aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/include/asm/processor.h2
-rw-r--r--arch/alpha/kernel/process.c5
-rw-r--r--arch/arc/Kconfig1
-rw-r--r--arch/arc/include/asm/cacheflush.h1
-rw-r--r--arch/arc/include/asm/pgtable.h5
-rw-r--r--arch/arc/include/asm/processor.h2
-rw-r--r--arch/arc/kernel/irq.c10
-rw-r--r--arch/arc/kernel/stacktrace.c4
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/boot/compressed/decompress.c3
-rw-r--r--arch/arm/boot/dts/bcm2711-rpi-4-b.dts11
-rw-r--r--arch/arm/boot/dts/bcm2711.dtsi12
-rw-r--r--arch/arm/boot/dts/bcm2835-common.dtsi8
-rw-r--r--arch/arm/boot/dts/bcm283x.dtsi8
-rw-r--r--arch/arm/boot/dts/spear3xx.dtsi2
-rw-r--r--arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts2
-rw-r--r--arch/arm/configs/multi_v7_defconfig1
-rw-r--r--arch/arm/configs/oxnas_v6_defconfig1
-rw-r--r--arch/arm/configs/shmobile_defconfig1
-rw-r--r--arch/arm/include/asm/arch_timer.h37
-rw-r--r--arch/arm/include/asm/cacheflush.h1
-rw-r--r--arch/arm/include/asm/processor.h2
-rw-r--r--arch/arm/include/asm/uaccess.h4
-rw-r--r--arch/arm/kernel/entry-armv.S5
-rw-r--r--arch/arm/kernel/head.S4
-rw-r--r--arch/arm/kernel/irq.c14
-rw-r--r--arch/arm/kernel/process.c4
-rw-r--r--arch/arm/kernel/traps.c2
-rw-r--r--arch/arm/kernel/vmlinux-xip.lds.S6
-rw-r--r--arch/arm/mach-bcm/Kconfig4
-rw-r--r--arch/arm/mach-imx/avic.c2
-rw-r--r--arch/arm/mach-imx/src.c40
-rw-r--r--arch/arm/mach-imx/tzic.c2
-rw-r--r--arch/arm/mach-omap1/irq.c2
-rw-r--r--arch/arm/mach-omap2/Kconfig1
-rw-r--r--arch/arm/mach-s3c/irq-s3c24xx.c2
-rw-r--r--arch/arm/mm/proc-macros.S1
-rw-r--r--arch/arm/probes/kprobes/core.c2
-rw-r--r--arch/arm/tools/syscall.tbl1
-rw-r--r--arch/arm64/Kconfig10
-rw-r--r--arch/arm64/Kconfig.platforms4
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts8
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi8
-rw-r--r--arch/arm64/boot/dts/qcom/sm8250.dtsi3
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/include/asm/arch_timer.h52
-rw-r--r--arch/arm64/include/asm/processor.h2
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h2
-rw-r--r--arch/arm64/kernel/entry-common.c52
-rw-r--r--arch/arm64/kernel/process.c4
-rw-r--r--arch/arm64/kernel/topology.c2
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/gfp.h1
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c13
-rw-r--r--arch/arm64/kvm/hyp/nvhe/page_alloc.c15
-rw-r--r--arch/arm64/kvm/mmu.c6
-rw-r--r--arch/arm64/mm/hugetlbpage.c2
-rw-r--r--arch/arm64/net/bpf_jit_comp.c5
-rw-r--r--arch/csky/Kconfig4
-rw-r--r--arch/csky/include/asm/bitops.h1
-rw-r--r--arch/csky/include/asm/processor.h2
-rw-r--r--arch/csky/kernel/entry.S2
-rw-r--r--arch/csky/kernel/irq.c5
-rw-r--r--arch/csky/kernel/ptrace.c3
-rw-r--r--arch/csky/kernel/signal.c4
-rw-r--r--arch/csky/kernel/stacktrace.c5
-rw-r--r--arch/h8300/include/asm/irq.h2
-rw-r--r--arch/h8300/include/asm/processor.h2
-rw-r--r--arch/h8300/kernel/irq.c1
-rw-r--r--arch/h8300/kernel/process.c5
-rw-r--r--arch/hexagon/include/asm/processor.h2
-rw-r--r--arch/hexagon/kernel/process.c4
-rw-r--r--arch/ia64/include/asm/processor.h2
-rw-r--r--arch/ia64/include/asm/spinlock.h23
-rw-r--r--arch/ia64/kernel/process.c5
-rw-r--r--arch/m68k/emu/nfblock.c12
-rw-r--r--arch/m68k/include/asm/cacheflush_mm.h1
-rw-r--r--arch/m68k/include/asm/processor.h2
-rw-r--r--arch/m68k/kernel/process.c4
-rw-r--r--arch/microblaze/include/asm/processor.h2
-rw-r--r--arch/microblaze/kernel/process.c2
-rw-r--r--arch/mips/Kconfig2
-rw-r--r--arch/mips/cavium-octeon/octeon-irq.c5
-rw-r--r--arch/mips/include/asm/cacheflush.h2
-rw-r--r--arch/mips/include/asm/processor.h2
-rw-r--r--arch/mips/kernel/irq.c8
-rw-r--r--arch/mips/kernel/process.c8
-rw-r--r--arch/mips/kernel/smp-bmips.c3
-rw-r--r--arch/mips/loongson64/smp.c1
-rw-r--r--arch/mips/rb532/prom.c1
-rw-r--r--arch/mips/sibyte/common/cfe.c1
-rw-r--r--arch/mips/sibyte/swarm/setup.c1
-rw-r--r--arch/nds32/Kconfig1
-rw-r--r--arch/nds32/include/asm/cacheflush.h1
-rw-r--r--arch/nds32/include/asm/processor.h2
-rw-r--r--arch/nds32/kernel/ftrace.c2
-rw-r--r--arch/nds32/kernel/process.c7
-rw-r--r--arch/nios2/include/asm/cacheflush.h3
-rw-r--r--arch/nios2/include/asm/irqflags.h4
-rw-r--r--arch/nios2/include/asm/processor.h2
-rw-r--r--arch/nios2/include/asm/registers.h2
-rw-r--r--arch/nios2/kernel/process.c5
-rw-r--r--arch/nios2/platform/Kconfig.platform1
-rw-r--r--arch/openrisc/Kconfig1
-rw-r--r--arch/openrisc/include/asm/processor.h2
-rw-r--r--arch/openrisc/include/asm/spinlock.h3
-rw-r--r--arch/openrisc/kernel/entry.S4
-rw-r--r--arch/openrisc/kernel/irq.c5
-rw-r--r--arch/openrisc/kernel/process.c2
-rw-r--r--arch/openrisc/mm/init.c1
-rw-r--r--arch/parisc/include/asm/cacheflush.h3
-rw-r--r--arch/parisc/include/asm/processor.h2
-rw-r--r--arch/parisc/include/asm/spinlock.h15
-rw-r--r--arch/parisc/kernel/process.c5
-rw-r--r--arch/powerpc/include/asm/processor.h2
-rw-r--r--arch/powerpc/include/asm/simple_spinlock.h21
-rw-r--r--arch/powerpc/kernel/idle_book3s.S10
-rw-r--r--arch/powerpc/kernel/process.c9
-rw-r--r--arch/powerpc/kernel/smp.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S28
-rw-r--r--arch/powerpc/perf/isa207-common.c26
-rw-r--r--arch/powerpc/perf/isa207-common.h2
-rw-r--r--arch/powerpc/platforms/cell/spufs/inode.c1
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c27
-rw-r--r--arch/powerpc/sysdev/xive/common.c3
-rw-r--r--arch/riscv/Kconfig7
-rw-r--r--arch/riscv/include/asm/kasan.h3
-rw-r--r--arch/riscv/include/asm/processor.h2
-rw-r--r--arch/riscv/kernel/entry.S3
-rw-r--r--arch/riscv/kernel/head.S1
-rw-r--r--arch/riscv/kernel/smp.c9
-rw-r--r--arch/riscv/kernel/stacktrace.c12
-rw-r--r--arch/riscv/mm/kasan_init.c14
-rw-r--r--arch/riscv/net/bpf_jit_core.c8
-rw-r--r--arch/s390/include/asm/processor.h2
-rw-r--r--arch/s390/include/asm/spinlock.h8
-rw-r--r--arch/s390/kernel/process.c4
-rw-r--r--arch/s390/kvm/gaccess.c12
-rw-r--r--arch/s390/kvm/intercept.c4
-rw-r--r--arch/s390/kvm/interrupt.c5
-rw-r--r--arch/s390/kvm/kvm-s390.c1
-rw-r--r--arch/s390/lib/string.c15
-rw-r--r--arch/sh/include/asm/cacheflush.h3
-rw-r--r--arch/sh/include/asm/processor_32.h2
-rw-r--r--arch/sh/kernel/process_32.c5
-rw-r--r--arch/sparc/include/asm/processor_32.h2
-rw-r--r--arch/sparc/include/asm/processor_64.h2
-rw-r--r--arch/sparc/kernel/process_32.c5
-rw-r--r--arch/sparc/kernel/process_64.c5
-rw-r--r--arch/um/drivers/ubd_kern.c14
-rw-r--r--arch/um/include/asm/processor-generic.h2
-rw-r--r--arch/um/kernel/process.c5
-rw-r--r--arch/um/kernel/um_arch.c4
-rw-r--r--arch/x86/Kconfig11
-rw-r--r--arch/x86/crypto/sm4-aesni-avx-asm_64.S6
-rw-r--r--arch/x86/crypto/sm4-aesni-avx2-asm_64.S6
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl1
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl1
-rw-r--r--arch/x86/events/core.c6
-rw-r--r--arch/x86/events/intel/bts.c6
-rw-r--r--arch/x86/events/intel/core.c21
-rw-r--r--arch/x86/events/intel/ds.c5
-rw-r--r--arch/x86/events/intel/uncore_discovery.h2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c16
-rw-r--r--arch/x86/events/msr.c1
-rw-r--r--arch/x86/events/perf_event.h1
-rw-r--r--arch/x86/include/asm/GEN-for-each-reg.h14
-rw-r--r--arch/x86/include/asm/alternative.h1
-rw-r--r--arch/x86/include/asm/asm-prototypes.h18
-rw-r--r--arch/x86/include/asm/irq_stack.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h5
-rw-r--r--arch/x86/include/asm/nospec-branch.h72
-rw-r--r--arch/x86/include/asm/paravirt.h31
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/ptrace.h2
-rw-r--r--arch/x86/include/asm/smp.h7
-rw-r--r--arch/x86/include/asm/topology.h3
-rw-r--r--arch/x86/include/asm/xen/hypercall.h6
-rw-r--r--arch/x86/kernel/alternative.c191
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c27
-rw-r--r--arch/x86/kernel/cpu/bugs.c7
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c1
-rw-r--r--arch/x86/kernel/cpu/common.c3
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/irqflags.S2
-rw-r--r--arch/x86/kernel/itmt.c2
-rw-r--r--arch/x86/kernel/module.c9
-rw-r--r--arch/x86/kernel/paravirt.c45
-rw-r--r--arch/x86/kernel/process.c65
-rw-r--r--arch/x86/kernel/sev-shared.c2
-rw-r--r--arch/x86/kernel/smpboot.c44
-rw-r--r--arch/x86/kernel/vmlinux.lds.S14
-rw-r--r--arch/x86/kvm/lapic.c20
-rw-r--r--arch/x86/kvm/mmu/mmu.c6
-rw-r--r--arch/x86/kvm/svm/sev.c29
-rw-r--r--arch/x86/kvm/svm/svm.h10
-rw-r--r--arch/x86/kvm/svm/svm_ops.h4
-rw-r--r--arch/x86/kvm/vmx/evmcs.h4
-rw-r--r--arch/x86/kvm/vmx/vmx.c32
-rw-r--r--arch/x86/kvm/x86.c189
-rw-r--r--arch/x86/kvm/xen.c27
-rw-r--r--arch/x86/lib/retpoline.S56
-rw-r--r--arch/x86/net/bpf_jit_comp.c160
-rw-r--r--arch/x86/net/bpf_jit_comp32.c22
-rw-r--r--arch/x86/xen/enlighten_pv.c70
-rw-r--r--arch/x86/xen/irq.c31
-rw-r--r--arch/x86/xen/mmu_pv.c93
-rw-r--r--arch/x86/xen/xen-asm.S79
-rw-r--r--arch/x86/xen/xen-head.S34
-rw-r--r--arch/xtensa/include/asm/cacheflush.h5
-rw-r--r--arch/xtensa/include/asm/processor.h2
-rw-r--r--arch/xtensa/kernel/process.c5
-rw-r--r--arch/xtensa/platforms/iss/simdisk.c16
214 files changed, 1414 insertions, 1044 deletions
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 6100431da07a..090499c99c1c 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -42,7 +42,7 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
struct task_struct;
extern void release_thread(struct task_struct *);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index a5123ea426ce..5f8527081da9 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -376,12 +376,11 @@ thread_saved_pc(struct task_struct *t)
}
unsigned long
-get_wchan(struct task_struct *p)
+__get_wchan(struct task_struct *p)
{
unsigned long schedule_frame;
unsigned long pc;
- if (!p || p == current || task_is_running(p))
- return 0;
+
/*
* This one depends on the frame size of schedule(). Do a
* "disass schedule" in gdb to find the frame size. Also, the
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 3a5a80f302e1..b4ae6058902a 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -40,7 +40,6 @@ config ARC
select HAVE_KRETPROBES
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_PERF_EVENTS
- select HANDLE_DOMAIN_IRQ
select IRQ_DOMAIN
select MODULES_USE_ELF_RELA
select OF
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index e201b4b1655a..e8c2c7469e10 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -36,6 +36,7 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
void dma_cache_inv(phys_addr_t start, unsigned long sz);
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 9320b04c04bf..4cf45a99fd79 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -26,11 +26,6 @@ extern char empty_zero_page[PAGE_SIZE];
extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
-/* Macro to mark a page protection as uncacheable */
-#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) & ~_PAGE_CACHEABLE))
-
-extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
-
/* to cope with aliasing VIPT cache */
#define HAVE_ARCH_UNMAPPED_AREA
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f28afcf5c6d1..54db9d7bb562 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -70,7 +70,7 @@ struct task_struct;
extern void start_thread(struct pt_regs * regs, unsigned long pc,
unsigned long usp);
-extern unsigned int get_wchan(struct task_struct *p);
+extern unsigned int __get_wchan(struct task_struct *p);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index ef909dd4b40c..dd09b58ff82d 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -6,6 +6,8 @@
#include <linux/interrupt.h>
#include <linux/irqchip.h>
#include <asm/mach_desc.h>
+
+#include <asm/irq_regs.h>
#include <asm/smp.h>
/*
@@ -39,5 +41,11 @@ void __init init_IRQ(void)
*/
void arch_do_IRQ(unsigned int hwirq, struct pt_regs *regs)
{
- handle_domain_irq(NULL, hwirq, regs);
+ struct pt_regs *old_regs;
+
+ irq_enter();
+ old_regs = set_irq_regs(regs);
+ generic_handle_domain_irq(NULL, hwirq);
+ set_irq_regs(old_regs);
+ irq_exit();
}
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index c376ff3147e7..5372dc04e784 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -15,7 +15,7 @@
* = specifics of data structs where trace is saved(CONFIG_STACKTRACE etc)
*
* vineetg: March 2009
- * -Implemented correct versions of thread_saved_pc() and get_wchan()
+ * -Implemented correct versions of thread_saved_pc() and __get_wchan()
*
* rajeshwarr: 2008
* -Initial implementation
@@ -248,7 +248,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
* Of course just returning schedule( ) would be pointless so unwind until
* the function is not in schedular code
*/
-unsigned int get_wchan(struct task_struct *tsk)
+unsigned int __get_wchan(struct task_struct *tsk)
{
return arc_unwind_core(tsk, NULL, __get_first_nonsched, NULL);
}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 59baf6c132a7..2c056c0e834e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -64,7 +64,6 @@ config ARM
select GENERIC_PCI_IOMAP
select GENERIC_SCHED_CLOCK
select GENERIC_SMP_IDLE_THREAD
- select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT
select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
@@ -92,6 +91,7 @@ config ARM
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index aa075d8372ea..74255e819831 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -47,7 +47,10 @@ extern char * strchrnul(const char *, int);
#endif
#ifdef CONFIG_KERNEL_XZ
+/* Prevent KASAN override of string helpers in decompressor */
+#undef memmove
#define memmove memmove
+#undef memcpy
#define memcpy memcpy
#include "../../../../lib/decompress_unxz.c"
#endif
diff --git a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts
index f24bdd0870a5..72ce80fbf266 100644
--- a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts
+++ b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts
@@ -40,8 +40,8 @@
regulator-always-on;
regulator-settling-time-us = <5000>;
gpios = <&expgpio 4 GPIO_ACTIVE_HIGH>;
- states = <1800000 0x1
- 3300000 0x0>;
+ states = <1800000 0x1>,
+ <3300000 0x0>;
status = "okay";
};
@@ -217,15 +217,16 @@
};
&pcie0 {
- pci@1,0 {
+ pci@0,0 {
+ device_type = "pci";
#address-cells = <3>;
#size-cells = <2>;
ranges;
reg = <0 0 0 0 0>;
- usb@1,0 {
- reg = <0x10000 0 0 0 0>;
+ usb@0,0 {
+ reg = <0 0 0 0 0>;
resets = <&reset RASPBERRYPI_FIRMWARE_RESET_ID_USB>;
};
};
diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi
index b8a4096192aa..3b60297af7f6 100644
--- a/arch/arm/boot/dts/bcm2711.dtsi
+++ b/arch/arm/boot/dts/bcm2711.dtsi
@@ -300,6 +300,14 @@
status = "disabled";
};
+ vec: vec@7ec13000 {
+ compatible = "brcm,bcm2711-vec";
+ reg = <0x7ec13000 0x1000>;
+ clocks = <&clocks BCM2835_CLOCK_VEC>;
+ interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
dvp: clock@7ef00000 {
compatible = "brcm,brcm2711-dvp";
reg = <0x7ef00000 0x10>;
@@ -532,8 +540,8 @@
compatible = "brcm,genet-mdio-v5";
reg = <0xe14 0x8>;
reg-names = "mdio";
- #address-cells = <0x0>;
- #size-cells = <0x1>;
+ #address-cells = <0x1>;
+ #size-cells = <0x0>;
};
};
};
diff --git a/arch/arm/boot/dts/bcm2835-common.dtsi b/arch/arm/boot/dts/bcm2835-common.dtsi
index 4119271c979d..c25e797b9060 100644
--- a/arch/arm/boot/dts/bcm2835-common.dtsi
+++ b/arch/arm/boot/dts/bcm2835-common.dtsi
@@ -106,6 +106,14 @@
status = "okay";
};
+ vec: vec@7e806000 {
+ compatible = "brcm,bcm2835-vec";
+ reg = <0x7e806000 0x1000>;
+ clocks = <&clocks BCM2835_CLOCK_VEC>;
+ interrupts = <2 27>;
+ status = "disabled";
+ };
+
pixelvalve@7e807000 {
compatible = "brcm,bcm2835-pixelvalve2";
reg = <0x7e807000 0x100>;
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 0f3be55201a5..a3e06b680947 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -464,14 +464,6 @@
status = "disabled";
};
- vec: vec@7e806000 {
- compatible = "brcm,bcm2835-vec";
- reg = <0x7e806000 0x1000>;
- clocks = <&clocks BCM2835_CLOCK_VEC>;
- interrupts = <2 27>;
- status = "disabled";
- };
-
usb: usb@7e980000 {
compatible = "brcm,bcm2835-usb";
reg = <0x7e980000 0x10000>;
diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi
index f266b7b03482..cc88ebe7a60c 100644
--- a/arch/arm/boot/dts/spear3xx.dtsi
+++ b/arch/arm/boot/dts/spear3xx.dtsi
@@ -47,7 +47,7 @@
};
gmac: eth@e0800000 {
- compatible = "st,spear600-gmac";
+ compatible = "snps,dwmac-3.40a";
reg = <0xe0800000 0x8000>;
interrupts = <23 22>;
interrupt-names = "macirq", "eth_wake_irq";
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
index 8077f1716fbc..ecb91fb899ff 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
@@ -112,7 +112,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index b4f74454f20f..33572998dbbe 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -197,7 +197,6 @@ CONFIG_PCI_EPF_TEST=m
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_OMAP_OCP2SCP=y
-CONFIG_SIMPLE_PM_BUS=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/oxnas_v6_defconfig b/arch/arm/configs/oxnas_v6_defconfig
index cae0db6b4eaf..de37f7e90999 100644
--- a/arch/arm/configs/oxnas_v6_defconfig
+++ b/arch/arm/configs/oxnas_v6_defconfig
@@ -46,7 +46,6 @@ CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=64
-CONFIG_SIMPLE_PM_BUS=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index d9a27e4e0914..18d2a960b2d2 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -40,7 +40,6 @@ CONFIG_PCI_RCAR_GEN2=y
CONFIG_PCIE_RCAR_HOST=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_SIMPLE_PM_BUS=y
CONFIG_MTD=y
CONFIG_MTD_BLOCK=y
CONFIG_MTD_CFI=y
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 99175812d903..bb129b6d2366 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -7,6 +7,7 @@
#include <asm/hwcap.h>
#include <linux/clocksource.h>
#include <linux/init.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/types.h>
#include <clocksource/arm_arch_timer.h>
@@ -24,29 +25,35 @@ int arch_timer_arch_init(void);
* the code. At least it does so with a recent GCC (4.6.3).
*/
static __always_inline
-void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u64 val)
{
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
+ asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" ((u32)val));
+ isb();
break;
- case ARCH_TIMER_REG_TVAL:
- asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
+ case ARCH_TIMER_REG_CVAL:
+ asm volatile("mcrr p15, 2, %Q0, %R0, c14" : : "r" (val));
break;
+ default:
+ BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
+ asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" ((u32)val));
+ isb();
break;
- case ARCH_TIMER_REG_TVAL:
- asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
+ case ARCH_TIMER_REG_CVAL:
+ asm volatile("mcrr p15, 3, %Q0, %R0, c14" : : "r" (val));
break;
+ default:
+ BUILD_BUG();
}
+ } else {
+ BUILD_BUG();
}
-
- isb();
}
static __always_inline
@@ -59,19 +66,19 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
case ARCH_TIMER_REG_CTRL:
asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
break;
- case ARCH_TIMER_REG_TVAL:
- asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
- break;
+ default:
+ BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
break;
- case ARCH_TIMER_REG_TVAL:
- asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
- break;
+ default:
+ BUILD_BUG();
}
+ } else {
+ BUILD_BUG();
}
return val;
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 5e56288e343b..e68fb879e4f9 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -290,6 +290,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
*/
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *folio);
#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
static inline void flush_kernel_vmap_range(void *addr, int size)
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 9e6b97286307..6af68edfa53a 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -84,7 +84,7 @@ struct task_struct;
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 084d1c07c2d0..36fbc3329252 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -176,6 +176,7 @@ extern int __get_user_64t_4(void *);
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
unsigned int __ua_flags = uaccess_save_and_enable(); \
+ int __tmp_e; \
switch (sizeof(*(__p))) { \
case 1: \
if (sizeof((x)) >= 8) \
@@ -203,9 +204,10 @@ extern int __get_user_64t_4(void *);
break; \
default: __e = __get_user_bad(); break; \
} \
+ __tmp_e = __e; \
uaccess_restore(__ua_flags); \
x = (typeof(*(p))) __r2; \
- __e; \
+ __tmp_e; \
})
#define get_user(x, p) \
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 241b73d64df7..3d0b6169ab86 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -38,14 +38,11 @@
*/
.macro irq_handler
#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
- ldr r1, =handle_arch_irq
mov r0, sp
- badr lr, 9997f
- ldr pc, [r1]
+ bl generic_handle_arch_irq
#else
arch_irq_handler_default
#endif
-9997:
.endm
.macro pabt_helper
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29070eb8df7d..3fc7f9750ce4 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -253,7 +253,7 @@ __create_page_tables:
add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
ldr r6, =(_end - 1)
adr_l r5, kernel_sec_start @ _pa(kernel_sec_start)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
str r8, [r5, #4] @ Save physical start of kernel (BE)
#else
str r8, [r5] @ Save physical start of kernel (LE)
@@ -266,7 +266,7 @@ __create_page_tables:
bls 1b
eor r3, r3, r7 @ Remove the MMU flags
adr_l r5, kernel_sec_end @ _pa(kernel_sec_end)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
str r3, [r5, #4] @ Save physical end of kernel (BE)
#else
str r3, [r5] @ Save physical end of kernel (LE)
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 20ab1e607522..b79975bd988c 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -63,11 +63,8 @@ int arch_show_interrupts(struct seq_file *p, int prec)
*/
void handle_IRQ(unsigned int irq, struct pt_regs *regs)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
struct irq_desc *desc;
- irq_enter();
-
/*
* Some hardware gives randomly wrong interrupts. Rather
* than crashing, do something sensible.
@@ -81,9 +78,6 @@ void handle_IRQ(unsigned int irq, struct pt_regs *regs)
handle_irq_desc(desc);
else
ack_bad_irq(irq);
-
- irq_exit();
- set_irq_regs(old_regs);
}
/*
@@ -92,7 +86,15 @@ void handle_IRQ(unsigned int irq, struct pt_regs *regs)
asmlinkage void __exception_irq_entry
asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
{
+ struct pt_regs *old_regs;
+
+ irq_enter();
+ old_regs = set_irq_regs(regs);
+
handle_IRQ(irq, regs);
+
+ set_irq_regs(old_regs);
+ irq_exit();
}
void __init init_IRQ(void)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 0e2d3051741e..96f577e59595 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -276,13 +276,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
return 0;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
struct stackframe frame;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 4a7edc6e848f..195dff58bafc 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -136,7 +136,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
if (p >= bottom && p < top) {
unsigned long val;
- if (get_kernel_nofault(val, (unsigned long *)p))
+ if (!get_kernel_nofault(val, (unsigned long *)p))
sprintf(str + i * 9, " %08lx", val);
else
sprintf(str + i * 9, " ????????");
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 50136828f5b5..f14c2360ea0b 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -40,6 +40,10 @@ SECTIONS
ARM_DISCARD
*(.alt.smp.init)
*(.pv_table)
+#ifndef CONFIG_ARM_UNWIND
+ *(.ARM.exidx) *(.ARM.exidx.*)
+ *(.ARM.extab) *(.ARM.extab.*)
+#endif
}
. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
@@ -172,7 +176,7 @@ ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA")
#endif
-#ifdef CONFIG_ARM_MPU
+#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST)
/*
* Due to PMSAv7 restriction on base address and size we have to
* enforce minimal alignment restrictions. It was seen that weaker
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 2890e61b2b46..bd3f82788ebc 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -161,7 +161,6 @@ config ARCH_BCM2835
select ARM_TIMER_SP804
select HAVE_ARM_ARCH_TIMER if ARCH_MULTI_V7
select BCM2835_TIMER
- select BRCMSTB_L2_IRQ
select PINCTRL
select PINCTRL_BCM2835
select MFD_CORE
@@ -209,9 +208,6 @@ config ARCH_BRCMSTB
select ARM_GIC
select ARM_ERRATA_798181 if SMP
select HAVE_ARM_ARCH_TIMER
- select BCM7038_L1_IRQ
- select BRCMSTB_L2_IRQ
- select BCM7120_L2_IRQ
select ZONE_DMA if ARM_LPAE
select SOC_BRCMSTB
select SOC_BUS
diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index 21bce4049cec..cf6546ddc7a3 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -154,7 +154,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs)
if (nivector == 0xffff)
break;
- handle_domain_irq(domain, nivector, regs);
+ generic_handle_domain_irq(domain, nivector);
} while (1);
}
diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c
index 95fd1fbb0826..59a8e8cc4469 100644
--- a/arch/arm/mach-imx/src.c
+++ b/arch/arm/mach-imx/src.c
@@ -9,6 +9,7 @@
#include <linux/iopoll.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/platform_device.h>
#include <linux/reset-controller.h>
#include <linux/smp.h>
#include <asm/smp_plat.h>
@@ -81,11 +82,6 @@ static const struct reset_control_ops imx_src_ops = {
.reset = imx_src_reset_module,
};
-static struct reset_controller_dev imx_reset_controller = {
- .ops = &imx_src_ops,
- .nr_resets = ARRAY_SIZE(sw_reset_bits),
-};
-
static void imx_gpcv2_set_m_core_pgc(bool enable, u32 offset)
{
writel_relaxed(enable, gpc_base + offset);
@@ -177,10 +173,6 @@ void __init imx_src_init(void)
src_base = of_iomap(np, 0);
WARN_ON(!src_base);
- imx_reset_controller.of_node = np;
- if (IS_ENABLED(CONFIG_RESET_CONTROLLER))
- reset_controller_register(&imx_reset_controller);
-
/*
* force warm reset sources to generate cold reset
* for a more reliable restart
@@ -214,3 +206,33 @@ void __init imx7_src_init(void)
if (!gpc_base)
return;
}
+
+static const struct of_device_id imx_src_dt_ids[] = {
+ { .compatible = "fsl,imx51-src" },
+ { /* sentinel */ }
+};
+
+static int imx_src_probe(struct platform_device *pdev)
+{
+ struct reset_controller_dev *rcdev;
+
+ rcdev = devm_kzalloc(&pdev->dev, sizeof(*rcdev), GFP_KERNEL);
+ if (!rcdev)
+ return -ENOMEM;
+
+ rcdev->ops = &imx_src_ops;
+ rcdev->dev = &pdev->dev;
+ rcdev->of_node = pdev->dev.of_node;
+ rcdev->nr_resets = ARRAY_SIZE(sw_reset_bits);
+
+ return devm_reset_controller_register(&pdev->dev, rcdev);
+}
+
+static struct platform_driver imx_src_driver = {
+ .driver = {
+ .name = "imx-src",
+ .of_match_table = imx_src_dt_ids,
+ },
+ .probe = imx_src_probe,
+};
+builtin_platform_driver(imx_src_driver);
diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c
index 479a01bdac56..8b3d98d288d9 100644
--- a/arch/arm/mach-imx/tzic.c
+++ b/arch/arm/mach-imx/tzic.c
@@ -134,7 +134,7 @@ static void __exception_irq_entry tzic_handle_irq(struct pt_regs *regs)
while (stat) {
handled = 1;
irqofs = fls(stat) - 1;
- handle_domain_irq(domain, irqofs + i * 32, regs);
+ generic_handle_domain_irq(domain, irqofs + i * 32);
stat &= ~(1 << irqofs);
}
}
diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c
index b11edc8a46f0..ee6a93083154 100644
--- a/arch/arm/mach-omap1/irq.c
+++ b/arch/arm/mach-omap1/irq.c
@@ -165,7 +165,7 @@ asmlinkage void __exception_irq_entry omap1_handle_irq(struct pt_regs *regs)
}
irq:
if (irqnr)
- handle_domain_irq(domain, irqnr, regs);
+ generic_handle_domain_irq(domain, irqnr);
else
break;
} while (irqnr);
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 7f13adf26e61..02c253de9b6e 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -112,7 +112,6 @@ config ARCH_OMAP2PLUS
select PM_GENERIC_DOMAINS
select PM_GENERIC_DOMAINS_OF
select RESET_CONTROLLER
- select SIMPLE_PM_BUS
select SOC_BUS
select TI_SYSC
select OMAP_IRQCHIP
diff --git a/arch/arm/mach-s3c/irq-s3c24xx.c b/arch/arm/mach-s3c/irq-s3c24xx.c
index 3edc5f614eef..45dfd546e6fa 100644
--- a/arch/arm/mach-s3c/irq-s3c24xx.c
+++ b/arch/arm/mach-s3c/irq-s3c24xx.c
@@ -354,7 +354,7 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
if (!(pnd & (1 << offset)))
offset = __ffs(pnd);
- handle_domain_irq(intc->domain, intc_offset + offset, regs);
+ generic_handle_domain_irq(intc->domain, intc_offset + offset);
return true;
}
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e2c743aa2eb2..d9f7dfe2a7ed 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -340,6 +340,7 @@ ENTRY(\name\()_cache_fns)
.macro define_tlb_functions name:req, flags_up:req, flags_smp
.type \name\()_tlb_fns, #object
+ .align 2
ENTRY(\name\()_tlb_fns)
.long \name\()_flush_user_tlb_range
.long \name\()_flush_kern_tlb_range
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 27e0af78e88b..9d8634e2f12f 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -439,7 +439,7 @@ static struct undef_hook kprobes_arm_break_hook = {
#endif /* !CONFIG_THUMB2_KERNEL */
-int __init arch_init_kprobes()
+int __init arch_init_kprobes(void)
{
arm_probes_decode_init();
#ifdef CONFIG_THUMB2_KERNEL
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index e842209e135d..543100151f2b 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -462,3 +462,4 @@
446 common landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fee914c716aa..bc8d3702f4ed 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -133,7 +133,6 @@ config ARM64
select GENERIC_TIME_VSYSCALL
select GENERIC_GETTIMEOFDAY
select GENERIC_VDSO_TIME_NS
- select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_MOVE_PMD
select HAVE_MOVE_PUD
@@ -989,6 +988,15 @@ config SCHED_MC
making when dealing with multi-core CPU chips at a cost of slightly
increased overhead in some places. If unsure say N here.
+config SCHED_CLUSTER
+ bool "Cluster scheduler support"
+ help
+ Cluster scheduler support improves the CPU scheduler's decision
+ making when dealing with machines that have clusters of CPUs.
+ Cluster usually means a couple of CPUs which are placed closely
+ by sharing mid-level caches, last-level cache tags or internal
+ busses.
+
config SCHED_SMT
bool "SMT scheduler support"
help
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index b0ce18d4cc98..96a81967c3bf 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -44,7 +44,6 @@ config ARCH_BCM2835
select ARM_AMBA
select ARM_GIC
select ARM_TIMER_SP804
- select BRCMSTB_L2_IRQ
help
This enables support for the Broadcom BCM2837 and BCM2711 SoC.
These SoCs are used in the Raspberry Pi 3 and 4 devices.
@@ -82,8 +81,6 @@ config ARCH_BITMAIN
config ARCH_BRCMSTB
bool "Broadcom Set-Top-Box SoCs"
select ARCH_HAS_RESET_CONTROLLER
- select BCM7038_L1_IRQ
- select BRCMSTB_L2_IRQ
select GENERIC_IRQ_CHIP
select PINCTRL
help
@@ -167,7 +164,6 @@ config ARCH_MEDIATEK
config ARCH_MESON
bool "Amlogic Platforms"
select COMMON_CLK
- select MESON_IRQ_GPIO
help
This enables support for the arm64 based Amlogic SoCs
such as the s905, S905X/D, S912, A113X/D or S905X/D2
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
index 02f8e72f0cad..05486cccee1c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
@@ -75,7 +75,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <&reg_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
index d17abb515835..e99e7644ff39 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
@@ -70,7 +70,9 @@
regulator-name = "rst-usb-eth2";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb_eth2>;
- gpio = <&gpio3 2 GPIO_ACTIVE_LOW>;
+ gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ regulator-always-on;
};
reg_vdd_5v: regulator-5v {
@@ -95,7 +97,7 @@
clocks = <&osc_can>;
interrupt-parent = <&gpio4>;
interrupts = <28 IRQ_TYPE_EDGE_FALLING>;
- spi-max-frequency = <100000>;
+ spi-max-frequency = <10000000>;
vdd-supply = <&reg_vdd_3v3>;
xceiver-supply = <&reg_vdd_5v>;
};
@@ -111,7 +113,7 @@
&fec1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet>;
- phy-connection-type = "rgmii";
+ phy-connection-type = "rgmii-rxid";
phy-handle = <&ethphy>;
status = "okay";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
index 9db9b90bf2bc..42bbbb3f532b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
@@ -91,10 +91,12 @@
reg_vdd_soc: BUCK1 {
regulator-name = "buck1";
regulator-min-microvolt = <800000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <850000>;
regulator-boot-on;
regulator-always-on;
regulator-ramp-delay = <3125>;
+ nxp,dvs-run-voltage = <850000>;
+ nxp,dvs-standby-voltage = <800000>;
};
reg_vdd_arm: BUCK2 {
@@ -111,7 +113,7 @@
reg_vdd_dram: BUCK3 {
regulator-name = "buck3";
regulator-min-microvolt = <850000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <950000>;
regulator-boot-on;
regulator-always-on;
};
@@ -150,7 +152,7 @@
reg_vdd_snvs: LDO2 {
regulator-name = "ldo2";
- regulator-min-microvolt = <850000>;
+ regulator-min-microvolt = <800000>;
regulator-max-microvolt = <900000>;
regulator-boot-on;
regulator-always-on;
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 8c15d9fed08f..d12e4cbfc852 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -2590,9 +2590,10 @@
power-domains = <&dispcc MDSS_GDSC>;
clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+ <&gcc GCC_DISP_HF_AXI_CLK>,
<&gcc GCC_DISP_SF_AXI_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>;
- clock-names = "iface", "nrt_bus", "core";
+ clock-names = "iface", "bus", "nrt_bus", "core";
assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>;
assigned-clock-rates = <460000000>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 156d96afbbfc..545197bc0501 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -245,7 +245,6 @@ CONFIG_DEVTMPFS_MOUNT=y
CONFIG_FW_LOADER_USER_HELPER=y
CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y
CONFIG_HISILICON_LPC=y
-CONFIG_SIMPLE_PM_BUS=y
CONFIG_FSL_MC_BUS=y
CONFIG_TEGRA_ACONNECT=m
CONFIG_GNSS=m
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 88d20f04c64a..519ac1f7f859 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -32,7 +32,7 @@
({ \
const struct arch_timer_erratum_workaround *__wa; \
__wa = __this_cpu_read(timer_unstable_counter_workaround); \
- (__wa && __wa->h) ? __wa->h : arch_timer_##h; \
+ (__wa && __wa->h) ? ({ isb(); __wa->h;}) : arch_timer_##h; \
})
#else
@@ -52,8 +52,6 @@ struct arch_timer_erratum_workaround {
enum arch_timer_erratum_match_type match_type;
const void *id;
const char *desc;
- u32 (*read_cntp_tval_el0)(void);
- u32 (*read_cntv_tval_el0)(void);
u64 (*read_cntpct_el0)(void);
u64 (*read_cntvct_el0)(void);
int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
@@ -64,24 +62,15 @@ struct arch_timer_erratum_workaround {
DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
timer_unstable_counter_workaround);
-/* inline sysreg accessors that make erratum_handler() work */
-static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
-{
- return read_sysreg(cntp_tval_el0);
-}
-
-static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
-{
- return read_sysreg(cntv_tval_el0);
-}
-
static inline notrace u64 arch_timer_read_cntpct_el0(void)
{
+ isb();
return read_sysreg(cntpct_el0);
}
static inline notrace u64 arch_timer_read_cntvct_el0(void)
{
+ isb();
return read_sysreg(cntvct_el0);
}
@@ -102,51 +91,58 @@ static inline notrace u64 arch_timer_read_cntvct_el0(void)
* the code.
*/
static __always_inline
-void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u64 val)
{
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
write_sysreg(val, cntp_ctl_el0);
+ isb();
break;
- case ARCH_TIMER_REG_TVAL:
- write_sysreg(val, cntp_tval_el0);
+ case ARCH_TIMER_REG_CVAL:
+ write_sysreg(val, cntp_cval_el0);
break;
+ default:
+ BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
write_sysreg(val, cntv_ctl_el0);
+ isb();
break;
- case ARCH_TIMER_REG_TVAL:
- write_sysreg(val, cntv_tval_el0);
+ case ARCH_TIMER_REG_CVAL:
+ write_sysreg(val, cntv_cval_el0);
break;
+ default:
+ BUILD_BUG();
}
+ } else {
+ BUILD_BUG();
}
-
- isb();
}
static __always_inline
-u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
+u64 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
{
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
return read_sysreg(cntp_ctl_el0);
- case ARCH_TIMER_REG_TVAL:
- return arch_timer_reg_read_stable(cntp_tval_el0);
+ default:
+ BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
return read_sysreg(cntv_ctl_el0);
- case ARCH_TIMER_REG_TVAL:
- return arch_timer_reg_read_stable(cntv_tval_el0);
+ default:
+ BUILD_BUG();
}
}
- BUG();
+ BUILD_BUG();
+ unreachable();
}
static inline u32 arch_timer_get_cntfrq(void)
@@ -169,7 +165,6 @@ static __always_inline u64 __arch_counter_get_cntpct_stable(void)
{
u64 cnt;
- isb();
cnt = arch_timer_reg_read_stable(cntpct_el0);
arch_counter_enforce_ordering(cnt);
return cnt;
@@ -189,7 +184,6 @@ static __always_inline u64 __arch_counter_get_cntvct_stable(void)
{
u64 cnt;
- isb();
cnt = arch_timer_reg_read_stable(cntvct_el0);
arch_counter_enforce_ordering(cnt);
return cnt;
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ee2bdc1b9f5b..55ca034238ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -257,7 +257,7 @@ struct task_struct;
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
void update_sctlr_el1(u64 sctlr);
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 3cb206aea3db..6bdb5f5db438 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 449
+#define __NR_compat_syscalls 450
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 844f6ae58662..41ea1195e44b 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -903,6 +903,8 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
#define __NR_process_mrelease 448
__SYSCALL(__NR_process_mrelease, sys_process_mrelease)
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 32f9796c4ffe..f7408edf8571 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -17,6 +17,7 @@
#include <asm/daifflags.h>
#include <asm/esr.h>
#include <asm/exception.h>
+#include <asm/irq_regs.h>
#include <asm/kprobes.h>
#include <asm/mmu.h>
#include <asm/processor.h>
@@ -219,22 +220,6 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
lockdep_hardirqs_on(CALLER_ADDR0);
}
-static void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
-{
- if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
- arm64_enter_nmi(regs);
- else
- enter_from_kernel_mode(regs);
-}
-
-static void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
-{
- if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
- arm64_exit_nmi(regs);
- else
- exit_to_kernel_mode(regs);
-}
-
static void __sched arm64_preempt_schedule_irq(void)
{
lockdep_assert_irqs_disabled();
@@ -263,10 +248,14 @@ static void __sched arm64_preempt_schedule_irq(void)
static void do_interrupt_handler(struct pt_regs *regs,
void (*handler)(struct pt_regs *))
{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
if (on_thread_stack())
call_on_irq_stack(regs, handler);
else
handler(regs);
+
+ set_irq_regs(old_regs);
}
extern void (*handle_arch_irq)(struct pt_regs *);
@@ -432,13 +421,22 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs)
}
}
-static void noinstr el1_interrupt(struct pt_regs *regs,
- void (*handler)(struct pt_regs *))
+static __always_inline void __el1_pnmi(struct pt_regs *regs,
+ void (*handler)(struct pt_regs *))
{
- write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+ arm64_enter_nmi(regs);
+ do_interrupt_handler(regs, handler);
+ arm64_exit_nmi(regs);
+}
+
+static __always_inline void __el1_irq(struct pt_regs *regs,
+ void (*handler)(struct pt_regs *))
+{
+ enter_from_kernel_mode(regs);
- enter_el1_irq_or_nmi(regs);
+ irq_enter_rcu();
do_interrupt_handler(regs, handler);
+ irq_exit_rcu();
/*
* Note: thread_info::preempt_count includes both thread_info::count
@@ -449,7 +447,17 @@ static void noinstr el1_interrupt(struct pt_regs *regs,
READ_ONCE(current_thread_info()->preempt_count) == 0)
arm64_preempt_schedule_irq();
- exit_el1_irq_or_nmi(regs);
+ exit_to_kernel_mode(regs);
+}
+static void noinstr el1_interrupt(struct pt_regs *regs,
+ void (*handler)(struct pt_regs *))
+{
+ write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+
+ if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
+ __el1_pnmi(regs, handler);
+ else
+ __el1_irq(regs, handler);
}
asmlinkage void noinstr el1h_64_irq_handler(struct pt_regs *regs)
@@ -667,7 +675,9 @@ static void noinstr el0_interrupt(struct pt_regs *regs,
if (regs->pc & BIT(55))
arm64_apply_bp_hardening();
+ irq_enter_rcu();
do_interrupt_handler(regs, handler);
+ irq_exit_rcu();
exit_to_user_mode(regs);
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 40adb8cdbf5a..aacf2f5559a8 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -528,13 +528,11 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
return last;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
struct stackframe frame;
unsigned long stack_page, ret = 0;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
stack_page = (unsigned long)try_get_task_stack(p);
if (!stack_page)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 4dd14a6620c1..9ab78ad826e2 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -103,6 +103,8 @@ int __init parse_acpi_topology(void)
cpu_topology[cpu].thread_id = -1;
cpu_topology[cpu].core_id = topology_id;
}
+ topology_id = find_acpi_cpu_topology_cluster(cpu);
+ cpu_topology[cpu].cluster_id = topology_id;
topology_id = find_acpi_cpu_topology_package(cpu);
cpu_topology[cpu].package_id = topology_id;
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fb0f523d1492..0a048dc06a7d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -24,6 +24,7 @@ struct hyp_pool {
/* Allocation */
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
void hyp_get_page(struct hyp_pool *pool, void *addr);
void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..34eeb524b686 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
- return hyp_alloc_pages(&host_s2_pool, get_order(size));
+ void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+ hyp_split_page(hyp_virt_to_page(addr));
+
+ /*
+ * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+ * so there should be no need to free any of the tail pages to make the
+ * allocation exact.
+ */
+ WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+ return addr;
}
static void *host_s2_zalloc_page(void *pool)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 41fc25bdfb34..0bd7701ad1df 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
+ BUG_ON(!p->refcount);
p->refcount--;
return (p->refcount == 0);
}
@@ -193,6 +194,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
hyp_spin_unlock(&pool->lock);
}
+void hyp_split_page(struct hyp_page *p)
+{
+ unsigned short order = p->order;
+ unsigned int i;
+
+ p->order = 0;
+ for (i = 1; i < (1 << order); i++) {
+ struct hyp_page *tail = p + i;
+
+ tail->order = 0;
+ hyp_set_page_refcounted(tail);
+ }
+}
+
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
{
unsigned short i = order;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1a94a7ca48f2..69bd1732a299 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
* when updating the PG_mte_tagged page flag, see
* sanitise_mte_tags for more details.
*/
- if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
- return -EINVAL;
+ if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) {
+ ret = -EINVAL;
+ break;
+ }
if (vma->vm_flags & VM_PFNMAP) {
/* IO region dirty page logging not allowed */
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 23505fc35324..a8158c948966 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -43,7 +43,7 @@ void __init arm64_hugetlb_cma_reserve(void)
#ifdef CONFIG_ARM64_4K_PAGES
order = PUD_SHIFT - PAGE_SHIFT;
#else
- order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT;
+ order = CONT_PMD_SHIFT - PAGE_SHIFT;
#endif
/*
* HugeTLB CMA reservation is required for gigantic
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 41c23f474ea6..803e7773fa86 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1136,6 +1136,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 9d4d898df76b..aed2b3e734ee 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -8,7 +8,7 @@ config CSKY
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_QUEUED_RWLOCKS
- select ARCH_WANT_FRAME_POINTERS if !CPU_CK610
+ select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace)
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
select COMMON_CLK
select CLKSRC_MMIO
@@ -17,7 +17,6 @@ config CSKY
select CSKY_APB_INTC
select DMA_DIRECT_REMAP
select IRQ_DOMAIN
- select HANDLE_DOMAIN_IRQ
select DW_APB_TIMER_OF
select GENERIC_IOREMAP
select GENERIC_LIB_ASHLDI3
@@ -241,6 +240,7 @@ endchoice
menuconfig HAVE_TCM
bool "Tightly-Coupled/Sram Memory"
+ depends on !COMPILE_TEST
help
The implementation are not only used by TCM (Tightly-Coupled Meory)
but also used by sram on SOC bus. It follow existed linux tcm
diff --git a/arch/csky/include/asm/bitops.h b/arch/csky/include/asm/bitops.h
index 91818787d860..02b72a000767 100644
--- a/arch/csky/include/asm/bitops.h
+++ b/arch/csky/include/asm/bitops.h
@@ -74,7 +74,6 @@ static __always_inline unsigned long __fls(unsigned long x)
* bug fix, why only could use atomic!!!!
*/
#include <asm-generic/bitops/non-atomic.h>
-#define __clear_bit(nr, vaddr) clear_bit(nr, vaddr)
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic.h>
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index 9e933021fe8e..817dd60ff152 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -81,7 +81,7 @@ static inline void release_thread(struct task_struct *dead_task)
extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->usp)
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index 00e3c8ebf9b8..a4ababf25e24 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -249,7 +249,7 @@ ENTRY(csky_irq)
mov a0, sp
- jbsr csky_do_IRQ
+ jbsr generic_handle_arch_irq
jmpi ret_from_exception
diff --git a/arch/csky/kernel/irq.c b/arch/csky/kernel/irq.c
index 03a1930f1cbb..fcdaf3156286 100644
--- a/arch/csky/kernel/irq.c
+++ b/arch/csky/kernel/irq.c
@@ -15,8 +15,3 @@ void __init init_IRQ(void)
setup_smp_ipi();
#endif
}
-
-asmlinkage void __irq_entry csky_do_IRQ(struct pt_regs *regs)
-{
- handle_arch_irq(regs);
-}
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
index 0105ac81b432..1a5f54e0d272 100644
--- a/arch/csky/kernel/ptrace.c
+++ b/arch/csky/kernel/ptrace.c
@@ -99,7 +99,8 @@ static int gpr_set(struct task_struct *target,
if (ret)
return ret;
- regs.sr = task_pt_regs(target)->sr;
+ /* BIT(0) of regs.sr is Condition Code/Carry bit */
+ regs.sr = (regs.sr & BIT(0)) | (task_pt_regs(target)->sr & ~BIT(0));
#ifdef CONFIG_CPU_HAS_HILO
regs.dcsr = task_pt_regs(target)->dcsr;
#endif
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index bc4238b9f709..c7b763d2f526 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -52,10 +52,14 @@ static long restore_sigcontext(struct pt_regs *regs,
struct sigcontext __user *sc)
{
int err = 0;
+ unsigned long sr = regs->sr;
/* sc_pt_regs is structured the same as the start of pt_regs */
err |= __copy_from_user(regs, &sc->sc_pt_regs, sizeof(struct pt_regs));
+ /* BIT(0) of regs->sr is Condition Code/Carry bit */
+ regs->sr = (sr & ~1) | (regs->sr & 1);
+
/* Restore the floating-point state. */
err |= restore_fpu_state(sc);
diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c
index 1b280ef08004..9f78f5d21511 100644
--- a/arch/csky/kernel/stacktrace.c
+++ b/arch/csky/kernel/stacktrace.c
@@ -111,12 +111,11 @@ static bool save_wchan(unsigned long pc, void *arg)
return false;
}
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
{
unsigned long pc = 0;
- if (likely(task && task != current && !task_is_running(task)))
- walk_stackframe(task, NULL, save_wchan, &pc);
+ walk_stackframe(task, NULL, save_wchan, &pc);
return pc;
}
diff --git a/arch/h8300/include/asm/irq.h b/arch/h8300/include/asm/irq.h
index 5fc5b436dde9..776cf06d7a59 100644
--- a/arch/h8300/include/asm/irq.h
+++ b/arch/h8300/include/asm/irq.h
@@ -2,8 +2,6 @@
#ifndef _H8300_IRQ_H_
#define _H8300_IRQ_H_
-#include <linux/irqchip.h>
-
#if defined(CONFIG_CPU_H8300H)
#define NR_IRQS 64
#define IRQ_CHIP h8300h_irq_chip
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
index a060b41b2d31..141a23eb62b7 100644
--- a/arch/h8300/include/asm/processor.h
+++ b/arch/h8300/include/asm/processor.h
@@ -105,7 +105,7 @@ static inline void release_thread(struct task_struct *dead_task)
{
}
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) \
({ \
diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c
index 834e4d7b1bcf..8ad6d702cd0b 100644
--- a/arch/h8300/kernel/irq.c
+++ b/arch/h8300/kernel/irq.c
@@ -8,6 +8,7 @@
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
+#include <linux/irqchip.h>
#include <linux/irqdomain.h>
#include <linux/of_irq.h>
#include <asm/traps.h>
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 2ac27e4248a4..8833fa4f5d51 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -128,15 +128,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
return 0;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long fp, pc;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
stack_page = (unsigned long)p;
fp = ((struct pt_regs *)p->thread.ksp)->er6;
do {
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 9f0cc99420be..615f7e49968e 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/arch/hexagon/include/asm/processor.h
@@ -64,7 +64,7 @@ struct thread_struct {
extern void release_thread(struct task_struct *dead_task);
/* Get wait channel for task P. */
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
/* The following stuff is pretty HEXAGON specific. */
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 6a6835fb4242..232dfd8956aa 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -130,13 +130,11 @@ void flush_thread(void)
* is an identification of the point at which the scheduler
* was invoked by a blocked thread.
*/
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long fp, pc;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
stack_page = (unsigned long)task_stack_page(p);
fp = ((struct hexagon_switch_stack *)p->thread.switch_sp)->fp;
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 2d8bcdc27d7f..45365c2ef598 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -330,7 +330,7 @@ struct task_struct;
#define release_thread(dead_task)
/* Get wait channel for task P. */
-extern unsigned long get_wchan (struct task_struct *p);
+extern unsigned long __get_wchan (struct task_struct *p);
/* Return instruction pointer of blocked task TSK. */
#define KSTK_EIP(tsk) \
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 864775970c50..0e5c1ad3239c 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -124,18 +124,13 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
__ticket_spin_unlock(lock);
}
-static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
- unsigned long flags)
-{
- arch_spin_lock(lock);
-}
-#define arch_spin_lock_flags arch_spin_lock_flags
-
#ifdef ASM_SUPPORTED
static __always_inline void
-arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
+arch_read_lock(arch_rwlock_t *lock)
{
+ unsigned long flags = 0;
+
__asm__ __volatile__ (
"tbit.nz p6, p0 = %1,%2\n"
"br.few 3f\n"
@@ -157,13 +152,8 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
: "p6", "p7", "r2", "memory");
}
-#define arch_read_lock_flags arch_read_lock_flags
-#define arch_read_lock(lock) arch_read_lock_flags(lock, 0)
-
#else /* !ASM_SUPPORTED */
-#define arch_read_lock_flags(rw, flags) arch_read_lock(rw)
-
#define arch_read_lock(rw) \
do { \
arch_rwlock_t *__read_lock_ptr = (rw); \
@@ -186,8 +176,10 @@ do { \
#ifdef ASM_SUPPORTED
static __always_inline void
-arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
+arch_write_lock(arch_rwlock_t *lock)
{
+ unsigned long flags = 0;
+
__asm__ __volatile__ (
"tbit.nz p6, p0 = %1, %2\n"
"mov ar.ccv = r0\n"
@@ -210,9 +202,6 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
}
-#define arch_write_lock_flags arch_write_lock_flags
-#define arch_write_lock(rw) arch_write_lock_flags(rw, 0)
-
#define arch_write_trylock(rw) \
({ \
register long result; \
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index e56d63f4abf9..834df24a88f1 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -523,15 +523,12 @@ exit_thread (struct task_struct *tsk)
}
unsigned long
-get_wchan (struct task_struct *p)
+__get_wchan (struct task_struct *p)
{
struct unw_frame_info info;
unsigned long ip;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
/*
* Note: p may not be a blocked task (it could be current or
* another process running on some other CPU. Rather than
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 9a8394e96388..9c57b245dc12 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -58,7 +58,7 @@ struct nfhd_device {
struct gendisk *disk;
};
-static blk_qc_t nfhd_submit_bio(struct bio *bio)
+static void nfhd_submit_bio(struct bio *bio)
{
struct nfhd_device *dev = bio->bi_bdev->bd_disk->private_data;
struct bio_vec bvec;
@@ -76,7 +76,6 @@ static blk_qc_t nfhd_submit_bio(struct bio *bio)
sec += len;
}
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
@@ -100,6 +99,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
{
struct nfhd_device *dev;
int dev_id = id - NFHD_DEV_OFFSET;
+ int err = -ENOMEM;
pr_info("nfhd%u: found device with %u blocks (%u bytes)\n", dev_id,
blocks, bsize);
@@ -130,16 +130,20 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
blk_queue_logical_block_size(dev->disk->queue, bsize);
- add_disk(dev->disk);
+ err = add_disk(dev->disk);
+ if (err)
+ goto out_cleanup_disk;
list_add_tail(&dev->list, &nfhd_list);
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(dev->disk);
free_dev:
kfree(dev);
out:
- return -ENOMEM;
+ return err;
}
static int __init nfhd_init(void)
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index 1ac55e7b47f0..8ab46625ddd3 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -250,6 +250,7 @@ static inline void __flush_page_to_ram(void *vaddr)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
#define flush_dcache_page(page) __flush_page_to_ram(page_address(page))
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
#define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page))
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index f4d82c619a5c..ffeda9aa526a 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -150,7 +150,7 @@ static inline void release_thread(struct task_struct *dead_task)
{
}
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) \
({ \
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 1ab692b952cd..a6030dbaa089 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -263,13 +263,11 @@ int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu)
}
EXPORT_SYMBOL(dump_fpu);
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long fp, pc;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
stack_page = (unsigned long)task_stack_page(p);
fp = ((struct switch_stack *)p->thread.ksp)->a6;
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 06c6e493590a..7e9e92670df3 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -68,7 +68,7 @@ static inline void release_thread(struct task_struct *dead_task)
{
}
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
/* The size allocated for kernel stacks. This _must_ be a power of two! */
# define KERNEL_STACK_SIZE 0x2000
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 62aa237180b6..5e2b91c1e8ce 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -112,7 +112,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
return 0;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
/* TBD (used by procfs) */
return 0;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 6b8f591c5054..95fc35669860 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -47,7 +47,6 @@ config MIPS
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL
select GUP_GET_PTE_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT
- select HANDLE_DOMAIN_IRQ
select HAVE_ARCH_COMPILER_H
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KGDB if MIPS_FP_SUPPORT
@@ -1782,6 +1781,7 @@ config CPU_BMIPS
select CPU_HAS_PREFETCH
select CPU_SUPPORTS_CPUFREQ
select MIPS_EXTERNAL_TIMER
+ select GENERIC_IRQ_MIGRATION if HOTPLUG_CPU
help
Support for BMIPS32/3300/4350/4380 and BMIPS5000 processors.
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index be5d4afcd30f..844f882096e6 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2609,7 +2609,10 @@ static void octeon_irq_ciu3_ip2(void)
else
hw = intsn;
- ret = handle_domain_irq(domain, hw, NULL);
+ irq_enter();
+ ret = generic_handle_domain_irq(domain, hw);
+ irq_exit();
+
if (ret < 0) {
union cvmx_ciu3_iscx_w1c isc_w1c;
u64 isc_w1c_addr = ciu3_addr + CIU3_ISC_W1C(intsn);
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index b3dc9c589442..f207388541d5 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -61,6 +61,8 @@ static inline void flush_dcache_page(struct page *page)
SetPageDcacheDirty(page);
}
+void flush_dcache_folio(struct folio *folio);
+
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 0c3550c82b72..252ed38ce8c5 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -369,7 +369,7 @@ static inline void flush_thread(void)
{
}
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \
THREAD_SIZE - 32 - sizeof(struct pt_regs))
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d20e002b3246..5e11582fe308 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -111,15 +111,9 @@ void __irq_entry do_IRQ(unsigned int irq)
#ifdef CONFIG_IRQ_DOMAIN
void __irq_entry do_domain_IRQ(struct irq_domain *domain, unsigned int hwirq)
{
- struct irq_desc *desc;
-
irq_enter();
check_stack_overflow();
-
- desc = irq_resolve_mapping(domain, hwirq);
- if (likely(desc))
- handle_irq_desc(desc);
-
+ generic_handle_domain_irq(domain, hwirq);
irq_exit();
}
#endif
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 95aa86fa6077..cbff1b974f88 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -511,7 +511,7 @@ static int __init frame_info_init(void)
/*
* Without schedule() frame info, result given by
- * thread_saved_pc() and get_wchan() are not reliable.
+ * thread_saved_pc() and __get_wchan() are not reliable.
*/
if (schedule_mfi.pc_offset < 0)
printk("Can't analyze schedule() prologue at %p\n", schedule);
@@ -652,9 +652,9 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
#endif
/*
- * get_wchan - a maintenance nightmare^W^Wpain in the ass ...
+ * __get_wchan - a maintenance nightmare^W^Wpain in the ass ...
*/
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
{
unsigned long pc = 0;
#ifdef CONFIG_KALLSYMS
@@ -662,8 +662,6 @@ unsigned long get_wchan(struct task_struct *task)
unsigned long ra = 0;
#endif
- if (!task || task == current || task_is_running(task))
- goto out;
if (!task_stack_page(task))
goto out;
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index b6ef5f7312cf..f5d7bfa3472a 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -26,6 +26,7 @@
#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
+#include <linux/irq.h>
#include <asm/time.h>
#include <asm/processor.h>
@@ -373,7 +374,7 @@ static int bmips_cpu_disable(void)
set_cpu_online(cpu, false);
calculate_cpu_foreign_map();
- irq_cpu_offline();
+ irq_migrate_all_off_this_cpu();
clear_c0_status(IE_IRQ5);
local_flush_tlb_all();
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index 09ebe84a17fe..660e1de4412a 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -550,7 +550,6 @@ static int loongson3_cpu_disable(void)
set_cpu_online(cpu, false);
calculate_cpu_foreign_map();
local_irq_save(flags);
- irq_cpu_offline();
clear_c0_status(ST0_IM);
local_irq_restore(flags);
local_flush_tlb_all();
diff --git a/arch/mips/rb532/prom.c b/arch/mips/rb532/prom.c
index 23ad8dd9aa5e..b11693715547 100644
--- a/arch/mips/rb532/prom.c
+++ b/arch/mips/rb532/prom.c
@@ -16,7 +16,6 @@
#include <linux/console.h>
#include <linux/memblock.h>
#include <linux/ioport.h>
-#include <linux/blkdev.h>
#include <asm/bootinfo.h>
#include <asm/mach-rc32434/ddr.h>
diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c
index a3323f8dcc1b..1a504294d85f 100644
--- a/arch/mips/sibyte/common/cfe.c
+++ b/arch/mips/sibyte/common/cfe.c
@@ -7,7 +7,6 @@
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/mm.h>
-#include <linux/blkdev.h>
#include <linux/memblock.h>
#include <linux/pm.h>
#include <linux/smp.h>
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 538a2791b48c..f07b15dd1c1a 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -11,7 +11,6 @@
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memblock.h>
-#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/screen_info.h>
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index aea26e739543..4d1421b18734 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -27,7 +27,6 @@ config NDS32
select GENERIC_LIB_MULDI3
select GENERIC_LIB_UCMPDI2
select GENERIC_TIME_VSYSCALL
- select HANDLE_DOMAIN_IRQ
select HAVE_ARCH_TRACEHOOK
select HAVE_DEBUG_KMEMLEAK
select HAVE_EXIT_THREAD
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index c2a222ebfa2a..3fc0bb7d6487 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -27,6 +27,7 @@ void flush_cache_vunmap(unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long vaddr, void *dst, void *src, int len);
void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h
index b82369c7659d..e6bfc74972bb 100644
--- a/arch/nds32/include/asm/processor.h
+++ b/arch/nds32/include/asm/processor.h
@@ -83,7 +83,7 @@ extern struct task_struct *last_task_used_math;
/* Prepare to copy thread state - unlazy all lazy status */
#define prepare_to_copy(tsk) do { } while (0)
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define cpu_relax() barrier()
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 0e23e3a8df6b..d55b73b18149 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -6,7 +6,7 @@
#ifndef CONFIG_DYNAMIC_FTRACE
extern void (*ftrace_trace_function)(unsigned long, unsigned long,
- struct ftrace_ops*, struct pt_regs*);
+ struct ftrace_ops*, struct ftrace_regs*);
extern void ftrace_graph_caller(void);
noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index 391895b54d13..49fab9e39cbf 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -233,15 +233,12 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu)
EXPORT_SYMBOL(dump_fpu);
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long fp, lr;
unsigned long stack_start, stack_end;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
if (IS_ENABLED(CONFIG_FRAME_POINTER)) {
stack_start = (unsigned long)end_of_stack(p);
stack_end = (unsigned long)task_stack_page(p) + THREAD_SIZE;
@@ -258,5 +255,3 @@ unsigned long get_wchan(struct task_struct *p)
}
return 0;
}
-
-EXPORT_SYMBOL(get_wchan);
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 18eb9f69f806..1999561b22aa 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -28,7 +28,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
unsigned long pfn);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
diff --git a/arch/nios2/include/asm/irqflags.h b/arch/nios2/include/asm/irqflags.h
index b3ec3e510706..25acf27862f9 100644
--- a/arch/nios2/include/asm/irqflags.h
+++ b/arch/nios2/include/asm/irqflags.h
@@ -9,7 +9,7 @@
static inline unsigned long arch_local_save_flags(void)
{
- return RDCTL(CTL_STATUS);
+ return RDCTL(CTL_FSTATUS);
}
/*
@@ -18,7 +18,7 @@ static inline unsigned long arch_local_save_flags(void)
*/
static inline void arch_local_irq_restore(unsigned long flags)
{
- WRCTL(CTL_STATUS, flags);
+ WRCTL(CTL_FSTATUS, flags);
}
static inline void arch_local_irq_disable(void)
diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h
index 94bcb86f679f..b8125dfbcad2 100644
--- a/arch/nios2/include/asm/processor.h
+++ b/arch/nios2/include/asm/processor.h
@@ -69,7 +69,7 @@ static inline void release_thread(struct task_struct *dead_task)
{
}
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
diff --git a/arch/nios2/include/asm/registers.h b/arch/nios2/include/asm/registers.h
index 183c720e454d..95b67dd16f81 100644
--- a/arch/nios2/include/asm/registers.h
+++ b/arch/nios2/include/asm/registers.h
@@ -11,7 +11,7 @@
#endif
/* control register numbers */
-#define CTL_STATUS 0
+#define CTL_FSTATUS 0
#define CTL_ESTATUS 1
#define CTL_BSTATUS 2
#define CTL_IENABLE 3
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 9ff37ba2bb60..f8ea522a1588 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -217,15 +217,12 @@ void dump(struct pt_regs *fp)
pr_emerg("\n\n");
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long fp, pc;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
stack_page = (unsigned long)p;
fp = ((struct switch_stack *)p->thread.ksp)->fp; /* ;dgt2 */
do {
diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform
index 9e32fb7f3d4c..e849daff6fd1 100644
--- a/arch/nios2/platform/Kconfig.platform
+++ b/arch/nios2/platform/Kconfig.platform
@@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR
config NIOS2_DTB_SOURCE_BOOL
bool "Compile and link device tree into kernel image"
+ depends on !COMPILE_TEST
help
This allows you to specify a dts (device tree source) file
which will be compiled and linked into the kernel image.
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index e804026b4797..c2491b295d60 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -13,7 +13,6 @@ config OPENRISC
select OF
select OF_EARLY_FLATTREE
select IRQ_DOMAIN
- select HANDLE_DOMAIN_IRQ
select GPIOLIB
select HAVE_ARCH_TRACEHOOK
select SPARSE_IRQ
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index ad53b3184885..aa1699c18add 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -73,7 +73,7 @@ struct thread_struct {
void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp);
void release_thread(struct task_struct *);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define cpu_relax() barrier()
diff --git a/arch/openrisc/include/asm/spinlock.h b/arch/openrisc/include/asm/spinlock.h
index a8940bdfcb7e..264944a71535 100644
--- a/arch/openrisc/include/asm/spinlock.h
+++ b/arch/openrisc/include/asm/spinlock.h
@@ -19,9 +19,6 @@
#include <asm/qrwlock.h>
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
#define arch_spin_relax(lock) cpu_relax()
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index edaa775a648e..59c6d3aa7081 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -569,8 +569,8 @@ EXCEPTION_ENTRY(_external_irq_handler)
#endif
CLEAR_LWA_FLAG(r3)
l.addi r3,r1,0
- l.movhi r8,hi(do_IRQ)
- l.ori r8,r8,lo(do_IRQ)
+ l.movhi r8,hi(generic_handle_arch_irq)
+ l.ori r8,r8,lo(generic_handle_arch_irq)
l.jalr r8
l.nop
l.j _ret_from_intr
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index c38fa863afa8..f38e10962a84 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -36,8 +36,3 @@ void __init init_IRQ(void)
{
irqchip_init();
}
-
-void __irq_entry do_IRQ(struct pt_regs *regs)
-{
- handle_arch_irq(regs);
-}
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index b0698d9ce14f..3c0c91bcdcba 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -263,7 +263,7 @@ void dump_elf_thread(elf_greg_t *dest, struct pt_regs* regs)
dest[35] = 0;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
/* TODO */
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index cfef61a7b6c2..97305bde1b16 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -25,7 +25,6 @@
#include <linux/memblock.h>
#include <linux/init.h>
#include <linux/delay.h>
-#include <linux/blkdev.h> /* for initrd_* */
#include <linux/pagemap.h>
#include <asm/pgalloc.h>
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index eef0096db5f8..da0cd4b3a28f 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -49,7 +49,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
#define flush_cache_vunmap(start, end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages)
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages)
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index eeb7da064289..85a2dbfe5278 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -273,7 +273,7 @@ struct mm_struct;
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) ((tsk)->thread.regs.iaoq[0])
#define KSTK_ESP(tsk) ((tsk)->thread.regs.gr[30])
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index fa5ee8a45dbd..a6e5d66a7656 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -23,21 +23,6 @@ static inline void arch_spin_lock(arch_spinlock_t *x)
continue;
}
-static inline void arch_spin_lock_flags(arch_spinlock_t *x,
- unsigned long flags)
-{
- volatile unsigned int *a;
-
- a = __ldcw_align(x);
- while (__ldcw(a) == 0)
- while (*a == 0)
- if (flags & PSW_SM_I) {
- local_irq_enable();
- local_irq_disable();
- }
-}
-#define arch_spin_lock_flags arch_spin_lock_flags
-
static inline void arch_spin_unlock(arch_spinlock_t *x)
{
volatile unsigned int *a;
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 38ec4ae81239..4f562dee65a2 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -240,15 +240,12 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
}
unsigned long
-get_wchan(struct task_struct *p)
+__get_wchan(struct task_struct *p)
{
struct unwind_frame_info info;
unsigned long ip;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
/*
* These bracket the sleeping functions..
*/
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index f348e564f7dd..e39bd0ff69f3 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -300,7 +300,7 @@ struct thread_struct {
#define task_pt_regs(tsk) ((tsk)->thread.regs)
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0)
#define KSTK_ESP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0)
diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h
index 8985791a2ba5..7ae6aeef8464 100644
--- a/arch/powerpc/include/asm/simple_spinlock.h
+++ b/arch/powerpc/include/asm/simple_spinlock.h
@@ -123,27 +123,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
}
}
-static inline
-void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
-{
- unsigned long flags_dis;
-
- while (1) {
- if (likely(__arch_spin_trylock(lock) == 0))
- break;
- local_save_flags(flags_dis);
- local_irq_restore(flags);
- do {
- HMT_low();
- if (is_shared_processor())
- splpar_spin_yield(lock);
- } while (unlikely(lock->slock != 0));
- HMT_medium();
- local_irq_restore(flags_dis);
- }
-}
-#define arch_spin_lock_flags arch_spin_lock_flags
-
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
__asm__ __volatile__("# arch_spin_unlock\n\t"
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index abb719b21cae..3d97fb833834 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -126,14 +126,16 @@ _GLOBAL(idle_return_gpr_loss)
/*
* This is the sequence required to execute idle instructions, as
* specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
- *
- * The 0(r1) slot is used to save r2 in isa206, so use that here.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
*/
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
- std r2,0(r1); \
+ std r2,-8(r1); \
ptesync; \
- ld r2,0(r1); \
+ ld r2,-8(r1); \
236: cmpd cr0,r2,r2; \
bne 236b; \
IDLE_INST; \
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 50436b52c213..406d7ee9e322 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -2111,14 +2111,11 @@ int validate_sp(unsigned long sp, struct task_struct *p,
EXPORT_SYMBOL(validate_sp);
-static unsigned long __get_wchan(struct task_struct *p)
+static unsigned long ___get_wchan(struct task_struct *p)
{
unsigned long ip, sp;
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
sp = p->thread.ksp;
if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD))
return 0;
@@ -2137,14 +2134,14 @@ static unsigned long __get_wchan(struct task_struct *p)
return 0;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long ret;
if (!try_get_task_stack(p))
return 0;
- ret = __get_wchan(p);
+ ret = ___get_wchan(p);
put_task_stack(p);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 9cc7d3dbf439..605bab448f84 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1730,8 +1730,6 @@ void __cpu_die(unsigned int cpu)
void arch_cpu_idle_dead(void)
{
- sched_preempt_enable_no_resched();
-
/*
* Disable on the down path. This will be re-enabled by
* start_secondary() via start_secondary_resume() below
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 90484425a1e6..eb776d0c5d8e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -255,13 +255,16 @@ kvm_novcpu_exit:
* r3 contains the SRR1 wakeup value, SRR1 is trashed.
*/
_GLOBAL(idle_kvm_start_guest)
- ld r4,PACAEMERGSP(r13)
mfcr r5
mflr r0
- std r1,0(r4)
- std r5,8(r4)
- std r0,16(r4)
- subi r1,r4,STACK_FRAME_OVERHEAD
+ std r5, 8(r1) // Save CR in caller's frame
+ std r0, 16(r1) // Save LR in caller's frame
+ // Create frame on emergency stack
+ ld r4, PACAEMERGSP(r13)
+ stdu r1, -SWITCH_FRAME_SIZE(r4)
+ // Switch to new frame on emergency stack
+ mr r1, r4
+ std r3, 32(r1) // Save SRR1 wakeup value
SAVE_NVGPRS(r1)
/*
@@ -313,6 +316,10 @@ kvm_unsplit_wakeup:
kvm_secondary_got_guest:
+ // About to go to guest, clear saved SRR1
+ li r0, 0
+ std r0, 32(r1)
+
/* Set HSTATE_DSCR(r13) to something sensible */
ld r6, PACA_DSCR_DEFAULT(r13)
std r6, HSTATE_DSCR(r13)
@@ -392,13 +399,12 @@ kvm_no_guest:
mfspr r4, SPRN_LPCR
rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
mtspr SPRN_LPCR, r4
- /* set up r3 for return */
- mfspr r3,SPRN_SRR1
+ // Return SRR1 wakeup value, or 0 if we went into the guest
+ ld r3, 32(r1)
REST_NVGPRS(r1)
- addi r1, r1, STACK_FRAME_OVERHEAD
- ld r0, 16(r1)
- ld r5, 8(r1)
- ld r1, 0(r1)
+ ld r1, 0(r1) // Switch back to caller stack
+ ld r0, 16(r1) // Reload LR
+ ld r5, 8(r1) // Reload CR
mtlr r0
mtcr r5
blr
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index f92bf5f6b74f..7ea873ab2e6f 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -238,11 +238,27 @@ static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
ret |= P(SNOOP, HIT);
break;
case 5:
- ret = PH(LVL, REM_CCE1);
- if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4))
- ret |= P(SNOOP, HIT);
- else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5))
- ret |= P(SNOOP, HITM);
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ ret = REM | P(HOPS, 0);
+
+ if (sub_idx == 0 || sub_idx == 4)
+ ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HIT);
+ else if (sub_idx == 1 || sub_idx == 5)
+ ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HITM);
+ else if (sub_idx == 2 || sub_idx == 6)
+ ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+ else if (sub_idx == 3 || sub_idx == 7)
+ ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+ } else {
+ if (sub_idx == 0)
+ ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+ else if (sub_idx == 1)
+ ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+ else if (sub_idx == 2 || sub_idx == 4)
+ ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+ else if (sub_idx == 3 || sub_idx == 5)
+ ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+ }
break;
case 6:
ret = PH(LVL, REM_CCE2);
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 4a2cbc3dc047..ff122603989b 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -273,6 +273,8 @@
#define P(a, b) PERF_MEM_S(a, b)
#define PH(a, b) (P(LVL, HIT) | P(a, b))
#define PM(a, b) (P(LVL, MISS) | P(a, b))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp, u64 event_config1);
int isa207_compute_mmcr(u64 event[], int n_ev,
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index bed05b644c2c..cb25acccd746 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -21,6 +21,7 @@
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/poll.h>
+#include <linux/seq_file.h>
#include <linux/slab.h>
#include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index dab5c56ffd0e..a52af8fbf571 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1302,6 +1302,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct property *default_win;
int reset_win_ext;
+ /* DDW + IOMMU on single window may fail if there is any allocation */
+ if (iommu_table_in_use(tbl)) {
+ dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
+ goto out_failed;
+ }
+
default_win = of_find_property(pdn, "ibm,dma-window", NULL);
if (!default_win)
goto out_failed;
@@ -1356,12 +1362,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
query.largest_available_block,
1ULL << page_shift);
- /* DDW + IOMMU on single window may fail if there is any allocation */
- if (default_win_removed && iommu_table_in_use(tbl)) {
- dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
- goto out_failed;
- }
-
len = order_base_2(query.largest_available_block << page_shift);
win_name = DMA64_PROPNAME;
} else {
@@ -1411,18 +1411,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
} else {
struct iommu_table *newtbl;
int i;
+ unsigned long start = 0, end = 0;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
/* Look for MMIO32 */
- if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+ start = pci->phb->mem_resources[i].start;
+ end = pci->phb->mem_resources[i].end;
break;
+ }
}
- if (i == ARRAY_SIZE(pci->phb->mem_resources))
- goto out_del_list;
-
/* New table for using DDW instead of the default DMA window */
newtbl = iommu_pseries_alloc_table(pci->phb->node);
if (!newtbl) {
@@ -1432,15 +1433,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
- iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
- pci->phb->mem_resources[i].end);
+ iommu_init_table(newtbl, pci->phb->node, start, end);
pci->table_group->tables[1] = newtbl;
/* Keep default DMA window stuct if removed */
if (default_win_removed) {
tbl->it_size = 0;
- kfree(tbl->it_map);
+ vfree(tbl->it_map);
+ tbl->it_map = NULL;
}
set_iommu_table_base(&dev->dev, newtbl);
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index c732ce5a3e1a..c5d75c02ad8b 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -945,7 +945,8 @@ static int xive_get_irqchip_state(struct irq_data *data,
* interrupt to be inactive in that case.
*/
*state = (pq != XIVE_ESB_INVALID) && !xd->stale_p &&
- (xd->saved_p || !!(pq & XIVE_ESB_VAL_P));
+ (xd->saved_p || (!!(pq & XIVE_ESB_VAL_P) &&
+ !irqd_irq_disabled(data)));
return 0;
default:
return -EINVAL;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 6a6fa9e976d5..c28b743eba57 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -62,7 +62,6 @@ config RISCV
select GENERIC_SCHED_CLOCK
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL if MMU && 64BIT
- select HANDLE_DOMAIN_IRQ
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
@@ -163,6 +162,12 @@ config PAGE_OFFSET
default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
+config KASAN_SHADOW_OFFSET
+ hex
+ depends on KASAN_GENERIC
+ default 0xdfffffc800000000 if 64BIT
+ default 0xffffffff if 32BIT
+
config ARCH_FLATMEM_ENABLE
def_bool !NUMA
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
index a2b3d9cdbc86..b00f503ec124 100644
--- a/arch/riscv/include/asm/kasan.h
+++ b/arch/riscv/include/asm/kasan.h
@@ -30,8 +30,7 @@
#define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
#define KASAN_SHADOW_START KERN_VIRT_START
#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
-#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \
- (64 - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
void kasan_init(void);
asmlinkage void kasan_early_init(void);
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 46b492c78cbb..0749924d9e55 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -66,7 +66,7 @@ static inline void release_thread(struct task_struct *dead_task)
{
}
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
static inline void wait_for_interrupt(void)
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 98f502654edd..64236f7efde5 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -130,8 +130,7 @@ skip_context_tracking:
/* Handle interrupts */
move a0, sp /* pt_regs */
- la a1, handle_arch_irq
- REG_L a1, (a1)
+ la a1, generic_handle_arch_irq
jr a1
1:
/*
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index fce5184b22c3..52c5ff9804c5 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -193,6 +193,7 @@ setup_trap_vector:
csrw CSR_SCRATCH, zero
ret
+.align 2
.Lsecondary_park:
/* We lack SMP support or have too many harts, so park this hart */
wfi
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 921d9d7df400..2f6da845c9ae 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -140,12 +140,9 @@ void arch_irq_work_raise(void)
void handle_IPI(struct pt_regs *regs)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
unsigned long *stats = ipi_data[smp_processor_id()].stats;
- irq_enter();
-
riscv_clear_ipi();
while (true) {
@@ -156,7 +153,7 @@ void handle_IPI(struct pt_regs *regs)
ops = xchg(pending_ipis, 0);
if (ops == 0)
- goto done;
+ return;
if (ops & (1 << IPI_RESCHEDULE)) {
stats[IPI_RESCHEDULE]++;
@@ -189,10 +186,6 @@ void handle_IPI(struct pt_regs *regs)
/* Order data access and bit testing. */
mb();
}
-
-done:
- irq_exit();
- set_irq_regs(old_regs);
}
static const char * const ipi_names[] = {
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 315db3d0229b..0fcdc0233fac 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -128,16 +128,14 @@ static bool save_wchan(void *arg, unsigned long pc)
return true;
}
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
{
unsigned long pc = 0;
- if (likely(task && task != current && !task_is_running(task))) {
- if (!try_get_task_stack(task))
- return 0;
- walk_stackframe(task, NULL, save_wchan, &pc);
- put_task_stack(task);
- }
+ if (!try_get_task_stack(task))
+ return 0;
+ walk_stackframe(task, NULL, save_wchan, &pc);
+ put_task_stack(task);
return pc;
}
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index d7189c8714a9..54294f83513d 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void)
uintptr_t i;
pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
for (i = 0; i < PTRS_PER_PTE; ++i)
set_pte(kasan_early_shadow_pte + i,
mk_pte(virt_to_page(kasan_early_shadow_page),
@@ -172,21 +175,10 @@ void __init kasan_init(void)
phys_addr_t p_start, p_end;
u64 i;
- /*
- * Populate all kernel virtual address space with kasan_early_shadow_page
- * except for the linear mapping and the modules/kernel/BPF mapping.
- */
- kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
- (void *)kasan_mem_to_shadow((void *)
- VMEMMAP_END));
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_shallow_populate(
(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
- else
- kasan_populate_early_shadow(
- (void *)kasan_mem_to_shadow((void *)VMALLOC_START),
- (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
/* Populate the linear mapping */
for_each_mem_range(i, &p_start, &p_end) {
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index fed86f42dfbe..753d85bdfad0 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (i == NR_JIT_ITERATIONS) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
- bpf_jit_binary_free(jit_data->header);
+ if (jit_data->header)
+ bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
@@ -166,6 +167,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 879b8e3f609c..f54c152bf2bf 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -192,7 +192,7 @@ static inline void release_thread(struct task_struct *tsk) { }
void guarded_storage_release(struct task_struct *tsk);
void gs_load_bc_cb(struct pt_regs *regs);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
#define task_pt_regs(tsk) ((struct pt_regs *) \
(task_stack_page(tsk) + THREAD_SIZE) - 1)
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->psw.addr)
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index ef59588a3042..888a2f1c9ee3 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -67,14 +67,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lp)
arch_spin_lock_wait(lp);
}
-static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
- unsigned long flags)
-{
- if (!arch_spin_trylock_once(lp))
- arch_spin_lock_wait(lp);
-}
-#define arch_spin_lock_flags arch_spin_lock_flags
-
static inline int arch_spin_trylock(arch_spinlock_t *lp)
{
if (!arch_spin_trylock_once(lp))
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 350e94d0cac2..e5dd46b1bff8 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -181,12 +181,12 @@ void execve_tail(void)
asm volatile("sfpc %0" : : "d" (0));
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
struct unwind_state state;
unsigned long ip = 0;
- if (!p || p == current || task_is_running(p) || !task_stack_page(p))
+ if (!task_stack_page(p))
return 0;
if (!try_get_task_stack(p))
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index b9f85b2dc053..6af59c59cc1b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
/**
* guest_translate_address - translate guest logical into guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @gpa: Guest physical address
+ * @mode: Translation access mode
*
* Parameter semantics are the same as the ones from guest_translate.
* The memory contents at the guest address are not changed.
@@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
/**
* check_gva_range - test a range of guest virtual addresses for accessibility
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @length: Length of test range
+ * @mode: Translation access mode
*/
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
unsigned long length, enum gacc_mode mode)
@@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
/**
* kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @vcpu: virtual cpu
* @gra: Guest real address
*
* Checks whether an address is subject to low-address protection and set
@@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
* @pgt: pointer to the beginning of the page table for the given address if
* successful (return value 0), or to the first invalid DAT entry in
* case of exceptions (return value > 0)
+ * @dat_protection: referenced memory is write protected
* @fake: pgt references contiguous guest memory block, not a pgtable
*/
static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 72b25b7cc6ae..2bd8f854f1b4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
/**
* handle_external_interrupt - used for external interruption interceptions
+ * @vcpu: virtual cpu
*
* This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
* the new PSW does not have external interrupts disabled. In the first case,
@@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
}
/**
- * Handle MOVE PAGE partial execution interception.
+ * handle_mvpg_pei - Handle MOVE PAGE partial execution interception.
+ * @vcpu: virtual cpu
*
* This interception can only happen for guests with DAT disabled and
* addresses that are currently not mapped in the host. Thus we try to
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 10722455fd02..2245f4b8d362 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_vcpu *vcpu;
+ u8 vcpu_isc_mask;
for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
vcpu = kvm_get_vcpu(kvm, vcpu_idx);
if (psw_ioint_disabled(vcpu))
continue;
- deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
- if (deliverable_mask) {
+ vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+ if (deliverable_mask & vcpu_isc_mask) {
/* lately kicked but not yet running */
if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
return;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6a6dd5e1daf6..1c97493d21e1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3363,6 +3363,7 @@ out_free_sie_block:
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
+ clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
return kvm_s390_vcpu_has_irq(vcpu, 0);
}
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index cfcdf76d6a95..a95ca6df4e5e 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -259,14 +259,13 @@ EXPORT_SYMBOL(strcmp);
#ifdef __HAVE_ARCH_STRRCHR
char *strrchr(const char *s, int c)
{
- size_t len = __strend(s) - s;
-
- if (len)
- do {
- if (s[len] == (char) c)
- return (char *) s + len;
- } while (--len > 0);
- return NULL;
+ ssize_t len = __strend(s) - s;
+
+ do {
+ if (s[len] == (char)c)
+ return (char *)s + len;
+ } while (--len >= 0);
+ return NULL;
}
EXPORT_SYMBOL(strrchr);
#endif
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 372afa82fee6..c7a97f32432f 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -42,7 +42,8 @@ extern void flush_cache_page(struct vm_area_struct *vma,
extern void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
#define flush_icache_user_range flush_icache_range
extern void flush_icache_page(struct vm_area_struct *vma,
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index aa92cc933889..45240ec6b85a 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -180,7 +180,7 @@ static inline void show_code(struct pt_regs *regs)
}
#endif
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[15])
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 717de05c81f4..1c28e3cddb60 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -182,13 +182,10 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
return prev;
}
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long pc;
- if (!p || p == current || task_is_running(p))
- return 0;
-
/*
* The same comment as on the Alpha applies here, too ...
*/
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index b6242f7771e9..647bf0ac7beb 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -89,7 +89,7 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc,
/* Free all resources held by a thread. */
#define release_thread(tsk) do { } while(0)
-unsigned long get_wchan(struct task_struct *);
+unsigned long __get_wchan(struct task_struct *);
#define task_pt_regs(tsk) ((tsk)->thread.kregs)
#define KSTK_EIP(tsk) ((tsk)->thread.kregs->pc)
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 5cf145f18f36..ae851e8fce4c 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -183,7 +183,7 @@ do { \
/* Free all resources held by a thread. */
#define release_thread(tsk) do { } while (0)
-unsigned long get_wchan(struct task_struct *task);
+unsigned long __get_wchan(struct task_struct *task);
#define task_pt_regs(tsk) (task_thread_info(tsk)->kregs)
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->tpc)
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index bbbe0cfef746..2dc0bf9fe62e 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -365,7 +365,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
return 0;
}
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
{
unsigned long pc, fp, bias = 0;
unsigned long task_base = (unsigned long) task;
@@ -373,9 +373,6 @@ unsigned long get_wchan(struct task_struct *task)
struct reg_window32 *rw;
int count = 0;
- if (!task || task == current || task_is_running(task))
- goto out;
-
fp = task_thread_info(task)->ksp + bias;
do {
/* Bogus frame pointer? */
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d1cc410d2f64..f5b2cac8669f 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -663,7 +663,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
return 0;
}
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
{
unsigned long pc, fp, bias = 0;
struct thread_info *tp;
@@ -671,9 +671,6 @@ unsigned long get_wchan(struct task_struct *task)
unsigned long ret = 0;
int count = 0;
- if (!task || task == current || task_is_running(task))
- goto out;
-
tp = task_thread_info(task);
bias = STACK_BIAS;
fp = task_thread_info(task)->ksp + bias;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index cd9dc0556e91..69d2d0049a61 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -27,6 +27,7 @@
#include <linux/blk-mq.h>
#include <linux/ata.h>
#include <linux/hdreg.h>
+#include <linux/major.h>
#include <linux/cdrom.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -854,8 +855,8 @@ static const struct attribute_group *ubd_attr_groups[] = {
NULL,
};
-static void ubd_disk_register(int major, u64 size, int unit,
- struct gendisk *disk)
+static int ubd_disk_register(int major, u64 size, int unit,
+ struct gendisk *disk)
{
disk->major = major;
disk->first_minor = unit << UBD_SHIFT;
@@ -872,7 +873,7 @@ static void ubd_disk_register(int major, u64 size, int unit,
disk->private_data = &ubd_devs[unit];
disk->queue = ubd_devs[unit].queue;
- device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
+ return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
}
#define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
@@ -919,10 +920,15 @@ static int ubd_add(int n, char **error_out)
blk_queue_write_cache(ubd_dev->queue, true, false);
blk_queue_max_segments(ubd_dev->queue, MAX_SG);
blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
- ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ if (err)
+ goto out_cleanup_disk;
+
ubd_gendisk[n] = disk;
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&ubd_dev->tag_set);
out:
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index b5cf0ed116d9..579692a40a55 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -106,6 +106,6 @@ extern struct cpuinfo_um boot_cpu_data;
#define cache_line_size() (boot_cpu_data.cache_alignment)
#define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
#endif
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 457a38db368b..82107373ac7e 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -364,14 +364,11 @@ unsigned long arch_align_stack(unsigned long sp)
}
#endif
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long stack_page, sp, ip;
bool seen_sched = 0;
- if ((p == NULL) || (p == current) || task_is_running(p))
- return 0;
-
stack_page = (unsigned long) task_stack_page(p);
/* Bail if the process has no kernel stack for some reason */
if (stack_page == 0)
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index a149a5e9a16a..54447690de11 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -421,6 +421,10 @@ void __init check_bugs(void)
os_check_bugs();
}
+void apply_retpolines(s32 *start, s32 *end)
+{
+}
+
void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
{
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8584b30e2536..244d3a429dbb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1002,6 +1002,17 @@ config NR_CPUS
This is purely to save memory: each supported CPU adds about 8KB
to the kernel image.
+config SCHED_CLUSTER
+ bool "Cluster scheduler support"
+ depends on SMP
+ default y
+ help
+ Cluster scheduler support improves the CPU scheduler's decision
+ making when dealing with machines that have clusters of CPUs.
+ Cluster usually means a couple of CPUs which are placed closely
+ by sharing mid-level caches, last-level cache tags or internal
+ busses.
+
config SCHED_SMT
def_bool y if SMP
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index 18d2f5199194..1cc72b4804fa 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -78,7 +78,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -133,6 +133,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index d2ffd7f76ee2..9c5d3f3ad45a 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -93,7 +93,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -148,6 +148,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 960a021d543e..7e25543693de 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -453,3 +453,4 @@
446 i386 landlock_restrict_self sys_landlock_restrict_self
447 i386 memfd_secret sys_memfd_secret
448 i386 process_mrelease sys_process_mrelease
+449 i386 futex_waitv sys_futex_waitv
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 18b5500ea8bf..fe8f8dd157b4 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -370,6 +370,7 @@
446 common landlock_restrict_self sys_landlock_restrict_self
447 common memfd_secret sys_memfd_secret
448 common process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6dfa8ddaa60f..38b2c779146f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all);
DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable);
DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign);
+
DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add);
DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del);
DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read);
@@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
+ static_call_cond(x86_pmu_assign)(event, idx);
+
switch (hwc->idx) {
case INTEL_PMC_IDX_FIXED_BTS:
case INTEL_PMC_IDX_FIXED_VLBR:
@@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void)
static_call_update(x86_pmu_enable, x86_pmu.enable);
static_call_update(x86_pmu_disable, x86_pmu.disable);
+ static_call_update(x86_pmu_assign, x86_pmu.assign);
+
static_call_update(x86_pmu_add, x86_pmu.add);
static_call_update(x86_pmu_del, x86_pmu.del);
static_call_update(x86_pmu_read, x86_pmu.read);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 6320d2cfd9d3..974e917e65b2 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -209,6 +209,12 @@ static void bts_update(struct bts_ctx *bts)
} else {
local_set(&buf->data_size, head);
}
+
+ /*
+ * Since BTS is coherent, just add compiler barrier to ensure
+ * BTS updating is ordered against bts::handle::event.
+ */
+ barrier();
}
static int
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9a044438072b..aa3f5b527dc0 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -243,7 +243,8 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
static struct event_constraint intel_icl_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
- FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* old INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
@@ -288,7 +289,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
static struct event_constraint intel_spr_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
- FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
@@ -2403,6 +2404,12 @@ static void intel_pmu_disable_event(struct perf_event *event)
intel_pmu_pebs_disable(event);
}
+static void intel_pmu_assign_event(struct perf_event *event, int idx)
+{
+ if (is_pebs_pt(event))
+ perf_report_aux_output_id(event, idx);
+}
+
static void intel_pmu_del_event(struct perf_event *event)
{
if (needs_branch_stack(event))
@@ -4495,8 +4502,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value)
return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
}
+static void intel_aux_output_init(void)
+{
+ /* Refer also intel_pmu_aux_output_match() */
+ if (x86_pmu.intel_cap.pebs_output_pt_available)
+ x86_pmu.assign = intel_pmu_assign_event;
+}
+
static int intel_pmu_aux_output_match(struct perf_event *event)
{
+ /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */
if (!x86_pmu.intel_cap.pebs_output_pt_available)
return 0;
@@ -6302,6 +6317,8 @@ __init int intel_pmu_init(void)
if (is_hybrid())
intel_pmu_check_hybrid_pmus((u64)fixed_mask);
+ intel_aux_output_init();
+
return 0;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8647713276a7..4dbb55a43dad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -923,7 +923,8 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
};
struct event_constraint intel_icl_pebs_event_constraints[] = {
- INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x100000000ULL), /* old INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */
INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
@@ -943,7 +944,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
};
struct event_constraint intel_spr_pebs_event_constraints[] = {
- INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 7280c8a3c831..6d735611c281 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -30,7 +30,7 @@
#define uncore_discovery_invalid_unit(unit) \
- (!unit.table1 || !unit.ctl || !unit.table3 || \
+ (!unit.table1 || !unit.ctl || \
unit.table1 == -1ULL || unit.ctl == -1ULL || \
unit.table3 == -1ULL)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 5ddc0f30db6f..eb2c6cea9d0d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -452,7 +452,7 @@
#define ICX_M3UPI_PCI_PMON_BOX_CTL 0xa0
/* ICX IMC */
-#define ICX_NUMBER_IMC_CHN 2
+#define ICX_NUMBER_IMC_CHN 3
#define ICX_IMC_MEM_STRIDE 0x4
/* SPR */
@@ -5076,8 +5076,10 @@ static struct event_constraint icx_uncore_iio_constraints[] = {
UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
UNCORE_EVENT_CONSTRAINT(0x03, 0x3),
UNCORE_EVENT_CONSTRAINT(0x83, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x88, 0xc),
UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0xd5, 0xc),
EVENT_CONSTRAINT_END
};
@@ -5463,7 +5465,7 @@ static struct intel_uncore_ops icx_uncore_mmio_ops = {
static struct intel_uncore_type icx_uncore_imc = {
.name = "imc",
.num_counters = 4,
- .num_boxes = 8,
+ .num_boxes = 12,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
.fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
@@ -5647,6 +5649,7 @@ static struct intel_uncore_type spr_uncore_chabox = {
.event_mask = SPR_CHA_PMON_EVENT_MASK,
.event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
.num_shared_regs = 1,
+ .constraints = skx_uncore_chabox_constraints,
.ops = &spr_uncore_chabox_ops,
.format_group = &spr_uncore_chabox_format_group,
.attr_update = uncore_alias_groups,
@@ -5658,6 +5661,7 @@ static struct intel_uncore_type spr_uncore_iio = {
.event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
.format_group = &snr_uncore_iio_format_group,
.attr_update = uncore_alias_groups,
+ .constraints = icx_uncore_iio_constraints,
};
static struct attribute *spr_uncore_raw_formats_attr[] = {
@@ -5686,9 +5690,16 @@ static struct intel_uncore_type spr_uncore_irp = {
};
+static struct event_constraint spr_uncore_m2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
static struct intel_uncore_type spr_uncore_m2pcie = {
SPR_UNCORE_COMMON_FORMAT(),
.name = "m2pcie",
+ .constraints = spr_uncore_m2pcie_constraints,
};
static struct intel_uncore_type spr_uncore_pcu = {
@@ -5765,6 +5776,7 @@ static struct intel_uncore_type spr_uncore_upi = {
static struct intel_uncore_type spr_uncore_m3upi = {
SPR_UNCORE_PCI_COMMON_FORMAT(),
.name = "m3upi",
+ .constraints = icx_uncore_m3upi_constraints,
};
static struct intel_uncore_type spr_uncore_mdf = {
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index c853b28efa33..96c775abe31f 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -68,6 +68,7 @@ static bool test_intel(int idx, void *data)
case INTEL_FAM6_BROADWELL_D:
case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
+ case INTEL_FAM6_SAPPHIRERAPIDS_X:
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_D:
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 134c08df7340..7b5167db3e78 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -727,6 +727,7 @@ struct x86_pmu {
void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
+ void (*assign)(struct perf_event *event, int idx);
void (*add)(struct perf_event *);
void (*del)(struct perf_event *);
void (*read)(struct perf_event *event);
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
index 1b07fb102c4e..07949102a08d 100644
--- a/arch/x86/include/asm/GEN-for-each-reg.h
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -1,11 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * These are in machine order; things rely on that.
+ */
#ifdef CONFIG_64BIT
GEN(rax)
-GEN(rbx)
GEN(rcx)
GEN(rdx)
+GEN(rbx)
+GEN(rsp)
+GEN(rbp)
GEN(rsi)
GEN(rdi)
-GEN(rbp)
GEN(r8)
GEN(r9)
GEN(r10)
@@ -16,10 +21,11 @@ GEN(r14)
GEN(r15)
#else
GEN(eax)
-GEN(ebx)
GEN(ecx)
GEN(edx)
+GEN(ebx)
+GEN(esp)
+GEN(ebp)
GEN(esi)
GEN(edi)
-GEN(ebp)
#endif
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a3c2315aca12..58eee6402832 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -75,6 +75,7 @@ extern int alternatives_patched;
extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
struct module;
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 4cb726c71ed8..8f80de627c60 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -17,21 +17,3 @@
extern void cmpxchg8b_emu(void);
#endif
-#ifdef CONFIG_RETPOLINE
-
-#undef GEN
-#define GEN(reg) \
- extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
- extern asmlinkage void __x86_indirect_alt_call_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
- extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 562854c60808..ea0c5ab31da4 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -185,6 +185,7 @@
IRQ_CONSTRAINTS, regs, vector); \
}
+#ifndef CONFIG_PREEMPT_RT
#define ASM_CALL_SOFTIRQ \
"call %P[__func] \n"
@@ -201,6 +202,8 @@
__this_cpu_write(hardirq_stack_inuse, false); \
}
+#endif
+
#else /* CONFIG_X86_64 */
/* System vector handlers always run on the stack they interrupted. */
#define run_sysvec_on_irqstack_cond(func, regs) \
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index eb0d69bb2fc6..32f300dade5e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -701,7 +701,8 @@ struct kvm_vcpu_arch {
struct kvm_pio_request pio;
void *pio_data;
- void *guest_ins_data;
+ void *sev_pio_data;
+ unsigned sev_pio_count;
u8 event_exit_inst_len;
@@ -1096,7 +1097,7 @@ struct kvm_arch {
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
- spinlock_t pvclock_gtod_sync_lock;
+ raw_spinlock_t pvclock_gtod_sync_lock;
bool use_master_clock;
u64 master_kernel_ns;
u64 master_cycle_now;
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index ec2d5c8c6694..cc74dc584836 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -5,12 +5,15 @@
#include <linux/static_key.h>
#include <linux/objtool.h>
+#include <linux/linkage.h>
#include <asm/alternative.h>
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
#include <asm/unwind_hints.h>
+#define RETPOLINE_THUNK_SIZE 32
+
/*
* Fill the CPU return stack buffer.
*
@@ -118,6 +121,16 @@
".popsection\n\t"
#ifdef CONFIG_RETPOLINE
+
+typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+
+#define GEN(reg) \
+ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+extern retpoline_thunk_t __x86_indirect_thunk_array[];
+
#ifdef CONFIG_X86_64
/*
@@ -303,63 +316,4 @@ static inline void mds_idle_clear_cpu_buffers(void)
#endif /* __ASSEMBLY__ */
-/*
- * Below is used in the eBPF JIT compiler and emits the byte sequence
- * for the following assembly:
- *
- * With retpolines configured:
- *
- * callq do_rop
- * spec_trap:
- * pause
- * lfence
- * jmp spec_trap
- * do_rop:
- * mov %rcx,(%rsp) for x86_64
- * mov %edx,(%esp) for x86_32
- * retq
- *
- * Without retpolines configured:
- *
- * jmp *%rcx for x86_64
- * jmp *%edx for x86_32
- */
-#ifdef CONFIG_RETPOLINE
-# ifdef CONFIG_X86_64
-# define RETPOLINE_RCX_BPF_JIT_SIZE 17
-# define RETPOLINE_RCX_BPF_JIT() \
-do { \
- EMIT1_off32(0xE8, 7); /* callq do_rop */ \
- /* spec_trap: */ \
- EMIT2(0xF3, 0x90); /* pause */ \
- EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \
- EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
- /* do_rop: */ \
- EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */ \
- EMIT1(0xC3); /* retq */ \
-} while (0)
-# else /* !CONFIG_X86_64 */
-# define RETPOLINE_EDX_BPF_JIT() \
-do { \
- EMIT1_off32(0xE8, 7); /* call do_rop */ \
- /* spec_trap: */ \
- EMIT2(0xF3, 0x90); /* pause */ \
- EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \
- EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
- /* do_rop: */ \
- EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */ \
- EMIT1(0xC3); /* ret */ \
-} while (0)
-# endif
-#else /* !CONFIG_RETPOLINE */
-# ifdef CONFIG_X86_64
-# define RETPOLINE_RCX_BPF_JIT_SIZE 2
-# define RETPOLINE_RCX_BPF_JIT() \
- EMIT2(0xFF, 0xE1); /* jmp *%rcx */
-# else /* !CONFIG_X86_64 */
-# define RETPOLINE_EDX_BPF_JIT() \
- EMIT2(0xFF, 0xE2) /* jmp *%edx */
-# endif
-#endif
-
#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index da3a1ac82be5..cebec95a7124 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -52,11 +52,11 @@ void __init paravirt_set_cap(void);
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
- pv_ops.cpu.io_delay();
+ PVOP_VCALL0(cpu.io_delay);
#ifdef REALLY_SLOW_IO
- pv_ops.cpu.io_delay();
- pv_ops.cpu.io_delay();
- pv_ops.cpu.io_delay();
+ PVOP_VCALL0(cpu.io_delay);
+ PVOP_VCALL0(cpu.io_delay);
+ PVOP_VCALL0(cpu.io_delay);
#endif
}
@@ -113,12 +113,12 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
/*
* These special macros can be used to get or set a debugging register
*/
-static inline unsigned long paravirt_get_debugreg(int reg)
+static __always_inline unsigned long paravirt_get_debugreg(int reg)
{
return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg);
}
#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
-static inline void set_debugreg(unsigned long val, int reg)
+static __always_inline void set_debugreg(unsigned long val, int reg)
{
PVOP_VCALL2(cpu.set_debugreg, reg, val);
}
@@ -133,14 +133,14 @@ static inline void write_cr0(unsigned long x)
PVOP_VCALL1(cpu.write_cr0, x);
}
-static inline unsigned long read_cr2(void)
+static __always_inline unsigned long read_cr2(void)
{
return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
"mov %%cr2, %%rax;",
ALT_NOT(X86_FEATURE_XENPV));
}
-static inline void write_cr2(unsigned long x)
+static __always_inline void write_cr2(unsigned long x)
{
PVOP_VCALL1(mmu.write_cr2, x);
}
@@ -653,10 +653,10 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
* functions.
*/
#define PV_THUNK_NAME(func) "__raw_callee_save_" #func
-#define PV_CALLEE_SAVE_REGS_THUNK(func) \
+#define __PV_CALLEE_SAVE_REGS_THUNK(func, section) \
extern typeof(func) __raw_callee_save_##func; \
\
- asm(".pushsection .text;" \
+ asm(".pushsection " section ", \"ax\";" \
".globl " PV_THUNK_NAME(func) ";" \
".type " PV_THUNK_NAME(func) ", @function;" \
PV_THUNK_NAME(func) ":" \
@@ -669,6 +669,9 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \
".popsection")
+#define PV_CALLEE_SAVE_REGS_THUNK(func) \
+ __PV_CALLEE_SAVE_REGS_THUNK(func, ".text")
+
/* Get a reference to a callee-save function */
#define PV_CALLEE_SAVE(func) \
((struct paravirt_callee_save) { __raw_callee_save_##func })
@@ -678,23 +681,23 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
((struct paravirt_callee_save) { func })
#ifdef CONFIG_PARAVIRT_XXL
-static inline notrace unsigned long arch_local_save_flags(void)
+static __always_inline unsigned long arch_local_save_flags(void)
{
return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
ALT_NOT(X86_FEATURE_XENPV));
}
-static inline notrace void arch_local_irq_disable(void)
+static __always_inline void arch_local_irq_disable(void)
{
PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
}
-static inline notrace void arch_local_irq_enable(void)
+static __always_inline void arch_local_irq_enable(void)
{
PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
}
-static inline notrace unsigned long arch_local_irq_save(void)
+static __always_inline unsigned long arch_local_irq_save(void)
{
unsigned long f;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1bd3e8d05604..f97aa49a31ea 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -586,7 +586,7 @@ static inline void load_sp0(unsigned long sp0)
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
/*
* Generic CPUID function
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index b94f615600d5..703663175a5a 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -181,7 +181,7 @@ static inline bool any_64bit_mode(struct pt_regs *regs)
#define current_user_stack_pointer() current_pt_regs()->sp
#define compat_user_stack_pointer() current_pt_regs()->sp
-static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs)
{
bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 630ff08532be..08b0e90623ad 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -16,7 +16,9 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
+DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
@@ -24,6 +26,11 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
return per_cpu(cpu_llc_shared_map, cpu);
}
+static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
+{
+ return per_cpu(cpu_l2c_shared_map, cpu);
+}
+
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 9239399e5491..cc164777e661 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -103,6 +103,7 @@ static inline void setup_node_to_cpumask_map(void) { }
#include <asm-generic/topology.h>
extern const struct cpumask *cpu_coregroup_mask(int cpu);
+extern const struct cpumask *cpu_clustergroup_mask(int cpu);
#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
@@ -113,7 +114,9 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
extern unsigned int __max_die_per_package;
#ifdef CONFIG_SMP
+#define topology_cluster_id(cpu) (per_cpu(cpu_l2c_id, cpu))
#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
+#define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 454b20815f35..4a7ff8b0db20 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -308,13 +308,13 @@ HYPERVISOR_platform_op(struct xen_platform_op *op)
return _hypercall1(int, platform_op, op);
}
-static inline int
+static __always_inline int
HYPERVISOR_set_debugreg(int reg, unsigned long value)
{
return _hypercall2(int, set_debugreg, reg, value);
}
-static inline unsigned long
+static __always_inline unsigned long
HYPERVISOR_get_debugreg(int reg)
{
return _hypercall1(unsigned long, get_debugreg, reg);
@@ -358,7 +358,7 @@ HYPERVISOR_event_channel_op(int cmd, void *arg)
return _hypercall2(int, event_channel_op, cmd, arg);
}
-static inline int
+static __always_inline int
HYPERVISOR_xen_version(int cmd, void *arg)
{
return _hypercall2(int, xen_version, cmd, arg);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e9da3dc71254..23fb4d51a5da 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -29,6 +29,7 @@
#include <asm/io.h>
#include <asm/fixmap.h>
#include <asm/paravirt.h>
+#include <asm/asm-prototypes.h>
int __read_mostly alternatives_patched;
@@ -113,6 +114,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
}
}
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -221,7 +223,7 @@ static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off)
* "noinline" to cause control flow change and thus invalidate I$ and
* cause refetch after modification.
*/
-static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
+static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
{
struct insn insn;
int i = 0;
@@ -239,11 +241,11 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins
* optimized.
*/
if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
- i += optimize_nops_range(instr, a->instrlen, i);
+ i += optimize_nops_range(instr, len, i);
else
i += insn.length;
- if (i >= a->instrlen)
+ if (i >= len)
return;
}
}
@@ -331,10 +333,185 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
text_poke_early(instr, insn_buff, insn_buff_sz);
next:
- optimize_nops(a, instr);
+ optimize_nops(instr, a->instrlen);
}
}
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+
+/*
+ * CALL/JMP *%\reg
+ */
+static int emit_indirect(int op, int reg, u8 *bytes)
+{
+ int i = 0;
+ u8 modrm;
+
+ switch (op) {
+ case CALL_INSN_OPCODE:
+ modrm = 0x10; /* Reg = 2; CALL r/m */
+ break;
+
+ case JMP32_INSN_OPCODE:
+ modrm = 0x20; /* Reg = 4; JMP r/m */
+ break;
+
+ default:
+ WARN_ON_ONCE(1);
+ return -1;
+ }
+
+ if (reg >= 8) {
+ bytes[i++] = 0x41; /* REX.B prefix */
+ reg -= 8;
+ }
+
+ modrm |= 0xc0; /* Mod = 3 */
+ modrm += reg;
+
+ bytes[i++] = 0xff; /* opcode */
+ bytes[i++] = modrm;
+
+ return i;
+}
+
+/*
+ * Rewrite the compiler generated retpoline thunk calls.
+ *
+ * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate
+ * indirect instructions, avoiding the extra indirection.
+ *
+ * For example, convert:
+ *
+ * CALL __x86_indirect_thunk_\reg
+ *
+ * into:
+ *
+ * CALL *%\reg
+ *
+ * It also tries to inline spectre_v2=retpoline,amd when size permits.
+ */
+static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
+{
+ retpoline_thunk_t *target;
+ int reg, ret, i = 0;
+ u8 op, cc;
+
+ target = addr + insn->length + insn->immediate.value;
+ reg = target - __x86_indirect_thunk_array;
+
+ if (WARN_ON_ONCE(reg & ~0xf))
+ return -1;
+
+ /* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */
+ BUG_ON(reg == 4);
+
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+ !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD))
+ return -1;
+
+ op = insn->opcode.bytes[0];
+
+ /*
+ * Convert:
+ *
+ * Jcc.d32 __x86_indirect_thunk_\reg
+ *
+ * into:
+ *
+ * Jncc.d8 1f
+ * [ LFENCE ]
+ * JMP *%\reg
+ * [ NOP ]
+ * 1:
+ */
+ /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+ if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+ cc = insn->opcode.bytes[1] & 0xf;
+ cc ^= 1; /* invert condition */
+
+ bytes[i++] = 0x70 + cc; /* Jcc.d8 */
+ bytes[i++] = insn->length - 2; /* sizeof(Jcc.d8) == 2 */
+
+ /* Continue as if: JMP.d32 __x86_indirect_thunk_\reg */
+ op = JMP32_INSN_OPCODE;
+ }
+
+ /*
+ * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+ bytes[i++] = 0x0f;
+ bytes[i++] = 0xae;
+ bytes[i++] = 0xe8; /* LFENCE */
+ }
+
+ ret = emit_indirect(op, reg, bytes + i);
+ if (ret < 0)
+ return ret;
+ i += ret;
+
+ for (; i < insn->length;)
+ bytes[i++] = BYTES_NOP1;
+
+ return i;
+}
+
+/*
+ * Generated by 'objtool --retpoline'.
+ */
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
+{
+ s32 *s;
+
+ for (s = start; s < end; s++) {
+ void *addr = (void *)s + *s;
+ struct insn insn;
+ int len, ret;
+ u8 bytes[16];
+ u8 op1, op2;
+
+ ret = insn_decode_kernel(&insn, addr);
+ if (WARN_ON_ONCE(ret < 0))
+ continue;
+
+ op1 = insn.opcode.bytes[0];
+ op2 = insn.opcode.bytes[1];
+
+ switch (op1) {
+ case CALL_INSN_OPCODE:
+ case JMP32_INSN_OPCODE:
+ break;
+
+ case 0x0f: /* escape */
+ if (op2 >= 0x80 && op2 <= 0x8f)
+ break;
+ fallthrough;
+ default:
+ WARN_ON_ONCE(1);
+ continue;
+ }
+
+ DPRINTK("retpoline at: %pS (%px) len: %d to: %pS",
+ addr, addr, insn.length,
+ addr + insn.length + insn.immediate.value);
+
+ len = patch_retpoline(addr, &insn, bytes);
+ if (len == insn.length) {
+ optimize_nops(bytes, len);
+ DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr);
+ DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+ text_poke_early(addr, bytes, len);
+ }
+ }
+}
+
+#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
+
#ifdef CONFIG_SMP
static void alternatives_smp_lock(const s32 *start, const s32 *end,
u8 *text, u8 *text_end)
@@ -643,6 +820,12 @@ void __init alternative_instructions(void)
apply_paravirt(__parainstructions, __parainstructions_end);
/*
+ * Rewrite the retpolines, must be done before alternatives since
+ * those can rewrite the retpoline thunks.
+ */
+ apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+
+ /*
* Then patch alternatives, such that those paravirt calls that are in
* alternatives can be overwritten by their immediate fragments.
*/
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index f4da9bb69a88..e696e22d0531 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -15,9 +15,15 @@ struct cluster_mask {
struct cpumask mask;
};
-static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+/*
+ * __x2apic_send_IPI_mask() possibly needs to read
+ * x86_cpu_to_logical_apicid for all online cpus in a sequential way.
+ * Using per cpu variable would cost one cache line per cpu.
+ */
+static u32 *x86_cpu_to_logical_apicid __read_mostly;
+
static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
-static DEFINE_PER_CPU(struct cluster_mask *, cluster_masks);
+static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks);
static struct cluster_mask *cluster_hotplug_mask;
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
@@ -27,7 +33,7 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
static void x2apic_send_IPI(int cpu, int vector)
{
- u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
+ u32 dest = x86_cpu_to_logical_apicid[cpu];
/* x2apic MSRs are special and need a special fence: */
weak_wrmsr_fence();
@@ -58,7 +64,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
dest = 0;
for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask)
- dest |= per_cpu(x86_cpu_to_logical_apicid, clustercpu);
+ dest |= x86_cpu_to_logical_apicid[clustercpu];
if (!dest)
continue;
@@ -94,7 +100,7 @@ static void x2apic_send_IPI_all(int vector)
static u32 x2apic_calc_apicid(unsigned int cpu)
{
- return per_cpu(x86_cpu_to_logical_apicid, cpu);
+ return x86_cpu_to_logical_apicid[cpu];
}
static void init_x2apic_ldr(void)
@@ -103,7 +109,7 @@ static void init_x2apic_ldr(void)
u32 cluster, apicid = apic_read(APIC_LDR);
unsigned int cpu;
- this_cpu_write(x86_cpu_to_logical_apicid, apicid);
+ x86_cpu_to_logical_apicid[smp_processor_id()] = apicid;
if (cmsk)
goto update;
@@ -166,12 +172,21 @@ static int x2apic_dead_cpu(unsigned int dead_cpu)
static int x2apic_cluster_probe(void)
{
+ u32 slots;
+
if (!x2apic_mode)
return 0;
+ slots = max_t(u32, L1_CACHE_BYTES/sizeof(u32), nr_cpu_ids);
+ x86_cpu_to_logical_apicid = kcalloc(slots, sizeof(u32), GFP_KERNEL);
+ if (!x86_cpu_to_logical_apicid)
+ return 0;
+
if (cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
x2apic_prepare_cpu, x2apic_dead_cpu) < 0) {
pr_err("Failed to register X2APIC_PREPARE\n");
+ kfree(x86_cpu_to_logical_apicid);
+ x86_cpu_to_logical_apicid = NULL;
return 0;
}
init_x2apic_ldr();
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6c8a86b58020..31e2412b3f17 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -882,13 +882,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
return SPECTRE_V2_CMD_AUTO;
}
- if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
- boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
- boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
- pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
- return SPECTRE_V2_CMD_AUTO;
- }
-
spec_v2_print_cond(mitigation_options[i].option,
mitigation_options[i].secure);
return cmd;
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index b5e36bd0425b..fe98a1465be6 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -846,6 +846,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
l2 = new_l2;
#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l2_id;
+ per_cpu(cpu_l2c_id, cpu) = l2_id;
#endif
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 486dc8c1d388..8ed18d00c211 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -85,6 +85,9 @@ u16 get_llc_id(unsigned int cpu)
}
EXPORT_SYMBOL_GPL(get_llc_id);
+/* L2 cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID;
+
/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 044902d5a3c4..e5dd6da78713 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -132,6 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
return 0;
}
+#ifndef CONFIG_PREEMPT_RT
void do_softirq_own_stack(void)
{
struct irq_stack *irqstk;
@@ -148,6 +149,7 @@ void do_softirq_own_stack(void)
call_on_stack(__do_softirq, isp);
}
+#endif
void __handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 8ef35063964b..760e1f293093 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -7,9 +7,11 @@
/*
* unsigned long native_save_fl(void)
*/
+.pushsection .noinstr.text, "ax"
SYM_FUNC_START(native_save_fl)
pushf
pop %_ASM_AX
ret
SYM_FUNC_END(native_save_fl)
+.popsection
EXPORT_SYMBOL(native_save_fl)
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 1afbdd1dd777..9ff480e94511 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -198,7 +198,7 @@ void sched_set_itmt_core_prio(int prio, int core_cpu)
* of the priority chain and only used when
* all other high priority cpus are out of capacity.
*/
- smt_prio = prio * smp_num_siblings / i;
+ smt_prio = prio * smp_num_siblings / (i * i);
per_cpu(sched_core_priority, cpu) = smt_prio;
i++;
}
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 5e9a34b5bd74..169fb6f4cd2e 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -251,7 +251,8 @@ int module_finalize(const Elf_Ehdr *hdr,
struct module *me)
{
const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
- *para = NULL, *orc = NULL, *orc_ip = NULL;
+ *para = NULL, *orc = NULL, *orc_ip = NULL,
+ *retpolines = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -267,8 +268,14 @@ int module_finalize(const Elf_Ehdr *hdr,
orc = s;
if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
orc_ip = s;
+ if (!strcmp(".retpoline_sites", secstrings + s->sh_name))
+ retpolines = s;
}
+ if (retpolines) {
+ void *rseg = (void *)retpolines->sh_addr;
+ apply_retpolines(rseg, rseg + retpolines->sh_size);
+ }
if (alt) {
/* patch .altinstructions */
void *aseg = (void *)alt->sh_addr;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 04cafc057bed..ebc45360ffd4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -218,6 +218,36 @@ void paravirt_end_context_switch(struct task_struct *next)
if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
arch_enter_lazy_mmu_mode();
}
+
+static noinstr unsigned long pv_native_read_cr2(void)
+{
+ return native_read_cr2();
+}
+
+static noinstr void pv_native_write_cr2(unsigned long val)
+{
+ native_write_cr2(val);
+}
+
+static noinstr unsigned long pv_native_get_debugreg(int regno)
+{
+ return native_get_debugreg(regno);
+}
+
+static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
+{
+ native_set_debugreg(regno, val);
+}
+
+static noinstr void pv_native_irq_enable(void)
+{
+ native_irq_enable();
+}
+
+static noinstr void pv_native_irq_disable(void)
+{
+ native_irq_disable();
+}
#endif
enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
@@ -244,8 +274,8 @@ struct paravirt_patch_template pv_ops = {
#ifdef CONFIG_PARAVIRT_XXL
.cpu.cpuid = native_cpuid,
- .cpu.get_debugreg = native_get_debugreg,
- .cpu.set_debugreg = native_set_debugreg,
+ .cpu.get_debugreg = pv_native_get_debugreg,
+ .cpu.set_debugreg = pv_native_set_debugreg,
.cpu.read_cr0 = native_read_cr0,
.cpu.write_cr0 = native_write_cr0,
.cpu.write_cr4 = native_write_cr4,
@@ -281,8 +311,8 @@ struct paravirt_patch_template pv_ops = {
/* Irq ops. */
.irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
- .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
- .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
+ .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
+ .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
.irq.safe_halt = native_safe_halt,
.irq.halt = native_halt,
#endif /* CONFIG_PARAVIRT_XXL */
@@ -298,8 +328,8 @@ struct paravirt_patch_template pv_ops = {
.mmu.exit_mmap = paravirt_nop,
#ifdef CONFIG_PARAVIRT_XXL
- .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(native_read_cr2),
- .mmu.write_cr2 = native_write_cr2,
+ .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
+ .mmu.write_cr2 = pv_native_write_cr2,
.mmu.read_cr3 = __native_read_cr3,
.mmu.write_cr3 = native_write_cr3,
@@ -371,9 +401,6 @@ struct paravirt_patch_template pv_ops = {
};
#ifdef CONFIG_PARAVIRT_XXL
-/* At this point, native_get/set_debugreg has real function entries */
-NOKPROBE_SYMBOL(native_get_debugreg);
-NOKPROBE_SYMBOL(native_set_debugreg);
NOKPROBE_SYMBOL(native_load_idt);
void (*paravirt_iret)(void) = native_iret;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f3f251787b99..eb470be0e5ae 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -45,6 +45,7 @@
#include <asm/io_bitmap.h>
#include <asm/proto.h>
#include <asm/frame.h>
+#include <asm/unwind.h>
#include "process.h"
@@ -957,60 +958,22 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
* because the task might wake up and we might look at a stack
* changing under us.
*/
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
- unsigned long start, bottom, top, sp, fp, ip, ret = 0;
- int count = 0;
+ struct unwind_state state;
+ unsigned long addr = 0;
- if (p == current || task_is_running(p))
- return 0;
-
- if (!try_get_task_stack(p))
- return 0;
-
- start = (unsigned long)task_stack_page(p);
- if (!start)
- goto out;
-
- /*
- * Layout of the stack page:
- *
- * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
- * PADDING
- * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
- * stack
- * ----------- bottom = start
- *
- * The tasks stack pointer points at the location where the
- * framepointer is stored. The data on the stack is:
- * ... IP FP ... IP FP
- *
- * We need to read FP and IP, so we need to adjust the upper
- * bound by another unsigned long.
- */
- top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
- top -= 2 * sizeof(unsigned long);
- bottom = start;
-
- sp = READ_ONCE(p->thread.sp);
- if (sp < bottom || sp > top)
- goto out;
-
- fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp);
- do {
- if (fp < bottom || fp > top)
- goto out;
- ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
- if (!in_sched_functions(ip)) {
- ret = ip;
- goto out;
- }
- fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
- } while (count++ < 16 && !task_is_running(p));
+ for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr)
+ break;
+ if (in_sched_functions(addr))
+ continue;
+ break;
+ }
-out:
- put_task_stack(p);
- return ret;
+ return addr;
}
long do_arch_prctl_common(struct task_struct *task, int option,
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index bf1033a62e48..ff1e82ff52d9 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -64,7 +64,7 @@ static bool sev_es_negotiate_protocol(void)
static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
{
ghcb->save.sw_exit_code = 0;
- memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+ __builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}
static bool vc_decoding_needed(unsigned long exit_code)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2577ed3b5e6b..959599ac25a6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,6 +101,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map);
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
+
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
@@ -464,6 +466,21 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
+static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ /* If the arch didn't set up l2c_id, fall back to SMT */
+ if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID)
+ return match_smt(c, o);
+
+ /* Do not match if L2 cache id does not match: */
+ if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2))
+ return false;
+
+ return topology_sane(c, o, "l2c");
+}
+
/*
* Unlike the other levels, we do not enforce keeping a
* multicore group inside a NUMA node. If this happens, we will
@@ -523,7 +540,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
}
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
static inline int x86_sched_itmt_flags(void)
{
return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -541,12 +558,21 @@ static int x86_smt_flags(void)
return cpu_smt_flags() | x86_sched_itmt_flags();
}
#endif
+#ifdef CONFIG_SCHED_CLUSTER
+static int x86_cluster_flags(void)
+{
+ return cpu_cluster_flags() | x86_sched_itmt_flags();
+}
+#endif
#endif
static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
+#ifdef CONFIG_SCHED_CLUSTER
+ { cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
#ifdef CONFIG_SCHED_MC
{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
@@ -557,6 +583,9 @@ static struct sched_domain_topology_level x86_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
+#ifdef CONFIG_SCHED_CLUSTER
+ { cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
#ifdef CONFIG_SCHED_MC
{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
@@ -584,6 +613,7 @@ void set_cpu_sibling_map(int cpu)
if (!has_mp) {
cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_l2c_shared_mask(cpu));
cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
c->booted_cores = 1;
@@ -602,6 +632,9 @@ void set_cpu_sibling_map(int cpu)
if ((i == cpu) || (has_mp && match_llc(c, o)))
link_mask(cpu_llc_shared_mask, cpu, i);
+ if ((i == cpu) || (has_mp && match_l2c(c, o)))
+ link_mask(cpu_l2c_shared_mask, cpu, i);
+
if ((i == cpu) || (has_mp && match_die(c, o)))
link_mask(topology_die_cpumask, cpu, i);
}
@@ -652,6 +685,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
return cpu_llc_shared_mask(cpu);
}
+const struct cpumask *cpu_clustergroup_mask(int cpu)
+{
+ return cpu_l2c_shared_mask(cpu);
+}
+
static void impress_friends(void)
{
int cpu;
@@ -1335,6 +1373,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
}
/*
@@ -1564,7 +1603,10 @@ static void remove_siblinginfo(int cpu)
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+ for_each_cpu(sibling, cpu_l2c_shared_mask(cpu))
+ cpumask_clear_cpu(cpu, cpu_l2c_shared_mask(sibling));
cpumask_clear(cpu_llc_shared_mask(cpu));
+ cpumask_clear(cpu_l2c_shared_mask(cpu));
cpumask_clear(topology_sibling_cpumask(cpu));
cpumask_clear(topology_core_cpumask(cpu));
cpumask_clear(topology_die_cpumask(cpu));
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index efd9e9ea17f2..3d6dc12d198f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -272,6 +272,20 @@ SECTIONS
__parainstructions_end = .;
}
+#ifdef CONFIG_RETPOLINE
+ /*
+ * List of instructions that call/jmp/jcc to retpoline thunks
+ * __x86_indirect_thunk_*(). These instructions can be patched along
+ * with alternatives, after which the section can be freed.
+ */
+ . = ALIGN(8);
+ .retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) {
+ __retpoline_sites = .;
+ *(.retpoline_sites)
+ __retpoline_sites_end = .;
+ }
+#endif
+
/*
* struct alt_inst entries. From the header (alternative.h):
* "Alternative instructions for different CPU types or capabilities"
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 76fb00921203..d6ac32f3f650 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);
void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ u64 msr_val;
int i;
if (!init_event) {
- vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE |
- MSR_IA32_APICBASE_ENABLE;
+ msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_reset_bsp(vcpu))
- vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ msr_val |= MSR_IA32_APICBASE_BSP;
+ kvm_lapic_set_base(vcpu, msr_val);
}
if (!apic)
@@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- if (!init_event) {
- apic->base_address = APIC_DEFAULT_PHYS_BASE;
-
+ /* The xAPIC ID is set at RESET even if the APIC was already enabled. */
+ if (!init_event)
kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
- }
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
@@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
lapic_timer_advance_dynamic = false;
}
+ /*
+ * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
+ * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset().
+ */
+ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
@@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
void kvm_lapic_exit(void)
{
static_key_deferred_flush(&apic_hw_disabled);
+ WARN_ON(static_branch_unlikely(&apic_hw_disabled.key));
static_key_deferred_flush(&apic_sw_disabled);
+ WARN_ON(static_branch_unlikely(&apic_sw_disabled.key));
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1a64ba5b9437..0cc58901bf7a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4596,10 +4596,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu)
unsigned bit;
bool wp;
- if (!is_cr4_pke(mmu)) {
- mmu->pkru_mask = 0;
+ mmu->pkru_mask = 0;
+
+ if (!is_cr4_pke(mmu))
return;
- }
wp = is_cr0_wp(mmu);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 3c57bd091120..5847b05d29da 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -618,7 +618,12 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
vmsa.address = __sme_pa(svm->vmsa);
vmsa.len = PAGE_SIZE;
- return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ if (ret)
+ return ret;
+
+ vcpu->arch.guest_state_protected = true;
+ return 0;
}
static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
@@ -1479,6 +1484,13 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
goto e_free_trans;
}
+ /*
+ * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP
+ * encrypts the written data with the guest's key, and the cache may
+ * contain dirty, unencrypted data.
+ */
+ sev_clflush_pages(guest_page, n);
+
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
data.guest_address |= sev_me_mask;
@@ -2579,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
{
- if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+ int count;
+ int bytes;
+
+ if (svm->vmcb->control.exit_info_2 > INT_MAX)
+ return -EINVAL;
+
+ count = svm->vmcb->control.exit_info_2;
+ if (unlikely(check_mul_overflow(count, size, &bytes)))
+ return -EINVAL;
+
+ if (!setup_vmgexit_scratch(svm, in, bytes))
return -EINVAL;
- return kvm_sev_es_string_io(&svm->vcpu, size, port,
- svm->ghcb_sa, svm->ghcb_sa_len, in);
+ return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
}
void sev_es_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 128a54b1fbf1..e63ac08115cf 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -191,7 +191,7 @@ struct vcpu_svm {
/* SEV-ES scratch area support */
void *ghcb_sa;
- u64 ghcb_sa_len;
+ u32 ghcb_sa_len;
bool ghcb_sa_sync;
bool ghcb_sa_free;
@@ -218,12 +218,12 @@ DECLARE_PER_CPU(struct svm_cpu_data *, svm_data);
void recalc_intercepts(struct vcpu_svm *svm);
-static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
+static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
{
return container_of(kvm, struct kvm_svm, kvm);
}
-static inline bool sev_guest(struct kvm *kvm)
+static __always_inline bool sev_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -234,7 +234,7 @@ static inline bool sev_guest(struct kvm *kvm)
#endif
}
-static inline bool sev_es_guest(struct kvm *kvm)
+static __always_inline bool sev_es_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -271,7 +271,7 @@ static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit)
return !test_bit(bit, (unsigned long *)&vmcb->control.clean);
}
-static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
+static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
{
return container_of(vcpu, struct vcpu_svm, vcpu);
}
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 22e2b019de37..9430d6437c9f 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -56,12 +56,12 @@ static inline void invlpga(unsigned long addr, u32 asid)
* VMSAVE, VMLOAD, etc... is still controlled by the effective address size,
* hence 'unsigned long' instead of 'hpa_t'.
*/
-static inline void vmsave(unsigned long pa)
+static __always_inline void vmsave(unsigned long pa)
{
svm_asm1(vmsave, "a" (pa), "memory");
}
-static inline void vmload(unsigned long pa)
+static __always_inline void vmload(unsigned long pa)
{
svm_asm1(vmload, "a" (pa), "memory");
}
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index 152ab0aa82cf..16731d2cf231 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -93,7 +93,7 @@ static __always_inline int get_evmcs_offset(unsigned long field,
return evmcs_field->offset;
}
-static inline void evmcs_write64(unsigned long field, u64 value)
+static __always_inline void evmcs_write64(unsigned long field, u64 value)
{
u16 clean_field;
int offset = get_evmcs_offset(field, &clean_field);
@@ -183,7 +183,7 @@ static inline void evmcs_load(u64 phys_addr)
__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
#else /* !IS_ENABLED(CONFIG_HYPERV) */
-static inline void evmcs_write64(unsigned long field, u64 value) {}
+static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
static inline void evmcs_write32(unsigned long field, u32 value) {}
static inline void evmcs_write16(unsigned long field, u16 value) {}
static inline u64 evmcs_read64(unsigned long field) { return 0; }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a979279a37b..fb9e4ac3df22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5562,9 +5562,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
{
- vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
- vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
- return 0;
+ /*
+ * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK
+ * VM-Exits. Unconditionally set the flag here and leave the handling to
+ * vmx_handle_exit().
+ */
+ to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+ return 1;
}
/*
@@ -6051,9 +6055,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
int ret = __vmx_handle_exit(vcpu, exit_fastpath);
/*
- * Even when current exit reason is handled by KVM internally, we
- * still need to exit to user space when bus lock detected to inform
- * that there is a bus lock in guest.
+ * Exit to user space when bus lock detected to inform that there is
+ * a bus lock in guest.
*/
if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
if (ret > 0)
@@ -6302,18 +6305,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
/*
* If we are running L2 and L1 has a new pending interrupt
- * which can be injected, we should re-evaluate
- * what should be done with this new L1 interrupt.
- * If L1 intercepts external-interrupts, we should
- * exit from L2 to L1. Otherwise, interrupt should be
- * delivered directly to L2.
+ * which can be injected, this may cause a vmexit or it may
+ * be injected into L2. Either way, this interrupt will be
+ * processed via KVM_REQ_EVENT, not RVI, because we do not use
+ * virtual interrupt delivery to inject L1 interrupts into L2.
*/
- if (is_guest_mode(vcpu) && max_irr_updated) {
- if (nested_exit_on_intr(vcpu))
- kvm_vcpu_exiting_guest_mode(vcpu);
- else
- kvm_make_request(KVM_REQ_EVENT, vcpu);
- }
+ if (is_guest_mode(vcpu) && max_irr_updated)
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
} else {
max_irr = kvm_lapic_find_highest_irr(vcpu);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c953ec24a75c..2686f2edb47c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
@@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
}
kvm_track_tsc_matching(vcpu);
- spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
kvm_make_mclock_inprogress_request(kvm);
/* no guest entries from this point */
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm)
unsigned long flags;
u64 ret;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
@@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -5983,13 +5983,13 @@ set_pit2_out:
* is slightly ahead) here we risk going negative on unsigned
* 'system_time' when 'user_ns.clock' is very small.
*/
- spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
if (kvm->arch.use_master_clock)
now_ns = ka->master_kernel_ns;
else
now_ns = get_kvmclock_base_ns();
ka->kvmclock_offset = user_ns.clock - now_ns;
- spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
@@ -6789,7 +6789,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
}
static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val,
+ unsigned short port,
unsigned int count, bool in)
{
vcpu->arch.pio.port = port;
@@ -6797,10 +6797,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
vcpu->arch.pio.count = count;
vcpu->arch.pio.size = size;
- if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
- vcpu->arch.pio.count = 0;
+ if (!kernel_pio(vcpu, vcpu->arch.pio_data))
return 1;
- }
vcpu->run->exit_reason = KVM_EXIT_IO;
vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
@@ -6812,26 +6810,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
return 0;
}
-static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val, unsigned int count)
+static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, unsigned int count)
{
- int ret;
+ WARN_ON(vcpu->arch.pio.count);
+ memset(vcpu->arch.pio_data, 0, size * count);
+ return emulator_pio_in_out(vcpu, size, port, count, true);
+}
- if (vcpu->arch.pio.count)
- goto data_avail;
+static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
+{
+ int size = vcpu->arch.pio.size;
+ unsigned count = vcpu->arch.pio.count;
+ memcpy(val, vcpu->arch.pio_data, size * count);
+ trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
+ vcpu->arch.pio.count = 0;
+}
- memset(vcpu->arch.pio_data, 0, size * count);
+static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, void *val, unsigned int count)
+{
+ if (vcpu->arch.pio.count) {
+ /* Complete previous iteration. */
+ } else {
+ int r = __emulator_pio_in(vcpu, size, port, count);
+ if (!r)
+ return r;
- ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
- if (ret) {
-data_avail:
- memcpy(val, vcpu->arch.pio_data, size * count);
- trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
- vcpu->arch.pio.count = 0;
- return 1;
+ /* Results already available, fall through. */
}
- return 0;
+ WARN_ON(count != vcpu->arch.pio.count);
+ complete_emulator_pio_in(vcpu, val);
+ return 1;
}
static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
@@ -6846,9 +6857,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size,
unsigned short port, const void *val,
unsigned int count)
{
+ int ret;
+
memcpy(vcpu->arch.pio_data, val, size * count);
trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
- return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+ ret = emulator_pio_in_out(vcpu, size, port, count, false);
+ if (ret)
+ vcpu->arch.pio.count = 0;
+
+ return ret;
}
static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
@@ -8022,9 +8039,9 @@ static void kvm_hyperv_tsc_notifier(void)
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -8656,9 +8673,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+ /*
+ * The call to kvm_ready_for_interrupt_injection() may end up in
+ * kvm_xen_has_interrupt() which may require the srcu lock to be
+ * held, to protect against changes in the vcpu_info address.
+ */
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_run->ready_for_interrupt_injection =
pic_in_kernel(vcpu->kvm) ||
kvm_vcpu_ready_for_interrupt_injection(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (is_smm(vcpu))
kvm_run->flags |= KVM_RUN_X86_SMM;
@@ -9516,14 +9541,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
- if (unlikely(kvm_vcpu_exit_request(vcpu))) {
+ if (vcpu->arch.apicv_active)
+ static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+
+ if (unlikely(kvm_vcpu_exit_request(vcpu))) {
exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
break;
}
-
- if (vcpu->arch.apicv_active)
- static_call(kvm_x86_sync_pir_to_irr)(vcpu);
- }
+ }
/*
* Do this here before restoring debug registers on the host. And
@@ -10986,7 +11011,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
- spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
pvclock_update_vm_gtod_copy(kvm);
@@ -11196,7 +11221,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
int level = i + 1;
int lpages = __kvm_mmu_slot_lpages(slot, npages, level);
- WARN_ON(slot->arch.rmap[i]);
+ if (slot->arch.rmap[i])
+ continue;
slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
if (!slot->arch.rmap[i]) {
@@ -12171,44 +12197,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
}
EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
-static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port);
+
+static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu)
{
- memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
- vcpu->arch.pio.count * vcpu->arch.pio.size);
- vcpu->arch.pio.count = 0;
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+ vcpu->arch.pio.count = 0;
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_outs(vcpu, size, port);
return 1;
}
static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port)
{
- int ret;
-
- ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret)
- return ret;
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count);
+
+ /* memcpy done already by emulator_pio_out. */
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+ if (!ret)
+ break;
- vcpu->arch.pio.count = 0;
+ /* Emulation done by the kernel. */
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
+ }
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs;
return 0;
}
static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port);
+
+static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
{
- int ret;
+ unsigned count = vcpu->arch.pio.count;
+ complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+}
- ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret) {
- vcpu->arch.pio.count = 0;
- } else {
- vcpu->arch.guest_ins_data = data;
- vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+
+ advance_sev_es_emulated_ins(vcpu);
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_ins(vcpu, size, port);
+ return 1;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port)
+{
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ if (!__emulator_pio_in(vcpu, size, port, count))
+ break;
+
+ /* Emulation done by the kernel. */
+ advance_sev_es_emulated_ins(vcpu);
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
}
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
return 0;
}
@@ -12216,8 +12279,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
unsigned int port, void *data, unsigned int count,
int in)
{
- return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
- : kvm_sev_es_outs(vcpu, size, port, data, count);
+ vcpu->arch.sev_pio_data = data;
+ vcpu->arch.sev_pio_count = count;
+ return in ? kvm_sev_es_ins(vcpu, size, port)
+ : kvm_sev_es_outs(vcpu, size, port);
}
EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9ea9c3dabe37..8f62baebd028 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
+ int err;
u8 rc = 0;
/*
@@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
if (likely(slots->generation == ghc->generation &&
!kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
/* Fast path */
- __get_user(rc, (u8 __user *)ghc->hva + offset);
- } else {
- /* Slow path */
- kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
- sizeof(rc));
+ pagefault_disable();
+ err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+ pagefault_enable();
+ if (!err)
+ return rc;
}
+ /* Slow path */
+
+ /*
+ * This function gets called from kvm_vcpu_block() after setting the
+ * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+ * from a HLT. So we really mustn't sleep. If the page ended up absent
+ * at that point, just return 1 in order to trigger an immediate wake,
+ * and we'll end up getting called again from a context where we *can*
+ * fault in the page and wait for it.
+ */
+ if (in_atomic() || !task_is_running(current))
+ return 1;
+
+ kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+ sizeof(rc));
+
return rc;
}
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index ec9922cba30a..cf0b39f97adc 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -28,46 +28,14 @@
.macro THUNK reg
- .align 32
-
-SYM_FUNC_START(__x86_indirect_thunk_\reg)
+ .align RETPOLINE_THUNK_SIZE
+SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_EMPTY
ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
__stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
-SYM_FUNC_END(__x86_indirect_thunk_\reg)
-
-.endm
-
-/*
- * This generates .altinstr_replacement symbols for use by objtool. They,
- * however, must not actually live in .altinstr_replacement since that will be
- * discarded after init, but module alternatives will also reference these
- * symbols.
- *
- * Their names matches the "__x86_indirect_" prefix to mark them as retpolines.
- */
-.macro ALT_THUNK reg
-
- .align 1
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg)
- ANNOTATE_RETPOLINE_SAFE
-1: call *%\reg
-2: .skip 5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_call_\reg)
-
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_call_\reg)
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg)
- ANNOTATE_RETPOLINE_SAFE
-1: jmp *%\reg
-2: .skip 5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_jmp_\reg)
-
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
-
.endm
/*
@@ -85,22 +53,16 @@ STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
-#undef GEN
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_thunk_array)
+
#define GEN(reg) THUNK reg
#include <asm/GEN-for-each-reg.h>
-
#undef GEN
-#define GEN(reg) EXPORT_THUNK(reg)
-#include <asm/GEN-for-each-reg.h>
-#undef GEN
-#define GEN(reg) ALT_THUNK reg
-#include <asm/GEN-for-each-reg.h>
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_thunk_array)
-#undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg)
+#define GEN(reg) EXPORT_THUNK(reg)
#include <asm/GEN-for-each-reg.h>
-
#undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg)
-#include <asm/GEN-for-each-reg.h>
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e63ca38acbe4..8796559f62a4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,7 +15,6 @@
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
-#include <asm/asm-prototypes.h>
static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
@@ -225,6 +224,14 @@ static void jit_fill_hole(void *area, unsigned int size)
struct jit_context {
int cleanup_addr; /* Epilogue code offset */
+
+ /*
+ * Program specific offsets of labels in the code; these rely on the
+ * JIT doing at least 2 passes, recording the position on the first
+ * pass, only to generate the correct offset on the second pass.
+ */
+ int tail_call_direct_label;
+ int tail_call_indirect_label;
};
/* Maximum number of bytes emitted while JITing one eBPF insn */
@@ -380,20 +387,23 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
}
-static int get_pop_bytes(bool *callee_regs_used)
+#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8)
+
+static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
{
- int bytes = 0;
+ u8 *prog = *pprog;
- if (callee_regs_used[3])
- bytes += 2;
- if (callee_regs_used[2])
- bytes += 2;
- if (callee_regs_used[1])
- bytes += 2;
- if (callee_regs_used[0])
- bytes += 1;
+#ifdef CONFIG_RETPOLINE
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+ EMIT_LFENCE();
+ EMIT2(0xFF, 0xE0 + reg);
+ } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+ emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
+ } else
+#endif
+ EMIT2(0xFF, 0xE0 + reg);
- return bytes;
+ *pprog = prog;
}
/*
@@ -411,29 +421,12 @@ static int get_pop_bytes(bool *callee_regs_used)
* out:
*/
static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
- u32 stack_depth)
+ u32 stack_depth, u8 *ip,
+ struct jit_context *ctx)
{
int tcc_off = -4 - round_up(stack_depth, 8);
- u8 *prog = *pprog;
- int pop_bytes = 0;
- int off1 = 42;
- int off2 = 31;
- int off3 = 9;
-
- /* count the additional bytes used for popping callee regs from stack
- * that need to be taken into account for each of the offsets that
- * are used for bailing out of the tail call
- */
- pop_bytes = get_pop_bytes(callee_regs_used);
- off1 += pop_bytes;
- off2 += pop_bytes;
- off3 += pop_bytes;
-
- if (stack_depth) {
- off1 += 7;
- off2 += 7;
- off3 += 7;
- }
+ u8 *prog = *pprog, *start = *pprog;
+ int offset;
/*
* rdi - pointer to ctx
@@ -448,8 +441,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
EMIT2(0x89, 0xD2); /* mov edx, edx */
EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */
offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
- EMIT2(X86_JBE, OFFSET1); /* jbe out */
+
+ offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+ EMIT2(X86_JBE, offset); /* jbe out */
/*
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -457,8 +451,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
- EMIT2(X86_JA, OFFSET2); /* ja out */
+
+ offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+ EMIT2(X86_JA, offset); /* ja out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
@@ -471,12 +466,11 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
* goto out;
*/
EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */
-#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
- EMIT2(X86_JE, OFFSET3); /* je out */
- *pprog = prog;
- pop_callee_regs(pprog, callee_regs_used);
- prog = *pprog;
+ offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+ EMIT2(X86_JE, offset); /* je out */
+
+ pop_callee_regs(&prog, callee_regs_used);
EMIT1(0x58); /* pop rax */
if (stack_depth)
@@ -493,41 +487,21 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
* rdi == ctx (1st arg)
* rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
*/
- RETPOLINE_RCX_BPF_JIT();
+ emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));
/* out: */
+ ctx->tail_call_indirect_label = prog - start;
*pprog = prog;
}
static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
- u8 **pprog, int addr, u8 *image,
- bool *callee_regs_used, u32 stack_depth)
+ u8 **pprog, u8 *ip,
+ bool *callee_regs_used, u32 stack_depth,
+ struct jit_context *ctx)
{
int tcc_off = -4 - round_up(stack_depth, 8);
- u8 *prog = *pprog;
- int pop_bytes = 0;
- int off1 = 20;
- int poke_off;
-
- /* count the additional bytes used for popping callee regs to stack
- * that need to be taken into account for jump offset that is used for
- * bailing out from of the tail call when limit is reached
- */
- pop_bytes = get_pop_bytes(callee_regs_used);
- off1 += pop_bytes;
-
- /*
- * total bytes for:
- * - nop5/ jmpq $off
- * - pop callee regs
- * - sub rsp, $val if depth > 0
- * - pop rax
- */
- poke_off = X86_PATCH_SIZE + pop_bytes + 1;
- if (stack_depth) {
- poke_off += 7;
- off1 += 7;
- }
+ u8 *prog = *pprog, *start = *pprog;
+ int offset;
/*
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -535,28 +509,30 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
- EMIT2(X86_JA, off1); /* ja out */
+
+ offset = ctx->tail_call_direct_label - (prog + 2 - start);
+ EMIT2(X86_JA, offset); /* ja out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
- poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+ poke->tailcall_bypass = ip + (prog - start);
poke->adj_off = X86_TAIL_CALL_OFFSET;
- poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
+ poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;
poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
poke->tailcall_bypass);
- *pprog = prog;
- pop_callee_regs(pprog, callee_regs_used);
- prog = *pprog;
+ pop_callee_regs(&prog, callee_regs_used);
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
+
/* out: */
+ ctx->tail_call_direct_label = prog - start;
*pprog = prog;
}
@@ -1220,8 +1196,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
/* speculation barrier */
case BPF_ST | BPF_NOSPEC:
if (boot_cpu_has(X86_FEATURE_XMM2))
- /* Emit 'lfence' */
- EMIT3(0x0F, 0xAE, 0xE8);
+ EMIT_LFENCE();
break;
/* ST: *(u8*)(dst_reg + off) = imm */
@@ -1405,13 +1380,16 @@ st: if (is_imm8(insn->off))
case BPF_JMP | BPF_TAIL_CALL:
if (imm32)
emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
- &prog, addrs[i], image,
+ &prog, image + addrs[i - 1],
callee_regs_used,
- bpf_prog->aux->stack_depth);
+ bpf_prog->aux->stack_depth,
+ ctx);
else
emit_bpf_tail_call_indirect(&prog,
callee_regs_used,
- bpf_prog->aux->stack_depth);
+ bpf_prog->aux->stack_depth,
+ image + addrs[i - 1],
+ ctx);
break;
/* cond jump */
@@ -2117,24 +2095,6 @@ cleanup:
return ret;
}
-static int emit_fallback_jump(u8 **pprog)
-{
- u8 *prog = *pprog;
- int err = 0;
-
-#ifdef CONFIG_RETPOLINE
- /* Note that this assumes the the compiler uses external
- * thunks for indirect calls. Both clang and GCC use the same
- * naming convention for external thunks.
- */
- err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog);
-#else
- EMIT2(0xFF, 0xE2); /* jmp rdx */
-#endif
- *pprog = prog;
- return err;
-}
-
static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
{
u8 *jg_reloc, *prog = *pprog;
@@ -2156,9 +2116,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
if (err)
return err;
- err = emit_fallback_jump(&prog); /* jmp thunk/indirect */
- if (err)
- return err;
+ emit_indirect_jump(&prog, 2 /* rdx */, prog);
*pprog = prog;
return 0;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 3bfda5f502cb..da9b7cfa4632 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -15,6 +15,7 @@
#include <asm/cacheflush.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
+#include <asm/asm-prototypes.h>
#include <linux/bpf.h>
/*
@@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
*pprog = prog;
}
+static int emit_jmp_edx(u8 **pprog, u8 *ip)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+#ifdef CONFIG_RETPOLINE
+ EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5));
+#else
+ EMIT2(0xFF, 0xE2);
+#endif
+ *pprog = prog;
+
+ return cnt;
+}
+
/*
* Generate the following code:
* ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
@@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
* goto *(prog->bpf_func + prologue_size);
* out:
*/
-static void emit_bpf_tail_call(u8 **pprog)
+static void emit_bpf_tail_call(u8 **pprog, u8 *ip)
{
u8 *prog = *pprog;
int cnt = 0;
@@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog)
* eax == ctx (1st arg)
* edx == prog->bpf_func + prologue_size
*/
- RETPOLINE_EDX_BPF_JIT();
+ cnt += emit_jmp_edx(&prog, ip + cnt);
if (jmp_label1 == -1)
jmp_label1 = cnt;
@@ -2122,7 +2138,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
break;
}
case BPF_JMP | BPF_TAIL_CALL:
- emit_bpf_tail_call(&prog);
+ emit_bpf_tail_call(&prog, image + addrs[i - 1]);
break;
/* cond jump */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index a7b7d674f500..4f63117f09bb 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -283,12 +283,12 @@ static void __init xen_init_capabilities(void)
}
}
-static void xen_set_debugreg(int reg, unsigned long val)
+static noinstr void xen_set_debugreg(int reg, unsigned long val)
{
HYPERVISOR_set_debugreg(reg, val);
}
-static unsigned long xen_get_debugreg(int reg)
+static noinstr unsigned long xen_get_debugreg(int reg)
{
return HYPERVISOR_get_debugreg(reg);
}
@@ -1025,52 +1025,54 @@ static const struct pv_info xen_info __initconst = {
.name = "Xen",
};
-static const struct pv_cpu_ops xen_cpu_ops __initconst = {
- .cpuid = xen_cpuid,
+static const typeof(pv_ops) xen_cpu_ops __initconst = {
+ .cpu = {
+ .cpuid = xen_cpuid,
- .set_debugreg = xen_set_debugreg,
- .get_debugreg = xen_get_debugreg,
+ .set_debugreg = xen_set_debugreg,
+ .get_debugreg = xen_get_debugreg,
- .read_cr0 = xen_read_cr0,
- .write_cr0 = xen_write_cr0,
+ .read_cr0 = xen_read_cr0,
+ .write_cr0 = xen_write_cr0,
- .write_cr4 = xen_write_cr4,
+ .write_cr4 = xen_write_cr4,
- .wbinvd = native_wbinvd,
+ .wbinvd = native_wbinvd,
- .read_msr = xen_read_msr,
- .write_msr = xen_write_msr,
+ .read_msr = xen_read_msr,
+ .write_msr = xen_write_msr,
- .read_msr_safe = xen_read_msr_safe,
- .write_msr_safe = xen_write_msr_safe,
+ .read_msr_safe = xen_read_msr_safe,
+ .write_msr_safe = xen_write_msr_safe,
- .read_pmc = xen_read_pmc,
+ .read_pmc = xen_read_pmc,
- .load_tr_desc = paravirt_nop,
- .set_ldt = xen_set_ldt,
- .load_gdt = xen_load_gdt,
- .load_idt = xen_load_idt,
- .load_tls = xen_load_tls,
- .load_gs_index = xen_load_gs_index,
+ .load_tr_desc = paravirt_nop,
+ .set_ldt = xen_set_ldt,
+ .load_gdt = xen_load_gdt,
+ .load_idt = xen_load_idt,
+ .load_tls = xen_load_tls,
+ .load_gs_index = xen_load_gs_index,
- .alloc_ldt = xen_alloc_ldt,
- .free_ldt = xen_free_ldt,
+ .alloc_ldt = xen_alloc_ldt,
+ .free_ldt = xen_free_ldt,
- .store_tr = xen_store_tr,
+ .store_tr = xen_store_tr,
- .write_ldt_entry = xen_write_ldt_entry,
- .write_gdt_entry = xen_write_gdt_entry,
- .write_idt_entry = xen_write_idt_entry,
- .load_sp0 = xen_load_sp0,
+ .write_ldt_entry = xen_write_ldt_entry,
+ .write_gdt_entry = xen_write_gdt_entry,
+ .write_idt_entry = xen_write_idt_entry,
+ .load_sp0 = xen_load_sp0,
#ifdef CONFIG_X86_IOPL_IOPERM
- .invalidate_io_bitmap = xen_invalidate_io_bitmap,
- .update_io_bitmap = xen_update_io_bitmap,
+ .invalidate_io_bitmap = xen_invalidate_io_bitmap,
+ .update_io_bitmap = xen_update_io_bitmap,
#endif
- .io_delay = xen_io_delay,
+ .io_delay = xen_io_delay,
- .start_context_switch = paravirt_start_context_switch,
- .end_context_switch = xen_end_context_switch,
+ .start_context_switch = paravirt_start_context_switch,
+ .end_context_switch = xen_end_context_switch,
+ },
};
static void xen_restart(char *msg)
@@ -1211,7 +1213,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
/* Install Xen paravirt ops */
pv_info = xen_info;
- pv_ops.cpu = xen_cpu_ops;
+ pv_ops.cpu = xen_cpu_ops.cpu;
paravirt_iret = xen_iret;
xen_init_irq_ops();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index dfa091d79c2e..4fe387e520af 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -19,12 +19,12 @@
* callback mask. We do this in a very simple manner, by making a call
* down into Xen. The pending flag will be checked by Xen on return.
*/
-void xen_force_evtchn_callback(void)
+noinstr void xen_force_evtchn_callback(void)
{
(void)HYPERVISOR_xen_version(0, NULL);
}
-asmlinkage __visible unsigned long xen_save_fl(void)
+asmlinkage __visible noinstr unsigned long xen_save_fl(void)
{
struct vcpu_info *vcpu;
unsigned long flags;
@@ -40,9 +40,9 @@ asmlinkage __visible unsigned long xen_save_fl(void)
*/
return (-flags) & X86_EFLAGS_IF;
}
-PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text");
-asmlinkage __visible void xen_irq_disable(void)
+asmlinkage __visible noinstr void xen_irq_disable(void)
{
/* There's a one instruction preempt window here. We need to
make sure we're don't switch CPUs between getting the vcpu
@@ -51,9 +51,9 @@ asmlinkage __visible void xen_irq_disable(void)
this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
preempt_enable_no_resched();
}
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text");
-asmlinkage __visible void xen_irq_enable(void)
+asmlinkage __visible noinstr void xen_irq_enable(void)
{
struct vcpu_info *vcpu;
@@ -76,7 +76,7 @@ asmlinkage __visible void xen_irq_enable(void)
preempt_enable();
}
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text");
static void xen_safe_halt(void)
{
@@ -94,17 +94,20 @@ static void xen_halt(void)
xen_safe_halt();
}
-static const struct pv_irq_ops xen_irq_ops __initconst = {
- .save_fl = PV_CALLEE_SAVE(xen_save_fl),
- .irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
- .irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+static const typeof(pv_ops) xen_irq_ops __initconst = {
+ .irq = {
- .safe_halt = xen_safe_halt,
- .halt = xen_halt,
+ .save_fl = PV_CALLEE_SAVE(xen_save_fl),
+ .irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
+ .irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+
+ .safe_halt = xen_safe_halt,
+ .halt = xen_halt,
+ },
};
void __init xen_init_irq_ops(void)
{
- pv_ops.irq = xen_irq_ops;
+ pv_ops.irq = xen_irq_ops.irq;
x86_init.irqs.intr_init = xen_init_IRQ;
}
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 3359c23573c5..1ce436eeda15 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1204,7 +1204,8 @@ static void __init xen_pagetable_init(void)
xen_remap_memory();
xen_setup_mfn_list_list();
}
-static void xen_write_cr2(unsigned long cr2)
+
+static noinstr void xen_write_cr2(unsigned long cr2)
{
this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
}
@@ -2078,67 +2079,69 @@ static void xen_leave_lazy_mmu(void)
preempt_enable();
}
-static const struct pv_mmu_ops xen_mmu_ops __initconst = {
- .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
- .write_cr2 = xen_write_cr2,
+static const typeof(pv_ops) xen_mmu_ops __initconst = {
+ .mmu = {
+ .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
+ .write_cr2 = xen_write_cr2,
- .read_cr3 = xen_read_cr3,
- .write_cr3 = xen_write_cr3_init,
+ .read_cr3 = xen_read_cr3,
+ .write_cr3 = xen_write_cr3_init,
- .flush_tlb_user = xen_flush_tlb,
- .flush_tlb_kernel = xen_flush_tlb,
- .flush_tlb_one_user = xen_flush_tlb_one_user,
- .flush_tlb_multi = xen_flush_tlb_multi,
- .tlb_remove_table = tlb_remove_table,
+ .flush_tlb_user = xen_flush_tlb,
+ .flush_tlb_kernel = xen_flush_tlb,
+ .flush_tlb_one_user = xen_flush_tlb_one_user,
+ .flush_tlb_multi = xen_flush_tlb_multi,
+ .tlb_remove_table = tlb_remove_table,
- .pgd_alloc = xen_pgd_alloc,
- .pgd_free = xen_pgd_free,
+ .pgd_alloc = xen_pgd_alloc,
+ .pgd_free = xen_pgd_free,
- .alloc_pte = xen_alloc_pte_init,
- .release_pte = xen_release_pte_init,
- .alloc_pmd = xen_alloc_pmd_init,
- .release_pmd = xen_release_pmd_init,
+ .alloc_pte = xen_alloc_pte_init,
+ .release_pte = xen_release_pte_init,
+ .alloc_pmd = xen_alloc_pmd_init,
+ .release_pmd = xen_release_pmd_init,
- .set_pte = xen_set_pte_init,
- .set_pmd = xen_set_pmd_hyper,
+ .set_pte = xen_set_pte_init,
+ .set_pmd = xen_set_pmd_hyper,
- .ptep_modify_prot_start = xen_ptep_modify_prot_start,
- .ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
+ .ptep_modify_prot_start = xen_ptep_modify_prot_start,
+ .ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
- .pte_val = PV_CALLEE_SAVE(xen_pte_val),
- .pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
+ .pte_val = PV_CALLEE_SAVE(xen_pte_val),
+ .pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
- .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
- .make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
+ .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
+ .make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
- .set_pud = xen_set_pud_hyper,
+ .set_pud = xen_set_pud_hyper,
- .make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
- .pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
+ .make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
+ .pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
- .pud_val = PV_CALLEE_SAVE(xen_pud_val),
- .make_pud = PV_CALLEE_SAVE(xen_make_pud),
- .set_p4d = xen_set_p4d_hyper,
+ .pud_val = PV_CALLEE_SAVE(xen_pud_val),
+ .make_pud = PV_CALLEE_SAVE(xen_make_pud),
+ .set_p4d = xen_set_p4d_hyper,
- .alloc_pud = xen_alloc_pmd_init,
- .release_pud = xen_release_pmd_init,
+ .alloc_pud = xen_alloc_pmd_init,
+ .release_pud = xen_release_pmd_init,
#if CONFIG_PGTABLE_LEVELS >= 5
- .p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
- .make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
+ .p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
+ .make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
#endif
- .activate_mm = xen_activate_mm,
- .dup_mmap = xen_dup_mmap,
- .exit_mmap = xen_exit_mmap,
+ .activate_mm = xen_activate_mm,
+ .dup_mmap = xen_dup_mmap,
+ .exit_mmap = xen_exit_mmap,
- .lazy_mode = {
- .enter = paravirt_enter_lazy_mmu,
- .leave = xen_leave_lazy_mmu,
- .flush = paravirt_flush_lazy_mmu,
- },
+ .lazy_mode = {
+ .enter = paravirt_enter_lazy_mmu,
+ .leave = xen_leave_lazy_mmu,
+ .flush = paravirt_flush_lazy_mmu,
+ },
- .set_fixmap = xen_set_fixmap,
+ .set_fixmap = xen_set_fixmap,
+ },
};
void __init xen_init_mmu_ops(void)
@@ -2146,7 +2149,7 @@ void __init xen_init_mmu_ops(void)
x86_init.paging.pagetable_init = xen_pagetable_init;
x86_init.hyper.init_after_bootmem = xen_after_bootmem;
- pv_ops.mmu = xen_mmu_ops;
+ pv_ops.mmu = xen_mmu_ops.mmu;
memset(dummy_mapping, 0xff, PAGE_SIZE);
}
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1e626444712b..220dd9678494 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -21,6 +21,45 @@
#include <linux/init.h>
#include <linux/linkage.h>
+.pushsection .noinstr.text, "ax"
+/*
+ * Disabling events is simply a matter of making the event mask
+ * non-zero.
+ */
+SYM_FUNC_START(xen_irq_disable_direct)
+ movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ ret
+SYM_FUNC_END(xen_irq_disable_direct)
+
+/*
+ * Force an event check by making a hypercall, but preserve regs
+ * before making the call.
+ */
+SYM_FUNC_START(check_events)
+ FRAME_BEGIN
+ push %rax
+ push %rcx
+ push %rdx
+ push %rsi
+ push %rdi
+ push %r8
+ push %r9
+ push %r10
+ push %r11
+ call xen_force_evtchn_callback
+ pop %r11
+ pop %r10
+ pop %r9
+ pop %r8
+ pop %rdi
+ pop %rsi
+ pop %rdx
+ pop %rcx
+ pop %rax
+ FRAME_END
+ ret
+SYM_FUNC_END(check_events)
+
/*
* Enable events. This clears the event mask and tests the pending
* event status with one and operation. If there are pending events,
@@ -47,16 +86,6 @@ SYM_FUNC_START(xen_irq_enable_direct)
ret
SYM_FUNC_END(xen_irq_enable_direct)
-
-/*
- * Disabling events is simply a matter of making the event mask
- * non-zero.
- */
-SYM_FUNC_START(xen_irq_disable_direct)
- movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
- ret
-SYM_FUNC_END(xen_irq_disable_direct)
-
/*
* (xen_)save_fl is used to get the current interrupt enable status.
* Callers expect the status to be in X86_EFLAGS_IF, and other bits
@@ -73,35 +102,6 @@ SYM_FUNC_START(xen_save_fl_direct)
ret
SYM_FUNC_END(xen_save_fl_direct)
-/*
- * Force an event check by making a hypercall, but preserve regs
- * before making the call.
- */
-SYM_FUNC_START(check_events)
- FRAME_BEGIN
- push %rax
- push %rcx
- push %rdx
- push %rsi
- push %rdi
- push %r8
- push %r9
- push %r10
- push %r11
- call xen_force_evtchn_callback
- pop %r11
- pop %r10
- pop %r9
- pop %r8
- pop %rdi
- pop %rsi
- pop %rdx
- pop %rcx
- pop %rax
- FRAME_END
- ret
-SYM_FUNC_END(check_events)
-
SYM_FUNC_START(xen_read_cr2)
FRAME_BEGIN
_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
@@ -116,6 +116,7 @@ SYM_FUNC_START(xen_read_cr2_direct)
FRAME_END
ret
SYM_FUNC_END(xen_read_cr2_direct);
+.popsection
.macro xen_pv_trap name
SYM_CODE_START(xen_\name)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index cb6538ae2fe0..9e27b86a0c31 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -20,6 +20,23 @@
#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
+ .skip 31, 0x90
+ ret
+ .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)
@@ -64,23 +81,6 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
#endif
#endif
-.pushsection .text
- .balign PAGE_SIZE
-SYM_CODE_START(hypercall_page)
- .rept (PAGE_SIZE / 32)
- UNWIND_HINT_FUNC
- .skip 31, 0x90
- ret
- .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
-
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")
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index cf907e5bf2f2..a8a041609c5d 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -120,7 +120,8 @@ void flush_cache_page(struct vm_area_struct*,
#define flush_cache_vunmap(start,end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page*);
+void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *);
void local_flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
@@ -137,7 +138,9 @@ void local_flush_cache_page(struct vm_area_struct *vma,
#define flush_cache_vunmap(start,end) do { } while (0)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
#define flush_dcache_page(page) do { } while (0)
+static inline void flush_dcache_folio(struct folio *folio) { }
#define flush_icache_range local_flush_icache_range
#define flush_cache_page(vma, addr, pfn) do { } while (0)
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 7f63aca6a0d3..ad15fbc57283 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -215,7 +215,7 @@ struct mm_struct;
/* Free all resources held by a thread. */
#define release_thread(thread) do { } while(0)
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1])
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 060165340612..47f933fed870 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -298,15 +298,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
* These bracket the sleeping functions..
*/
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
{
unsigned long sp, pc;
unsigned long stack_page = (unsigned long) task_stack_page(p);
int count = 0;
- if (!p || p == current || task_is_running(p))
- return 0;
-
sp = p->thread.sp;
pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp);
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 3cdfa00738e0..07b642c1916a 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -100,7 +100,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
spin_unlock(&dev->lock);
}
-static blk_qc_t simdisk_submit_bio(struct bio *bio)
+static void simdisk_submit_bio(struct bio *bio)
{
struct simdisk *dev = bio->bi_bdev->bd_disk->private_data;
struct bio_vec bvec;
@@ -118,7 +118,6 @@ static blk_qc_t simdisk_submit_bio(struct bio *bio)
}
bio_endio(bio);
- return BLK_QC_T_NONE;
}
static int simdisk_open(struct block_device *bdev, fmode_t mode)
@@ -259,6 +258,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
struct proc_dir_entry *procdir)
{
char tmp[2] = { '0' + which, 0 };
+ int err = -ENOMEM;
dev->fd = -1;
dev->filename = NULL;
@@ -267,7 +267,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd = blk_alloc_disk(NUMA_NO_NODE);
if (!dev->gd)
- return -ENOMEM;
+ goto out;
dev->gd->major = simdisk_major;
dev->gd->first_minor = which;
dev->gd->minors = SIMDISK_MINORS;
@@ -275,10 +275,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd->private_data = dev;
snprintf(dev->gd->disk_name, 32, "simdisk%d", which);
set_capacity(dev->gd, 0);
- add_disk(dev->gd);
+ err = add_disk(dev->gd);
+ if (err)
+ goto out_cleanup_disk;
dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev);
+
return 0;
+
+out_cleanup_disk:
+ blk_cleanup_disk(dev->gd);
+out:
+ return err;
}
static int __init simdisk_init(void)