_hypercall, xen_hypercall_intel);
+}
+
+/*
+ * Evaluate processor vendor in order to select the correct hypercall
+ * function for HVM/PVH guests.
+ * Might be called very early in boot before vendor has been set by
+ * early_cpu_init().
+ */
+noinstr void *__xen_hypercall_setfunc(void)
+{
+ void (*func)(void);
+
+ /*
+ * Xen is supported only on CPUs with CPUID, so testing for
+ * X86_FEATURE_CPUID is a test for early_cpu_init() having been
+ * run.
+ *
+ * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
+ * dependency chain: it is being called via the xen_hypercall static
+ * call when running as a PVH or HVM guest. Hypercalls need to be
+ * noinstr due to PV guests using hypercalls in noinstr code. So we
+ * can safely tag the function body as "instrumentation ok", since
+ * the PV guest requirement is not of interest here (xen_get_vendor()
+ * calls noinstr functions, and static_call_update_early() might do
+ * so, too).
+ */
+ instrumentation_begin();
+
+ if (!boot_cpu_has(X86_FEATURE_CPUID))
+ xen_get_vendor();
+
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
+ func = xen_hypercall_amd;
+ else
+ func = xen_hypercall_intel;
+
+ static_call_update_early(xen_hypercall, func);
+
+ instrumentation_end();
+
+ return func;
+}
+
static int xen_cpu_up_online(unsigned int cpu)
{
xen_init_lock_cpu(cpu);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 24d2957a4726..fe57ff85d004 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void)
/* PVH set up hypercall page in xen_prepare_pvh(). */
if (xen_pvh_domain())
pv_info.name = "Xen PVH";
- else {
- u64 pfn;
- uint32_t msr;
-
+ else
pv_info.name = "Xen HVM";
- msr = cpuid_ebx(base + 2);
- pfn = __pa(hypercall_page);
- wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
- }
xen_setup_features();
@@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void)
if (xen_pv_domain())
return 0;
+ /* Set correct hypercall function. */
+ if (xen_domain)
+ xen_hypercall_setfunc();
+
if (xen_pvh_domain() && nopv) {
/* Guest booting via the Xen-PVH boot entry goes here */
pr_info("\"nopv\" parameter is ignored in PVH guest\n");
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index d6818c6cafda..a8eb7e0c473c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
xen_domain_type = XEN_PV_DOMAIN;
xen_start_flags = xen_start_info->flags;
+ /* Interrupts are guaranteed to be off initially. */
+ early_boot_irqs_disabled = true;
+ static_call_update_early(xen_hypercall, xen_hypercall_pv);
xen_setup_features();
@@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
local_irq_disable();
- early_boot_irqs_disabled = true;
xen_raw_console_write("mapping kernel into physical memory\n");
xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index bf68c329fc01..0e3d930bcb89 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void)
void __init xen_pvh_init(struct boot_params *boot_params)
{
- u32 msr;
- u64 pfn;
-
xen_pvh = 1;
xen_domain_type = XEN_HVM_DOMAIN;
xen_start_flags = pvh_start_info.flags;
- msr = cpuid_ebx(xen_cpuid_base() + 2);
- pfn = __pa(hypercall_page);
- wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-
x86_init.oem.arch_setup = pvh_arch_setup;
x86_init.oem.banner = xen_banner;
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 83189cf5cdce..b518f36d1ca2 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -20,10 +20,33 @@
#include <linux/init.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <../entry/calling.h>
.pushsection .noinstr.text, "ax"
/*
+ * PV hypercall interface to the hypervisor.
+ *
+ * Called via inline asm(), so better preserve %rcx and %r11.
+ *
+ * Input:
+ * %eax: hypercall number
+ * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall
+ * Output: %rax
+ */
+SYM_FUNC_START(xen_hypercall_pv)
+ ANNOTATE_NOENDBR
+ push %rcx
+ push %r11
+ UNWIND_HINT_SAVE
+ syscall
+ UNWIND_HINT_RESTORE
+ pop %r11
+ pop %rcx
+ RET
+SYM_FUNC_END(xen_hypercall_pv)
+
+/*
* Disabling events is simply a matter of making the event mask
* non-zero.
*/
@@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array)
SYM_CODE_END(xen_early_idt_handler_array)
__FINIT
-hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
* Xen64 iret frame:
*
@@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
* cs
* rip <-- standard iret frame
*
- * flags
+ * flags <-- xen_iret must push from here on
*
- * rcx }
- * r11 }<-- pushed by hypercall page
- * rsp->rax }
+ * rcx
+ * r11
+ * rsp->rax
*/
+.macro xen_hypercall_iret
+ pushq $0 /* Flags */
+ push %rcx
+ push %r11
+ push %rax
+ mov $__HYPERVISOR_iret, %eax
+ syscall /* Do the IRET. */
+#ifdef CONFIG_MITIGATION_SLS
+ int3
+#endif
+.endm
+
SYM_CODE_START(xen_iret)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
- pushq $0
- jmp hypercall_iret
+ xen_hypercall_iret
SYM_CODE_END(xen_iret)
/*
@@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat)
ENDBR
lea 16(%rsp), %rsp /* strip %rcx, %r11 */
mov $-ENOSYS, %rax
- pushq $0
- jmp hypercall_iret
+ xen_hypercall_iret
SYM_CODE_END(xen_entry_SYSENTER_compat)
SYM_CODE_END(xen_entry_SYSCALL_compat)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 7f6c69dbb816..9252652afe59 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -6,9 +6,11 @@
#include <linux/elfnote.h>
#include <linux/init.h>
+#include <linux/instrumentation.h>
#include <asm/boot.h>
#include <asm/asm.h>
+#include <asm/frame.h>
#include <asm/msr.h>
#include <asm/page_types.h>
#include <asm/percpu.h>
@@ -20,28 +22,6 @@
#include <xen/interface/xen-mca.h>
#include <asm/xen/interface.h>
-.pushsection .noinstr.text, "ax"
- .balign PAGE_SIZE
-SYM_CODE_START(hypercall_page)
- .rept (PAGE_SIZE / 32)
- UNWIND_HINT_FUNC
- ANNOTATE_NOENDBR
- ANNOTATE_UNRET_SAFE
- ret
- /*
- * Xen will write the hypercall page, and sort out ENDBR.
- */
- .skip 31, 0xcc
- .endr
-
-#define HYPERCALL(n) \
- .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
- .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
-#include <asm/xen-hypercalls.h>
-#undef HYPERCALL
-SYM_CODE_END(hypercall_page)
-.popsection
-
#ifdef CONFIG_XEN_PV
__INIT
SYM_CODE_START(startup_xen)
@@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again)
#endif
#endif
+ .pushsection .noinstr.text, "ax"
+/*
+ * Xen hypercall interface to the hypervisor.
+ *
+ * Input:
+ * %eax: hypercall number
+ * 32-bit:
+ * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall
+ * 64-bit:
+ * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall
+ * Output: %[er]ax
+ */
+SYM_FUNC_START(xen_hypercall_hvm)
+ ENDBR
+ FRAME_BEGIN
+ /* Save all relevant registers (caller save and arguments). */
+#ifdef CONFIG_X86_32
+ push %eax
+ push %ebx
+ push %ecx
+ push %edx
+ push %esi
+ push %edi
+#else
+ push %rax
+ push %rcx
+ push %rdx
+ push %rdi
+ push %rsi
+ push %r11
+ push %r10
+ push %r9
+ push %r8
+#ifdef CONFIG_FRAME_POINTER
+ pushq $0 /* Dummy push for stack alignment. */
+#endif
+#endif
+ /* Set the vendor specific function. */
+ call __xen_hypercall_setfunc
+ /* Set ZF = 1 if AMD, Restore saved registers. */
+#ifdef CONFIG_X86_32
+ lea xen_hypercall_amd, %ebx
+ cmp %eax, %ebx
+ pop %edi
+ pop %esi
+ pop %edx
+ pop %ecx
+ pop %ebx
+ pop %eax
+#else
+ lea xen_hypercall_amd(%rip), %rbx
+ cmp %rax, %rbx
+#ifdef CONFIG_FRAME_POINTER
+ pop %rax /* Dummy pop. */
+#endif
+ pop %r8
+ pop %r9
+ pop %r10
+ pop %r11
+ pop %rsi
+ pop %rdi
+ pop %rdx
+ pop %rcx
+ pop %rax
+#endif
+ /* Use correct hypercall function. */
+ jz xen_hypercall_amd
+ jmp xen_hypercall_intel
+SYM_FUNC_END(xen_hypercall_hvm)
+
+SYM_FUNC_START(xen_hypercall_amd)
+ vmmcall
+ RET
+SYM_FUNC_END(xen_hypercall_amd)
+
+SYM_FUNC_START(xen_hypercall_intel)
+ vmcall
+ RET
+SYM_FUNC_END(xen_hypercall_intel)
+ .popsection
+
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6")
ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0")
@@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again)
#else
# define FEATURES_DOM0 0
#endif
- ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page;
- xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .)
ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES,
.long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0)
ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index e1b782e823e6..63c13a2ccf55 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
static inline void xen_smp_count_cpus(void) { }
#endif /* CONFIG_SMP */
+#ifdef CONFIG_XEN_PV
+void xen_hypercall_pv(void);
+#endif
+void xen_hypercall_hvm(void);
+void xen_hypercall_amd(void);
+void xen_hypercall_intel(void);
+void xen_hypercall_setfunc(void);
+void *__xen_hypercall_setfunc(void);
+
#endif /* XEN_OPS_H */
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 99177835cade..b39dee7b93af 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -27,7 +27,8 @@
#include <asm/mshyperv.h>
static struct clock_event_device __percpu *hv_clock_event;
-static u64 hv_sched_clock_offset __ro_after_init;
+/* Note: offset can hold negative values after hibernation. */
+static u64 hv_sched_clock_offset __read_mostly;
/*
* If false, we're using the old mechanism for stimer0 interrupts
@@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
}
+/*
+ * Called during resume from hibernation, from overridden
+ * x86_platform.restore_sched_clock_state routine. This is to adjust offsets
+ * used to calculate time for hv tsc page based sched_clock, to account for
+ * time spent before hibernation.
+ */
+void hv_adj_sched_clock_offset(u64 offset)
+{
+ hv_sched_clock_offset -= offset;
+}
+
#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK
static int hv_cs_enable(struct clocksource *cs)
{
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index d77899650798..b98b1ccffd1c 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
struct cxl_region_params *p = &cxlr->params;
struct cxl_decoder *cxld = cxl_rr->decoder;
struct cxl_switch_decoder *cxlsd;
+ struct cxl_port *iter = port;
u16 eig, peig;
u8 eiw, peiw;
@@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port,
cxlsd = to_cxl_switch_decoder(&cxld->dev);
if (cxl_rr->nr_targets_set) {
- int i, distance;
+ int i, distance = 1;
+ struct cxl_region_ref *cxl_rr_iter;
/*
- * Passthrough decoders impose no distance requirements between
- * peers
+ * The "distance" between peer downstream ports represents which
+ * endpoint positions in the region interleave a given port can
+ * host.
+ *
+ * For example, at the root of a hierarchy the distance is
+ * always 1 as every index targets a different host-bridge. At
+ * each subsequent switch level those ports map every Nth region
+ * position where N is the width of the switch == distance.
*/
- if (cxl_rr->nr_targets == 1)
- distance = 0;
- else
- distance = p->nr_targets / cxl_rr->nr_targets;
+ do {
+ cxl_rr_iter = cxl_rr_load(iter, cxlr);
+ distance *= cxl_rr_iter->nr_targets;
+ iter = to_cxl_port(iter->dev.parent);
+ } while (!is_cxl_root(iter));
+ distance *= cxlrd->cxlsd.cxld.interleave_ways;
+
for (i = 0; i < cxl_rr->nr_targets_set; i++)
if (ep->dport == cxlsd->target[i]) {
rc = check_last_peer(cxled, ep, cxl_rr,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 0241d1d7133a..6d94ff4a4f1a 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -836,6 +836,9 @@ static ssize_t rcd_pcie_cap_emit(struct device *dev, u16 offset, char *buf, size
if (!root_dev)
return -ENXIO;
+ if (!dport->regs.rcd_pcie_cap)
+ return -ENXIO;
+
guard(device)(root_dev);
if (!root_dev->driver)
return -ENXIO;
@@ -1032,8 +1035,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (rc)
return rc;
- rc = cxl_pci_ras_unmask(pdev);
- if (rc)
+ if (cxl_pci_ras_unmask(pdev))
dev_dbg(&pdev->dev, "No RAS reporting unmasked\n");
pci_save_state(pdev);
diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c
index eb17d03b66fe..dfda5ffc14db 100644
--- a/drivers/firmware/arm_ffa/bus.c
+++ b/drivers/firmware/arm_ffa/bus.c
@@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev)
return valid;
}
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops)
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops)
{
int id, ret;
+ uuid_t uuid;
struct device *dev;
struct ffa_device *ffa_dev;
+ if (!part_info)
+ return NULL;
+
id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL);
if (id < 0)
return NULL;
@@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id);
ffa_dev->id = id;
- ffa_dev->vm_id = vm_id;
+ ffa_dev->vm_id = part_info->id;
+ ffa_dev->properties = part_info->properties;
ffa_dev->ops = ops;
- uuid_copy(&ffa_dev->uuid, uuid);
+ import_uuid(&uuid, (u8 *)part_info->uuid);
+ uuid_copy(&ffa_dev->uuid, &uuid);
ret = device_register(&ffa_dev->dev);
if (ret) {
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index b14cbdae94e8..2c2ec3c35f15 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = {
static int ffa_setup_partitions(void)
{
int count, idx, ret;
- uuid_t uuid;
struct ffa_device *ffa_dev;
struct ffa_dev_part_info *info;
struct ffa_partition_info *pbuf, *tpbuf;
@@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void)
xa_init(&drv_info->partition_info);
for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) {
- import_uuid(&uuid, (u8 *)tpbuf->uuid);
-
/* Note that if the UUID will be uuid_null, that will require
* ffa_bus_notifier() to find the UUID of this partition id
* with help of ffa_device_match_uuid(). FF-A v1.1 and above
* provides UUID here for each partition as part of the
* discovery API and the same is passed.
*/
- ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops);
+ ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops);
if (!ffa_dev) {
pr_err("%s: failed to register partition ID 0x%x\n",
__func__, tpbuf->id);
continue;
}
- ffa_dev->properties = tpbuf->properties;
-
if (drv_info->version > FFA_VERSION_1_0 &&
!(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC))
ffa_mode_32bit_set(ffa_dev);
diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig
index 2883ed24a84d..a01bf5e47301 100644
--- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig
+++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig
@@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT
config IMX_SCMI_MISC_EXT
tristate "i.MX SCMI MISC EXTENSION"
depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF)
+ depends on IMX_SCMI_MISC_DRV
default y if ARCH_MXC
help
This enables i.MX System MISC control logic such as gpio expander
diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 477d3f32d99a..907cd149c40a 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -25,7 +25,6 @@ config IMX_SCU
config IMX_SCMI_MISC_DRV
tristate "IMX SCMI MISC Protocol driver"
- depends on IMX_SCMI_MISC_EXT || COMPILE_TEST
default y if ARCH_MXC
help
The System Controller Management Interface firmware (SCMI FW) is
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index c38dcdfcb914..a99112e6f0b8 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -756,7 +756,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
* adding succeeded, it is ok to proceed even if the memory was
* not onlined in time.
*/
- wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ);
+ wait_for_completion_timeout(&dm_device.ol_waitevent, secs_to_jiffies(5));
post_status(&dm_device);
}
}
@@ -1373,7 +1373,8 @@ static int dm_thread_func(void *dm_dev)
struct hv_dynmem_device *dm = dm_dev;
while (!kthread_should_stop()) {
- wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ);
+ wait_for_completion_interruptible_timeout(&dm_device.config_event,
+ secs_to_jiffies(1));
/*
* The host expects us to post information on the memory
* pressure every second.
@@ -1748,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev)
if (ret)
goto out;
- t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ);
+ t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5));
if (t == 0) {
ret = -ETIMEDOUT;
goto out;
@@ -1806,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev)
if (ret)
goto out;
- t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ);
+ t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5));
if (t == 0) {
ret = -ETIMEDOUT;
goto out;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index d35b60c06114..7400a5a4d2bd 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -655,7 +655,7 @@ void hv_kvp_onchannelcallback(void *context)
if (host_negotiatied == NEGO_NOT_STARTED) {
host_negotiatied = NEGO_IN_PROGRESS;
schedule_delayed_work(&kvp_host_handshake_work,
- HV_UTIL_NEGO_TIMEOUT * HZ);
+ secs_to_jiffies(HV_UTIL_NEGO_TIMEOUT));
}
return;
}
@@ -724,7 +724,7 @@ void hv_kvp_onchannelcallback(void *context)
*/
schedule_work(&kvp_sendkey_work);
schedule_delayed_work(&kvp_timeout_work,
- HV_UTIL_TIMEOUT * HZ);
+ secs_to_jiffies(HV_UTIL_TIMEOUT));
return;
@@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv)
*/
kvp_transaction.state = HVUTIL_DEVICE_INIT;
+ return 0;
+}
+
+int
+hv_kvp_init_transport(void)
+{
hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL,
kvp_on_msg, kvp_on_reset);
if (!hvt)
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 0d2184be1691..bde637a96c37 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -193,7 +193,8 @@ static void vss_send_op(void)
vss_transaction.state = HVUTIL_USERSPACE_REQ;
schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ?
- VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ);
+ secs_to_jiffies(VSS_FREEZE_TIMEOUT) :
+ secs_to_jiffies(HV_UTIL_TIMEOUT));
rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);
if (rc) {
@@ -388,6 +389,12 @@ hv_vss_init(struct hv_util_service *srv)
*/
vss_transaction.state = HVUTIL_DEVICE_INIT;
+ return 0;
+}
+
+int
+hv_vss_init_transport(void)
+{
hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL,
vss_on_msg, vss_on_reset);
if (!hvt) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index c4f525325790..36ee89c0358b 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = {
static struct hv_util_service util_kvp = {
.util_cb = hv_kvp_onchannelcallback,
.util_init = hv_kvp_init,
+ .util_init_transport = hv_kvp_init_transport,
.util_pre_suspend = hv_kvp_pre_suspend,
.util_pre_resume = hv_kvp_pre_resume,
.util_deinit = hv_kvp_deinit,
@@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = {
static struct hv_util_service util_vss = {
.util_cb = hv_vss_onchannelcallback,
.util_init = hv_vss_init,
+ .util_init_transport = hv_vss_init_transport,
.util_pre_suspend = hv_vss_pre_suspend,
.util_pre_resume = hv_vss_pre_resume,
.util_deinit = hv_vss_deinit,
@@ -590,10 +592,8 @@ static int util_probe(struct hv_device *dev,
srv->channel = dev->channel;
if (srv->util_init) {
ret = srv->util_init(srv);
- if (ret) {
- ret = -ENODEV;
+ if (ret)
goto error1;
- }
}
/*
@@ -613,6 +613,13 @@ static int util_probe(struct hv_device *dev,
if (ret)
goto error;
+ if (srv->util_init_transport) {
+ ret = srv->util_init_transport();
+ if (ret) {
+ vmbus_close(dev->channel);
+ goto error;
+ }
+ }
return 0;
error:
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index d2856023d53c..52cb744b4d7f 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data);
void vmbus_on_msg_dpc(unsigned long data);
int hv_kvp_init(struct hv_util_service *srv);
+int hv_kvp_init_transport(void);
void hv_kvp_deinit(void);
int hv_kvp_pre_suspend(void);
int hv_kvp_pre_resume(void);
void hv_kvp_onchannelcallback(void *context);
int hv_vss_init(struct hv_util_service *srv);
+int hv_vss_init_transport(void);
void hv_vss_deinit(void);
int hv_vss_pre_suspend(void);
int hv_vss_pre_resume(void);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 6d89d37b069a..2892b8da20a5 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2507,7 +2507,7 @@ static int vmbus_bus_resume(struct device *dev)
vmbus_request_offers();
if (wait_for_completion_timeout(
- &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0)
+ &vmbus_connection.ready_for_resume_event, secs_to_jiffies(10)) == 0)
pr_err("Some vmbus device is missing after suspending?\n");
/* Reset the event for the next suspend. */
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 4265c1cd0ff7..63fe51d0e64d 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
static int xennet_close(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
- unsigned int num_queues = dev->real_num_tx_queues;
+ unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0;
unsigned int i;
struct netfront_queue *queue;
netif_tx_stop_all_queues(np->netdev);
@@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info)
{
unsigned int i;
+ if (!info->queues)
+ return;
+
for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
struct netfront_queue *queue = &info->queues[i];
diff --git a/drivers/platform/x86/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c
index 77465ed9b449..341d01d3e3e4 100644
--- a/drivers/platform/x86/dell/alienware-wmi.c
+++ b/drivers/platform/x86/dell/alienware-wmi.c
@@ -190,7 +190,7 @@ static struct quirk_entry quirk_asm201 = {
};
static struct quirk_entry quirk_g_series = {
- .num_zones = 2,
+ .num_zones = 0,
.hdmi_mux = 0,
.amplifier = 0,
.deepslp = 0,
@@ -199,7 +199,7 @@ static struct quirk_entry quirk_g_series = {
};
static struct quirk_entry quirk_x_series = {
- .num_zones = 2,
+ .num_zones = 0,
.hdmi_mux = 0,
.amplifier = 0,
.deepslp = 0,
@@ -243,6 +243,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = {
},
{
.callback = dmi_matched,
+ .ident = "Alienware m16 R1 AMD",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
+ },
+ .driver_data = &quirk_x_series,
+ },
+ {
+ .callback = dmi_matched,
.ident = "Alienware m17 R5",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
@@ -687,6 +696,9 @@ static void alienware_zone_exit(struct platform_device *dev)
{
u8 zone;
+ if (!quirks->num_zones)
+ return;
+
sysfs_remove_group(&dev->dev.kobj, &zone_attribute_group);
led_classdev_unregister(&global_led);
if (zone_dev_attrs) {
@@ -1229,9 +1241,11 @@ static int __init alienware_wmi_init(void)
goto fail_prep_thermal_profile;
}
- ret = alienware_zone_init(platform_device);
- if (ret)
- goto fail_prep_zones;
+ if (quirks->num_zones > 0) {
+ ret = alienware_zone_init(platform_device);
+ if (ret)
+ goto fail_prep_zones;
+ }
return 0;
diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c
index bc252b883210..1ae50702bdb7 100644
--- a/drivers/platform/x86/intel/ifs/core.c
+++ b/drivers/platform/x86/intel/ifs/core.c
@@ -20,6 +20,7 @@ static const struct x86_cpu_id ifs_cpu_ids[] __initconst = {
X86_MATCH(INTEL_GRANITERAPIDS_X, ARRAY_GEN0),
X86_MATCH(INTEL_GRANITERAPIDS_D, ARRAY_GEN0),
X86_MATCH(INTEL_ATOM_CRESTMONT_X, ARRAY_GEN1),
+ X86_MATCH(INTEL_ATOM_DARKMONT_X, ARRAY_GEN1),
{}
};
MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids);
diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 4a85aad2475a..8272f1dd0fbc 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -423,6 +423,7 @@ static const struct intel_vsec_platform_info lnl_info = {
#define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d
#define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d
#define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d
+#define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d
static const struct pci_device_id intel_vsec_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) },
@@ -432,6 +433,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) },
+ { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) },
{ }
};
MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids);
diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index d51eb0db0626..cbbb0f809704 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -43,6 +43,7 @@ struct p2sb_res_cache {
};
static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE];
+static bool p2sb_hidden_by_bios;
static void p2sb_get_devfn(unsigned int *devfn)
{
@@ -97,6 +98,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn)
static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
{
+ /*
+ * The BIOS prevents the P2SB device from being enumerated by the PCI
+ * subsystem, so we need to unhide and hide it back to lookup the BAR.
+ */
+ pci_bus_write_config_dword(bus, devfn, P2SBC, 0);
+
/* Scan the P2SB device and cache its BAR0 */
p2sb_scan_and_cache_devfn(bus, devfn);
@@ -104,6 +111,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
if (devfn == P2SB_DEVFN_GOLDMONT)
p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT);
+ pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE);
+
if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res))
return -ENOENT;
@@ -129,7 +138,7 @@ static int p2sb_cache_resources(void)
u32 value = P2SBC_HIDE;
struct pci_bus *bus;
u16 class;
- int ret;
+ int ret = 0;
/* Get devfn for P2SB device itself */
p2sb_get_devfn(&devfn_p2sb);
@@ -152,22 +161,53 @@ static int p2sb_cache_resources(void)
*/
pci_lock_rescan_remove();
+ pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
+ p2sb_hidden_by_bios = value & P2SBC_HIDE;
+
/*
- * The BIOS prevents the P2SB device from being enumerated by the PCI
- * subsystem, so we need to unhide and hide it back to lookup the BAR.
- * Unhide the P2SB device here, if needed.
+ * If the BIOS does not hide the P2SB device then its resources
+ * are accesilble. Cache them only if the P2SB device is hidden.
*/
- pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
- if (value & P2SBC_HIDE)
- pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0);
+ if (p2sb_hidden_by_bios)
+ ret = p2sb_scan_and_cache(bus, devfn_p2sb);
- ret = p2sb_scan_and_cache(bus, devfn_p2sb);
+ pci_unlock_rescan_remove();
- /* Hide the P2SB device, if it was hidden */
- if (value & P2SBC_HIDE)
- pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE);
+ return ret;
+}
- pci_unlock_rescan_remove();
+static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn,
+ struct resource *mem)
+{
+ struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)];
+
+ if (cache->bus_dev_id != bus->dev.id)
+ return -ENODEV;
+
+ if (!p2sb_valid_resource(&cache->res))
+ return -ENOENT;
+
+ memcpy(mem, &cache->res, sizeof(*mem));
+
+ return 0;
+}
+
+static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn,
+ struct resource *mem)
+{
+ struct pci_dev *pdev;
+ int ret = 0;
+
+ pdev = pci_get_slot(bus, devfn);
+ if (!pdev)
+ return -ENODEV;
+
+ if (p2sb_valid_resource(pci_resource_n(pdev, 0)))
+ p2sb_read_bar0(pdev, mem);
+ else
+ ret = -ENOENT;
+
+ pci_dev_put(pdev);
return ret;
}
@@ -188,8 +228,6 @@ static int p2sb_cache_resources(void)
*/
int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
{
- struct p2sb_res_cache *cache;
-
bus = p2sb_get_bus(bus);
if (!bus)
return -ENODEV;
@@ -197,15 +235,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
if (!devfn)
p2sb_get_devfn(&devfn);
- cache = &p2sb_resources[PCI_FUNC(devfn)];
- if (cache->bus_dev_id != bus->dev.id)
- return -ENODEV;
+ if (p2sb_hidden_by_bios)
+ return p2sb_read_from_cache(bus, devfn, mem);
- if (!p2sb_valid_resource(&cache->res))
- return -ENOENT;
-
- memcpy(mem, &cache->res, sizeof(*mem));
- return 0;
+ return p2sb_read_from_dev(bus, devfn, mem);
}
EXPORT_SYMBOL_GPL(p2sb_bar);
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 0a39f68c641d..bdc19cd8d3ed 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -855,6 +855,23 @@ static const struct ts_dmi_data rwc_nanote_next_data = {
.properties = rwc_nanote_next_props,
};
+static const struct property_entry sary_tab_3_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1730),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1151),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-sary-tab-3.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ PROPERTY_ENTRY_BOOL("silead,home-button"),
+ { }
+};
+
+static const struct ts_dmi_data sary_tab_3_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = sary_tab_3_props,
+};
+
static const struct property_entry schneider_sct101ctm_props[] = {
PROPERTY_ENTRY_U32("touchscreen-size-x", 1715),
PROPERTY_ENTRY_U32("touchscreen-size-y", 1140),
@@ -1616,6 +1633,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
},
},
{
+ /* SARY Tab 3 */
+ .driver_data = (void *)&sary_tab_3_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "SARY"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C210C"),
+ DMI_MATCH(DMI_PRODUCT_SKU, "TAB3"),
+ },
+ },
+ {
/* Schneider SCT101CTM */
.driver_data = (void *)&schneider_sct101ctm_data,
.matches = {
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index af3db0a7ae4d..7ea6f0b43b95 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio)
INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
} else {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
+ if (bio_is_zone_append(bio) && !bio->bi_status)
btrfs_record_physical_zoned(bbio);
btrfs_bio_end_io(bbio, bbio->bio.bi_status);
}
@@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio)
else
bio->bi_status = BLK_STS_OK;
- if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
+ if (bio_is_zone_append(bio) && !bio->bi_status)
stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
btrfs_bio_end_io(bbio, bbio->bio.bi_status);
@@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio)
if (bio->bi_status) {
atomic_inc(&stripe->bioc->error);
btrfs_log_dev_io_error(bio, stripe->dev);
- } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ } else if (bio_is_zone_append(bio)) {
stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
}
@@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length)
map_length = min(map_length, bbio->fs_info->max_zone_append_size);
sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits,
&nr_segs, map_length);
- if (sector_offset)
- return sector_offset << SECTOR_SHIFT;
+ if (sector_offset) {
+ /*
+ * bio_split_rw_at() could split at a size smaller than our
+ * sectorsize and thus cause unaligned I/Os. Fix that by
+ * always rounding down to the nearest boundary.
+ */
+ return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize);
+ }
return map_length;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 307dedf95c70..2c341956a01c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi
}
/*
+ * Return the generation this root started with.
+ *
+ * Every normal root that is created with root->root_key.offset set to it's
+ * originating generation. If it is a snapshot it is the generation when the
+ * snapshot was created.
+ *
+ * However for TREE_RELOC roots root_key.offset is the objectid of the owning
+ * tree root. Thankfully we copy the root item of the owning tree root, which
+ * has it's last_snapshot set to what we would have root_key.offset set to, so
+ * return that if this is a TREE_RELOC root.
+ */
+static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root)
+{
+ if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
+ return btrfs_root_last_snapshot(&root->root_item);
+ return root->root_key.offset;
+}
+
+/*
* Structure that conveys information about an extent that is going to replace
* all the extents in a file range.
*/
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bd09dd3ad1a0..3c6f7fecbb9a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control *
* reference to it.
*/
generation = btrfs_node_ptr_generation(eb, slot);
- if (!wc->update_ref || generation <= root->root_key.offset)
+ if (!wc->update_ref || generation <= btrfs_root_origin_generation(root))
return false;
/*
@@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
goto reada;
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset)
+ generation <= btrfs_root_origin_generation(root))
continue;
/* We don't lock the tree block, it's OK to be racy here */
@@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
* for the subtree
*/
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset) {
+ generation <= btrfs_root_origin_generation(root)) {
wc->lookup_info = 1;
return 1;
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 148d8cefa40e..dfeee033f31f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf,
dref_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_extent_data_ref_count(leaf, dref);
break;
/* Contains parent bytenr and ref count */
@@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf,
inline_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_shared_data_ref_count(leaf, sref);
break;
case BTRFS_EXTENT_OWNER_REF_KEY:
@@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf,
{
u32 expect_item_size = 0;
- if (key->type == BTRFS_SHARED_DATA_REF_KEY)
+ if (key->type == BTRFS_SHARED_DATA_REF_KEY) {
+ struct btrfs_shared_data_ref *sref;
+
+ sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref);
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
+
expect_item_size = sizeof(struct btrfs_shared_data_ref);
+ }
if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) {
generic_err(leaf, slot,
@@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
offset, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
}
return 0;
}
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 1c49f8962021..0cd6b5c4df98 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
buf->file = NULL;
if (erofs_is_fileio_mode(sbi)) {
- buf->file = sbi->fdev; /* some fs like FUSE needs it */
+ buf->file = sbi->dif0.file; /* some fs like FUSE needs it */
buf->mapping = buf->file->f_mapping;
} else if (erofs_is_fscache_mode(sb))
- buf->mapping = sbi->s_fscache->inode->i_mapping;
+ buf->mapping = sbi->dif0.fscache->inode->i_mapping;
else
buf->mapping = sb->s_bdev->bd_mapping;
}
@@ -179,19 +179,13 @@ out:
}
static void erofs_fill_from_devinfo(struct erofs_map_dev *map,
- struct erofs_device_info *dif)
+ struct super_block *sb, struct erofs_device_info *dif)
{
+ map->m_sb = sb;
+ map->m_dif = dif;
map->m_bdev = NULL;
- map->m_fp = NULL;
- if (dif->file) {
- if (S_ISBLK(file_inode(dif->file)->i_mode))
- map->m_bdev = file_bdev(dif->file);
- else
- map->m_fp = dif->file;
- }
- map->m_daxdev = dif->dax_dev;
- map->m_dax_part_off = dif->dax_part_off;
- map->m_fscache = dif->fscache;
+ if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode))
+ map->m_bdev = file_bdev(dif->file);
}
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
@@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
erofs_off_t startoff, length;
int id;
- map->m_bdev = sb->s_bdev;
- map->m_daxdev = EROFS_SB(sb)->dax_dev;
- map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
- map->m_fscache = EROFS_SB(sb)->s_fscache;
- map->m_fp = EROFS_SB(sb)->fdev;
-
+ erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0);
+ map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */
if (map->m_deviceid) {
down_read(&devs->rwsem);
dif = idr_find(&devs->tree, map->m_deviceid - 1);
@@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
up_read(&devs->rwsem);
return 0;
}
- erofs_fill_from_devinfo(map, dif);
+ erofs_fill_from_devinfo(map, sb, dif);
up_read(&devs->rwsem);
} else if (devs->extra_devices && !devs->flatdev) {
down_read(&devs->rwsem);
@@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
if (map->m_pa >= startoff &&
map->m_pa < startoff + length) {
map->m_pa -= startoff;
- erofs_fill_from_devinfo(map, dif);
+ erofs_fill_from_devinfo(map, sb, dif);
break;
}
}
@@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
iomap->offset = map.m_la;
if (flags & IOMAP_DAX)
- iomap->dax_dev = mdev.m_daxdev;
+ iomap->dax_dev = mdev.m_dif->dax_dev;
else
iomap->bdev = mdev.m_bdev;
iomap->length = map.m_llen;
@@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
iomap->type = IOMAP_MAPPED;
iomap->addr = mdev.m_pa;
if (flags & IOMAP_DAX)
- iomap->addr += mdev.m_dax_part_off;
+ iomap->addr += mdev.m_dif->dax_part_off;
}
return 0;
}
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 3af96b1e2c2a..33f8539dda4a 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -9,6 +9,7 @@ struct erofs_fileio_rq {
struct bio_vec bvecs[BIO_MAX_VECS];
struct bio bio;
struct kiocb iocb;
+ struct super_block *sb;
};
struct erofs_fileio {
@@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT;
rq->iocb.ki_ioprio = get_current_ioprio();
rq->iocb.ki_complete = erofs_fileio_ki_complete;
- rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ?
- IOCB_DIRECT : 0;
+ if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) &&
+ rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT)
+ rq->iocb.ki_flags = IOCB_DIRECT;
iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt,
rq->bio.bi_iter.bi_size);
ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter);
@@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev)
GFP_KERNEL | __GFP_NOFAIL);
bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ);
- rq->iocb.ki_filp = mdev->m_fp;
+ rq->iocb.ki_filp = mdev->m_dif->file;
+ rq->sb = mdev->m_sb;
return rq;
}
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index fda16eedafb5..ce3d8737df85 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev)
io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL);
bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ);
- io->io.private = mdev->m_fscache->cookie;
+ io->io.private = mdev->m_dif->fscache->cookie;
io->io.end_io = erofs_fscache_bio_endio;
refcount_set(&io->io.ref, 1);
return &io->bio;
@@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req)
if (!io)
return -ENOMEM;
iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count);
- ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie,
+ ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie,
mdev.m_pa + (pos - map.m_la), io);
erofs_fscache_req_io_put(io);
@@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb)
if (IS_ERR(fscache))
return PTR_ERR(fscache);
- sbi->s_fscache = fscache;
+ sbi->dif0.fscache = fscache;
return 0;
}
@@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
- erofs_fscache_unregister_cookie(sbi->s_fscache);
+ erofs_fscache_unregister_cookie(sbi->dif0.fscache);
if (sbi->domain)
erofs_fscache_domain_put(sbi->domain);
else
fscache_relinquish_volume(sbi->volume, NULL, false);
- sbi->s_fscache = NULL;
+ sbi->dif0.fscache = NULL;
sbi->volume = NULL;
sbi->domain = NULL;
}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 1c847c30a918..686d835eb533 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item {
};
struct erofs_sb_info {
+ struct erofs_device_info dif0;
struct erofs_mount_opts opt; /* options */
#ifdef CONFIG_EROFS_FS_ZIP
/* list for all registered superblocks, mainly for shrinker */
@@ -124,13 +125,9 @@ struct erofs_sb_info {
struct erofs_sb_lz4_info lz4;
#endif /* CONFIG_EROFS_FS_ZIP */
- struct file *fdev;
struct inode *packed_inode;
struct erofs_dev_context *devs;
- struct dax_device *dax_dev;
- u64 dax_part_off;
u64 total_blocks;
- u32 primarydevice_blocks;
u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
@@ -166,7 +163,6 @@ struct erofs_sb_info {
/* fscache support */
struct fscache_volume *volume;
- struct erofs_fscache *s_fscache;
struct erofs_domain *domain;
char *fsid;
char *domain_id;
@@ -180,6 +176,7 @@ struct erofs_sb_info {
#define EROFS_MOUNT_POSIX_ACL 0x00000020
#define EROFS_MOUNT_DAX_ALWAYS 0x00000040
#define EROFS_MOUNT_DAX_NEVER 0x00000080
+#define EROFS_MOUNT_DIRECT_IO 0x00000100
#define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option)
#define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option)
@@ -187,7 +184,7 @@ struct erofs_sb_info {
static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi)
{
- return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev;
+ return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file;
}
static inline bool erofs_is_fscache_mode(struct super_block *sb)
@@ -357,11 +354,9 @@ enum {
};
struct erofs_map_dev {
- struct erofs_fscache *m_fscache;
+ struct super_block *m_sb;
+ struct erofs_device_info *m_dif;
struct block_device *m_bdev;
- struct dax_device *m_daxdev;
- struct file *m_fp;
- u64 m_dax_part_off;
erofs_off_t m_pa;
unsigned int m_deviceid;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index c235a8e4315e..f5956474bfde 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb,
struct erofs_device_info *dif;
int id, err = 0;
- sbi->total_blocks = sbi->primarydevice_blocks;
+ sbi->total_blocks = sbi->dif0.blocks;
if (!erofs_sb_has_device_table(sbi))
ondisk_extradevs = 0;
else
@@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb)
sbi->sb_size);
goto out;
}
- sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
+ sbi->dif0.blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
@@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
}
enum {
- Opt_user_xattr,
- Opt_acl,
- Opt_cache_strategy,
- Opt_dax,
- Opt_dax_enum,
- Opt_device,
- Opt_fsid,
- Opt_domain_id,
+ Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
+ Opt_device, Opt_fsid, Opt_domain_id, Opt_directio,
Opt_err
};
@@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
fsparam_string("device", Opt_device),
fsparam_string("fsid", Opt_fsid),
fsparam_string("domain_id", Opt_domain_id),
+ fsparam_flag_no("directio", Opt_directio),
{}
};
@@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc,
errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
#endif
+ case Opt_directio:
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+ if (result.boolean)
+ set_opt(&sbi->opt, DIRECT_IO);
+ else
+ clear_opt(&sbi->opt, DIRECT_IO);
+#else
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+#endif
+ break;
default:
return -ENOPARAM;
}
@@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
return -EINVAL;
}
- sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
- &sbi->dax_part_off,
- NULL, NULL);
+ sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
+ &sbi->dif0.dax_part_off, NULL, NULL);
}
err = erofs_read_superblock(sb);
@@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
}
if (test_opt(&sbi->opt, DAX_ALWAYS)) {
- if (!sbi->dax_dev) {
+ if (!sbi->dif0.dax_dev) {
errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
clear_opt(&sbi->opt, DAX_ALWAYS);
} else if (sbi->blkszbits != PAGE_SHIFT) {
@@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc)
GET_TREE_BDEV_QUIET_LOOKUP : 0);
#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
if (ret == -ENOTBLK) {
+ struct file *file;
+
if (!fc->source)
return invalf(fc, "No source specified");
- sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
- if (IS_ERR(sbi->fdev))
- return PTR_ERR(sbi->fdev);
+ file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ sbi->dif0.file = file;
- if (S_ISREG(file_inode(sbi->fdev)->i_mode) &&
- sbi->fdev->f_mapping->a_ops->read_folio)
+ if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) &&
+ sbi->dif0.file->f_mapping->a_ops->read_folio)
return get_tree_nodev(fc, erofs_fc_fill_super);
- fput(sbi->fdev);
}
#endif
return ret;
@@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs)
kfree(devs);
}
-static void erofs_fc_free(struct fs_context *fc)
+static void erofs_sb_free(struct erofs_sb_info *sbi)
{
- struct erofs_sb_info *sbi = fc->s_fs_info;
-
- if (!sbi)
- return;
-
erofs_free_dev_context(sbi->devs);
kfree(sbi->fsid);
kfree(sbi->domain_id);
+ if (sbi->dif0.file)
+ fput(sbi->dif0.file);
kfree(sbi);
}
+static void erofs_fc_free(struct fs_context *fc)
+{
+ struct erofs_sb_info *sbi = fc->s_fs_info;
+
+ if (sbi) /* free here if an error occurs before transferring to sb */
+ erofs_sb_free(sbi);
+}
+
static const struct fs_context_operations erofs_context_ops = {
.parse_param = erofs_fc_parse_param,
.get_tree = erofs_fc_get_tree,
@@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
- if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev)
+ if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) ||
+ sbi->dif0.file)
kill_anon_super(sb);
else
kill_block_super(sb);
-
- erofs_free_dev_context(sbi->devs);
- fs_put_dax(sbi->dax_dev, NULL);
+ fs_put_dax(sbi->dif0.dax_dev, NULL);
erofs_fscache_unregister_fs(sb);
- kfree(sbi->fsid);
- kfree(sbi->domain_id);
- if (sbi->fdev)
- fput(sbi->fdev);
- kfree(sbi);
+ erofs_sb_free(sbi);
sb->s_fs_info = NULL;
}
@@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",dax=always");
if (test_opt(opt, DAX_NEVER))
seq_puts(seq, ",dax=never");
+ if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
+ seq_puts(seq, ",directio");
#ifdef CONFIG_EROFS_FS_ONDEMAND
if (sbi->fsid)
seq_printf(seq, ",fsid=%s", sbi->fsid);
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 01f147505487..19ef4ff2a134 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1792,9 +1792,9 @@ drain_io:
erofs_fscache_submit_bio(bio);
else
submit_bio(bio);
- if (memstall)
- psi_memstall_leave(&pflags);
}
+ if (memstall)
+ psi_memstall_leave(&pflags);
/*
* although background is preferred, no one is pending for submission.
diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
index 75704f58ecfa..0dd65cefce33 100644
--- a/fs/erofs/zutil.c
+++ b/fs/erofs/zutil.c
@@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb)
struct erofs_sb_info *const sbi = EROFS_SB(sb);
mutex_lock(&sbi->umount_mutex);
- /* clean up all remaining pclusters in memory */
- z_erofs_shrink_scan(sbi, ~0UL);
-
+ while (!xa_empty(&sbi->managed_pslots)) {
+ z_erofs_shrink_scan(sbi, ~0UL);
+ cond_resched();
+ }
spin_lock(&erofs_sb_list_lock);
list_del(&sbi->list);
spin_unlock(&erofs_sb_list_lock);
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 6cdc873ac907..aa5233b1eba9 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void);
extern unsigned long hv_get_tsc_pfn(void);
extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+extern void hv_adj_sched_clock_offset(u64 offset);
+
static __always_inline bool
hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
u64 *cur_tsc, u64 *time)
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index a28e2a6a13d0..74169dd0f659 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev)
return dev_get_drvdata(&fdev->dev);
}
+struct ffa_partition_info;
+
#if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT)
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops);
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops);
void ffa_device_unregister(struct ffa_device *ffa_dev);
int ffa_driver_register(struct ffa_driver *driver, struct module *owner,
const char *mod_name);
@@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver);
bool ffa_device_is_valid(struct ffa_device *ffa_dev);
#else
-static inline
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops)
+static inline struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops)
{
return NULL;
}
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 469a64dd6495..240c632c5b95 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
#endif /* __KERNEL__ */
+/**
+ * offset_to_ptr - convert a relative memory offset to an absolute pointer
+ * @off: the address of the 32-bit offset value
+ */
+static inline void *offset_to_ptr(const int *off)
+{
+ return (void *)((unsigned long)off + *off);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_64BIT
+#define ARCH_SEL(a,b) a
+#else
+#define ARCH_SEL(a,b) b
+#endif
+
/*
* Force the compiler to emit 'sym' as a symbol, so that we can reference
* it from inline assembler. Necessary in case 'sym' could be inlined
* otherwise, or eliminated entirely due to lack of references that are
* visible to the compiler.
*/
-#define ___ADDRESSABLE(sym, __attrs) \
- static void * __used __attrs \
+#define ___ADDRESSABLE(sym, __attrs) \
+ static void * __used __attrs \
__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym;
+
#define __ADDRESSABLE(sym) \
___ADDRESSABLE(sym, __section(".discard.addressable"))
-/**
- * offset_to_ptr - convert a relative memory offset to an absolute pointer
- * @off: the address of the 32-bit offset value
- */
-static inline void *offset_to_ptr(const int *off)
-{
- return (void *)((unsigned long)off + *off);
-}
+#define __ADDRESSABLE_ASM(sym) \
+ .pushsection .discard.addressable,"aw"; \
+ .align ARCH_SEL(8,4); \
+ ARCH_SEL(.quad, .long) __stringify(sym); \
+ .popsection;
-#endif /* __ASSEMBLY__ */
+#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym))
#ifdef __CHECKER__
#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 0d99bf11d260..e4ce1cae03bf 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
return false;
}
+/*
+ * To work around what seems to be an optimizer bug, the macro arguments
+ * need to have const copies or the values end up changed by the time they
+ * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture
+ * __bos() results in const temp vars") for more details.
+ */
#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \
p_size_field, q_size_field, op) ({ \
const size_t __fortify_size = (size_t)(size); \
@@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
const size_t __q_size = (q_size); \
const size_t __p_size_field = (p_size_field); \
const size_t __q_size_field = (q_size_field); \
+ /* Keep a mutable version of the size for the final copy. */ \
+ size_t __copy_size = __fortify_size; \
fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \
__q_size, __p_size_field, \
__q_size_field, FORTIFY_FUNC_ ##op), \
@@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
__fortify_size, \
"field \"" #p "\" at " FILE_LINE, \
__p_size_field); \
- __underlying_##op(p, q, __fortify_size); \
+ /* Hide only the run-time size from value range tracking to */ \
+ /* silence compile-time false positive bounds warnings. */ \
+ if (!__builtin_constant_p(__copy_size)) \
+ OPTIMIZER_HIDE_VAR(__copy_size); \
+ __underlying_##op(p, q, __copy_size); \
})
/*
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 22c22fb91042..02a226bcf0ed 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1559,6 +1559,7 @@ struct hv_util_service {
void *channel;
void (*util_cb)(void *);
int (*util_init)(struct hv_util_service *);
+ int (*util_init_transport)(void);
void (*util_deinit)(void);
int (*util_pre_suspend)(void);
int (*util_pre_resume)(void);
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 141e6b176a1b..78a77a4ae0ea 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+extern int static_call_initialized;
+
extern int __init static_call_init(void);
extern void static_call_force_reinit(void);
@@ -225,6 +227,8 @@ extern long __static_call_return0(void);
#elif defined(CONFIG_HAVE_STATIC_CALL)
+#define static_call_initialized 0
+
static inline int static_call_init(void) { return 0; }
#define DEFINE_STATIC_CALL(name, _func) \
@@ -281,6 +285,8 @@ extern long __static_call_return0(void);
#else /* Generic implementation */
+#define static_call_initialized 0
+
static inline int static_call_init(void) { return 0; }
static inline long __static_call_return0(void)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2a5df5b62cfc..91b8ffbdfa8c 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -273,7 +273,8 @@ struct trace_event_fields {
const char *name;
const int size;
const int align;
- const int is_signed;
+ const unsigned int is_signed:1;
+ unsigned int needs_test:1;
const int filter_type;
const int len;
};
@@ -324,6 +325,7 @@ enum {
TRACE_EVENT_FL_EPROBE_BIT,
TRACE_EVENT_FL_FPROBE_BIT,
TRACE_EVENT_FL_CUSTOM_BIT,
+ TRACE_EVENT_FL_TEST_STR_BIT,
};
/*
@@ -340,6 +342,7 @@ enum {
* CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint)
* This is set when the custom event has not been attached
* to a tracepoint yet, then it is cleared when it is.
+ * TEST_STR - The event has a "%s" that points to a string outside the event
*/
enum {
TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
@@ -352,6 +355,7 @@ enum {
TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT),
TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT),
TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT),
+ TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT),
};
#define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE)
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
index 5259cda486d0..bb7d066a7c39 100644
--- a/kernel/static_call_inline.c
+++ b/kernel/static_call_inline.c
@@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[],
extern struct static_call_tramp_key __start_static_call_tramp_key[],
__stop_static_call_tramp_key[];
-static int static_call_initialized;
+int static_call_initialized;
/*
* Must be called before early_initcall() to be effective.
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 0bf78517b5d4..ddedcb50917f 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void)
static int start_graph_tracing(void)
{
unsigned long **ret_stack_list;
- int ret;
+ int ret, cpu;
ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
sizeof(*ret_stack_list), GFP_KERNEL);
@@ -1223,6 +1223,12 @@ static int start_graph_tracing(void)
if (!ret_stack_list)
return -ENOMEM;
+ /* The cpu_boot init_task->ret_stack will never be freed */
+ for_each_online_cpu(cpu) {
+ if (!idle_task(cpu)->ret_stack)
+ ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+ }
+
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index be62f0ea1814..7cc18b9bce27 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter)
}
/* Returns true if the string is safe to dereference from an event */
-static bool trace_safe_str(struct trace_iterator *iter, const char *str,
- bool star, int len)
+static bool trace_safe_str(struct trace_iterator *iter, const char *str)
{
unsigned long addr = (unsigned long)str;
struct trace_event *trace_event;
struct trace_event_call *event;
- /* Ignore strings with no length */
- if (star && !len)
- return true;
-
/* OK if part of the event data */
if ((addr >= (unsigned long)iter->ent) &&
(addr < (unsigned long)iter->ent + iter->ent_size))
@@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
return false;
}
-static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
-
-static int test_can_verify_check(const char *fmt, ...)
-{
- char buf[16];
- va_list ap;
- int ret;
-
- /*
- * The verifier is dependent on vsnprintf() modifies the va_list
- * passed to it, where it is sent as a reference. Some architectures
- * (like x86_32) passes it by value, which means that vsnprintf()
- * does not modify the va_list passed to it, and the verifier
- * would then need to be able to understand all the values that
- * vsnprintf can use. If it is passed by value, then the verifier
- * is disabled.
- */
- va_start(ap, fmt);
- vsnprintf(buf, 16, "%d", ap);
- ret = va_arg(ap, int);
- va_end(ap);
-
- return ret;
-}
-
-static void test_can_verify(void)
-{
- if (!test_can_verify_check("%d %d", 0, 1)) {
- pr_info("trace event string verifier disabled\n");
- static_branch_inc(&trace_no_verify);
- }
-}
-
/**
- * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
+ * ignore_event - Check dereferenced fields while writing to the seq buffer
* @iter: The iterator that holds the seq buffer and the event being printed
- * @fmt: The format used to print the event
- * @ap: The va_list holding the data to print from @fmt.
*
- * This writes the data into the @iter->seq buffer using the data from
- * @fmt and @ap. If the format has a %s, then the source of the string
- * is examined to make sure it is safe to print, otherwise it will
- * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
- * pointer.
+ * At boot up, test_event_printk() will flag any event that dereferences
+ * a string with "%s" that does exist in the ring buffer. It may still
+ * be valid, as the string may point to a static string in the kernel
+ * rodata that never gets freed. But if the string pointer is pointing
+ * to something that was allocated, there's a chance that it can be freed
+ * by the time the user reads the trace. This would cause a bad memory
+ * access by the kernel and possibly crash the system.
+ *
+ * This function will check if the event has any fields flagged as needing
+ * to be checked at runtime and perform those checks.
+ *
+ * If it is found that a field is unsafe, it will write into the @iter->seq
+ * a message stating what was found to be unsafe.
+ *
+ * @return: true if the event is unsafe and should be ignored,
+ * false otherwise.
*/
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
- va_list ap)
+bool ignore_event(struct trace_iterator *iter)
{
- long text_delta = 0;
- long data_delta = 0;
- const char *p = fmt;
- const char *str;
- bool good;
- int i, j;
+ struct ftrace_event_field *field;
+ struct trace_event *trace_event;
+ struct trace_event_call *event;
+ struct list_head *head;
+ struct trace_seq *seq;
+ const void *ptr;
- if (WARN_ON_ONCE(!fmt))
- return;
+ trace_event = ftrace_find_event(iter->ent->type);
- if (static_branch_unlikely(&trace_no_verify))
- goto print;
+ seq = &iter->seq;
- /*
- * When the kernel is booted with the tp_printk command line
- * parameter, trace events go directly through to printk().
- * It also is checked by this function, but it does not
- * have an associated trace_array (tr) for it.
- */
- if (iter->tr) {
- text_delta = iter->tr->text_delta;
- data_delta = iter->tr->data_delta;
+ if (!trace_event) {
+ trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type);
+ return true;
}
- /* Don't bother checking when doing a ftrace_dump() */
- if (iter->fmt == static_fmt_buf)
- goto print;
-
- while (*p) {
- bool star = false;
- int len = 0;
-
- j = 0;
-
- /*
- * We only care about %s and variants
- * as well as %p[sS] if delta is non-zero
- */
- for (i = 0; p[i]; i++) {
- if (i + 1 >= iter->fmt_size) {
- /*
- * If we can't expand the copy buffer,
- * just print it.
- */
- if (!trace_iter_expand_format(iter))
- goto print;
- }
-
- if (p[i] == '\\' && p[i+1]) {
- i++;
- continue;
- }
- if (p[i] == '%') {
- /* Need to test cases like %08.*s */
- for (j = 1; p[i+j]; j++) {
- if (isdigit(p[i+j]) ||
- p[i+j] == '.')
- continue;
- if (p[i+j] == '*') {
- star = true;
- continue;
- }
- break;
- }
- if (p[i+j] == 's')
- break;
-
- if (text_delta && p[i+1] == 'p' &&
- ((p[i+2] == 's' || p[i+2] == 'S')))
- break;
-
- star = false;
- }
- j = 0;
- }
- /* If no %s found then just print normally */
- if (!p[i])
- break;
-
- /* Copy up to the %s, and print that */
- strncpy(iter->fmt, p, i);
- iter->fmt[i] = '\0';
- trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+ event = container_of(trace_event, struct trace_event_call, event);
+ if (!(event->flags & TRACE_EVENT_FL_TEST_STR))
+ return false;
- /* Add delta to %pS pointers */
- if (p[i+1] == 'p') {
- unsigned long addr;
- char fmt[4];
+ head = trace_get_fields(event);
+ if (!head) {
+ trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n",
+ trace_event_name(event));
+ return true;
+ }
- fmt[0] = '%';
- fmt[1] = 'p';
- fmt[2] = p[i+2]; /* Either %ps or %pS */
- fmt[3] = '\0';
+ /* Offsets are from the iter->ent that points to the raw event */
+ ptr = iter->ent;
- addr = va_arg(ap, unsigned long);
- addr += text_delta;
- trace_seq_printf(&iter->seq, fmt, (void *)addr);
+ list_for_each_entry(field, head, link) {
+ const char *str;
+ bool good;
- p += i + 3;
+ if (!field->needs_test)
continue;
- }
- /*
- * If iter->seq is full, the above call no longer guarantees
- * that ap is in sync with fmt processing, and further calls
- * to va_arg() can return wrong positional arguments.
- *
- * Ensure that ap is no longer used in this case.
- */
- if (iter->seq.full) {
- p = "";
- break;
- }
-
- if (star)
- len = va_arg(ap, int);
-
- /* The ap now points to the string data of the %s */
- str = va_arg(ap, const char *);
+ str = *(const char **)(ptr + field->offset);
- good = trace_safe_str(iter, str, star, len);
-
- /* Could be from the last boot */
- if (data_delta && !good) {
- str += data_delta;
- good = trace_safe_str(iter, str, star, len);
- }
+ good = trace_safe_str(iter, str);
/*
* If you hit this warning, it is likely that the
@@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
* instead. See samples/trace_events/trace-events-sample.h
* for reference.
*/
- if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'",
- fmt, seq_buf_str(&iter->seq.seq))) {
- int ret;
-
- /* Try to safely read the string */
- if (star) {
- if (len + 1 > iter->fmt_size)
- len = iter->fmt_size - 1;
- if (len < 0)
- len = 0;
- ret = copy_from_kernel_nofault(iter->fmt, str, len);
- iter->fmt[len] = 0;
- star = false;
- } else {
- ret = strncpy_from_kernel_nofault(iter->fmt, str,
- iter->fmt_size);
- }
- if (ret < 0)
- trace_seq_printf(&iter->seq, "(0x%px)", str);
- else
- trace_seq_printf(&iter->seq, "(0x%px:%s)",
- str, iter->fmt);
- str = "[UNSAFE-MEMORY]";
- strcpy(iter->fmt, "%s");
- } else {
- strncpy(iter->fmt, p + i, j + 1);
- iter->fmt[j+1] = '\0';
+ if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'",
+ trace_event_name(event), field->name)) {
+ trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n",
+ trace_event_name(event), field->name);
+ return true;
}
- if (star)
- trace_seq_printf(&iter->seq, iter->fmt, len, str);
- else
- trace_seq_printf(&iter->seq, iter->fmt, str);
-
- p += i + j + 1;
}
- print:
- if (*p)
- trace_seq_vprintf(&iter->seq, p, ap);
+ return false;
}
const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
@@ -10777,8 +10630,6 @@ __init static int tracer_alloc_buffers(void)
register_snapshot_cmd();
- test_can_verify();
-
return 0;
out_free_pipe_cpumask:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 266740b4e121..9691b47b5f3d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
bool trace_is_tracepoint_string(const char *str);
const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
- va_list ap) __printf(2, 0);
char *trace_iter_expand_format(struct trace_iterator *iter);
+bool ignore_event(struct trace_iterator *iter);
int trace_empty(struct trace_iterator *iter);
@@ -1413,7 +1412,8 @@ struct ftrace_event_field {
int filter_type;
int offset;
int size;
- int is_signed;
+ unsigned int is_signed:1;
+ unsigned int needs_test:1;
int len;
};
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 77e68efbd43e..1545cc8b49d0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system)
}
static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
+__find_event_field(struct list_head *head, const char *name)
{
struct ftrace_event_field *field;
@@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name)
static int __trace_define_field(struct list_head *head, const char *type,
const char *name, int offset, int size,
- int is_signed, int filter_type, int len)
+ int is_signed, int filter_type, int len,
+ int need_test)
{
struct ftrace_event_field *field;
@@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
field->offset = offset;
field->size = size;
field->is_signed = is_signed;
+ field->needs_test = need_test;
field->len = len;
list_add(&field->link, head);
@@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type,
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type, 0);
+ is_signed, filter_type, 0, 0);
}
EXPORT_SYMBOL_GPL(trace_define_field);
static int trace_define_field_ext(struct trace_event_call *call, const char *type,
const char *name, int offset, int size, int is_signed,
- int filter_type, int len)
+ int filter_type, int len, int need_test)
{
struct list_head *head;
@@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type, len);
+ is_signed, filter_type, len, need_test);
}
#define __generic_field(type, item, filter_type) \
ret = __trace_define_field(&ftrace_generic_fields, #type, \
#item, 0, 0, is_signed_type(type), \
- filter_type, 0); \
+ filter_type, 0, 0); \
if (ret) \
return ret;
@@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
"common_" #item, \
offsetof(typeof(ent), item), \
sizeof(ent.item), \
- is_signed_type(type), FILTER_OTHER, 0); \
+ is_signed_type(type), FILTER_OTHER, \
+ 0, 0); \
if (ret) \
return ret;
@@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call)
return tail->offset + tail->size;
}
-/*
- * Check if the referenced field is an array and return true,
- * as arrays are OK to dereference.
- */
-static bool test_field(const char *fmt, struct trace_event_call *call)
+
+static struct trace_event_fields *find_event_field(const char *fmt,
+ struct trace_event_call *call)
{
struct trace_event_fields *field = call->class->fields_array;
- const char *array_descriptor;
const char *p = fmt;
int len;
if (!(len = str_has_prefix(fmt, "REC->")))
- return false;
+ return NULL;
fmt += len;
for (p = fmt; *p; p++) {
if (!isalnum(*p) && *p != '_')
@@ -265,16 +265,129 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
len = p - fmt;
for (; field->type; field++) {
- if (strncmp(field->name, fmt, len) ||
- field->name[len])
+ if (strncmp(field->name, fmt, len) || field->name[len])
continue;
- array_descriptor = strchr(field->type, '[');
- /* This is an array and is OK to dereference. */
- return array_descriptor != NULL;
+
+ return field;
+ }
+ return NULL;
+}
+
+/*
+ * Check if the referenced field is an array and return true,
+ * as arrays are OK to dereference.
+ */
+static bool test_field(const char *fmt, struct trace_event_call *call)
+{
+ struct trace_event_fields *field;
+
+ field = find_event_field(fmt, call);
+ if (!field)
+ return false;
+
+ /* This is an array and is OK to dereference. */
+ return strchr(field->type, '[') != NULL;
+}
+
+/* Look for a string within an argument */
+static bool find_print_string(const char *arg, const char *str, const char *end)
+{
+ const char *r;
+
+ r = strstr(arg, str);
+ return r && r < end;
+}
+
+/* Return true if the argument pointer is safe */
+static bool process_pointer(const char *fmt, int len, struct trace_event_call *call)
+{
+ const char *r, *e, *a;
+
+ e = fmt + len;
+
+ /* Find the REC-> in the argument */
+ r = strstr(fmt, "REC->");
+ if (r && r < e) {
+ /*
+ * Addresses of events on the buffer, or an array on the buffer is
+ * OK to dereference. There's ways to fool this, but
+ * this is to catch common mistakes, not malicious code.
+ */
+ a = strchr(fmt, '&');
+ if ((a && (a < r)) || test_field(r, call))
+ return true;
+ } else if (find_print_string(fmt, "__get_dynamic_array(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_sockaddr(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) {
+ return true;
}
return false;
}
+/* Return true if the string is safe */
+static bool process_string(const char *fmt, int len, struct trace_event_call *call)
+{
+ struct trace_event_fields *field;
+ const char *r, *e, *s;
+
+ e = fmt + len;
+
+ /*
+ * There are several helper functions that return strings.
+ * If the argument contains a function, then assume its field is valid.
+ * It is considered that the argument has a function if it has:
+ * alphanumeric or '_' before a parenthesis.
+ */
+ s = fmt;
+ do {
+ r = strstr(s, "(");
+ if (!r || r >= e)
+ break;
+ for (int i = 1; r - i >= s; i++) {
+ char ch = *(r - i);
+ if (isspace(ch))
+ continue;
+ if (isalnum(ch) || ch == '_')
+ return true;
+ /* Anything else, this isn't a function */
+ break;
+ }
+ /* A function could be wrapped in parethesis, try the next one */
+ s = r + 1;
+ } while (s < e);
+
+ /*
+ * If there's any strings in the argument consider this arg OK as it
+ * could be: REC->field ? "foo" : "bar" and we don't want to get into
+ * verifying that logic here.
+ */
+ if (find_print_string(fmt, "\"", e))
+ return true;
+
+ /* Dereferenced strings are also valid like any other pointer */
+ if (process_pointer(fmt, len, call))
+ return true;
+
+ /* Make sure the field is found */
+ field = find_event_field(fmt, call);
+ if (!field)
+ return false;
+
+ /* Test this field's string before printing the event */
+ call->flags |= TRACE_EVENT_FL_TEST_STR;
+ field->needs_test = 1;
+
+ return true;
+}
+
/*
* Examine the print fmt of the event looking for unsafe dereference
* pointers using %p* that could be recorded in the trace event and
@@ -284,13 +397,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
static void test_event_printk(struct trace_event_call *call)
{
u64 dereference_flags = 0;
+ u64 string_flags = 0;
bool first = true;
- const char *fmt, *c, *r, *a;
+ const char *fmt;
int parens = 0;
char in_quote = 0;
int start_arg = 0;
int arg = 0;
- int i;
+ int i, e;
fmt = call->print_fmt;
@@ -374,8 +488,16 @@ static void test_event_printk(struct trace_event_call *call)
star = true;
continue;
}
- if ((fmt[i + j] == 's') && star)
- arg++;
+ if ((fmt[i + j] == 's')) {
+ if (star)
+ arg++;
+ if (WARN_ONCE(arg == 63,
+ "Too many args for event: %s",
+ trace_event_name(call)))
+ return;
+ dereference_flags |= 1ULL << arg;
+ string_flags |= 1ULL << arg;
+ }
break;
}
break;
@@ -403,42 +525,47 @@ static void test_event_printk(struct trace_event_call *call)
case ',':
if (in_quote || parens)
continue;
+ e = i;
i++;
while (isspace(fmt[i]))
i++;
- start_arg = i;
- if (!(dereference_flags & (1ULL << arg)))
- goto next_arg;
- /* Find the REC-> in the argument */
- c = strchr(fmt + i, ',');
- r = strstr(fmt + i, "REC->");
- if (r && (!c || r < c)) {
- /*
- * Addresses of events on the buffer,
- * or an array on the buffer is
- * OK to dereference.
- * There's ways to fool this, but
- * this is to catch common mistakes,
- * not malicious code.
- */
- a = strchr(fmt + i, '&');
- if ((a && (a < r)) || test_field(r, call))
+ /*
+ * If start_arg is zero, then this is the start of the
+ * first argument. The processing of the argument happens
+ * when the end of the argument is found, as it needs to
+ * handle paranthesis and such.
+ */
+ if (!start_arg) {
+ start_arg = i;
+ /* Balance out the i++ in the for loop */
+ i--;
+ continue;
+ }
+
+ if (dereference_flags & (1ULL << arg)) {
+ if (string_flags & (1ULL << arg)) {
+ if (process_string(fmt + start_arg, e - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ } else if (process_pointer(fmt + start_arg, e - start_arg, call))
dereference_flags &= ~(1ULL << arg);
- } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
- (!c || r < c)) {
- dereference_flags &= ~(1ULL << arg);
- } else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
- (!c || r < c)) {
- dereference_flags &= ~(1ULL << arg);
}
- next_arg:
- i--;
+ start_arg = i;
arg++;
+ /* Balance out the i++ in the for loop */
+ i--;
}
}
+ if (dereference_flags & (1ULL << arg)) {
+ if (string_flags & (1ULL << arg)) {
+ if (process_string(fmt + start_arg, i - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ } else if (process_pointer(fmt + start_arg, i - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ }
+
/*
* If you triggered the below warning, the trace event reported
* uses an unsafe dereference pointer %p*. As the data stored
@@ -2471,7 +2598,7 @@ event_define_fields(struct trace_event_call *call)
ret = trace_define_field_ext(call, field->type, field->name,
offset, field->size,
field->is_signed, field->filter_type,
- field->len);
+ field->len, field->needs_test);
if (WARN_ON_ONCE(ret)) {
pr_err("error code is %d\n", ret);
break;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 74c353164ca1..d358c9935164 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr)
tracing_reset_online_cpus(&tr->array_buffer);
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
static __always_inline unsigned long
function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
{
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index da748b7cbc4d..03d56f711ad1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep);
void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...)
{
+ struct trace_seq *s = &iter->seq;
va_list ap;
+ if (ignore_event(iter))
+ return;
+
va_start(ap, fmt);
- trace_check_vprintf(iter, trace_event_format(iter, fmt), ap);
+ trace_seq_vprintf(s, trace_event_format(iter, fmt), ap);
va_end(ap);
}
EXPORT_SYMBOL(trace_event_printf);
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 971c45d576ba..3d5c563cfc4c 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -979,7 +979,10 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
return;
break;
default:
- BUG();
+ pr_warn_once(
+ "SELinux: unknown extended permission (%u) will be ignored\n",
+ node->datum.u.xperms->specified);
+ return;
}
if (node->key.specified == AVTAB_XPERMS_ALLOWED) {
@@ -998,7 +1001,8 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
&node->datum.u.xperms->perms,
xpermd->dontaudit);
} else {
- BUG();
+ pr_warn_once("SELinux: unknown specified key (%u)\n",
+ node->key.specified);
}
}
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 8e88830e8e57..678540b78280 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -29,8 +29,8 @@ config SND_SOC_FSL_SAI
config SND_SOC_FSL_MQS
tristate "Medium Quality Sound (MQS) module support"
depends on SND_SOC_FSL_SAI
+ depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV
select REGMAP_MMIO
- select IMX_SCMI_MISC_DRV if IMX_SCMI_MISC_EXT !=n
help
Say Y if you want to add Medium Quality Sound (MQS)
support for the Freescale CPUs.
diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore
new file mode 100644
index 000000000000..0c5bc15d602f
--- /dev/null
+++ b/tools/hv/.gitignore
@@ -0,0 +1,3 @@
+hv_fcopy_uio_daemon
+hv_kvp_daemon
+hv_vss_daemon
diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c
index 7a00f3066a98..0198321d14a2 100644
--- a/tools/hv/hv_fcopy_uio_daemon.c
+++ b/tools/hv/hv_fcopy_uio_daemon.c
@@ -35,8 +35,6 @@
#define WIN8_SRV_MINOR 1
#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
-#define MAX_FOLDER_NAME 15
-#define MAX_PATH_LEN 15
#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio"
#define FCOPY_VER_COUNT 1
@@ -51,7 +49,7 @@ static const int fw_versions[] = {
#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */
-unsigned char desc[HV_RING_SIZE];
+static unsigned char desc[HV_RING_SIZE];
static int target_fd;
static char target_fname[PATH_MAX];
@@ -409,8 +407,8 @@ int main(int argc, char *argv[])
struct vmbus_br txbr, rxbr;
void *ring;
uint32_t len = HV_RING_SIZE;
- char uio_name[MAX_FOLDER_NAME] = {0};
- char uio_dev_path[MAX_PATH_LEN] = {0};
+ char uio_name[NAME_MAX] = {0};
+ char uio_dev_path[PATH_MAX] = {0};
static struct option long_options[] = {
{"help", no_argument, 0, 'h' },
@@ -468,8 +466,10 @@ int main(int argc, char *argv[])
*/
ret = pread(fcopy_fd, &tmp, sizeof(int), 0);
if (ret < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
syslog(LOG_ERR, "pread failed: %s", strerror(errno));
- continue;
+ goto close;
}
len = HV_RING_SIZE;
diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh
index 058c17b46ffc..268521234d4b 100755
--- a/tools/hv/hv_get_dns_info.sh
+++ b/tools/hv/hv_get_dns_info.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
# This example script parses /etc/resolv.conf to retrive DNS information.
# In the interest of keeping the KVP daemon code free of distro specific
@@ -10,4 +10,4 @@
# this script can be based on the Network Manager APIs for retrieving DNS
# entries.
-cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }'
+exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index ae57bf69ad4a..04ba035d67e9 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* .
*/
- sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info");
+ sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name);
/*
* Execute the command to gather DNS info.
@@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* Enabled: DHCP enabled.
*/
- sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name);
+ sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name);
file = popen(cmd, "r");
if (file == NULL)
@@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
* invoke the external script to do its magic.
*/
- str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s",
- "hv_set_ifconfig", if_filename, nm_filename);
+ str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s",
+ KVP_SCRIPTS_PATH "hv_set_ifconfig",
+ if_filename, nm_filename);
/*
* This is a little overcautious, but it's necessary to suppress some
* false warnings from gcc 8.0.1.
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index 440a91b35823..2f8baed2b8f7 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1
cp $1 /etc/sysconfig/network-scripts/
-chmod 600 $2
+umask 0177
interface=$(echo $2 | awk -F - '{ print $2 }')
filename="${2##*/}"
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4ce176ad411f..76060da755b5 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
case INSN_CONTEXT_SWITCH:
- if (func && (!next_insn || !next_insn->hint)) {
- WARN_INSN(insn, "unsupported instruction in callable function");
- return 1;
+ if (func) {
+ if (!next_insn || !next_insn->hint) {
+ WARN_INSN(insn, "unsupported instruction in callable function");
+ return 1;
+ }
+ break;
}
return 0;