This file allows to turn off the disk entropy contribution. Default
value of this file is '1'(on).
+dax (RO)
+--------
+This file indicates whether the device supports Direct Access (DAX),
+used by CPU-addressable storage to bypass the pagecache. It shows '1'
+if true, '0' if not.
+
discard_granularity (RO)
-----------------------
This shows the size of internal allocation of the device in bytes, if
-------------------
This is the hardware sector size of the device, in bytes.
+io_poll (RW)
+------------
+When read, this file shows the total number of block IO polls and how
+many returned success. Writing '0' to this file will disable polling
+for this device. Writing any non-zero value will enable this feature.
+
iostats (RW)
-------------
This file is used to control (on/off) the iostats accounting of the
setting from "write back" to "write through", since that will also
eliminate cache flushes issued by the kernel.
+write_same_max_bytes (RO)
+-------------------------
+This is the number of bytes the device can write in a single write-same
+command. A value of '0' means write-same is not supported by this
+device.
+
Jens Axboe <jens.axboe@oracle.com>, February 2009
ARM/Annapurna Labs ALPINE ARCHITECTURE
M: Tsahee Zidenberg <tsahee@annapurnalabs.com>
M: Antoine Tenart <antoine.tenart@free-electrons.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-alpine/
F: arch/arm/boot/dts/alpine*
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
-PHONY += gcc-plugins
-gcc-plugins: scripts_basic
-ifdef CONFIG_GCC_PLUGINS
- $(Q)$(MAKE) $(build)=scripts/gcc-plugins
-endif
- @:
-
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
endchoice
+config HAVE_ARCH_WITHIN_STACK_FRAMES
+ bool
+ help
+ An architecture should select this if it can walk the kernel stack
+ frames to determine if an object is part of either the arguments
+ or local variables (i.e. that it excludes saved return addresses,
+ and similar) by implementing an inline arch_within_stack_frames(),
+ which is used by CONFIG_HARDENED_USERCOPY.
+
config HAVE_CONTEXT_TRACKING
bool
help
select HARDIRQS_SW_RESEND
select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_MMAP_RND_BITS if MMU
platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y)))
ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y)
+ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y)
ifeq ($(KBUILD_SRC),)
KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs))
else
KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs))
endif
endif
+endif
export TEXT_OFFSET GZFLAGS MMUEXT
* associativity as these may be erroneously set
* up by boot loader(s).
*/
- cache-size = <1048576>; // 1MB
- cache-sets = <4096>;
+ cache-size = <131072>; // 128KB
+ cache-sets = <512>;
cache-line-size = <32>;
arm,parity-disable;
- arm,tag-latency = <1>;
- arm,data-latency = <1 1>;
- arm,dirty-latency = <1>;
+ arm,tag-latency = <1 1 1>;
+ arm,data-latency = <1 1 1>;
};
scu: scu@1f000000 {
};
syscon {
- compatible = "arm,integrator-ap-syscon";
+ compatible = "arm,integrator-ap-syscon", "syscon";
reg = <0x11000000 0x100>;
interrupt-parent = <&pic>;
/* These are the logical module IRQs */
};
syscon {
- compatible = "arm,integrator-cp-syscon";
+ compatible = "arm,integrator-cp-syscon", "syscon";
reg = <0xcb000000 0x100>;
};
cpu_on = <0x84000003>;
};
- psci {
- compatible = "arm,psci";
- method = "smc";
- cpu_suspend = <0x84000001>;
- cpu_off = <0x84000002>;
- cpu_on = <0x84000003>;
- };
-
soc {
#address-cells = <1>;
#size-cells = <1>;
* Pin 41: BR_UART1_TXD
* Pin 44: BR_UART1_RXD
*/
- serial@70006000 {
+ serial@0,70006000 {
compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
status = "okay";
};
* Pin 71: UART2_CTS_L
* Pin 74: UART2_RTS_L
*/
- serial@70006040 {
+ serial@0,70006040 {
compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
status = "okay";
};
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_PAGE_POISONING=y
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_PAGE_POISONING=y
static inline unsigned long __must_check
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
- unsigned int __ua_flags = uaccess_save_and_enable();
+ unsigned int __ua_flags;
+
+ check_object_size(to, n, false);
+ __ua_flags = uaccess_save_and_enable();
n = arm_copy_from_user(to, from, n);
uaccess_restore(__ua_flags);
return n;
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
#ifndef CONFIG_UACCESS_WITH_MEMCPY
- unsigned int __ua_flags = uaccess_save_and_enable();
+ unsigned int __ua_flags;
+
+ check_object_size(from, n, true);
+ __ua_flags = uaccess_save_and_enable();
n = arm_copy_to_user(to, from, n);
uaccess_restore(__ua_flags);
return n;
#else
+ check_object_size(from, n, true);
return arm_copy_to_user(to, from, n);
#endif
}
mm_segment_t fs;
long ret, err, i;
- if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+ if (maxevents <= 0 ||
+ maxevents > (INT_MAX/sizeof(*kbuf)) ||
+ maxevents > (INT_MAX/sizeof(*events)))
return -EINVAL;
+ if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+ return -EFAULT;
kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
if (nsops < 1 || nsops > SEMOPM)
return -EINVAL;
+ if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+ return -EFAULT;
sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
if (!sops)
return -ENOMEM;
switch (ioctl) {
case KVM_CREATE_IRQCHIP: {
+ int ret;
if (!vgic_present)
return -ENXIO;
- return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+ mutex_lock(&kvm->lock);
+ ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+ mutex_unlock(&kvm->lock);
+ return ret;
}
case KVM_ARM_SET_DEVICE_ADDR: {
struct kvm_arm_device_addr dev_addr;
menuconfig ARCH_CLPS711X
bool "Cirrus Logic EP721x/EP731x-based"
depends on ARCH_MULTI_V4T
- select ARCH_REQUIRE_GPIOLIB
select AUTO_ZRELADDR
select CLKSRC_OF
select CLPS711X_TIMER
select COMMON_CLK
select CPU_ARM720T
select GENERIC_CLOCKEVENTS
+ select GPIOLIB
select MFD_SYSCON
select OF_IRQ
select USE_OF
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
- -I$(srctree)/arch/arm/plat-orion/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include
AFLAGS_coherency_ll.o := -Wa,-march=armv7-a
CFLAGS_pmsu.o := -march=armv7-a
config MACH_OX810SE
bool "Support OX810SE Based Products"
+ select ARCH_HAS_RESET_CONTROLLER
select COMMON_CLK_OXNAS
select CPU_ARM926T
select MFD_SYSCON
select OXNAS_RPS_TIMER
select PINCTRL_OXNAS
+ select RESET_CONTROLLER
select RESET_OXNAS
select VERSATILE_FPGA_IRQ
help
*/
#include <linux/kernel.h>
+#include <linux/module.h> /* symbol_get ; symbol_put */
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/major.h>
*/
#include <linux/kernel.h>
+#include <linux/module.h> /* symbol_get ; symbol_put */
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/gpio_keys.h>
#
# Makefile for the linux kernel.
#
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
- -I$(srctree)/arch/arm/plat-versatile/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include
obj-y := core.o
obj-$(CONFIG_REALVIEW_DT) += realview-dt.o
#
# Licensed under GPLv2
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include
# Core
bool __init shmobile_smp_init_fallback_ops(void)
{
/* fallback on PSCI/smp_ops if no other DT based method is detected */
+ if (!IS_ENABLED(CONFIG_SMP))
+ return false;
+
return platform_can_secondary_boot() ? true : false;
}
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
config ARCH_ALPINE
bool "Annapurna Labs Alpine platform"
- select ALPINE_MSI
+ select ALPINE_MSI if PCI
help
This enables support for the Annapurna Labs Alpine
Soc family.
config ARCH_HISI
bool "Hisilicon SoC Family"
select ARM_TIMER_SP804
- select HISILICON_IRQ_MBIGEN
+ select HISILICON_IRQ_MBIGEN if PCI
help
This enables support for Hisilicon ARMv8 SoC family
/dts-v1/;
#include "exynos7.dtsi"
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/samsung,s2mps11.h>
/ {
model = "Samsung Exynos7 Espresso board based on EXYNOS7";
&rtc {
status = "okay";
+ clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>;
+ clock-names = "rtc", "rtc_src";
};
&watchdog {
-# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_AUDIT=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
CONFIG_CGROUP_HUGETLB=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_NET_NS is not set
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CMA=y
+CONFIG_SECCOMP=y
CONFIG_XEN=y
CONFIG_KEXEC=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
+CONFIG_IPV6=m
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_TARGET_MASQUERADE=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+CONFIG_VLAN_8021Q_MVRP=y
CONFIG_BPF_JIT=y
CONFIG_CFG80211=m
CONFIG_MAC80211=m
CONFIG_MTD_M25P80=y
CONFIG_MTD_SPI_NOR=y
CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=m
CONFIG_VIRTIO_BLK=y
CONFIG_SRAM=y
# CONFIG_SCSI_PROC_FS is not set
CONFIG_PATA_PLATFORM=y
CONFIG_PATA_OF_PLATFORM=y
CONFIG_NETDEVICES=y
+CONFIG_MACVLAN=m
+CONFIG_MACVTAP=m
CONFIG_TUN=y
+CONFIG_VETH=m
CONFIG_VIRTIO_NET=y
CONFIG_AMD_XGBE=y
CONFIG_NET_XGENE=y
CONFIG_PWM_SAMSUNG=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_FANOTIFY=y
CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA=y
CONFIG_AUTOFS4_FS=y
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=y
+CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_OVERLAY_FS=m
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
CONFIG_HUGETLBFS=y
#define __ARCH_WANT_KPROBES_INSN_SLOT
#define MAX_INSN_SIZE 1
-#define MAX_STACK_SIZE 128
#define flush_insn_slot(p) do { } while (0)
#define kretprobe_blacklist_size 0
struct prev_kprobe prev_kprobe;
struct kprobe_step_ctx ss_ctx;
struct pt_regs jprobe_saved_regs;
- char jprobes_stack[MAX_STACK_SIZE];
};
void arch_remove_kprobe(struct kprobe *);
static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
{
kasan_check_write(to, n);
- return __arch_copy_from_user(to, from, n);
+ check_object_size(to, n, false);
+ return __arch_copy_from_user(to, from, n);
}
static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
{
kasan_check_read(from, n);
- return __arch_copy_to_user(to, from, n);
+ check_object_size(from, n, true);
+ return __arch_copy_to_user(to, from, n);
}
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
kasan_check_write(to, n);
- if (access_ok(VERIFY_READ, from, n))
+ if (access_ok(VERIFY_READ, from, n)) {
+ check_object_size(to, n, false);
n = __arch_copy_from_user(to, from, n);
- else /* security hole - plug it */
+ } else /* security hole - plug it */
memset(to, 0, n);
return n;
}
{
kasan_check_read(from, n);
- if (access_ok(VERIFY_WRITE, to, n))
+ if (access_ok(VERIFY_WRITE, to, n)) {
+ check_object_size(from, n, true);
n = __arch_copy_to_user(to, from, n);
+ }
return n;
}
lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class
cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1
b.eq el1_da
+ cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1
+ b.eq el1_ia
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
b.eq el1_undef
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1
b.ge el1_dbg
b el1_inv
+
+el1_ia:
+ /*
+ * Fall through to the Data abort case
+ */
el1_da:
/*
* Data abort handling
#include <asm/sections.h>
#include <asm/smp.h>
#include <asm/suspend.h>
+#include <asm/sysreg.h>
#include <asm/virt.h>
/*
set_pte(pte, __pte(virt_to_phys((void *)dst) |
pgprot_val(PAGE_KERNEL_EXEC)));
- /* Load our new page tables */
- asm volatile("msr ttbr0_el1, %0;"
- "isb;"
- "tlbi vmalle1is;"
- "dsb ish;"
- "isb" : : "r"(virt_to_phys(pgd)));
+ /*
+ * Load our new page tables. A strict BBM approach requires that we
+ * ensure that TLBs are free of any entries that may overlap with the
+ * global mappings we are about to install.
+ *
+ * For a real hibernate/resume cycle TTBR0 currently points to a zero
+ * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
+ * runtime services), while for a userspace-driven test_resume cycle it
+ * points to userspace page tables (and we must point it at a zero page
+ * ourselves). Elsewhere we only (un)install the idmap with preemption
+ * disabled, so T0SZ should be as required regardless.
+ */
+ cpu_set_reserved_ttbr0();
+ local_flush_tlb_all();
+ write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+ isb();
*phys_dst_addr = virt_to_phys((void *)dst);
void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
void *, phys_addr_t, phys_addr_t);
+ /*
+ * Restoring the memory image will overwrite the ttbr1 page tables.
+ * Create a second copy of just the linear map, and use this when
+ * restoring.
+ */
+ tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+ if (!tmp_pg_dir) {
+ pr_err("Failed to allocate memory for temporary page tables.");
+ rc = -ENOMEM;
+ goto out;
+ }
+ rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+ if (rc)
+ goto out;
+
+ /*
+ * Since we only copied the linear map, we need to find restore_pblist's
+ * linear map address.
+ */
+ lm_restore_pblist = LMADDR(restore_pblist);
+
+ /*
+ * We need a zero page that is zero before & after resume in order to
+ * to break before make on the ttbr1 page tables.
+ */
+ zero_page = (void *)get_safe_page(GFP_ATOMIC);
+ if (!zero_page) {
+ pr_err("Failed to allocate zero page.");
+ rc = -ENOMEM;
+ goto out;
+ }
+
/*
* Locate the exit code in the bottom-but-one page, so that *NULL
* still has disastrous affects.
*/
__flush_dcache_area(hibernate_exit, exit_size);
- /*
- * Restoring the memory image will overwrite the ttbr1 page tables.
- * Create a second copy of just the linear map, and use this when
- * restoring.
- */
- tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
- if (!tmp_pg_dir) {
- pr_err("Failed to allocate memory for temporary page tables.");
- rc = -ENOMEM;
- goto out;
- }
- rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
- if (rc)
- goto out;
-
- /*
- * Since we only copied the linear map, we need to find restore_pblist's
- * linear map address.
- */
- lm_restore_pblist = LMADDR(restore_pblist);
-
/*
* KASLR will cause the el2 vectors to be in a different location in
* the resumed kernel. Load hibernate's temporary copy into el2.
__hyp_set_vectors(el2_vectors);
}
- /*
- * We need a zero page that is zero before & after resume in order to
- * to break before make on the ttbr1 page tables.
- */
- zero_page = (void *)get_safe_page(GFP_ATOMIC);
-
hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
resume_hdr.reenter_kernel, lm_restore_pblist,
resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
static void __kprobes
post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
-static inline unsigned long min_stack_size(unsigned long addr)
-{
- unsigned long size;
-
- if (on_irq_stack(addr, raw_smp_processor_id()))
- size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
- else
- size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
-
- return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
-}
-
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
/* prepare insn slot */
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- long stack_ptr = kernel_stack_pointer(regs);
kcb->jprobe_saved_regs = *regs;
/*
- * As Linus pointed out, gcc assumes that the callee
- * owns the argument space and could overwrite it, e.g.
- * tailcall optimization. So, to be absolutely safe
- * we also save and restore enough stack bytes to cover
- * the argument area.
+ * Since we can't be sure where in the stack frame "stacked"
+ * pass-by-value arguments are stored we just don't try to
+ * duplicate any of the stack. Do not use jprobes on functions that
+ * use more than 64 bytes (after padding each to an 8 byte boundary)
+ * of arguments, or pass individual arguments larger than 16 bytes.
*/
- kasan_disable_current();
- memcpy(kcb->jprobes_stack, (void *)stack_ptr,
- min_stack_size(stack_ptr));
- kasan_enable_current();
instruction_pointer_set(regs, (unsigned long) jp->entry);
preempt_disable();
}
unpause_graph_tracing();
*regs = kcb->jprobe_saved_regs;
- kasan_disable_current();
- memcpy((void *)stack_addr, kcb->jprobes_stack,
- min_stack_size(stack_addr));
- kasan_enable_current();
preempt_enable_no_resched();
return 1;
}
acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
acpi_parse_gic_cpu_interface, 0);
- if (cpu_count > NR_CPUS)
- pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
- cpu_count, NR_CPUS);
+ if (cpu_count > nr_cpu_ids)
+ pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n",
+ cpu_count, nr_cpu_ids);
if (!bootcpu_valid) {
pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
* with entries in cpu_logical_map while initializing the cpus.
* If the cpu set-up fails, invalidate the cpu_logical_map entry.
*/
- for (i = 1; i < NR_CPUS; i++) {
+ for (i = 1; i < nr_cpu_ids; i++) {
if (cpu_logical_map(i) != INVALID_HWID) {
if (smp_cpu_setup(i))
cpu_logical_map(i) = INVALID_HWID;
}
#endif
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
/*
* The kernel tried to access some page that wasn't present.
*/
{
/*
* Are we prepared to handle this kernel fault?
+ * We are almost certainly not prepared to handle instruction faults.
*/
- if (fixup_exception(regs))
+ if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
/*
unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
- return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+ return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
+ (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
}
static bool is_el0_instruction_abort(unsigned int esr)
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
+ if (is_el1_instruction_abort(esr))
+ die("Attempting to execute userspace memory", regs, esr);
+
if (!search_exception_tables(regs->pc))
die("Accessing user space memory outside uaccess.h routines", regs, esr);
}
#ifdef __KERNEL__
+#include <linux/types.h>
+
/* H8/300 internal I/O functions */
#define __raw_readb __raw_readb
select MODULES_USE_ELF_RELA
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HARDENED_USERCOPY
default y
help
The Itanium Processor Family is Intel's 64-bit successor to
static inline unsigned long
__copy_to_user (void __user *to, const void *from, unsigned long count)
{
+ if (!__builtin_constant_p(count))
+ check_object_size(from, count, true);
+
return __copy_user(to, (__force void __user *) from, count);
}
static inline unsigned long
__copy_from_user (void *to, const void __user *from, unsigned long count)
{
+ if (!__builtin_constant_p(count))
+ check_object_size(to, count, false);
+
return __copy_user((__force void __user *) to, from, count);
}
const void *__cu_from = (from); \
long __cu_len = (n); \
\
- if (__access_ok(__cu_to, __cu_len, get_fs())) \
- __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
+ if (__access_ok(__cu_to, __cu_len, get_fs())) { \
+ if (!__builtin_constant_p(n)) \
+ check_object_size(__cu_from, __cu_len, true); \
+ __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
+ } \
__cu_len; \
})
long __cu_len = (n); \
\
__chk_user_ptr(__cu_from); \
- if (__access_ok(__cu_from, __cu_len, get_fs())) \
+ if (__access_ok(__cu_from, __cu_len, get_fs())) { \
+ if (!__builtin_constant_p(n)) \
+ check_object_size(__cu_to, __cu_len, false); \
__cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \
+ } \
__cu_len; \
})
free_all_bootmem();
mem_init_print_info(NULL);
- show_mem(0);
}
void free_initmem(void)
preempt_disable();
if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
- if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
- kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+ if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+ kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+ kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+ __func__, va, vcpu, read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
+ }
} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
int index;
run, vcpu);
preempt_enable();
goto dont_update_pc;
- } else {
- /*
- * We fault an entry from the guest tlb to the
- * shadow host TLB
- */
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+ }
+ /*
+ * We fault an entry from the guest tlb to the
+ * shadow host TLB
+ */
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
}
}
} else {
* OK we have a Guest TLB entry, now inject it into the
* shadow host TLB
*/
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ }
}
}
}
gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
- if (gfn >= kvm->arch.guest_pmap_npages) {
+ if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
gfn, badvaddr);
kvm_mips_dump_host_tlbs();
unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
struct kvm *kvm = vcpu->kvm;
kvm_pfn_t pfn0, pfn1;
+ gfn_t gfn0, gfn1;
+ long tlb_lo[2];
int ret;
- if ((tlb->tlb_hi & VPN2_MASK) == 0) {
- pfn0 = 0;
- pfn1 = 0;
- } else {
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0])
- >> PAGE_SHIFT) < 0)
- return -1;
-
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1])
- >> PAGE_SHIFT) < 0)
- return -1;
-
- pfn0 = kvm->arch.guest_pmap[
- mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT];
- pfn1 = kvm->arch.guest_pmap[
- mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT];
+ tlb_lo[0] = tlb->tlb_lo[0];
+ tlb_lo[1] = tlb->tlb_lo[1];
+
+ /*
+ * The commpage address must not be mapped to anything else if the guest
+ * TLB contains entries nearby, or commpage accesses will break.
+ */
+ if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+ VPN2_MASK & (PAGE_MASK << 1)))
+ tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+ gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+ gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+ if (gfn0 >= kvm->arch.guest_pmap_npages ||
+ gfn1 >= kvm->arch.guest_pmap_npages) {
+ kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+ __func__, gfn0, gfn1, tlb->tlb_hi);
+ kvm_mips_dump_guest_tlbs(vcpu);
+ return -1;
}
+ if (kvm_mips_map_page(kvm, gfn0) < 0)
+ return -1;
+
+ if (kvm_mips_map_page(kvm, gfn1) < 0)
+ return -1;
+
+ pfn0 = kvm->arch.guest_pmap[gfn0];
+ pfn1 = kvm->arch.guest_pmap[gfn1];
+
/* Get attributes from the Guest TLB */
entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
- (tlb->tlb_lo[0] & ENTRYLO_D) |
- (tlb->tlb_lo[0] & ENTRYLO_V);
+ (tlb_lo[0] & ENTRYLO_D) |
+ (tlb_lo[0] & ENTRYLO_V);
entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
- (tlb->tlb_lo[1] & ENTRYLO_D) |
- (tlb->tlb_lo[1] & ENTRYLO_V);
+ (tlb_lo[1] & ENTRYLO_D) |
+ (tlb_lo[1] & ENTRYLO_V);
kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
tlb->tlb_lo[0], tlb->tlb_lo[1]);
local_irq_restore(flags);
return KVM_INVALID_INST;
}
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
- &vcpu->arch.
- guest_tlb[index]);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+ &vcpu->arch.guest_tlb[index])) {
+ kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, opc, index, vcpu,
+ read_c0_entryhi());
+ kvm_mips_dump_guest_tlbs(vcpu);
+ local_irq_restore(flags);
+ return KVM_INVALID_INST;
+ }
inst = *(opc);
}
local_irq_restore(flags);
select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
select GENERIC_CPU_AUTOPROBE
select HAVE_VIRT_CPU_ACCOUNTING
+ select HAVE_ARCH_HARDENED_USERCOPY
config GENERIC_CSUM
def_bool CPU_LITTLE_ENDIAN
UTS_MACHINE := $(OLDARCH)
ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override CC += -mlittle-endian
-ifneq ($(cc-name),clang)
-override CC += -mno-strict-align
-endif
-override AS += -mlittle-endian
override LD += -EL
-override CROSS32CC += -mlittle-endian
override CROSS32AS += -mlittle-endian
LDEMULATION := lppc
GNUTARGET := powerpcle
MULTIPLEWORD := -mno-multiple
KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect)
else
-ifeq ($(call cc-option-yn,-mbig-endian),y)
-override CC += -mbig-endian
-override AS += -mbig-endian
-endif
override LD += -EB
LDEMULATION := ppc
GNUTARGET := powerpc
MULTIPLEWORD := -mmultiple
endif
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+ifneq ($(cc-name),clang)
+ cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align
+endif
+
+aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+
ifeq ($(HAS_BIARCH),y)
override AS += -a$(CONFIG_WORD_SIZE)
override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION)
KBUILD_AFLAGS += $(cpu-as-y)
KBUILD_CFLAGS += $(cpu-as-y)
+KBUILD_AFLAGS += $(aflags-y)
+KBUILD_CFLAGS += $(cflags-y)
+
head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o
head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o
head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o
#include <linux/module.h>
#include <linux/string.h>
#include <linux/kernel.h>
+#include <linux/cpufeature.h>
#include <asm/switch_to.h>
#define CHKSUM_BLOCK_SIZE 1
crypto_unregister_shash(&alg);
}
-module_init(crc32c_vpmsum_mod_init);
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init);
module_exit(crc32c_vpmsum_mod_fini);
MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
#endif
+/* Idle state entry routines */
+#ifdef CONFIG_PPC_P7_NAP
+#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r0,0(r1); \
+ ptesync; \
+ ld r0,0(r1); \
+1: cmp cr0,r0,r0; \
+ bne 1b; \
+ IDLE_INST; \
+ b .
+#endif /* CONFIG_PPC_P7_NAP */
+
#endif
#ifndef __ASSEMBLY__
void apply_feature_fixups(void);
+void setup_feature_keys(void);
#endif
#endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */
static inline void __giveup_spe(struct task_struct *t) { }
#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-extern void flush_tmregs_to_thread(struct task_struct *);
-#else
-static inline void flush_tmregs_to_thread(struct task_struct *t)
-{
-}
-#endif
-
static inline void clear_task_ebb(struct task_struct *t)
{
#ifdef CONFIG_PPC_BOOK3S_64
{
unsigned long over;
- if (access_ok(VERIFY_READ, from, n))
+ if (access_ok(VERIFY_READ, from, n)) {
+ if (!__builtin_constant_p(n))
+ check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
+ }
if ((unsigned long)from < TASK_SIZE) {
over = (unsigned long)from + n - TASK_SIZE;
+ if (!__builtin_constant_p(n - over))
+ check_object_size(to, n - over, false);
return __copy_tofrom_user((__force void __user *)to, from,
n - over) + over;
}
{
unsigned long over;
- if (access_ok(VERIFY_WRITE, to, n))
+ if (access_ok(VERIFY_WRITE, to, n)) {
+ if (!__builtin_constant_p(n))
+ check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force void __user *)from, n);
+ }
if ((unsigned long)to < TASK_SIZE) {
over = (unsigned long)to + n - TASK_SIZE;
+ if (!__builtin_constant_p(n))
+ check_object_size(from, n - over, true);
return __copy_tofrom_user(to, (__force void __user *)from,
n - over) + over;
}
if (ret == 0)
return 0;
}
+
+ if (!__builtin_constant_p(n))
+ check_object_size(to, n, false);
+
return __copy_tofrom_user((__force void __user *)to, from, n);
}
if (ret == 0)
return 0;
}
+ if (!__builtin_constant_p(n))
+ check_object_size(from, n, true);
+
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
extern void xics_kexec_teardown_cpu(int secondary);
extern void xics_migrate_irqs_away(void);
extern void icp_native_eoi(struct irq_data *d);
+extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type);
+extern int xics_retrigger(struct irq_data *data);
#ifdef CONFIG_SMP
extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
unsigned int strict_check);
int n = 0, l = 0;
char buffer[128];
- n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+ n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
edev->phb->global_number, pdn->busno,
PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
- pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+ pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
edev->phb->global_number, pdn->busno,
PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
* vector
*/
SET_SCRATCH0(r13) /* save r13 */
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
- /* Running native on arch 2.06 or later, check if we are
- * waking up from nap. We only handle no state loss and
- * supervisor state loss. We do -not- handle hypervisor
- * state loss at this time.
+ /*
+ * Running native on arch 2.06 or later, we may wakeup from winkle
+ * inside machine check. If yes, then last bit of HSPGR0 would be set
+ * to 1. Hence clear it unconditionally.
*/
- mfspr r13,SPRN_SRR1
- rlwinm. r13,r13,47-31,30,31
- OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
- beq 9f
-
- mfspr r13,SPRN_SRR1
- rlwinm. r13,r13,47-31,30,31
- /* waking up from powersave (nap) state */
- cmpwi cr1,r13,2
- /* Total loss of HV state is fatal. let's just stay stuck here */
- OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
- bgt cr1,.
-9:
- OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
+ GET_PACA(r13)
+ clrrdi r13,r13,1
+ SET_PACA(r13)
EXCEPTION_PROLOG_0(PACA_EXMC)
BEGIN_FTR_SECTION
b machine_check_powernv_early
* Check if thread was in power saving mode. We come here when any
* of the following is true:
* a. thread wasn't in power saving mode
- * b. thread was in power saving mode with no state loss or
- * supervisor state loss
+ * b. thread was in power saving mode with no state loss,
+ * supervisor state loss or hypervisor state loss.
*
- * Go back to nap again if (b) is true.
+ * Go back to nap/sleep/winkle mode again if (b) is true.
*/
rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */
beq 4f /* No, it wasn;t */
/* Thread was in power saving mode. Go back to nap again. */
cmpwi r11,2
- bne 3f
- /* Supervisor state loss */
+ blt 3f
+ /* Supervisor/Hypervisor state loss */
li r0,1
stb r0,PACA_NAPSTATELOST(r13)
3: bl machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
GET_PACA(r13)
ld r1,PACAR1(r13)
- li r3,PNV_THREAD_NAP
- b pnv_enter_arch207_idle_mode
+ /*
+ * Check what idle state this CPU was in and go back to same mode
+ * again.
+ */
+ lbz r3,PACA_THREAD_IDLE_STATE(r13)
+ cmpwi r3,PNV_THREAD_NAP
+ bgt 10f
+ IDLE_STATE_ENTER_SEQ(PPC_NAP)
+ /* No return */
+10:
+ cmpwi r3,PNV_THREAD_SLEEP
+ bgt 2f
+ IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+ /* No return */
+
+2:
+ /*
+ * Go back to winkle. Please note that this thread was woken up in
+ * machine check from winkle and have not restored the per-subcore
+ * state. Hence before going back to winkle, set last bit of HSPGR0
+ * to 1. This will make sure that if this thread gets woken up
+ * again at reset vector 0x100 then it will get chance to restore
+ * the subcore state.
+ */
+ ori r13,r13,1
+ SET_PACA(r13)
+ IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
+ /* No return */
4:
#endif
/*
PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
PSSCR_MTL_MASK
-/* Idle state entry routines */
-
-#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
- /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
- std r0,0(r1); \
- ptesync; \
- ld r0,0(r1); \
-1: cmp cr0,r0,r0; \
- bne 1b; \
- IDLE_INST; \
- b .
-
.text
/*
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
_GLOBAL(pnv_restore_hyp_resource)
- ld r2,PACATOC(r13);
BEGIN_FTR_SECTION
+ ld r2,PACATOC(r13);
/*
* POWER ISA 3. Use PSSCR to determine if we
* are waking up from deep idle state
*/
clrldi r5,r13,63
clrrdi r13,r13,1
+
+ /* Now that we are sure r13 is corrected, load TOC */
+ ld r2,PACATOC(r13);
cmpwi cr4,r5,1
mtspr SPRN_HSPRG0,r13
mce->in_use = 1;
mce->initiator = MCE_INITIATOR_CPU;
- if (handled)
+ /* Mark it recovered if we have handled it and MSR(RI=1). */
+ if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
static int get_phb_number(struct device_node *dn)
{
int ret, phb_id = -1;
+ u32 prop_32;
u64 prop;
/*
* reading "ibm,opal-phbid", only present in OPAL environment.
*/
ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
- if (ret)
- ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop);
+ if (ret) {
+ ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+ prop = prop_32;
+ }
if (!ret)
phb_id = (int)(prop & (MAX_PHBS - 1));
#endif
}
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void flush_tmregs_to_thread(struct task_struct *tsk)
-{
- /*
- * Process self tracing is not yet supported through
- * ptrace interface. Ptrace generic code should have
- * prevented this from happening in the first place.
- * Warn once here with the message, if some how it
- * is attempted.
- */
- WARN_ONCE(tsk == current,
- "Not expecting ptrace on self: TM regs may be incorrect\n");
-
- /*
- * If task is not current, it should have been flushed
- * already to it's thread_struct during __switch_to().
- */
-}
-#endif
-
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *new)
{
/* Don't print anything after quiesce under OPAL, it crashes OFW */
if (of_platform != PLATFORM_OPAL) {
- prom_printf("Booting Linux via __start() ...\n");
+ prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
prom_debug("->dt_header_start=0x%x\n", hdr);
}
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/switch_to.h>
+#include <asm/tm.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
REG_OFFSET_END,
};
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+ /*
+ * If task is not current, it will have been flushed already to
+ * it's thread_struct during __switch_to().
+ *
+ * A reclaim flushes ALL the state.
+ */
+
+ if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(TM_CAUSE_SIGNAL);
+
+}
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
/**
* regs_query_register_offset() - query register offset from its name
* @name: the name of a register
* and we are running with enough of the MMU enabled to have our
* proper kernel virtual addresses
*
- * Find out what kind of machine we're on and save any data we need
- * from the early boot process (devtree is copied on pmac by prom_init()).
- * This is called very early on the boot process, after a minimal
- * MMU environment has been set up but before MMU_init is called.
+ * We do the initial parsing of the flat device-tree and prepares
+ * for the MMU to be fully initialized.
*/
extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
notrace void __init machine_init(u64 dt_ptr)
{
+ /* Configure static keys first, now that we're relocated. */
+ setup_feature_keys();
+
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
/* Apply all the dynamic patching */
apply_feature_fixups();
+ setup_feature_keys();
/* Initialize the hash table or TLB handling */
early_init_mmu();
#include <linux/security.h>
#include <linux/memblock.h>
+#include <asm/cpu_has_feature.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/mmu.h>
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
$(call if_changed,vdso32ld)
# strip rule for the .so file
$(call if_changed,objcopy)
# assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
$(call if_changed_dep,vdso32as)
# actual build commands
quiet_cmd_vdso32ld = VDSO32L $@
- cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@
+ cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
quiet_cmd_vdso32as = VDSO32A $@
cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $<
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
$(call if_changed,vdso64ld)
# strip rule for the .so file
$(call if_changed,objcopy)
# assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
$(call if_changed_dep,vdso64as)
# actual build commands
quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+ cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
quiet_cmd_vdso64as = VDSO64A $@
cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
xics->kvm = kvm;
/* Already there ? */
- mutex_lock(&kvm->lock);
if (kvm->arch.xics)
ret = -EEXIST;
else
kvm->arch.xics = xics;
- mutex_unlock(&kvm->lock);
if (ret) {
kfree(xics);
return ret;
}
- xics_debugfs_init(xics);
-
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
if (cpu_has_feature(CPU_FTR_ARCH_206)) {
/* Enable real mode support */
return 0;
}
+static void kvmppc_xics_init(struct kvm_device *dev)
+{
+ struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;
+
+ xics_debugfs_init(xics);
+}
+
struct kvm_device_ops kvm_xics_ops = {
.name = "kvm-xics",
.create = kvmppc_xics_create,
+ .init = kvmppc_xics_init,
.destroy = kvmppc_xics_free,
.set_attr = xics_set_attr,
.get_attr = xics_get_attr,
stw r7,12(r1)
stw r8,8(r1)
- andi. r0,r4,1 /* is destination address even ? */
- cmplwi cr7,r0,0
+ rlwinm r0,r4,3,0x8
+ rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */
+ cmplwi cr7,r0,0 /* is destination address even ? */
addic r12,r6,0
addi r6,r4,-4
neg r0,r4
66: addze r3,r12
addi r1,r1,16
beqlr+ cr7
- rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */
+ rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */
blr
/* read fault */
&__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
#endif
do_final_fixups();
+}
+void __init setup_feature_keys(void)
+{
/*
* Initialise jump label. This causes all the cpu/mmu_has_feature()
* checks to take on their correct polarity based on the current set of
gang = alloc_spu_gang();
SPUFS_I(inode)->i_ctx = NULL;
SPUFS_I(inode)->i_gang = gang;
- if (!gang)
+ if (!gang) {
+ ret = -ENOMEM;
goto out_iput;
+ }
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
!firmware_has_feature(FW_FEATURE_LPAR)) {
dev->dev.archdata.dma_ops = &dma_direct_ops;
+ /*
+ * Set the coherent DMA mask to prevent the iommu
+ * being used unnecessarily
+ */
+ dev->dev.coherent_dma_mask = DMA_BIT_MASK(44);
return;
}
#endif
}
/* Install interrupt handler */
- rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+ rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW,
+ "opal", NULL);
if (rc) {
irq_dispose_mapping(virq);
pr_warn("Error %d requesting irq %d (0x%x)\n",
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
+ pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
recovered = 0;
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
}
early_param("iommu", iommu_setup);
-static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
+static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
{
- return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) ==
- (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
+ /*
+ * WARNING: We cannot rely on the resource flags. The Linux PCI
+ * allocation code sometimes decides to put a 64-bit prefetchable
+ * BAR in the 32-bit window, so we have to compare the addresses.
+ *
+ * For simplicity we only test resource start.
+ */
+ return (r->start >= phb->ioda.m64_base &&
+ r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
}
static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
sgsz = phb->ioda.m64_segsize;
for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
r = &pdev->resource[i];
- if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags))
+ if (!r->parent || !pnv_pci_is_m64(phb, r))
continue;
start = _ALIGN_DOWN(r->start - base, sgsz);
unsigned shift, unsigned long index,
unsigned long npages)
{
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
+ __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
unsigned long start, end, inc;
/* We'll invalidate DMA address in PE scope */
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags)) {
+ if (!pnv_pci_is_m64(phb, res)) {
dev_warn(&pdev->dev, "Don't support SR-IOV with"
" non M64 VF BAR%d: %pR. \n",
i, res);
index++;
}
} else if ((res->flags & IORESOURCE_MEM) &&
- !pnv_pci_is_mem_pref_64(res->flags)) {
+ !pnv_pci_is_m64(phb, res)) {
region.start = res->start -
phb->hose->mem_offset[0] -
phb->ioda.m32_pci_base;
bridge = bridge->bus->self;
}
- /* We fail back to M32 if M64 isn't supported */
- if (phb->ioda.m64_segsize &&
- pnv_pci_is_mem_pref_64(type))
+ /*
+ * We fall back to M32 if M64 isn't supported. We enforce the M64
+ * alignment for any 64-bit resource, PCIe doesn't care and
+ * bridges only do 64-bit prefetchable anyway.
+ */
+ if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64))
return phb->ioda.m64_segsize;
if (type & IORESOURCE_MEM)
return phb->ioda.m32_segsize;
w = NULL;
if (r->flags & type & IORESOURCE_IO)
w = &hose->io_resource;
- else if (pnv_pci_is_mem_pref_64(r->flags) &&
+ else if (pnv_pci_is_m64(phb, r) &&
(type & IORESOURCE_PREFETCH) &&
phb->ioda.m64_segsize)
w = &hose->mem_resources[1];
return dlpar_update_device_tree_lmb(lmb);
}
-static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
-{
- unsigned long section_nr;
- struct mem_section *mem_sect;
- struct memory_block *mem_block;
-
- section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
- mem_sect = __nr_to_section(section_nr);
-
- mem_block = find_memory_block(mem_sect);
- return mem_block;
-}
-
#ifdef CONFIG_MEMORY_HOTREMOVE
static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
{
static int dlpar_add_lmb(struct of_drconf_cell *);
+static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
+{
+ unsigned long section_nr;
+ struct mem_section *mem_sect;
+ struct memory_block *mem_block;
+
+ section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
+ mem_sect = __nr_to_section(section_nr);
+
+ mem_block = find_memory_block(mem_sect);
+ return mem_block;
+}
+
static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
{
struct memory_block *mem_block;
config PPC_XICS
def_bool n
select PPC_SMP_MUXED_IPI
+ select HARDIRQS_SW_RESEND
config PPC_ICP_NATIVE
def_bool n
.irq_mask = ics_opal_mask_irq,
.irq_unmask = ics_opal_unmask_irq,
.irq_eoi = NULL, /* Patched at init time */
- .irq_set_affinity = ics_opal_set_affinity
+ .irq_set_affinity = ics_opal_set_affinity,
+ .irq_set_type = xics_set_irq_type,
+ .irq_retrigger = xics_retrigger,
};
static int ics_opal_map(struct ics *ics, unsigned int virq);
.irq_mask = ics_rtas_mask_irq,
.irq_unmask = ics_rtas_unmask_irq,
.irq_eoi = NULL, /* Patched at init time */
- .irq_set_affinity = ics_rtas_set_affinity
+ .irq_set_affinity = ics_rtas_set_affinity,
+ .irq_set_type = xics_set_irq_type,
+ .irq_retrigger = xics_retrigger,
};
static int ics_rtas_map(struct ics *ics, unsigned int virq)
pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
- /* They aren't all level sensitive but we just don't really know */
- irq_set_status_flags(virq, IRQ_LEVEL);
+ /*
+ * Mark interrupts as edge sensitive by default so that resend
+ * actually works. The device-tree parsing will turn the LSIs
+ * back to level.
+ */
+ irq_clear_status_flags(virq, IRQ_LEVEL);
/* Don't call into ICS for IPIs */
if (hw == XICS_IPI) {
irq_hw_number_t *out_hwirq, unsigned int *out_flags)
{
- /* Current xics implementation translates everything
- * to level. It is not technically right for MSIs but this
- * is irrelevant at this point. We might get smarter in the future
- */
*out_hwirq = intspec[0];
- *out_flags = IRQ_TYPE_LEVEL_LOW;
+ /*
+ * If intsize is at least 2, we look for the type in the second cell,
+ * we assume the LSB indicates a level interrupt.
+ */
+ if (intsize > 1) {
+ if (intspec[1] & 1)
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+ else
+ *out_flags = IRQ_TYPE_EDGE_RISING;
+ } else
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+
+ return 0;
+}
+
+int xics_set_irq_type(struct irq_data *d, unsigned int flow_type)
+{
+ /*
+ * We only support these. This has really no effect other than setting
+ * the corresponding descriptor bits mind you but those will in turn
+ * affect the resend function when re-enabling an edge interrupt.
+ *
+ * Set set the default to edge as explained in map().
+ */
+ if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE)
+ flow_type = IRQ_TYPE_EDGE_RISING;
+
+ if (flow_type != IRQ_TYPE_EDGE_RISING &&
+ flow_type != IRQ_TYPE_LEVEL_LOW)
+ return -EINVAL;
+
+ irqd_set_trigger_type(d, flow_type);
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+int xics_retrigger(struct irq_data *data)
+{
+ /*
+ * We need to push a dummy CPPR when retriggering, since the subsequent
+ * EOI will try to pop it. Passing 0 works, as the function hard codes
+ * the priority value anyway.
+ */
+ xics_push_cppr(0);
+
+ /* Tell the core to do a soft retrigger */
return 0;
}
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_EARLY_PFN_TO_NID
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL
select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
Select this option if you want to run the kernel as a guest under
the KVM hypervisor.
+config S390_GUEST_OLD_TRANSPORT
+ def_bool y
+ prompt "Guest support for old s390 virtio transport (DEPRECATED)"
+ depends on S390_GUEST
+ help
+ Enable this option to add support for the old s390-virtio
+ transport (i.e. virtio devices NOT based on virtio-ccw). This
+ type of virtio devices is only available on the experimental
+ kuli userspace or with old (< 2.6) qemu. If you are running
+ with a modern version of qemu (which supports virtio-ccw since
+ 1.4 and uses it by default since version 2.4), you probably won't
+ need this.
+
endmenu
KVM_SYNC_CRS |
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT;
+ kvm_s390_set_prefix(vcpu, 0);
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
/* fprs can be synchronized via vrs, even if the guest has no vx. With
rc = gmap_mprotect_notify(vcpu->arch.gmap,
kvm_s390_get_prefix(vcpu),
PAGE_SIZE * 2, PROT_WRITE);
- if (rc)
+ if (rc) {
+ kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
return rc;
+ }
goto retry;
}
unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ check_object_size(to, n, false);
if (static_branch_likely(&have_mvcos))
return copy_from_user_mvcos(to, from, n);
return copy_from_user_mvcp(to, from, n);
unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
if (static_branch_likely(&have_mvcos))
return copy_to_user_mvcos(to, from, n);
return copy_to_user_mvcs(to, from, n);
select OLD_SIGSUSPEND
select ARCH_HAS_SG_CHAIN
select CPU_NO_EFFICIENT_FFS
+ select HAVE_ARCH_HARDENED_USERCOPY
config SPARC32
def_bool !64BIT
static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (n && __access_ok((unsigned long) to, n))
+ if (n && __access_ok((unsigned long) to, n)) {
+ if (!__builtin_constant_p(n))
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
- else
+ } else
return n;
}
static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ if (!__builtin_constant_p(n))
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
}
static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (n && __access_ok((unsigned long) from, n))
+ if (n && __access_ok((unsigned long) from, n)) {
+ if (!__builtin_constant_p(n))
+ check_object_size(to, n, false);
return __copy_user((__force void __user *) to, from, n);
- else
+ } else
return n;
}
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long size)
{
- unsigned long ret = ___copy_from_user(to, from, size);
+ unsigned long ret;
+ if (!__builtin_constant_p(size))
+ check_object_size(to, size, false);
+
+ ret = ___copy_from_user(to, from, size);
if (unlikely(ret))
ret = copy_from_user_fixup(to, from, size);
static inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long size)
{
- unsigned long ret = ___copy_to_user(to, from, size);
+ unsigned long ret;
+ if (!__builtin_constant_p(size))
+ check_object_size(from, size, true);
+ ret = ___copy_to_user(to, from, size);
if (unlikely(ret))
ret = copy_to_user_fixup(to, from, size);
return ret;
}
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
- bool write, bool foreign)
+ bool write, bool execute, bool foreign)
{
/* by default, allow everything */
return true;
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_AOUT if X86_32
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
select HAVE_ARCH_SOFT_DIRTY if X86_64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_EBPF_JIT if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y
OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
+CFLAGS_syscall_64.o += -Wno-override-init
+CFLAGS_syscall_32.o += -Wno-override-init
obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
obj-y += common.o
jne opportunistic_sysret_failed
/*
- * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
- * restoring TF results in a trap from userspace immediately after
- * SYSRET. This would cause an infinite loop whenever #DB happens
- * with register state that satisfies the opportunistic SYSRET
- * conditions. For example, single-stepping this user code:
+ * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+ * restore RF properly. If the slowpath sets it for whatever reason, we
+ * need to restore it correctly.
+ *
+ * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+ * trap from userspace immediately after SYSRET. This would cause an
+ * infinite loop whenever #DB happens with register state that satisfies
+ * the opportunistic SYSRET conditions. For example, single-stepping
+ * this user code:
*
* movq $stuck_here, %rcx
* pushfq
.endm
#endif
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+# define POP_SECTION_IRQENTRY .popsection
+#else
+# define PUSH_SECTION_IRQENTRY
+# define POP_SECTION_IRQENTRY
+#endif
+
.macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
apicinterrupt3 \num \sym \do_sym
trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
.endm
#ifdef CONFIG_SMP
}
}
+static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
static struct intel_uncore_ops snb_uncore_msr_ops = {
.init_box = snb_uncore_msr_init_box,
+ .enable_box = snb_uncore_msr_enable_box,
.exit_box = snb_uncore_msr_exit_box,
.disable_event = snb_uncore_msr_disable_event,
.enable_event = snb_uncore_msr_enable_event,
}
}
+static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
static struct intel_uncore_ops skl_uncore_msr_ops = {
.init_box = skl_uncore_msr_init_box,
+ .enable_box = skl_uncore_msr_enable_box,
.exit_box = skl_uncore_msr_exit_box,
.disable_event = snb_uncore_msr_disable_event,
.enable_event = snb_uncore_msr_enable_event,
static struct intel_uncore_type hswep_uncore_ha = {
.name = "ha",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 2,
.perf_ctr_bits = 48,
SNBEP_UNCORE_PCI_COMMON_INIT(),
static struct intel_uncore_type hswep_uncore_imc = {
.name = "imc",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 8,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
static struct intel_uncore_type hswep_uncore_qpi = {
.name = "qpi",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 3,
.perf_ctr_bits = 48,
.perf_ctr = SNBEP_PCI_PMON_CTR0,
static struct intel_uncore_type hswep_uncore_r3qpi = {
.name = "r3qpi",
- .num_counters = 4,
+ .num_counters = 3,
.num_boxes = 3,
.perf_ctr_bits = 44,
.constraints = hswep_uncore_r3qpi_constraints,
static struct intel_uncore_type bdx_uncore_imc = {
.name = "imc",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 8,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
+extern void lapic_update_tsc_freq(void);
extern int APIC_init_uniprocessor(void);
#ifdef CONFIG_X86_64
static inline void disable_local_APIC(void) { }
# define setup_boot_APIC_clock x86_init_noop
# define setup_secondary_APIC_clock x86_init_noop
+static inline void lapic_update_tsc_freq(void) { }
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_X2APIC
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
- /*
- * irq_tlb_count is double-counted in irq_call_count, so it must be
- * subtracted from irq_call_count when displaying irq_call_count
- */
unsigned int irq_tlb_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
unsigned long pmd_flag; /* page flag for PMD entry */
- bool kernel_mapping; /* kernel mapping or ident mapping */
+ unsigned long offset; /* ident mapping offset */
};
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
- unsigned long addr, unsigned long end);
+ unsigned long pstart, unsigned long pend);
#endif /* _ASM_X86_INIT_H */
*
* | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number
* | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry
*
* G (8) is aliased and used as a PROT_NONE indicator for
* !present ptes. We need to start storing swap entries above
#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
#define SWP_TYPE_BITS 5
/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
extern unsigned char secondary_startup_64[];
#endif
+static inline size_t real_mode_size_needed(void)
+{
+ if (real_mode_header)
+ return 0; /* already allocated. */
+
+ return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
+}
+
+void set_real_mode_mem(phys_addr_t mem, size_t size);
void reserve_real_mode(void);
-void setup_real_mode(void);
#endif /* _ARCH_X86_REALMODE_H */
return sp;
}
+/*
+ * Walks up the stack frames to make sure that the specified object is
+ * entirely contained by a single stack frame.
+ *
+ * Returns:
+ * 1 if within a frame
+ * -1 if placed across a frame boundary (or outside stack)
+ * 0 unable to determine (no frame pointers, etc)
+ */
+static inline int arch_within_stack_frames(const void * const stack,
+ const void * const stackend,
+ const void *obj, unsigned long len)
+{
+#if defined(CONFIG_FRAME_POINTER)
+ const void *frame = NULL;
+ const void *oldframe;
+
+ oldframe = __builtin_frame_address(1);
+ if (oldframe)
+ frame = __builtin_frame_address(2);
+ /*
+ * low ----------------------------------------------> high
+ * [saved bp][saved ip][args][local vars][saved bp][saved ip]
+ * ^----------------^
+ * allow copies only within here
+ */
+ while (stack <= frame && frame < stackend) {
+ /*
+ * If obj + len extends past the last frame, this
+ * check won't pass and the next frame will be 0,
+ * causing us to bail out and correctly report
+ * the copy as invalid.
+ */
+ if (obj + len <= frame)
+ return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1;
+ oldframe = frame;
+ frame = *(const void * const *)frame;
+ }
+ return -1;
+#else
+ return 0;
+#endif
+}
+
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_X86_64
static inline void __native_flush_tlb(void)
{
+ /*
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
+ */
+ preempt_disable();
native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
* case, and do only runtime checking for non-constant sizes.
*/
- if (likely(sz < 0 || sz >= n))
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(to, n, false);
n = _copy_from_user(to, from, n);
- else if(__builtin_constant_p(n))
+ } else if (__builtin_constant_p(n))
copy_from_user_overflow();
else
__copy_from_user_overflow(sz, n);
might_fault();
/* See the comment in copy_from_user() above. */
- if (likely(sz < 0 || sz >= n))
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(from, n, true);
n = _copy_to_user(to, from, n);
- else if(__builtin_constant_p(n))
+ } else if (__builtin_constant_p(n))
copy_to_user_overflow();
else
__copy_to_user_overflow(sz, n);
#define user_access_begin() __uaccess_begin()
#define user_access_end() __uaccess_end()
-#define unsafe_put_user(x, ptr) \
-({ \
+#define unsafe_put_user(x, ptr, err_label) \
+do { \
int __pu_err; \
__put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
- __builtin_expect(__pu_err, 0); \
-})
+ if (unlikely(__pu_err)) goto err_label; \
+} while (0)
-#define unsafe_get_user(x, ptr) \
-({ \
+#define unsafe_get_user(x, ptr, err_label) \
+do { \
int __gu_err; \
unsigned long __gu_val; \
__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
- __builtin_expect(__gu_err, 0); \
-})
+ if (unlikely(__gu_err)) goto err_label; \
+} while (0)
#endif /* _ASM_X86_UACCESS_H */
static __always_inline unsigned long __must_check
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
return __copy_to_user_ll(to, from, n);
}
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
might_fault();
+ check_object_size(to, n, false);
if (__builtin_constant_p(n)) {
unsigned long ret;
{
int ret = 0;
+ check_object_size(dst, size, false);
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
{
int ret = 0;
+ check_object_size(src, size, true);
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
u16 nasid; /* HNasid */
u16 sockid; /* Socket ID, high bits of APIC ID */
u16 pnode; /* Index to MMR and GRU spaces */
- u32 pxm; /* ACPI proximity domain number */
+ u32 unused2;
u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
};
#define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */
#define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */
#define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */
-#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2
+#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */
+#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3
#define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */
#define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */
/* Clock divisor */
#define APIC_DIVISOR 16
-#define TSC_DIVISOR 32
+#define TSC_DIVISOR 8
/*
* This function sets up the local APIC timer, with a timeout of
CLOCK_EVT_FEAT_DUMMY);
levt->set_next_event = lapic_next_deadline;
clockevents_config_and_register(levt,
- (tsc_khz / TSC_DIVISOR) * 1000,
+ tsc_khz * (1000 / TSC_DIVISOR),
0xF, ~0UL);
} else
clockevents_register_device(levt);
}
+/*
+ * Install the updated TSC frequency from recalibration at the TSC
+ * deadline clockevent devices.
+ */
+static void __lapic_update_tsc_freq(void *info)
+{
+ struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
+
+ if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return;
+
+ clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR));
+}
+
+void lapic_update_tsc_freq(void)
+{
+ /*
+ * The clockevent device's ->mult and ->shift can both be
+ * changed. In order to avoid races, schedule the frequency
+ * update code on each CPU.
+ */
+ on_each_cpu(__lapic_update_tsc_freq, NULL, 0);
+}
+
/*
* In this functions we calibrate APIC bus clocks to the external timer.
*
/*
* At CPU state changes, update the x2apic cluster sibling info.
*/
-int x2apic_prepare_cpu(unsigned int cpu)
+static int x2apic_prepare_cpu(unsigned int cpu)
{
if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
return -ENOMEM;
return 0;
}
-int x2apic_dead_cpu(unsigned int this_cpu)
+static int x2apic_dead_cpu(unsigned int this_cpu)
{
int cpu;
static int x2apic_cluster_probe(void)
{
int cpu = smp_processor_id();
+ int ret;
if (!x2apic_mode)
return 0;
+ ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+ x2apic_prepare_cpu, x2apic_dead_cpu);
+ if (ret < 0) {
+ pr_err("Failed to register X2APIC_PREPARE\n");
+ return 0;
+ }
cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
- cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
- x2apic_prepare_cpu, x2apic_dead_cpu);
return 1;
}
if (strncmp(oem_id, "SGI", 3) != 0)
return 0;
+ if (numa_off) {
+ pr_err("UV: NUMA is off, disabling UV support\n");
+ return 0;
+ }
+
/* Setup early hub type field in uv_hub_info for Node 0 */
uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
struct uv_gam_range_entry *gre = uv_gre_table;
struct uv_gam_range_s *grt;
unsigned long last_limit = 0, ram_limit = 0;
- int bytes, i, sid, lsid = -1;
+ int bytes, i, sid, lsid = -1, indx = 0, lindx = -1;
if (!gre)
return;
}
sid = gre->sockid - _min_socket;
if (lsid < sid) { /* new range */
- grt = &_gr_table[sid];
- grt->base = lsid;
+ grt = &_gr_table[indx];
+ grt->base = lindx;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
lsid = sid;
+ lindx = indx++;
continue;
}
if (lsid == sid && !ram_limit) { /* update range */
}
if (!ram_limit) { /* non-contiguous ram range */
grt++;
- grt->base = sid - 1;
+ grt->base = lindx;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
continue;
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (!index) {
pr_info("UV: GAM Range Table...\n");
- pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+ pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n",
"Range", "", "Size", "Type", "NASID",
- "SID", "PN", "PXM");
+ "SID", "PN");
}
pr_info(
- "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n",
+ "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n",
index++,
(unsigned long)lgre << UV_GAM_RANGE_SHFT,
(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
((unsigned long)(gre->limit - lgre)) >>
(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
- gre->type, gre->nasid, gre->sockid,
- gre->pnode, gre->pxm);
+ gre->type, gre->nasid, gre->sockid, gre->pnode);
lgre = gre->limit;
if (sock_min > gre->sockid)
_pnode_to_socket[i] = SOCK_EMPTY;
/* fill in pnode/node/addr conversion list values */
- pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+ pr_info("UV: GAM Building socket/pnode conversion tables\n");
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
continue;
if (_socket_to_pnode[i] != SOCK_EMPTY)
continue; /* duplicate */
_socket_to_pnode[i] = gre->pnode;
- _socket_to_node[i] = gre->pxm;
i = gre->pnode - minpnode;
_pnode_to_socket[i] = gre->sockid;
pr_info(
- "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+ "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
gre->sockid, gre->type, gre->nasid,
_socket_to_pnode[gre->sockid - minsock],
- _socket_to_node[gre->sockid - minsock],
_pnode_to_socket[gre->pnode - minpnode]);
}
- /* check socket -> node values */
+ /* Set socket -> node values */
lnid = -1;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
lnid = nid;
apicid = per_cpu(x86_cpu_to_apicid, cpu);
sockid = apicid >> uv_cpuid.socketid_shift;
- i = sockid - minsock;
-
- if (nid != _socket_to_node[i]) {
- pr_warn(
- "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
- i, sockid, gre->type, _socket_to_node[i], nid);
- _socket_to_node[i] = nid;
- }
+ _socket_to_node[sockid - minsock] = nid;
+ pr_info("UV: sid:%02x: apicid:%04x node:%2d\n",
+ sockid, apicid, nid);
}
/* Setup physical blade to pnode translation from GAM Range Table */
return get_xsave_addr(&fpu->state.xsave, xsave_state);
}
-
-/*
- * Set xfeatures (aka XSTATE_BV) bit for a feature that we want
- * to take out of its "init state". This will ensure that an
- * XRSTOR actually restores the state.
- */
-static void fpu__xfeature_set_non_init(struct xregs_state *xsave,
- int xstate_feature_mask)
-{
- xsave->header.xfeatures |= xstate_feature_mask;
-}
-
-/*
- * This function is safe to call whether the FPU is in use or not.
- *
- * Note that this only works on the current task.
- *
- * Inputs:
- * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
- * XFEATURE_MASK_SSE, etc...)
- * @xsave_state_ptr: a pointer to a copy of the state that you would
- * like written in to the current task's FPU xsave state. This pointer
- * must not be located in the current tasks's xsave area.
- * Output:
- * address of the state in the xsave area or NULL if the state
- * is not present or is in its 'init state'.
- */
-static void fpu__xfeature_set_state(int xstate_feature_mask,
- void *xstate_feature_src, size_t len)
-{
- struct xregs_state *xsave = ¤t->thread.fpu.state.xsave;
- struct fpu *fpu = ¤t->thread.fpu;
- void *dst;
-
- if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
- WARN_ONCE(1, "%s() attempted with no xsave support", __func__);
- return;
- }
-
- /*
- * Tell the FPU code that we need the FPU state to be in
- * 'fpu' (not in the registers), and that we need it to
- * be stable while we write to it.
- */
- fpu__current_fpstate_write_begin();
-
- /*
- * This method *WILL* *NOT* work for compact-format
- * buffers. If the 'xstate_feature_mask' is unset in
- * xcomp_bv then we may need to move other feature state
- * "up" in the buffer.
- */
- if (xsave->header.xcomp_bv & xstate_feature_mask) {
- WARN_ON_ONCE(1);
- goto out;
- }
-
- /* find the location in the xsave buffer of the desired state */
- dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask);
-
- /*
- * Make sure that the pointer being passed in did not
- * come from the xsave buffer itself.
- */
- WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself");
-
- /* put the caller-provided data in the location */
- memcpy(dst, xstate_feature_src, len);
-
- /*
- * Mark the xfeature so that the CPU knows there is state
- * in the buffer now.
- */
- fpu__xfeature_set_non_init(xsave, xstate_feature_mask);
-out:
- /*
- * We are done writing to the 'fpu'. Reenable preeption
- * and (possibly) move the fpstate back in to the fpregs.
- */
- fpu__current_fpstate_write_end();
-}
-
#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
/*
- * This will go out and modify the XSAVE buffer so that PKRU is
- * set to a particular state for access to 'pkey'.
- *
- * PKRU state does affect kernel access to user memory. We do
- * not modfiy PKRU *itself* here, only the XSAVE state that will
- * be restored in to PKRU when we return back to userspace.
+ * This will go out and modify PKRU register to set the access
+ * rights for @pkey to @init_val.
*/
int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
unsigned long init_val)
{
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
- struct pkru_state *old_pkru_state;
- struct pkru_state new_pkru_state;
+ u32 old_pkru;
int pkey_shift = (pkey * PKRU_BITS_PER_PKEY);
u32 new_pkru_bits = 0;
*/
if (!boot_cpu_has(X86_FEATURE_OSPKE))
return -EINVAL;
+ /*
+ * For most XSAVE components, this would be an arduous task:
+ * brining fpstate up to date with fpregs, updating fpstate,
+ * then re-populating fpregs. But, for components that are
+ * never lazily managed, we can just access the fpregs
+ * directly. PKRU is never managed lazily, so we can just
+ * manipulate it directly. Make sure it stays that way.
+ */
+ WARN_ON_ONCE(!use_eager_fpu());
/* Set the bits we need in PKRU: */
if (init_val & PKEY_DISABLE_ACCESS)
/* Shift the bits in to the correct place in PKRU for pkey: */
new_pkru_bits <<= pkey_shift;
- /* Locate old copy of the state in the xsave buffer: */
- old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU);
-
- /*
- * When state is not in the buffer, it is in the init
- * state, set it manually. Otherwise, copy out the old
- * state.
- */
- if (!old_pkru_state)
- new_pkru_state.pkru = 0;
- else
- new_pkru_state.pkru = old_pkru_state->pkru;
-
- /* Mask off any old bits in place: */
- new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
-
- /* Set the newly-requested bits: */
- new_pkru_state.pkru |= new_pkru_bits;
-
- /*
- * We could theoretically live without zeroing pkru.pad.
- * The current XSAVE feature state definition says that
- * only bytes 0->3 are used. But we do not want to
- * chance leaking kernel stack out to userspace in case a
- * memcpy() of the whole xsave buffer was done.
- *
- * They're in the same cacheline anyway.
- */
- new_pkru_state.pad = 0;
+ /* Get old PKRU and mask off any old bits in place: */
+ old_pkru = read_pkru();
+ old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
- fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state));
+ /* Write old part along with new part: */
+ write_pkru(old_pkru | new_pkru_bits);
return 0;
}
/* Initialize 32bit specific setup functions */
x86_init.resources.reserve_resources = i386_reserve_resources;
x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
-
- reserve_bios_regions();
}
asmlinkage __visible void __init i386_start_kernel(void)
copy_bootdata(__va(real_mode_data));
x86_early_init_platform_quirks();
- reserve_bios_regions();
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_INTEL_MID:
memset(&curr_time, 0, sizeof(struct rtc_time));
if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
- mc146818_set_time(&curr_time);
+ mc146818_get_time(&curr_time);
if (hpet_rtc_flags & RTC_UIE &&
curr_time.tm_sec != hpet_prev_update_sec) {
seq_puts(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
- irq_stats(j)->irq_tlb_count);
+ seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
seq_puts(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
x86_init.oem.arch_setup();
- kernel_randomize_memory();
-
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
setup_memory_map();
parse_setup_data();
max_possible_pfn = max_pfn;
+ /*
+ * Define random base addresses for memory sections after max_pfn is
+ * defined and before each memory section base is used.
+ */
+ kernel_randomize_memory();
+
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
find_low_pfn_range();
efi_find_mirror();
}
+ reserve_bios_regions();
+
/*
* The EFI specification says that boot service code won't be called
* after ExitBootServices(). This is, in fact, a lie.
early_trap_pf_init();
- setup_real_mode();
+ /*
+ * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
+ * with the current CR4 value. This may not be necessary, but
+ * auditing all the early-boot CR4 manipulation would be needed to
+ * rule it out.
+ */
+ if (boot_cpu_data.cpuid_level >= 0)
+ /* A CPU has %cr4 if and only if it has CPUID. */
+ mmu_cr4_features = __read_cr4();
memblock_set_current_limit(get_max_mapped());
kasan_init();
- if (boot_cpu_data.cpuid_level >= 0) {
- /* A CPU has %cr4 if and only if it has CPUID */
- mmu_cr4_features = __read_cr4();
- if (trampoline_cr4_features)
- *trampoline_cr4_features = mmu_cr4_features;
- }
-
#ifdef CONFIG_X86_32
/* sync back kernel address range */
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
#include <asm/nmi.h>
#include <asm/x86_init.h>
#include <asm/geode.h>
+#include <asm/apic.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
(unsigned long)tsc_khz / 1000,
(unsigned long)tsc_khz % 1000);
+ /* Inform the TSC deadline clockevent devices about the recalibration */
+ lapic_update_tsc_freq();
+
out:
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
*cursor &= 0xfe;
}
/*
- * Similar treatment for VEX3 prefix.
- * TODO: add XOP/EVEX treatment when insn decoder supports them
+ * Similar treatment for VEX3/EVEX prefix.
+ * TODO: add XOP treatment when insn decoder supports them
*/
- if (insn->vex_prefix.nbytes == 3) {
+ if (insn->vex_prefix.nbytes >= 3) {
/*
* vex2: c5 rvvvvLpp (has no b bit)
* vex3/xop: c4/8f rxbmmmmm wvvvvLpp
* evex: 62 rxbR00mm wvvvv1pp zllBVaaa
- * (evex will need setting of both b and x since
- * in non-sib encoding evex.x is 4th bit of MODRM.rm)
- * Setting VEX3.b (setting because it has inverted meaning):
+ * Setting VEX3.b (setting because it has inverted meaning).
+ * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+ * is the 4th bit of MODRM.rm, and needs the same treatment.
+ * For VEX3-encoded insns, VEX3.x value has no effect in
+ * non-SIB encoding, the change is superfluous but harmless.
*/
cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
- *cursor |= 0x20;
+ *cursor |= 0x60;
}
/*
reg = MODRM_REG(insn); /* Fetch modrm.reg */
reg2 = 0xff; /* Fetch vex.vvvv */
- if (insn->vex_prefix.nbytes == 2)
- reg2 = insn->vex_prefix.bytes[1];
- else if (insn->vex_prefix.nbytes == 3)
+ if (insn->vex_prefix.nbytes)
reg2 = insn->vex_prefix.bytes[2];
/*
- * TODO: add XOP, EXEV vvvv reading.
+ * TODO: add XOP vvvv reading.
*
* vex.vvvv field is in bits 6-3, bits are inverted.
* But in 32-bit mode, high-order bit may be ignored.
ENTRY(__sw_hweight64)
#ifdef CONFIG_X86_64
+ pushq %rdi
pushq %rdx
movq %rdi, %rdx # w -> t
shrq $56, %rax # w = w_tmp >> 56
popq %rdx
+ popq %rdi
ret
#else /* CONFIG_X86_32 */
/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
#include <asm/cpufeature.h>
#include <asm/setup.h>
-#define debug_putstr(v) early_printk(v)
+#define debug_putstr(v) early_printk("%s", v)
#define has_cpuflag(f) boot_cpu_has(f)
#define get_boot_seed() kaslr_offset()
#endif
* included by both the compressed kernel and the regular kernel.
*/
-static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
unsigned long addr, unsigned long end)
{
addr &= PMD_MASK;
for (; addr < end; addr += PMD_SIZE) {
pmd_t *pmd = pmd_page + pmd_index(addr);
- if (!pmd_present(*pmd))
- set_pmd(pmd, __pmd(addr | pmd_flag));
+ if (pmd_present(*pmd))
+ continue;
+
+ set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
}
}
if (pud_present(*pud)) {
pmd = pmd_offset(pud, 0);
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
+ ident_pmd_init(info, pmd, addr, next);
continue;
}
pmd = (pmd_t *)info->alloc_pgt_page(info->context);
if (!pmd)
return -ENOMEM;
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
+ ident_pmd_init(info, pmd, addr, next);
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
}
}
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
- unsigned long addr, unsigned long end)
+ unsigned long pstart, unsigned long pend)
{
+ unsigned long addr = pstart + info->offset;
+ unsigned long end = pend + info->offset;
unsigned long next;
int result;
- int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
for (; addr < end; addr = next) {
- pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+ pgd_t *pgd = pgd_page + pgd_index(addr);
pud_t *pud;
next = (addr & PGDIR_MASK) + PGDIR_SIZE;
return __va(pfn << PAGE_SHIFT);
}
-/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE)
+/*
+ * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS.
+ * With KASLR memory randomization, depending on the machine e820 memory
+ * and the PUD alignment. We may need twice more pages when KASLR memory
+ * randomization is enabled.
+ */
+#ifndef CONFIG_RANDOMIZE_MEMORY
+#define INIT_PGD_PAGE_COUNT 6
+#else
+#define INIT_PGD_PAGE_COUNT 12
+#endif
+#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE)
RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
void __init early_alloc_pgt_buf(void)
{
* add padding if needed (especially for memory hotplug support).
*/
BUG_ON(kaslr_regions[0].base != &page_offset_base);
- memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) +
+ memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
/* Adapt phyiscal memory region size based on available memory */
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+ size_t rm_size;
if (md->type != EFI_BOOT_SERVICES_CODE &&
md->type != EFI_BOOT_SERVICES_DATA)
if (md->attribute & EFI_MEMORY_RUNTIME)
continue;
+ /*
+ * Nasty quirk: if all sub-1MB memory is used for boot
+ * services, we can get here without having allocated the
+ * real mode trampoline. It's too late to hand boot services
+ * memory back to the memblock allocator, so instead
+ * try to manually allocate the trampoline if needed.
+ *
+ * I've seen this on a Dell XPS 13 9350 with firmware
+ * 1.4.4 with SGX enabled booting Linux via Fedora 24's
+ * grub2-efi on a hard disk. (And no, I don't know why
+ * this happened, but Linux should still try to boot rather
+ * panicing early.)
+ */
+ rm_size = real_mode_size_needed();
+ if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
+ set_real_mode_mem(start, rm_size);
+ start += rm_size;
+ size -= rm_size;
+ }
+
free_bootmem_late(start, size);
}
void uv_bios_init(void)
{
uv_systab = NULL;
- if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) {
+ if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
+ !efi.uv_systab || efi_runtime_disabled()) {
pr_crit("UV: UVsystab: missing\n");
return;
}
return;
}
+ /* Starting with UV4 the UV systab size is variable */
if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+ int size = uv_systab->size;
+
iounmap(uv_systab);
- uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+ uv_systab = ioremap(efi.uv_systab, size);
if (!uv_systab) {
- pr_err("UV: UVsystab: ioremap(%d) failed!\n",
- uv_systab->size);
+ pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
return;
}
}
struct x86_mapping_info info = {
.alloc_pgt_page = alloc_pgt_page,
.pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
- .kernel_mapping = true,
+ .offset = __PAGE_OFFSET,
};
unsigned long mstart, mend;
pgd_t *pgd;
#include <linux/io.h>
+#include <linux/slab.h>
#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>
#include <asm/realmode.h>
+#include <asm/tlbflush.h>
struct real_mode_header *real_mode_header;
u32 *trampoline_cr4_features;
/* Hold the pgd entry used on booting additional CPUs */
pgd_t trampoline_pgd_entry;
+void __init set_real_mode_mem(phys_addr_t mem, size_t size)
+{
+ void *base = __va(mem);
+
+ real_mode_header = (struct real_mode_header *) base;
+ printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
+ base, (unsigned long long)mem, size);
+}
+
void __init reserve_real_mode(void)
{
phys_addr_t mem;
- unsigned char *base;
- size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
+ size_t size = real_mode_size_needed();
+
+ if (!size)
+ return;
+
+ WARN_ON(slab_is_available());
/* Has to be under 1M so we can execute real-mode AP code. */
mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
- if (!mem)
- panic("Cannot allocate trampoline\n");
+ if (!mem) {
+ pr_info("No sub-1M memory is available for the trampoline\n");
+ return;
+ }
- base = __va(mem);
memblock_reserve(mem, size);
- real_mode_header = (struct real_mode_header *) base;
- printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
- base, (unsigned long long)mem, size);
+ set_real_mode_mem(mem, size);
}
-void __init setup_real_mode(void)
+static void __init setup_real_mode(void)
{
u16 real_mode_seg;
const u32 *rel;
trampoline_header->start = (u64) secondary_startup_64;
trampoline_cr4_features = &trampoline_header->cr4;
- *trampoline_cr4_features = __read_cr4();
+ *trampoline_cr4_features = mmu_cr4_features;
trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
trampoline_pgd[0] = trampoline_pgd_entry.pgd;
* need to mark it executable at do_pre_smp_initcalls() at least,
* thus run it as a early_initcall().
*/
-static int __init set_real_mode_permissions(void)
+static void __init set_real_mode_permissions(void)
{
unsigned char *base = (unsigned char *) real_mode_header;
size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
set_memory_nx((unsigned long) base, size >> PAGE_SHIFT);
set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT);
set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT);
+}
+
+static int __init init_real_mode(void)
+{
+ if (!real_mode_header)
+ panic("Real mode trampoline was not allocated");
+
+ setup_real_mode();
+ set_real_mode_permissions();
return 0;
}
-early_initcall(set_real_mode_permissions);
+early_initcall(init_real_mode);
{
struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
u64 offset = nfit_blk->stat_offset + mmio->size * bw;
+ const u32 STATUS_MASK = 0x80000037;
if (mmio->num_lines)
offset = to_interleave_offset(offset, mmio);
- return readl(mmio->addr.base + offset);
+ return readl(mmio->addr.base + offset) & STATUS_MASK;
}
static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
bool need_put = !!rbd_dev->opts;
ceph_oid_destroy(&rbd_dev->header_oid);
+ ceph_oloc_destroy(&rbd_dev->header_oloc);
rbd_put_client(rbd_dev->rbd_client);
rbd_spec_put(rbd_dev->spec);
}
spec->pool_id = (u64)rc;
- /* The ceph file layout needs to fit pool id in 32 bits */
-
- if (spec->pool_id > (u64)U32_MAX) {
- rbd_warn(NULL, "pool id too large (%llu > %u)",
- (unsigned long long)spec->pool_id, U32_MAX);
- rc = -EIO;
- goto err_out_client;
- }
-
rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts);
if (!rbd_dev) {
rc = -ENOMEM;
num_vqs = 1;
vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
- if (!vblk->vqs) {
- err = -ENOMEM;
- goto out;
- }
+ if (!vblk->vqs)
+ return -ENOMEM;
names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
- if (!names)
- goto err_names;
-
callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
- if (!callbacks)
- goto err_callbacks;
-
vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
- if (!vqs)
- goto err_vqs;
+ if (!names || !callbacks || !vqs) {
+ err = -ENOMEM;
+ goto out;
+ }
for (i = 0; i < num_vqs; i++) {
callbacks[i] = virtblk_done;
/* Discover virtqueues and write information to configuration. */
err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
if (err)
- goto err_find_vqs;
+ goto out;
for (i = 0; i < num_vqs; i++) {
spin_lock_init(&vblk->vqs[i].lock);
}
vblk->num_vqs = num_vqs;
- err_find_vqs:
+out:
kfree(vqs);
- err_vqs:
kfree(callbacks);
- err_callbacks:
kfree(names);
- err_names:
if (err)
kfree(vblk->vqs);
- out:
return err;
}
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+
+#define pr_fmt(fmt) "arm_arch_timer: " fmt
+
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/device.h>
arch_timer_ppi[PHYS_NONSECURE_PPI]);
}
+static u32 check_ppi_trigger(int irq)
+{
+ u32 flags = irq_get_trigger_type(irq);
+
+ if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) {
+ pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq);
+ pr_warn("WARNING: Please fix your firmware\n");
+ flags = IRQF_TRIGGER_LOW;
+ }
+
+ return flags;
+}
+
static int arch_timer_starting_cpu(unsigned int cpu)
{
struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
+ u32 flags;
__arch_timer_setup(ARCH_CP15_TIMER, clk);
- enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+ flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]);
+ enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags);
- if (arch_timer_has_nonsecure_ppi())
- enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
+ if (arch_timer_has_nonsecure_ppi()) {
+ flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags);
+ }
arch_counter_set_user_access();
if (evtstrm_enable)
/* Use following macros for conversions between pstate_id and index */
static inline int idx_to_pstate(unsigned int i)
{
+ if (unlikely(i >= powernv_pstate_info.nr_pstates)) {
+ pr_warn_once("index %u is out of bound\n", i);
+ return powernv_freqs[powernv_pstate_info.nominal].driver_data;
+ }
+
return powernv_freqs[i].driver_data;
}
static inline unsigned int pstate_to_idx(int pstate)
{
+ int min = powernv_freqs[powernv_pstate_info.min].driver_data;
+ int max = powernv_freqs[powernv_pstate_info.max].driver_data;
+
+ if (min > 0) {
+ if (unlikely((pstate < max) || (pstate > min))) {
+ pr_warn_once("pstate %d is out of bound\n", pstate);
+ return powernv_pstate_info.nominal;
+ }
+ } else {
+ if (unlikely((pstate > max) || (pstate < min))) {
+ pr_warn_once("pstate %d is out of bound\n", pstate);
+ return powernv_pstate_info.nominal;
+ }
+ }
/*
* abs() is deliberately used so that is works with
* both monotonically increasing and decreasing
} else {
gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
gpstates->highest_lpstate_idx,
- freq_data.pstate_id);
+ gpstates->last_lpstate_idx);
}
/*
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/efi.h>
+#include <linux/vmalloc.h>
#define NO_FURTHER_WRITE_ACTION -1
int ret;
void *cap_hdr_temp;
- cap_hdr_temp = kmap(cap_info->pages[0]);
+ cap_hdr_temp = vmap(cap_info->pages, cap_info->index,
+ VM_MAP, PAGE_KERNEL);
if (!cap_hdr_temp) {
- pr_debug("%s: kmap() failed\n", __func__);
+ pr_debug("%s: vmap() failed\n", __func__);
return -EFAULT;
}
ret = efi_capsule_update(cap_hdr_temp, cap_info->pages);
- kunmap(cap_info->pages[0]);
+ vunmap(cap_hdr_temp);
if (ret) {
pr_err("%s: efi_capsule_update() failed\n", __func__);
return ret;
* map the capsule described by @capsule with its data in @pages and
* send it to the firmware via the UpdateCapsule() runtime service.
*
- * @capsule must be a virtual mapping of the first page in @pages
- * (@pages[0]) in the kernel address space. That is, a
- * capsule_header_t that describes the entire contents of the capsule
+ * @capsule must be a virtual mapping of the complete capsule update in the
+ * kernel address space, as the capsule can be consumed immediately.
+ * A capsule_header_t that describes the entire contents of the capsule
* must be at the start of the first data page.
*
* Even though this function will validate that the firmware supports
struct drm_device *ddev = dev_get_drvdata(dev);
struct amdgpu_device *adev = ddev->dev_private;
char *table = NULL;
- int size, i;
+ int size;
if (adev->pp_enabled)
size = amdgpu_dpm_get_pp_table(adev, &table);
if (size >= PAGE_SIZE)
size = PAGE_SIZE - 1;
- for (i = 0; i < size; i++) {
- sprintf(buf + i, "%02x", table[i]);
- }
- sprintf(buf + i, "\n");
+ memcpy(buf, table, size);
return size;
}
if (unlikely(r)) {
goto out_cleanup;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem);
out_cleanup:
ttm_bo_mem_put(bo, &tmp_mem);
return r;
if (unlikely(r)) {
return r;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem);
if (unlikely(r)) {
goto out_cleanup;
}
break;
case CHIP_KAVERI:
case CHIP_KABINI:
+ case CHIP_MULLINS:
default: BUG();
}
static const u32 golden_settings_polaris11_a11[] =
{
- mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208,
+ mmCB_HW_CONTROL, 0x0000f3cf, 0x00007208,
+ mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000,
mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c,
mmRLC_CGCG_CGLS_CTRL_3D, 0xffffffff, 0x0001003c,
- mmSQ_CONFIG, 0x07f80000, 0x07180000,
+ mmSQ_CONFIG, 0x07f80000, 0x01180000,
mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3,
static const u32 golden_settings_polaris10_a11[] =
{
mmATC_MISC_CG, 0x000c0fc0, 0x000c0200,
- mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208,
- mmCB_HW_CONTROL_2, 0, 0x0f000000,
+ mmCB_HW_CONTROL, 0x0001f3cf, 0x00007208,
+ mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
mmPA_SC_RASTER_CONFIG, 0x3f3fffff, 0x00000002,
mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000,
+ mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c,
mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd,
mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmGB_GPU_ID, 0x0000000f, 0x00000000,
mmPA_SC_ENHANCE, 0xffffffff, 0x00000001,
mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
+ mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c,
mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd,
mmTA_CNTL_AUX, 0x000f000f, 0x00010000,
+ mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmTCC_EXE_DISABLE, 0x00000002, 0x00000002,
mmTCP_ADDR_CONFIG, 0x0000000f, 0x000000f3,
mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00001302
break;
case CHIP_KAVERI:
case CHIP_KABINI:
+ case CHIP_MULLINS:
return 0;
default: BUG();
}
mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104
};
+static const u32 golden_settings_stoney_common[] =
+{
+ mmMC_HUB_RDREQ_UVD, MC_HUB_RDREQ_UVD__PRESCALE_MASK, 0x00000004,
+ mmMC_RD_GRP_OTH, MC_RD_GRP_OTH__UVD_MASK, 0x00600000
+};
static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev)
{
amdgpu_program_register_sequence(adev,
stoney_mgcg_cgcg_init,
(const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
+ amdgpu_program_register_sequence(adev,
+ golden_settings_stoney_common,
+ (const u32)ARRAY_SIZE(golden_settings_stoney_common));
break;
default:
break;
goto out;
}
+ /*
+ * cirrus_modeset_init() is initializing/registering the emulated fbdev
+ * and DRM internals can access/test some of the fields in
+ * mode_config->funcs as part of the fbdev registration process.
+ * Make sure dev->mode_config.funcs is properly set to avoid
+ * dereferencing a NULL pointer.
+ * FIXME: mode_config.funcs assignment should probably be done in
+ * cirrus_modeset_init() (that's a common pattern seen in other DRM
+ * drivers).
+ */
+ dev->mode_config.funcs = &cirrus_mode_funcs;
r = cirrus_modeset_init(cdev);
if (r) {
dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r);
goto out;
}
- dev->mode_config.funcs = (void *)&cirrus_mode_funcs;
-
return 0;
out:
cirrus_driver_unload(dev);
struct drm_connector *connector;
int ret;
- mutex_lock(&dev->mode_config.mutex);
-
- drm_for_each_connector(connector, dev) {
+ /* FIXME: taking the mode config mutex ends up in a clash with
+ * fbcon/backlight registration */
+ list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
ret = drm_connector_register(connector);
if (ret)
goto err;
}
- mutex_unlock(&dev->mode_config.mutex);
-
return 0;
err:
#define EDID_QUIRK_FORCE_8BPC (1 << 8)
/* Force 12bpc */
#define EDID_QUIRK_FORCE_12BPC (1 << 9)
+/* Force 6bpc */
+#define EDID_QUIRK_FORCE_6BPC (1 << 10)
struct detailed_mode_closure {
struct drm_connector *connector;
/* Unknown Acer */
{ "ACR", 2423, EDID_QUIRK_FIRST_DETAILED_PREFERRED },
+ /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */
+ { "AEO", 0, EDID_QUIRK_FORCE_6BPC },
+
/* Belinea 10 15 55 */
{ "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 },
{ "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 },
/* HDMI deep color modes supported? Assign to info, if so */
drm_assign_hdmi_deep_color_info(edid, info, connector);
+ /*
+ * Digital sink with "DFP 1.x compliant TMDS" according to EDID 1.3?
+ *
+ * For such displays, the DFP spec 1.0, section 3.10 "EDID support"
+ * tells us to assume 8 bpc color depth if the EDID doesn't have
+ * extensions which tell otherwise.
+ */
+ if ((info->bpc == 0) && (edid->revision < 4) &&
+ (edid->input & DRM_EDID_DIGITAL_TYPE_DVI)) {
+ info->bpc = 8;
+ DRM_DEBUG("%s: Assigning DFP sink color depth as %d bpc.\n",
+ connector->name, info->bpc);
+ }
+
/* Only defined for 1.4 with digital displays */
if (edid->revision < 4)
return;
drm_add_display_info(edid, &connector->display_info, connector);
+ if (quirks & EDID_QUIRK_FORCE_6BPC)
+ connector->display_info.bpc = 6;
+
if (quirks & EDID_QUIRK_FORCE_8BPC)
connector->display_info.bpc = 8;
static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
{
- unsigned int i;
-
- for (i = 0; i < 15; i++) {
- if (skl_cdclk_pcu_ready(dev_priv))
- return true;
- udelay(10);
- }
-
- return false;
+ return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0;
}
static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
pipe_config->pipe_bpp = connector->base.display_info.bpc*3;
}
- /* Clamp bpp to default limit on screens without EDID 1.4 */
- if (connector->base.display_info.bpc == 0) {
- int type = connector->base.connector_type;
- int clamp_bpp = 24;
-
- /* Fall back to 18 bpp when DP sink capability is unknown. */
- if (type == DRM_MODE_CONNECTOR_DisplayPort ||
- type == DRM_MODE_CONNECTOR_eDP)
- clamp_bpp = 18;
-
- if (bpp > clamp_bpp) {
- DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n",
- bpp, clamp_bpp);
- pipe_config->pipe_bpp = clamp_bpp;
- }
+ /* Clamp bpp to 8 on screens without EDID 1.4 */
+ if (connector->base.display_info.bpc == 0 && bpp > 24) {
+ DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n",
+ bpp);
+ pipe_config->pipe_bpp = 24;
}
}
struct intel_fbdev *ifbdev = dev_priv->fbdev;
struct fb_info *info;
- if (!ifbdev)
+ if (!ifbdev || !ifbdev->fb)
return;
info = ifbdev->helper.fbdev;
void intel_fbdev_output_poll_changed(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
- if (dev_priv->fbdev)
- drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
+ struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
+
+ if (ifbdev && ifbdev->fb)
+ drm_fb_helper_hotplug_event(&ifbdev->helper);
}
void intel_fbdev_restore_mode(struct drm_device *dev)
{
- int ret;
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct intel_fbdev *ifbdev = dev_priv->fbdev;
- struct drm_fb_helper *fb_helper;
+ struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
if (!ifbdev)
return;
intel_fbdev_sync(ifbdev);
+ if (!ifbdev->fb)
+ return;
- fb_helper = &ifbdev->helper;
-
- ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
- if (ret) {
+ if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper)) {
DRM_DEBUG("failed to restore crtc mode\n");
} else {
- mutex_lock(&fb_helper->dev->struct_mutex);
+ mutex_lock(&dev->struct_mutex);
intel_fb_obj_invalidate(ifbdev->fb->obj, ORIGIN_GTT);
- mutex_unlock(&fb_helper->dev->struct_mutex);
+ mutex_unlock(&dev->struct_mutex);
}
}
else
gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
dev_priv->rps.last_adj = 0;
- I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
+ I915_WRITE(GEN6_PMINTRMSK,
+ gen6_sanitize_rps_pm_mask(dev_priv, ~0));
}
mutex_unlock(&dev_priv->rps.hw_lock);
if (ret)
goto out;
- ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, new_mem);
out:
ttm_bo_mem_put(bo, &tmp_mem);
return ret;
if (ret)
return ret;
- ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, &tmp_mem);
if (ret)
goto out;
if (unlikely(r)) {
goto out_cleanup;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem);
out_cleanup:
ttm_bo_mem_put(bo, &tmp_mem);
return r;
if (unlikely(r)) {
return r;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem);
if (unlikely(r)) {
goto out_cleanup;
}
/* Link drm_bridge to encoder */
bridge->encoder = encoder;
+ encoder->bridge = bridge;
ret = drm_bridge_attach(rcdu->ddev, bridge);
if (ret) {
if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
- ret = ttm_bo_move_ttm(bo, evict, no_wait_gpu, mem);
+ ret = ttm_bo_move_ttm(bo, evict, interruptible, no_wait_gpu,
+ mem);
else if (bdev->driver->move)
ret = bdev->driver->move(bo, evict, interruptible,
no_wait_gpu, mem);
}
int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
- bool evict,
+ bool evict, bool interruptible,
bool no_wait_gpu, struct ttm_mem_reg *new_mem)
{
struct ttm_tt *ttm = bo->ttm;
int ret;
if (old_mem->mem_type != TTM_PL_SYSTEM) {
+ ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+
+ if (unlikely(ret != 0)) {
+ if (ret != -ERESTARTSYS)
+ pr_err("Failed to expire sync object before unbinding TTM\n");
+ return ret;
+ }
+
ttm_tt_unbind(ttm);
ttm_bo_free_old_node(bo);
ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM,
OBJCOPYFLAGS_lkdtm_rodata_objcopy.o := \
--set-section-flags .text=alloc,readonly \
--rename-section .text=.rodata
-$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o
+targets += lkdtm_rodata.o lkdtm_rodata_objcopy.o
+$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o FORCE
$(call if_changed,objcopy)
*/
mutex_lock(&afu->contexts_lock);
idr_preload(GFP_KERNEL);
- i = idr_alloc(&ctx->afu->contexts_idr, ctx,
- ctx->afu->adapter->native->sl_ops->min_pe,
+ i = idr_alloc(&ctx->afu->contexts_idr, ctx, ctx->afu->adapter->min_pe,
ctx->afu->num_procs, GFP_NOWAIT);
idr_preload_end();
mutex_unlock(&afu->contexts_lock);
u64 (*timebase_read)(struct cxl *adapter);
int capi_mode;
bool needs_reset_before_disable;
- int min_pe;
};
struct cxl_native {
struct bin_attribute cxl_attr;
int adapter_num;
int user_irqs;
+ int min_pe;
u64 ps_size;
u16 psl_rev;
u16 base_image;
return fail_psl_irq(afu, &irq_info);
}
-void native_irq_wait(struct cxl_context *ctx)
+static void native_irq_wait(struct cxl_context *ctx)
{
u64 dsisr;
int timeout = 1000;
static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev)
{
- u64 psl_dsnctl;
+ u64 psl_dsnctl, psl_fircntl;
u64 chipid;
u64 capp_unit_id;
int rc;
cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
/* snoop write mask */
cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
- /* set fir_accum */
- cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL);
+ /* set fir_cntl to recommended value for production env */
+ psl_fircntl = (0x2ULL << (63-3)); /* ce_report */
+ psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */
+ psl_fircntl |= 0x1ULL; /* ce_thresh */
+ cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl);
/* for debugging with trace arrays */
cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);
.write_timebase_ctrl = write_timebase_ctrl_xsl,
.timebase_read = timebase_read_xsl,
.capi_mode = OPAL_PHB_CAPI_MODE_DMA,
- .min_pe = 1, /* Workaround for Mellanox CX4 HW bug */
};
static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev)
{
if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) {
+ /* Mellanox CX-4 */
dev_info(&adapter->dev, "Device uses an XSL\n");
adapter->native->sl_ops = &xsl_ops;
+ adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */
} else {
dev_info(&adapter->dev, "Device uses a PSL\n");
adapter->native->sl_ops = &psl_ops;
/* Setup the PHB using arch provided callback */
phb->ops = &cxl_pcie_pci_ops;
phb->cfg_addr = NULL;
- phb->cfg_data = 0;
+ phb->cfg_data = NULL;
phb->private_data = afu;
phb->controller_ops = cxl_pci_controller_ops;
/* This is a pointer to outside our current stack frame. */
if (bad_frame) {
- bad_stack = do_usercopy_stack_callee((uintptr_t)bad_stack);
+ bad_stack = do_usercopy_stack_callee((uintptr_t)&bad_stack);
} else {
/* Put start address just inside stack. */
bad_stack = task_stack_page(current) + THREAD_SIZE;
}
}
set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
+ btt->nd_btt->size = btt->nlba * (u64)btt->sector_size;
revalidate_disk(btt->btt_disk);
return 0;
}
static DEVICE_ATTR_RW(namespace);
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ if (dev->driver)
+ rc = sprintf(buf, "%llu\n", nd_btt->size);
+ else {
+ /* no size to convey if the btt instance is disabled */
+ rc = -ENXIO;
+ }
+ device_unlock(dev);
+
+ return rc;
+}
+static DEVICE_ATTR_RO(size);
+
static struct attribute *nd_btt_attributes[] = {
&dev_attr_sector_size.attr,
&dev_attr_namespace.attr,
&dev_attr_uuid.attr,
+ &dev_attr_size.attr,
NULL,
};
struct nd_namespace_common *ndns;
struct btt *btt;
unsigned long lbasize;
+ u64 size;
u8 *uuid;
int id;
};
reinit_completion(&dev->ioq_wait);
retry:
timeout = ADMIN_TIMEOUT;
- for (; i > 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
-
- if (!pass)
- nvme_suspend_queue(nvmeq);
- if (nvme_delete_queue(nvmeq, opcode))
+ for (; i > 0; i--, sent++)
+ if (nvme_delete_queue(dev->queues[i], opcode))
break;
- ++sent;
- }
+
while (sent--) {
timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout);
if (timeout == 0)
nvme_stop_queues(&dev->ctrl);
csts = readl(dev->bar + NVME_REG_CSTS);
}
+
+ for (i = dev->queue_count - 1; i > 0; i--)
+ nvme_suspend_queue(dev->queues[i]);
+
if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- for (i = dev->queue_count - 1; i >= 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- nvme_suspend_queue(nvmeq);
- }
+ nvme_suspend_queue(dev->queues[0]);
} else {
nvme_disable_io_queues(dev);
nvme_disable_admin_queue(dev, shutdown);
* more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/delay.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/string.h>
-#include <linux/jiffies.h>
#include <linux/atomic.h>
#include <linux/blk-mq.h>
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/nvme.h>
-#include <linux/t10-pi.h>
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event);
static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
-static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl);
/* XXX: really should move to a generic header sooner or later.. */
static inline void put_unaligned_le24(u32 val, u8 *p)
list_del(&ctrl->list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
- if (ctrl->ctrl.tagset) {
- blk_cleanup_queue(ctrl->ctrl.connect_q);
- blk_mq_free_tag_set(&ctrl->tag_set);
- nvme_rdma_dev_put(ctrl->device);
- }
kfree(ctrl->queues);
nvmf_free_options(nctrl->opts);
free_ctrl:
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
- if (ctrl->queue_count > 1)
+ if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
+ nvme_queue_scan(&ctrl->ctrl);
+ nvme_queue_async_events(&ctrl->ctrl);
+ }
dev_info(ctrl->ctrl.device, "Successfully reconnected\n");
{
struct nvme_rdma_ctrl *ctrl = queue->ctrl;
struct rdma_conn_param param = { };
- struct nvme_rdma_cm_req priv;
+ struct nvme_rdma_cm_req priv = { };
int ret;
param.qp_num = queue->qp->qp_num;
* that caught the event. Since we hold the callout until the controller
* deletion is completed, we'll deadlock if the controller deletion will
* call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
- * of destroying this queue before-hand, destroy the queue resources
- * after the controller deletion completed with the exception of destroying
- * the cm_id implicitely by returning a non-zero rc to the callout.
+ * of destroying this queue before-hand, destroy the queue resources,
+ * then queue the controller deletion which won't destroy this queue and
+ * we destroy the cm_id implicitely by returning a non-zero rc to the callout.
*/
static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
{
struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- int ret, ctrl_deleted = 0;
+ int ret;
- /* First disable the queue so ctrl delete won't free it */
- if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
- goto out;
+ /* Own the controller deletion */
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
+ return 0;
- /* delete the controller */
- ret = __nvme_rdma_del_ctrl(ctrl);
- if (!ret) {
- dev_warn(ctrl->ctrl.device,
- "Got rdma device removal event, deleting ctrl\n");
- flush_work(&ctrl->delete_work);
+ dev_warn(ctrl->ctrl.device,
+ "Got rdma device removal event, deleting ctrl\n");
- /* Return non-zero so the cm_id will destroy implicitly */
- ctrl_deleted = 1;
+ /* Get rid of reconnect work if its running */
+ cancel_delayed_work_sync(&ctrl->reconnect_work);
+ /* Disable the queue so ctrl delete won't free it */
+ if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) {
/* Free this queue ourselves */
- rdma_disconnect(queue->cm_id);
- ib_drain_qp(queue->qp);
+ nvme_rdma_stop_queue(queue);
nvme_rdma_destroy_queue_ib(queue);
+
+ /* Return non-zero so the cm_id will destroy implicitly */
+ ret = 1;
}
-out:
- return ctrl_deleted;
+ /* Queue controller deletion */
+ queue_work(nvme_rdma_wq, &ctrl->delete_work);
+ flush_work(&ctrl->delete_work);
+ return ret;
}
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
nvme_rdma_free_io_queues(ctrl);
}
- if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+ if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags))
nvme_shutdown_ctrl(&ctrl->ctrl);
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
nvme_rdma_destroy_admin_queue(ctrl);
}
+static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
+{
+ nvme_uninit_ctrl(&ctrl->ctrl);
+ if (shutdown)
+ nvme_rdma_shutdown_ctrl(ctrl);
+
+ if (ctrl->ctrl.tagset) {
+ blk_cleanup_queue(ctrl->ctrl.connect_q);
+ blk_mq_free_tag_set(&ctrl->tag_set);
+ nvme_rdma_dev_put(ctrl->device);
+ }
+
+ nvme_put_ctrl(&ctrl->ctrl);
+}
+
static void nvme_rdma_del_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_rdma_shutdown_ctrl(ctrl);
- nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
+ __nvme_rdma_remove_ctrl(ctrl, true);
}
static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl)
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
+ __nvme_rdma_remove_ctrl(ctrl, false);
}
static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
nvme_queue_scan(&ctrl->ctrl);
+ nvme_queue_async_events(&ctrl->ctrl);
}
return;
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
-#include <linux/random.h>
#include <generated/utsrelease.h>
#include "nvmet.h"
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
- u64 serial;
u16 status = 0;
id = kzalloc(sizeof(*id), GFP_KERNEL);
id->vid = 0;
id->ssvid = 0;
- /* generate a random serial number as our controllers are ephemeral: */
- get_random_bytes(&serial, sizeof(serial));
memset(id->sn, ' ', sizeof(id->sn));
- snprintf(id->sn, sizeof(id->sn), "%llx", serial);
+ snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial);
memset(id->mn, ' ', sizeof(id->mn));
strncpy((char *)id->mn, "Linux", sizeof(id->mn));
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
+#include <linux/random.h>
#include "nvmet.h"
static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
+ /* generate a random serial number as our controllers are ephemeral: */
+ get_random_bytes(&ctrl->serial, sizeof(ctrl->serial));
+
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
struct nvme_loop_ctrl *ctrl = container_of(work,
struct nvme_loop_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_loop_shutdown_ctrl(ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
+ nvme_loop_shutdown_ctrl(ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
nvme_loop_destroy_admin_queue(ctrl);
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
- nvme_remove_namespaces(&ctrl->ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
struct mutex lock;
u64 cap;
+ u64 serial;
u32 cc;
u32 csts;
NVMET_RDMA_Q_CONNECTING,
NVMET_RDMA_Q_LIVE,
NVMET_RDMA_Q_DISCONNECTING,
+ NVMET_RDMA_IN_DEVICE_REMOVAL,
};
struct nvmet_rdma_queue {
if (!len)
return 0;
- /* use the already allocated data buffer if possible */
- if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) {
- nvmet_rdma_use_inline_sg(rsp, len, 0);
- } else {
- status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
- len);
- if (status)
- return status;
- }
+ status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
+ len);
+ if (status)
+ return status;
ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
struct nvmet_rdma_device *dev = queue->dev;
nvmet_rdma_free_queue(queue);
- rdma_destroy_id(cm_id);
+
+ if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL)
+ rdma_destroy_id(cm_id);
+
kref_put(&dev->ref, nvmet_rdma_free_dev);
}
switch (queue->state) {
case NVMET_RDMA_Q_CONNECTING:
case NVMET_RDMA_Q_LIVE:
- disconnect = true;
queue->state = NVMET_RDMA_Q_DISCONNECTING;
+ case NVMET_RDMA_IN_DEVICE_REMOVAL:
+ disconnect = true;
break;
case NVMET_RDMA_Q_DISCONNECTING:
break;
schedule_work(&queue->release_work);
}
+/**
+ * nvme_rdma_device_removal() - Handle RDMA device removal
+ * @queue: nvmet rdma queue (cm id qp_context)
+ * @addr: nvmet address (cm_id context)
+ *
+ * DEVICE_REMOVAL event notifies us that the RDMA device is about
+ * to unplug so we should take care of destroying our RDMA resources.
+ * This event will be generated for each allocated cm_id.
+ *
+ * Note that this event can be generated on a normal queue cm_id
+ * and/or a device bound listener cm_id (where in this case
+ * queue will be null).
+ *
+ * we claim ownership on destroying the cm_id. For queues we move
+ * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port
+ * we nullify the priv to prevent double cm_id destruction and destroying
+ * the cm_id implicitely by returning a non-zero rc to the callout.
+ */
+static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id,
+ struct nvmet_rdma_queue *queue)
+{
+ unsigned long flags;
+
+ if (!queue) {
+ struct nvmet_port *port = cm_id->context;
+
+ /*
+ * This is a listener cm_id. Make sure that
+ * future remove_port won't invoke a double
+ * cm_id destroy. use atomic xchg to make sure
+ * we don't compete with remove_port.
+ */
+ if (xchg(&port->priv, NULL) != cm_id)
+ return 0;
+ } else {
+ /*
+ * This is a queue cm_id. Make sure that
+ * release queue will not destroy the cm_id
+ * and schedule all ctrl queues removal (only
+ * if the queue is not disconnecting already).
+ */
+ spin_lock_irqsave(&queue->state_lock, flags);
+ if (queue->state != NVMET_RDMA_Q_DISCONNECTING)
+ queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL;
+ spin_unlock_irqrestore(&queue->state_lock, flags);
+ nvmet_rdma_queue_disconnect(queue);
+ flush_scheduled_work();
+ }
+
+ /*
+ * We need to return 1 so that the core will destroy
+ * it's own ID. What a great API design..
+ */
+ return 1;
+}
+
static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
break;
case RDMA_CM_EVENT_ADDR_CHANGE:
case RDMA_CM_EVENT_DISCONNECTED:
- case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_TIMEWAIT_EXIT:
- /*
- * We can get the device removal callback even for a
- * CM ID that we aren't actually using. In that case
- * the context pointer is NULL, so we shouldn't try
- * to disconnect a non-existing queue. But we also
- * need to return 1 so that the core will destroy
- * it's own ID. What a great API design..
- */
- if (queue)
- nvmet_rdma_queue_disconnect(queue);
- else
- ret = 1;
+ nvmet_rdma_queue_disconnect(queue);
+ break;
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ ret = nvmet_rdma_device_removal(cm_id, queue);
break;
case RDMA_CM_EVENT_REJECTED:
case RDMA_CM_EVENT_UNREACHABLE:
static void nvmet_rdma_remove_port(struct nvmet_port *port)
{
- struct rdma_cm_id *cm_id = port->priv;
+ struct rdma_cm_id *cm_id = xchg(&port->priv, NULL);
- rdma_destroy_id(cm_id);
+ if (cm_id)
+ rdma_destroy_id(cm_id);
}
static struct nvmet_fabrics_ops nvmet_rdma_ops = {
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
pci_msi_domain_update_chip_ops(info);
+ info->flags |= MSI_FLAG_ACTIVATE_EARLY;
+
domain = msi_create_irq_domain(fwnode, info, parent);
if (!domain)
return NULL;
return 0;
}
-static DEFINE_MUTEX(arm_pmu_mutex);
+static DEFINE_SPINLOCK(arm_pmu_lock);
static LIST_HEAD(arm_pmu_list);
/*
{
struct arm_pmu *pmu;
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_for_each_entry(pmu, &arm_pmu_list, entry) {
if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
if (pmu->reset)
pmu->reset(pmu);
}
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
return 0;
}
if (!cpu_hw_events)
return -ENOMEM;
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_add_tail(&cpu_pmu->entry, &arm_pmu_list);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
err = cpu_pm_pmu_register(cpu_pmu);
if (err)
return 0;
out_unregister:
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_del(&cpu_pmu->entry);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
free_percpu(cpu_hw_events);
return err;
}
static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
{
cpu_pm_pmu_unregister(cpu_pmu);
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_del(&cpu_pmu->entry);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
free_percpu(cpu_pmu->hw_events);
}
/* If we didn't manage to parse anything, try the interrupt affinity */
if (cpumask_weight(&pmu->supported_cpus) == 0) {
- if (!using_spi) {
+ int irq = platform_get_irq(pdev, 0);
+
+ if (irq_is_percpu(irq)) {
/* If using PPIs, check the affinity of the partition */
- int ret, irq;
+ int ret;
- irq = platform_get_irq(pdev, 0);
ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus);
if (ret) {
kfree(irqs);
/* BIOS error detected */
{ KE_IGNORE, 0xe00d, { KEY_RESERVED } },
- /* Unknown, defined in ACPI DSDT */
- /* { KE_IGNORE, 0xe00e, { KEY_RESERVED } }, */
+ /* Battery was removed or inserted */
+ { KE_IGNORE, 0xe00e, { KEY_RESERVED } },
/* Wifi Catcher */
{ KE_KEY, 0xe011, { KEY_PROG2 } },
static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id,
long timeout)
{
- struct rio_channel *ch = NULL;
- struct rio_channel *new_ch = NULL;
+ struct rio_channel *ch;
+ struct rio_channel *new_ch;
struct conn_req *req;
struct cm_peer *peer;
int found = 0;
spin_unlock_bh(&ch->lock);
riocm_put_channel(ch);
+ ch = NULL;
kfree(req);
down_read(&rdev_sem);
if (!found) {
/* If peer device object not found, simply ignore the request */
err = -ENODEV;
- goto err_nodev;
+ goto err_put_new_ch;
}
new_ch->rdev = peer->rdev;
*new_ch_id = new_ch->id;
return new_ch;
+
+err_put_new_ch:
+ spin_lock_bh(&idr_lock);
+ idr_remove(&ch_idr, new_ch->id);
+ spin_unlock_bh(&idr_lock);
+ riocm_put_channel(new_ch);
+
err_put:
- riocm_put_channel(ch);
-err_nodev:
- if (new_ch) {
- spin_lock_bh(&idr_lock);
- idr_remove(&ch_idr, new_ch->id);
- spin_unlock_bh(&idr_lock);
- riocm_put_channel(new_ch);
- }
+ if (ch)
+ riocm_put_channel(ch);
*new_ch_id = 0;
return ERR_PTR(err);
}
# it under the terms of the GNU General Public License (version 2 only)
# as published by the Free Software Foundation.
-obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o
+s390-virtio-objs := virtio_ccw.o
+ifdef CONFIG_S390_GUEST_OLD_TRANSPORT
+s390-virtio-objs += kvm_virtio.o
+endif
+obj-$(CONFIG_S390_GUEST) += $(s390-virtio-objs)
if (test_devices_support(total_memory_size) < 0)
return -ENODEV;
+ pr_warn("The s390-virtio transport is deprecated. Please switch to a modern host providing virtio-ccw.\n");
+
rc = vmem_add_mapping(total_memory_size, PAGE_SIZE);
if (rc)
return rc;
}
/* code for early console output with virtio_console */
-static __init int early_put_chars(u32 vtermno, const char *buf, int count)
+static int early_put_chars(u32 vtermno, const char *buf, int count)
{
char scratch[17];
unsigned int len = count;
__ipr_remove(pdev);
return rc;
}
+ spin_lock_irqsave(ioa_cfg->host->host_lock, flags);
+ ioa_cfg->scan_enabled = 1;
+ schedule_work(&ioa_cfg->work_q);
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags);
- scsi_scan_host(ioa_cfg->host);
ioa_cfg->iopoll_weight = ioa_cfg->chip_cfg->iopoll_weight;
if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
}
}
- spin_lock_irqsave(ioa_cfg->host->host_lock, flags);
- ioa_cfg->scan_enabled = 1;
- schedule_work(&ioa_cfg->work_q);
- spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags);
+ scsi_scan_host(ioa_cfg->host);
+
return 0;
}
}
static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
- uint32_t flags, void *data)
+ unsigned int count, uint32_t flags,
+ void *data)
{
- int32_t fd = *(int32_t *)data;
-
- if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
- return -EINVAL;
-
/* DATA_NONE/DATA_BOOL enables loopback testing */
if (flags & VFIO_IRQ_SET_DATA_NONE) {
- if (*ctx)
- eventfd_signal(*ctx, 1);
- return 0;
+ if (*ctx) {
+ if (count) {
+ eventfd_signal(*ctx, 1);
+ } else {
+ eventfd_ctx_put(*ctx);
+ *ctx = NULL;
+ }
+ return 0;
+ }
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
- uint8_t trigger = *(uint8_t *)data;
+ uint8_t trigger;
+
+ if (!count)
+ return -EINVAL;
+
+ trigger = *(uint8_t *)data;
if (trigger && *ctx)
eventfd_signal(*ctx, 1);
- return 0;
- }
- /* Handle SET_DATA_EVENTFD */
- if (fd == -1) {
- if (*ctx)
- eventfd_ctx_put(*ctx);
- *ctx = NULL;
return 0;
- } else if (fd >= 0) {
- struct eventfd_ctx *efdctx;
- efdctx = eventfd_ctx_fdget(fd);
- if (IS_ERR(efdctx))
- return PTR_ERR(efdctx);
- if (*ctx)
- eventfd_ctx_put(*ctx);
- *ctx = efdctx;
+ } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+ int32_t fd;
+
+ if (!count)
+ return -EINVAL;
+
+ fd = *(int32_t *)data;
+ if (fd == -1) {
+ if (*ctx)
+ eventfd_ctx_put(*ctx);
+ *ctx = NULL;
+ } else if (fd >= 0) {
+ struct eventfd_ctx *efdctx;
+
+ efdctx = eventfd_ctx_fdget(fd);
+ if (IS_ERR(efdctx))
+ return PTR_ERR(efdctx);
+
+ if (*ctx)
+ eventfd_ctx_put(*ctx);
+
+ *ctx = efdctx;
+ }
return 0;
- } else
- return -EINVAL;
+ }
+
+ return -EINVAL;
}
static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
- if (index != VFIO_PCI_ERR_IRQ_INDEX)
+ if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
- /*
- * We should sanitize start & count, but that wasn't caught
- * originally, so this IRQ index must forever ignore them :-(
- */
-
- return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data);
+ return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger,
+ count, flags, data);
}
static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
- if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1)
+ if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
- return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data);
+ return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger,
+ count, flags, data);
}
int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
vhost_disable_notify(&vsock->dev, vq);
for (;;) {
+ u32 len;
+
if (!vhost_vsock_more_replies(vsock)) {
/* Stop tx until the device processes already
* pending replies. Leave tx virtqueue
continue;
}
+ len = pkt->len;
+
/* Only accept correctly addressed packets */
if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
virtio_transport_recv_pkt(pkt);
else
virtio_transport_free_pkt(pkt);
- vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
+ vhost_add_used(vq, head, sizeof(pkt->hdr) + len);
added = true;
}
* host should service the ring ASAP. */
if (out_sgs)
vq->notify(&vq->vq);
+ if (indirect)
+ kfree(desc);
END_USE(vq);
return -ENOSPC;
}
if (indirect)
kfree(desc);
+ END_USE(vq);
return -EIO;
}
return 0;
}
-int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- u64 ref_root, u64 bytenr, u64 num_bytes)
-{
- struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_delayed_ref_head *ref_head;
- int ret = 0;
-
- if (!fs_info->quota_enabled || !is_fstree(ref_root))
- return 0;
-
- delayed_refs = &trans->transaction->delayed_refs;
-
- spin_lock(&delayed_refs->lock);
- ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0);
- if (!ref_head) {
- ret = -ENOENT;
- goto out;
- }
- WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root);
- ref_head->qgroup_ref_root = ref_root;
- ref_head->qgroup_reserved = num_bytes;
-out:
- spin_unlock(&delayed_refs->lock);
- return ret;
-}
-
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
u64 parent, u64 ref_root,
u64 owner, u64 offset, u64 reserved, int action,
struct btrfs_delayed_extent_op *extent_op);
-int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- u64 ref_root, u64 bytenr, u64 num_bytes);
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
*/
clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
+ /*
+ * An ordered extent might have started before and completed
+ * already with io errors, in which case the inode was not
+ * updated and we end up here. So check the inode's mapping
+ * flags for any errors that might have happened while doing
+ * writeback of file data.
+ */
+ ret = btrfs_inode_check_errors(inode);
inode_unlock(inode);
goto out;
}
found_key.offset = 0;
inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
ret = PTR_ERR_OR_ZERO(inode);
- if (ret && ret != -ESTALE)
+ if (ret && ret != -ENOENT)
goto out;
- if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ if (ret == -ENOENT && root == root->fs_info->tree_root) {
struct btrfs_root *dead_root;
struct btrfs_fs_info *fs_info = root->fs_info;
int is_dead_root = 0;
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
*/
- if (ret == -ESTALE) {
+ if (ret == -ENOENT) {
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
/*
* read an inode from the btree into the in-memory inode
*/
-static void btrfs_read_locked_inode(struct inode *inode)
+static int btrfs_read_locked_inode(struct inode *inode)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
filled = true;
path = btrfs_alloc_path();
- if (!path)
+ if (!path) {
+ ret = -ENOMEM;
goto make_bad;
+ }
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
- if (ret)
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
goto make_bad;
+ }
leaf = path->nodes[0];
}
btrfs_update_iflags(inode);
- return;
+ return 0;
make_bad:
btrfs_free_path(path);
make_bad_inode(inode);
+ return ret;
}
/*
int err = 0;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
+ u64 last_unlink_trans;
if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
return -ENOTEMPTY;
if (err)
goto out;
+ last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
+
/* now the directory is empty */
err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
dentry->d_name.name, dentry->d_name.len);
- if (!err)
+ if (!err) {
btrfs_i_size_write(inode, 0);
+ /*
+ * Propagate the last_unlink_trans value of the deleted dir to
+ * its parent directory. This is to prevent an unrecoverable
+ * log tree in the case we do something like this:
+ * 1) create dir foo
+ * 2) create snapshot under dir foo
+ * 3) delete the snapshot
+ * 4) rmdir foo
+ * 5) mkdir foo
+ * 6) fsync foo or some file inside foo
+ */
+ if (last_unlink_trans >= trans->transid)
+ BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
+ }
out:
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- btrfs_read_locked_inode(inode);
+ int ret;
+
+ ret = btrfs_read_locked_inode(inode);
if (!is_bad_inode(inode)) {
inode_tree_add(inode);
unlock_new_inode(inode);
} else {
unlock_new_inode(inode);
iput(inode);
- inode = ERR_PTR(-ESTALE);
+ ASSERT(ret < 0);
+ inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
}
}
u64 parent_ino;
u64 ino;
u64 gen;
- bool is_orphan;
struct list_head update_refs;
};
char name[];
};
+static void inconsistent_snapshot_error(struct send_ctx *sctx,
+ enum btrfs_compare_tree_result result,
+ const char *what)
+{
+ const char *result_string;
+
+ switch (result) {
+ case BTRFS_COMPARE_TREE_NEW:
+ result_string = "new";
+ break;
+ case BTRFS_COMPARE_TREE_DELETED:
+ result_string = "deleted";
+ break;
+ case BTRFS_COMPARE_TREE_CHANGED:
+ result_string = "updated";
+ break;
+ case BTRFS_COMPARE_TREE_SAME:
+ ASSERT(0);
+ result_string = "unchanged";
+ break;
+ default:
+ ASSERT(0);
+ result_string = "unexpected";
+ }
+
+ btrfs_err(sctx->send_root->fs_info,
+ "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu",
+ result_string, what, sctx->cmp_key->objectid,
+ sctx->send_root->root_key.objectid,
+ (sctx->parent_root ?
+ sctx->parent_root->root_key.objectid : 0));
+}
+
static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
static struct waiting_dir_move *
* was already unlinked/moved, so we can safely assume that we will not
* overwrite anything at this point in time.
*/
- if (other_inode > sctx->send_progress) {
+ if (other_inode > sctx->send_progress ||
+ is_waiting_for_move(sctx, other_inode)) {
ret = get_inode_info(sctx->parent_root, other_inode, NULL,
who_gen, NULL, NULL, NULL, NULL);
if (ret < 0)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0);
+ if (ret > 0)
+ ret = -ENOENT;
if (ret < 0)
goto out;
}
if (loc.objectid > send_progress) {
+ struct orphan_dir_info *odi;
+
+ odi = get_orphan_dir_info(sctx, dir);
+ free_orphan_dir_info(sctx, odi);
ret = 0;
goto out;
}
pm->parent_ino = parent_ino;
pm->ino = ino;
pm->gen = ino_gen;
- pm->is_orphan = is_orphan;
INIT_LIST_HEAD(&pm->list);
INIT_LIST_HEAD(&pm->update_refs);
RB_CLEAR_NODE(&pm->node);
return NULL;
}
+static int path_loop(struct send_ctx *sctx, struct fs_path *name,
+ u64 ino, u64 gen, u64 *ancestor_ino)
+{
+ int ret = 0;
+ u64 parent_inode = 0;
+ u64 parent_gen = 0;
+ u64 start_ino = ino;
+
+ *ancestor_ino = 0;
+ while (ino != BTRFS_FIRST_FREE_OBJECTID) {
+ fs_path_reset(name);
+
+ if (is_waiting_for_rm(sctx, ino))
+ break;
+ if (is_waiting_for_move(sctx, ino)) {
+ if (*ancestor_ino == 0)
+ *ancestor_ino = ino;
+ ret = get_first_ref(sctx->parent_root, ino,
+ &parent_inode, &parent_gen, name);
+ } else {
+ ret = __get_cur_name_and_parent(sctx, ino, gen,
+ &parent_inode,
+ &parent_gen, name);
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ }
+ if (ret < 0)
+ break;
+ if (parent_inode == start_ino) {
+ ret = 1;
+ if (*ancestor_ino == 0)
+ *ancestor_ino = ino;
+ break;
+ }
+ ino = parent_inode;
+ gen = parent_gen;
+ }
+ return ret;
+}
+
static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
{
struct fs_path *from_path = NULL;
u64 parent_ino, parent_gen;
struct waiting_dir_move *dm = NULL;
u64 rmdir_ino = 0;
+ u64 ancestor;
+ bool is_orphan;
int ret;
name = fs_path_alloc();
dm = get_waiting_dir_move(sctx, pm->ino);
ASSERT(dm);
rmdir_ino = dm->rmdir_ino;
+ is_orphan = dm->orphanized;
free_waiting_dir_move(sctx, dm);
- if (pm->is_orphan) {
+ if (is_orphan) {
ret = gen_unique_name(sctx, pm->ino,
pm->gen, from_path);
} else {
goto out;
sctx->send_progress = sctx->cur_ino + 1;
+ ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor);
+ if (ret < 0)
+ goto out;
+ if (ret) {
+ LIST_HEAD(deleted_refs);
+ ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
+ ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
+ &pm->update_refs, &deleted_refs,
+ is_orphan);
+ if (ret < 0)
+ goto out;
+ if (rmdir_ino) {
+ dm = get_waiting_dir_move(sctx, pm->ino);
+ ASSERT(dm);
+ dm->rmdir_ino = rmdir_ino;
+ }
+ goto out;
+ }
fs_path_reset(name);
to_path = name;
name = NULL;
/* already deleted */
goto finish;
}
- ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino + 1);
+ ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino);
if (ret < 0)
goto out;
if (!ret)
* and old parent(s).
*/
list_for_each_entry(cur, &pm->update_refs, list) {
- if (cur->dir == rmdir_ino)
+ /*
+ * The parent inode might have been deleted in the send snapshot
+ */
+ ret = get_inode_info(sctx->send_root, cur->dir, NULL,
+ NULL, NULL, NULL, NULL, NULL);
+ if (ret == -ENOENT) {
+ ret = 0;
continue;
+ }
+ if (ret < 0)
+ goto out;
+
ret = send_utimes(sctx, cur->dir, cur->dir_gen);
if (ret < 0)
goto out;
u64 left_gen;
u64 right_gen;
int ret = 0;
+ struct waiting_dir_move *wdm;
if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
return 0;
goto out;
}
- if (is_waiting_for_move(sctx, di_key.objectid)) {
+ wdm = get_waiting_dir_move(sctx, di_key.objectid);
+ if (wdm && !wdm->orphanized) {
ret = add_pending_dir_move(sctx,
sctx->cur_ino,
sctx->cur_inode_gen,
ret = is_ancestor(sctx->parent_root,
sctx->cur_ino, sctx->cur_inode_gen,
ino, path_before);
- break;
+ if (ret)
+ break;
}
fs_path_reset(path_before);
goto out;
if (ret) {
struct name_cache_entry *nce;
+ struct waiting_dir_move *wdm;
ret = orphanize_inode(sctx, ow_inode, ow_gen,
cur->full_path);
if (ret < 0)
goto out;
+
+ /*
+ * If ow_inode has its rename operation delayed
+ * make sure that its orphanized name is used in
+ * the source path when performing its rename
+ * operation.
+ */
+ if (is_waiting_for_move(sctx, ow_inode)) {
+ wdm = get_waiting_dir_move(sctx,
+ ow_inode);
+ ASSERT(wdm);
+ wdm->orphanized = true;
+ }
+
/*
* Make sure we clear our orphanized inode's
* name from the name cache. This is because the
name_cache_delete(sctx, nce);
kfree(nce);
}
+
+ /*
+ * ow_inode might currently be an ancestor of
+ * cur_ino, therefore compute valid_path (the
+ * current path of cur_ino) again because it
+ * might contain the pre-orphanization name of
+ * ow_inode, which is no longer valid.
+ */
+ fs_path_reset(valid_path);
+ ret = get_cur_path(sctx, sctx->cur_ino,
+ sctx->cur_inode_gen, valid_path);
+ if (ret < 0)
+ goto out;
} else {
ret = send_unlink(sctx, cur->full_path);
if (ret < 0)
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "reference");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen &&
sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) {
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "xattr");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
if (result == BTRFS_COMPARE_TREE_NEW)
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "extent");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
if (result != BTRFS_COMPARE_TREE_DELETED)
static int btrfs_check_ref_name_override(struct extent_buffer *eb,
const int slot,
const struct btrfs_key *key,
- struct inode *inode)
+ struct inode *inode,
+ u64 *other_ino)
{
int ret;
struct btrfs_path *search_path;
search_path, parent,
name, this_name_len, 0);
if (di && !IS_ERR(di)) {
- ret = 1;
+ struct btrfs_key di_key;
+
+ btrfs_dir_item_key_to_cpu(search_path->nodes[0],
+ di, &di_key);
+ if (di_key.type == BTRFS_INODE_ITEM_KEY) {
+ ret = 1;
+ *other_ino = di_key.objectid;
+ } else {
+ ret = -EAGAIN;
+ }
goto out;
} else if (IS_ERR(di)) {
ret = PTR_ERR(di);
if ((min_key.type == BTRFS_INODE_REF_KEY ||
min_key.type == BTRFS_INODE_EXTREF_KEY) &&
BTRFS_I(inode)->generation == trans->transid) {
+ u64 other_ino = 0;
+
ret = btrfs_check_ref_name_override(path->nodes[0],
path->slots[0],
- &min_key, inode);
+ &min_key, inode,
+ &other_ino);
if (ret < 0) {
err = ret;
goto out_unlock;
} else if (ret > 0) {
- err = 1;
- btrfs_set_log_full_commit(root->fs_info, trans);
- goto out_unlock;
+ struct btrfs_key inode_key;
+ struct inode *other_inode;
+
+ if (ins_nr > 0) {
+ ins_nr++;
+ } else {
+ ins_nr = 1;
+ ins_start_slot = path->slots[0];
+ }
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, ins_start_slot,
+ ins_nr, inode_only,
+ logged_isize);
+ if (ret < 0) {
+ err = ret;
+ goto out_unlock;
+ }
+ ins_nr = 0;
+ btrfs_release_path(path);
+ inode_key.objectid = other_ino;
+ inode_key.type = BTRFS_INODE_ITEM_KEY;
+ inode_key.offset = 0;
+ other_inode = btrfs_iget(root->fs_info->sb,
+ &inode_key, root,
+ NULL);
+ /*
+ * If the other inode that had a conflicting dir
+ * entry was deleted in the current transaction,
+ * we don't need to do more work nor fallback to
+ * a transaction commit.
+ */
+ if (IS_ERR(other_inode) &&
+ PTR_ERR(other_inode) == -ENOENT) {
+ goto next_key;
+ } else if (IS_ERR(other_inode)) {
+ err = PTR_ERR(other_inode);
+ goto out_unlock;
+ }
+ /*
+ * We are safe logging the other inode without
+ * acquiring its i_mutex as long as we log with
+ * the LOG_INODE_EXISTS mode. We're safe against
+ * concurrent renames of the other inode as well
+ * because during a rename we pin the log and
+ * update the log with the new name before we
+ * unpin it.
+ */
+ err = btrfs_log_inode(trans, root, other_inode,
+ LOG_INODE_EXISTS,
+ 0, LLONG_MAX, ctx);
+ iput(other_inode);
+ if (err)
+ goto out_unlock;
+ else
+ goto next_key;
}
}
ins_nr = 0;
}
btrfs_release_path(path);
-
+next_key:
if (min_key.offset < (u64)-1) {
min_key.offset++;
} else if (min_key.type < max_key.type) {
if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
- if (IS_ROOT(parent))
+ if (IS_ROOT(parent)) {
+ inode = d_inode(parent);
+ if (btrfs_must_commit_transaction(trans, inode))
+ ret = 1;
break;
+ }
parent = dget_parent(parent);
dput(old_parent);
{
struct inode *inode = &ci->vfs_inode;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
- struct ceph_mds_session *session = *psession;
+ struct ceph_mds_session *session = NULL;
int mds;
+
dout("ceph_flush_snaps %p\n", inode);
+ if (psession)
+ session = *psession;
retry:
spin_lock(&ci->i_ceph_lock);
if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) {
} else {
path = NULL;
pathlen = 0;
+ pathbase = 0;
}
spin_lock(&ci->i_ceph_lock);
{
struct backing_dev_info *bdi;
+ /*
+ * If we are expecting writeback progress we must submit plugged IO.
+ */
+ if (blk_needs_flush_plug(current))
+ blk_schedule_flush_plug(current);
+
if (!nr_pages)
nr_pages = get_nr_dirty_pages();
case 0:
break;
case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
extern void nfs4_kill_renewd(struct nfs_client *);
extern void nfs4_renew_state(struct work_struct *);
+extern void nfs4_set_lease_period(struct nfs_client *clp,
+ unsigned long lease,
+ unsigned long lastrenewed);
+
/* nfs4state.c */
struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp);
err = _nfs4_do_fsinfo(server, fhandle, fsinfo);
trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err);
if (err == 0) {
- struct nfs_client *clp = server->nfs_client;
-
- spin_lock(&clp->cl_lock);
- clp->cl_lease_time = fsinfo->lease_time * HZ;
- clp->cl_last_renewal = now;
- spin_unlock(&clp->cl_lock);
+ nfs4_set_lease_period(server->nfs_client,
+ fsinfo->lease_time * HZ,
+ now);
break;
}
err = nfs4_handle_exception(server, err, &exception);
cancel_delayed_work_sync(&clp->cl_renewd);
}
+/**
+ * nfs4_set_lease_period - Sets the lease period on a nfs_client
+ *
+ * @clp: pointer to nfs_client
+ * @lease: new value for lease period
+ * @lastrenewed: time at which lease was last renewed
+ */
+void nfs4_set_lease_period(struct nfs_client *clp,
+ unsigned long lease,
+ unsigned long lastrenewed)
+{
+ spin_lock(&clp->cl_lock);
+ clp->cl_lease_time = lease;
+ clp->cl_last_renewal = lastrenewed;
+ spin_unlock(&clp->cl_lock);
+
+ /* Cap maximum reconnect timeout at 1/2 lease period */
+ rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1);
+}
+
/*
* Local variables:
* c-basic-offset: 8
{
int status;
struct nfs_fsinfo fsinfo;
+ unsigned long now;
if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
nfs4_schedule_state_renewal(clp);
return 0;
}
+ now = jiffies;
status = nfs4_proc_get_lease_time(clp, &fsinfo);
if (status == 0) {
- /* Update lease time and schedule renewal */
- spin_lock(&clp->cl_lock);
- clp->cl_lease_time = fsinfo.lease_time * HZ;
- clp->cl_last_renewal = jiffies;
- spin_unlock(&clp->cl_lock);
-
+ nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
nfs4_schedule_state_renewal(clp);
}
return nfs_ok;
}
+static __be32
+nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
+{
+ struct nfs4_ol_stateid *stp = openlockstateid(s);
+ __be32 ret;
+
+ mutex_lock(&stp->st_mutex);
+
+ ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
+ if (ret)
+ goto out;
+
+ ret = nfserr_locks_held;
+ if (check_for_locks(stp->st_stid.sc_file,
+ lockowner(stp->st_stateowner)))
+ goto out;
+
+ release_lock_stateid(stp);
+ ret = nfs_ok;
+
+out:
+ mutex_unlock(&stp->st_mutex);
+ nfs4_put_stid(s);
+ return ret;
+}
+
__be32
nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_free_stateid *free_stateid)
stateid_t *stateid = &free_stateid->fr_stateid;
struct nfs4_stid *s;
struct nfs4_delegation *dp;
- struct nfs4_ol_stateid *stp;
struct nfs4_client *cl = cstate->session->se_client;
__be32 ret = nfserr_bad_stateid;
ret = nfserr_locks_held;
break;
case NFS4_LOCK_STID:
- ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
- if (ret)
- break;
- stp = openlockstateid(s);
- ret = nfserr_locks_held;
- if (check_for_locks(stp->st_stid.sc_file,
- lockowner(stp->st_stateowner)))
- break;
- WARN_ON(!unhash_lock_stateid(stp));
+ atomic_inc(&s->sc_count);
spin_unlock(&cl->cl_lock);
- nfs4_put_stid(s);
- ret = nfs_ok;
+ ret = nfsd4_free_lock_stateid(stateid, s);
goto out;
case NFS4_REVOKED_DELEG_STID:
dp = delegstateid(s);
lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
struct nfs4_ol_stateid *ost,
struct nfsd4_lock *lock,
- struct nfs4_ol_stateid **lst, bool *new)
+ struct nfs4_ol_stateid **plst, bool *new)
{
__be32 status;
struct nfs4_file *fi = ost->st_stid.sc_file;
struct nfs4_client *cl = oo->oo_owner.so_client;
struct inode *inode = d_inode(cstate->current_fh.fh_dentry);
struct nfs4_lockowner *lo;
+ struct nfs4_ol_stateid *lst;
unsigned int strhashval;
+ bool hashed;
lo = find_lockowner_str(cl, &lock->lk_new_owner);
if (!lo) {
goto out;
}
- *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
- if (*lst == NULL) {
+retry:
+ lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
+ if (lst == NULL) {
status = nfserr_jukebox;
goto out;
}
+
+ mutex_lock(&lst->st_mutex);
+
+ /* See if it's still hashed to avoid race with FREE_STATEID */
+ spin_lock(&cl->cl_lock);
+ hashed = !list_empty(&lst->st_perfile);
+ spin_unlock(&cl->cl_lock);
+
+ if (!hashed) {
+ mutex_unlock(&lst->st_mutex);
+ nfs4_put_stid(&lst->st_stid);
+ goto retry;
+ }
status = nfs_ok;
+ *plst = lst;
out:
nfs4_put_stateowner(&lo->lo_owner);
return status;
goto out;
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new);
- if (status == nfs_ok)
- mutex_lock(&lock_stp->st_mutex);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
if (IS_ERR(dchild))
return nfserrno(host_err);
err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
- if (err) {
- dput(dchild);
+ /*
+ * We unconditionally drop our ref to dchild as fh_compose will have
+ * already grabbed its own ref for it.
+ */
+ dput(dchild);
+ if (err)
return err;
- }
return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type,
rdev, resfhp);
}
struct page *page = buf->page;
if (page_count(page) == 1) {
- if (memcg_kmem_enabled()) {
+ if (memcg_kmem_enabled())
memcg_kmem_uncharge(page, 0);
- __ClearPageKmemcg(page);
- }
__SetPageLocked(page);
return 0;
}
cached = 0;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
available = si_mem_available();
#include <asm-generic/qrwlock_types.h>
/*
- * Writer states & reader shift and bias
+ * Writer states & reader shift and bias.
+ *
+ * | +0 | +1 | +2 | +3 |
+ * ----+----+----+----+----+
+ * LE | 78 | 56 | 34 | 12 | 0x12345678
+ * ----+----+----+----+----+
+ * | wr | rd |
+ * +----+----+----+----+
+ *
+ * ----+----+----+----+----+
+ * BE | 12 | 34 | 56 | 78 | 0x12345678
+ * ----+----+----+----+----+
+ * | rd | wr |
+ * +----+----+----+----+
*/
#define _QW_WAITING 1 /* A writer is waiting */
#define _QW_LOCKED 0xff /* A writer holds the lock */
(void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
}
+/**
+ * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: the write byte address of a queue rwlock
+ */
+static inline u8 *__qrwlock_write_byte(struct qrwlock *lock)
+{
+ return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN);
+}
+
/**
* queued_write_unlock - release write lock of a queue rwlock
* @lock : Pointer to queue rwlock structure
*/
static inline void queued_write_unlock(struct qrwlock *lock)
{
- smp_store_release((u8 *)&lock->cnts, 0);
+ smp_store_release(__qrwlock_write_byte(lock), 0);
}
/*
*
* @bo: A pointer to a struct ttm_buffer_object.
* @evict: 1: This is an eviction. Don't try to pipeline.
+ * @interruptible: Sleep interruptible if waiting.
* @no_wait_gpu: Return immediately if the GPU is busy.
* @new_mem: struct ttm_mem_reg indicating where to move.
*
*/
extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
- bool evict, bool no_wait_gpu,
+ bool evict, bool interruptible, bool no_wait_gpu,
struct ttm_mem_reg *new_mem);
/**
"Attempted to advance past end of bvec iter\n");
while (bytes) {
- unsigned len = min(bytes, bvec_iter_len(bv, *iter));
+ unsigned iter_len = bvec_iter_len(bv, *iter);
+ unsigned len = min(bytes, iter_len);
bytes -= len;
iter->bi_size -= len;
/* create, destroy, and name are mandatory */
struct kvm_device_ops {
const char *name;
+
+ /*
+ * create is called holding kvm->lock and any operations not suitable
+ * to do while holding the lock should be deferred to init (see
+ * below).
+ */
int (*create)(struct kvm_device *dev, u32 type);
+ /*
+ * init is called after create if create is successful and is called
+ * outside of holding kvm->lock.
+ */
+ void (*init)(struct kvm_device *dev);
+
/*
* Destroy is responsible for freeing dev.
*
#ifdef CONFIG_CMA
# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
+# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
#else
# define is_migrate_cma(migratetype) false
+# define is_migrate_cma_page(_page) false
#endif
#define for_each_migratetype_order(order, type) \
MSI_FLAG_MULTI_PCI_MSI = (1 << 2),
/* Support PCI MSIX interrupts */
MSI_FLAG_PCI_MSIX = (1 << 3),
+ /* Needs early activate, required for PCI */
+ MSI_FLAG_ACTIVATE_EARLY = (1 << 4),
};
int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
u64 parent_gen;
u64 generation;
int pin_count;
+#ifdef CONFIG_CGROUP_PERF
int nr_cgroups; /* cgroup evts */
+#endif
void *task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
};
unsigned int hrtimer_active;
struct pmu *unique_pmu;
+#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
+#endif
};
struct perf_output_handle {
* and other debug macros are compiled out unless either DEBUG is defined
* or CONFIG_DYNAMIC_DEBUG is set.
*/
-
-#ifdef CONFIG_PRINTK
-
-asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...);
-
-#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__)
-
-#else
-
-#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-
-#endif
-
-#define pr_warning pr_warn
-
+#define pr_emerg(fmt, ...) \
+ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_alert(fmt, ...) \
+ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_crit(fmt, ...) \
+ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_err(fmt, ...) \
+ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warn pr_warning
+#define pr_notice(fmt, ...) \
+ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/*
* Like KERN_CONT, pr_cont() should only be used when continuing
* a line with no newline ('\n') enclosed. Otherwise it defaults
void kzfree(const void *);
size_t ksize(const void *);
+#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page);
+#else
+static inline const char *__check_heap_object(const void *ptr,
+ unsigned long n,
+ struct page *page)
+{
+ return NULL;
+}
+#endif
+
/*
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
* alignment larger than the alignment of a 64-bit integer.
struct rpc_xprt *,
void *),
void *data);
+void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
+ unsigned long timeo);
const char *rpc_proc_name(const struct rpc_task *task);
#endif /* __KERNEL__ */
struct work_struct task_cleanup;
struct timer_list timer;
unsigned long last_used,
- idle_timeout;
+ idle_timeout,
+ max_reconnect_timeout;
/*
* Send stuff
#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
+static inline int arch_within_stack_frames(const void * const stack,
+ const void * const stackend,
+ const void *obj, unsigned long len)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_HARDENED_USERCOPY
+extern void __check_object_size(const void *ptr, unsigned long n,
+ bool to_user);
+
+static inline void check_object_size(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ __check_object_size(ptr, n, to_user);
+}
+#else
+static inline void check_object_size(const void *ptr, unsigned long n,
+ bool to_user)
+{ }
+#endif /* CONFIG_HARDENED_USERCOPY */
+
#endif /* __KERNEL__ */
#endif /* _LINUX_THREAD_INFO_H */
#ifndef user_access_begin
#define user_access_begin() do { } while (0)
#define user_access_end() do { } while (0)
-#define unsafe_get_user(x, ptr) __get_user(x, ptr)
-#define unsafe_put_user(x, ptr) __put_user(x, ptr)
+#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
+#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
#endif
#endif /* __LINUX_UACCESS_H__ */
#ifdef CONFIG_NO_HZ_COMMON
#define TICK_DEP_NAMES \
- tick_dep_name(NONE) \
+ tick_dep_mask_name(NONE) \
tick_dep_name(POSIX_TIMER) \
tick_dep_name(PERF_EVENTS) \
tick_dep_name(SCHED) \
tick_dep_name_end(CLOCK_UNSTABLE)
#undef tick_dep_name
+#undef tick_dep_mask_name
#undef tick_dep_name_end
-#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
-#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+/* The MASK will convert to their bits and they need to be processed too */
+#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \
+ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \
+ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+/* NONE only has a mask defined for it */
+#define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
TICK_DEP_NAMES
#undef tick_dep_name
+#undef tick_dep_mask_name
#undef tick_dep_name_end
#define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
+#define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
#define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep }
#define show_tick_dep_name(val) \
*/
#ifndef _UAPI_LINUX_VIRTIO_VSOCK_H
-#define _UAPI_LINUX_VIRTIO_VOSCK_H
+#define _UAPI_LINUX_VIRTIO_VSOCK_H
#include <linux/types.h>
#include <linux/virtio_ids.h>
*
* Of course the contents will be ABI, but that's up the AFU driver.
*/
- size_t data_size;
- u8 data[];
+ __u32 data_size;
+ __u8 data[];
};
struct cxl_event {
config SLAB
bool "SLAB"
+ select HAVE_HARDENED_USERCOPY_ALLOCATOR
help
The regular slab allocator that is established and known to work
well in all environments. It organizes cache hot objects in
config SLUB
bool "SLUB (Unqueued Allocator)"
+ select HAVE_HARDENED_USERCOPY_ALLOCATOR
help
SLUB is a slab allocator that minimizes cache line usage
instead of managing queues of cached objects (SLAB approach).
}
}
}
+
+/*
+ * Update cpuctx->cgrp so that it is set when first cgroup event is added and
+ * cleared when last cgroup event is removed.
+ */
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+ struct perf_cpu_context *cpuctx;
+
+ if (!is_cgroup_event(event))
+ return;
+
+ if (add && ctx->nr_cgroups++)
+ return;
+ else if (!add && --ctx->nr_cgroups)
+ return;
+ /*
+ * Because cgroup events are always per-cpu events,
+ * this will always be called from the right CPU.
+ */
+ cpuctx = __get_cpu_context(ctx);
+ cpuctx->cgrp = add ? event->cgrp : NULL;
+}
+
#else /* !CONFIG_CGROUP_PERF */
static inline bool
struct perf_event_context *ctx)
{
}
+
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+}
+
#endif
/*
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
+
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
list_add_tail(&event->group_entry, list);
}
- if (is_cgroup_event(event))
- ctx->nr_cgroups++;
+ list_update_cgroup_event(event, ctx, true);
list_add_rcu(&event->event_entry, &ctx->event_list);
ctx->nr_events++;
static void
list_del_event(struct perf_event *event, struct perf_event_context *ctx)
{
- struct perf_cpu_context *cpuctx;
-
WARN_ON_ONCE(event->ctx != ctx);
lockdep_assert_held(&ctx->lock);
event->attach_state &= ~PERF_ATTACH_CONTEXT;
- if (is_cgroup_event(event)) {
- ctx->nr_cgroups--;
- /*
- * Because cgroup events are always per-cpu events, this will
- * always be called from the right CPU.
- */
- cpuctx = __get_cpu_context(ctx);
- /*
- * If there are no more cgroup events then clear cgrp to avoid
- * stale pointer in update_cgrp_time_from_cpuctx().
- */
- if (!ctx->nr_cgroups)
- cpuctx->cgrp = NULL;
- }
+ list_update_cgroup_event(event, ctx, false);
ctx->nr_events--;
if (event->attr.inherit_stat)
static inline int
event_filter_match(struct perf_event *event)
{
- return (event->cpu == -1 || event->cpu == smp_processor_id())
- && perf_cgroup_match(event) && pmu_filter_match(event);
+ return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+ perf_cgroup_match(event) && pmu_filter_match(event);
}
static void
* maintained, otherwise bogus information is return
* via read() for time_enabled, time_running:
*/
- if (event->state == PERF_EVENT_STATE_INACTIVE
- && !event_filter_match(event)) {
+ if (event->state == PERF_EVENT_STATE_INACTIVE &&
+ !event_filter_match(event)) {
delta = tstamp - event->tstamp_stopped;
event->tstamp_running += delta;
event->tstamp_stopped = tstamp;
lockdep_assert_held(&ctx->mutex);
- event->ctx = ctx;
if (event->cpu != -1)
event->cpu = cpu;
+ /*
+ * Ensures that if we can observe event->ctx, both the event and ctx
+ * will be 'complete'. See perf_iterate_sb_cpu().
+ */
+ smp_store_release(&event->ctx, ctx);
+
if (!task) {
cpu_function_call(cpu, __perf_install_in_context, event);
return;
struct perf_event *event;
list_for_each_entry_rcu(event, &pel->list, sb_list) {
+ /*
+ * Skip events that are not fully formed yet; ensure that
+ * if we observe event->ctx, both event and ctx will be
+ * complete enough. See perf_install_in_context().
+ */
+ if (!smp_load_acquire(&event->ctx))
+ continue;
+
if (event->state < PERF_EVENT_STATE_INACTIVE)
continue;
if (!event_filter_match(event))
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
-#define FLAGS_SHARED 0x01
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED 0x01
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED 0x00
+#endif
#define FLAGS_CLOCKRT 0x02
#define FLAGS_HAS_TIMEOUT 0x04
if (!key->both.ptr)
return;
+ /*
+ * On MMU less systems futexes are always "private" as there is no per
+ * process address space. We need the smp wmb nevertheless - yes,
+ * arch/blackfin has MMU less SMP ...
+ */
+ if (!IS_ENABLED(CONFIG_MMU)) {
+ smp_mb(); /* explicit smp_mb(); (B) */
+ return;
+ }
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
ihold(key->shared.inode); /* implies smp_mb(); (B) */
return;
}
+ if (!IS_ENABLED(CONFIG_MMU))
+ return;
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
iput(key->shared.inode);
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
+ /*
+ * This flag is set by the PCI layer as we need to activate
+ * the MSI entries before the PCI layer enables MSI in the
+ * card. Otherwise the card latches a random msi message.
+ */
+ if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+ struct irq_data *irq_data;
+
+ irq_data = irq_domain_get_irq_data(domain, desc->irq);
+ irq_domain_activate_irq(irq_data);
+ }
}
return 0;
goto gotlock;
}
}
- WRITE_ONCE(pn->state, vcpu_halted);
+ WRITE_ONCE(pn->state, vcpu_hashed);
qstat_inc(qstat_pv_wait_head, true);
qstat_inc(qstat_pv_wait_again, waitcnt);
pv_wait(&l->locked, _Q_SLOW_VAL);
*/
if ((counter == qstat_pv_latency_kick) ||
(counter == qstat_pv_latency_wake)) {
- stat = 0;
if (kicks)
stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
}
save_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
error = swsusp_arch_suspend();
+ /* Restore control flow magically appears here */
+ restore_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
printk(KERN_ERR "PM: Error %d creating hibernation image\n",
error);
- /* Restore control flow magically appears here */
- restore_processor_state();
if (!in_suspend)
events_check_enabled = false;
*/
#include <linux/percpu.h>
-typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
- va_list args);
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
-__printf(2, 0)
-int vprintk_default(int level, const char *fmt, va_list args);
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
#ifdef CONFIG_PRINTK_NMI
* via per-CPU variable.
*/
DECLARE_PER_CPU(printk_func_t, printk_func);
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return this_cpu_read(printk_func)(level, fmt, args);
+ return this_cpu_read(printk_func)(fmt, args);
}
extern atomic_t nmi_message_lost;
#else /* CONFIG_PRINTK_NMI */
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return vprintk_default(level, fmt, args);
+ return vprintk_default(fmt, args);
}
static inline int get_nmi_message_lost(void)
* one writer running. But the buffer might get flushed from another
* CPU, so we need to be careful.
*/
-static int vprintk_nmi(int level, const char *fmt, va_list args)
+static int vprintk_nmi(const char *fmt, va_list args)
{
struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
int add = 0;
if (!len)
smp_rmb();
- if (level != LOGLEVEL_DEFAULT) {
- add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
- KERN_SOH "%c", '0' + level);
- add += vsnprintf(s->buffer + len + add,
- sizeof(s->buffer) - len - add,
- fmt, args);
- } else {
- add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
- fmt, args);
- }
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
/*
* Do it once again if the buffer has been flushed in the meantime.
}
EXPORT_SYMBOL(printk_emit);
-#ifdef CONFIG_PRINTK
-#define define_pr_level(func, loglevel) \
-asmlinkage __visible void func(const char *fmt, ...) \
-{ \
- va_list args; \
- \
- va_start(args, fmt); \
- vprintk_default(loglevel, fmt, args); \
- va_end(args); \
-} \
-EXPORT_SYMBOL(func)
-
-define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
-define_pr_level(__pr_alert, LOGLEVEL_ALERT);
-define_pr_level(__pr_crit, LOGLEVEL_CRIT);
-define_pr_level(__pr_err, LOGLEVEL_ERR);
-define_pr_level(__pr_warn, LOGLEVEL_WARNING);
-define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
-define_pr_level(__pr_info, LOGLEVEL_INFO);
-#endif
-
-int vprintk_default(int level, const char *fmt, va_list args)
+int vprintk_default(const char *fmt, va_list args)
{
int r;
return r;
}
#endif
- r = vprintk_emit(0, level, NULL, 0, fmt, args);
+ r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
return r;
}
int r;
va_start(args, fmt);
- r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
+ r = vprintk_func(fmt, args);
va_end(args);
return r;
#include <linux/context_tracking.h>
#include <linux/compiler.h>
#include <linux/frame.h>
+#include <linux/prefetch.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
+/*
+ * The function fair_sched_class.update_curr accesses the struct curr
+ * and its field curr->exec_start; when called from task_sched_runtime(),
+ * we observe a high rate of cache misses in practice.
+ * Prefetching this data results in improved performance.
+ */
+static inline void prefetch_curr_exec_start(struct task_struct *p)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity *curr = (&p->se)->cfs_rq->curr;
+#else
+ struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
+#endif
+ prefetch(curr);
+ prefetch(&curr->exec_start);
+}
+
/*
* Return accounted runtime for the task.
* In case the task is currently running, return the runtime plus current's
* thread, breaking clock_gettime().
*/
if (task_current(rq, p) && task_on_rq_queued(p)) {
+ prefetch_curr_exec_start(p);
update_rq_clock(rq);
p->sched_class->update_curr(rq);
}
if (old_idx == IDX_INVALID) {
cp->size++;
- cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].dl = dl;
cp->elements[cp->size - 1].cpu = cpu;
cp->elements[cpu].idx = cp->size - 1;
cpudl_change_key(cp, cp->size - 1, dl);
*/
void account_idle_ticks(unsigned long ticks)
{
+ cputime_t cputime, steal;
if (sched_clock_irqtime) {
irqtime_account_idle_ticks(ticks);
return;
}
- account_idle_time(jiffies_to_cputime(ticks));
+ cputime = jiffies_to_cputime(ticks);
+ steal = steal_account_process_time(cputime);
+
+ if (steal >= cputime)
+ return;
+
+ cputime -= steal;
+ account_idle_time(cputime);
}
/*
*
* XXX figure out if select_task_rq_dl() deals with offline cpus.
*/
- if (unlikely(!rq->online))
+ if (unlikely(!rq->online)) {
+ lockdep_unpin_lock(&rq->lock, rf.cookie);
rq = dl_task_offline_migration(rq, p);
+ rf.cookie = lockdep_pin_lock(&rq->lock);
+ }
/*
* Queueing this task back might have overloaded rq, check if we need
pcfs_rq = tg->parent->cfs_rq[cpu];
cfs_rq->throttle_count = pcfs_rq->throttle_count;
- pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+ cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
+ bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
spin_lock(&base->lock);
nextevt = __next_timer_interrupt(base);
+ is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
base->next_expiry = nextevt;
/*
* We have a fresh next event. Check whether we can forward the base:
expires = basem;
base->is_idle = false;
} else {
- expires = basem + (nextevt - basej) * TICK_NSEC;
+ if (!is_max_delta)
+ expires = basem + (nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle:
*/
unsigned long c, data;
/* Fall back to byte-at-a-time if we get a page fault */
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res))))
- break;
+ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
+
*(unsigned long *)(dst+res) = c;
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
while (max) {
char c;
- if (unlikely(unsafe_get_user(c,src+res)))
- return -EFAULT;
+ unsafe_get_user(c,src+res, efault);
dst[res] = c;
if (!c)
return res;
* Nope: we hit the address space limit, and we still had more
* characters the caller would have wanted. That's an EFAULT.
*/
+efault:
return -EFAULT;
}
src -= align;
max += align;
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)src)))
- return 0;
+ unsafe_get_user(c, (unsigned long __user *)src, efault);
c |= aligned_byte_mask(align);
for (;;) {
if (unlikely(max <= sizeof(unsigned long)))
break;
max -= sizeof(unsigned long);
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res))))
- return 0;
+ unsafe_get_user(c, (unsigned long __user *)(src+res), efault);
}
res -= align;
* Nope: we hit the address space limit, and we still had more
* characters the caller would have wanted. That's 0.
*/
+efault:
return 0;
}
KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
+# Since __builtin_frame_address does work as used, disable the warning.
+CFLAGS_usercopy.o += $(call cc-disable-warning, frame-address)
+
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
+obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
list_del(&page->lru);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
+ h->max_huge_pages--;
update_and_free_page(h, page);
}
spin_unlock(&hugetlb_lock);
new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
QUARANTINE_FRACTION;
percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
- if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
- "Too little memory, disabling global KASAN quarantine.\n"))
- new_quarantine_size = 0;
- else
- new_quarantine_size -= percpu_quarantines;
+ new_quarantine_size = (new_quarantine_size < percpu_quarantines) ?
+ 0 : new_quarantine_size - percpu_quarantines;
WRITE_ONCE(quarantine_size, new_quarantine_size);
last = global_quarantine.head;
return 0;
memcg = get_mem_cgroup_from_mm(current->mm);
- if (!mem_cgroup_is_root(memcg))
+ if (!mem_cgroup_is_root(memcg)) {
ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ if (!ret)
+ __SetPageKmemcg(page);
+ }
css_put(&memcg->css);
return ret;
}
page_counter_uncharge(&memcg->memsw, nr_pages);
page->mem_cgroup = NULL;
+
+ /* slab pages do not have PageKmemcg flag set */
+ if (PageKmemcg(page))
+ __ClearPageKmemcg(page);
+
css_put_many(&memcg->css, nr_pages);
}
#endif /* !CONFIG_SLOB */
static DEFINE_IDR(mem_cgroup_idr);
-static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
{
- atomic_inc(&memcg->id.ref);
+ atomic_add(n, &memcg->id.ref);
}
-static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
{
- if (atomic_dec_and_test(&memcg->id.ref)) {
+ while (!atomic_inc_not_zero(&memcg->id.ref)) {
+ /*
+ * The root cgroup cannot be destroyed, so it's refcount must
+ * always be >= 1.
+ */
+ if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ VM_BUG_ON(1);
+ break;
+ }
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ }
+ return memcg;
+}
+
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
+{
+ if (atomic_sub_and_test(n, &memcg->id.ref)) {
idr_remove(&mem_cgroup_idr, memcg->id.id);
memcg->id.id = 0;
}
}
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_put_many(memcg, 1);
+}
+
/**
* mem_cgroup_from_id - look up a memcg from a memcg id
* @id: the memcg id to look up
if (!mem_cgroup_is_root(mc.from))
page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
+ mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
/*
* we charged both to->memory and to->memsw, so we
* should uncharge to->memory.
if (!mem_cgroup_is_root(mc.to))
page_counter_uncharge(&mc.to->memory, mc.moved_swap);
- css_put_many(&mc.from->css, mc.moved_swap);
+ mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+ css_put_many(&mc.to->css, mc.moved_swap);
- /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);
else
nr_file += nr_pages;
pgpgout++;
- } else
+ } else {
nr_kmem += 1 << compound_order(page);
+ __ClearPageKmemcg(page);
+ }
page->mem_cgroup = NULL;
} while (next != page_list);
*/
void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *swap_memcg;
unsigned short oldid;
VM_BUG_ON_PAGE(PageLRU(page), page);
if (!memcg)
return;
- mem_cgroup_id_get(memcg);
- oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+ /*
+ * In case the memcg owning these pages has been offlined and doesn't
+ * have an ID allocated to it anymore, charge the closest online
+ * ancestor for the swap instead and transfer the memory+swap charge.
+ */
+ swap_memcg = mem_cgroup_id_get_online(memcg);
+ oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(memcg, true);
+ mem_cgroup_swap_statistics(swap_memcg, true);
page->mem_cgroup = NULL;
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, 1);
+ if (memcg != swap_memcg) {
+ if (!mem_cgroup_is_root(swap_memcg))
+ page_counter_charge(&swap_memcg->memsw, 1);
+ page_counter_uncharge(&memcg->memsw, 1);
+ }
+
/*
* Interrupts should be disabled here because the caller holds the
* mapping->tree_lock lock which is taken with interrupts-off. It is
if (!memcg)
return 0;
+ memcg = mem_cgroup_id_get_online(memcg);
+
if (!mem_cgroup_is_root(memcg) &&
- !page_counter_try_charge(&memcg->swap, 1, &counter))
+ !page_counter_try_charge(&memcg->swap, 1, &counter)) {
+ mem_cgroup_id_put(memcg);
return -ENOMEM;
+ }
- mem_cgroup_id_get(memcg);
oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
VM_BUG_ON_PAGE(oldid, page);
mem_cgroup_swap_statistics(memcg, true);
/* init node's zones as empty zones, we don't have any present pages.*/
free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+ pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
/*
* The node we allocated has no zone fallback lists. For avoiding
static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
arch_refresh_nodedata(nid, NULL);
+ free_percpu(pgdat->per_cpu_nodestats);
arch_free_nodedata(pgdat);
return;
}
{
struct mm_struct *mm = task->mm;
struct task_struct *p;
- bool ret;
+ bool ret = true;
/*
* Skip tasks without mm because it might have passed its exit_mm and
}
if (PageMappingFlags(page))
page->mapping = NULL;
- if (memcg_kmem_enabled() && PageKmemcg(page)) {
+ if (memcg_kmem_enabled() && PageKmemcg(page))
memcg_kmem_uncharge(page, order);
- __ClearPageKmemcg(page);
- }
if (check_free)
bad += free_pages_check(page);
if (bad)
}
out:
- if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
- if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
- __free_pages(page, order);
- page = NULL;
- } else
- __SetPageKmemcg(page);
+ if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
+ unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ __free_pages(page, order);
+ page = NULL;
}
if (kmemcheck_enabled && page)
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
}
#endif
+static void setup_min_unmapped_ratio(void);
+static void setup_min_slab_ratio(void);
#else /* CONFIG_NUMA */
static void set_zonelist_order(void)
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
- / 100;
- pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
+
+#ifdef CONFIG_NUMA
+ setup_min_unmapped_ratio();
+ setup_min_slab_ratio();
+#endif
+
return 0;
}
core_initcall(init_per_zone_wmark_min)
}
#ifdef CONFIG_NUMA
+static void setup_min_unmapped_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
+ for_each_online_pgdat(pgdat)
+ pgdat->min_unmapped_pages = 0;
+
+ for_each_zone(zone)
+ zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
+ sysctl_min_unmapped_ratio) / 100;
+}
+
+
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
+ setup_min_unmapped_ratio();
+
+ return 0;
+}
+
+static void setup_min_slab_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
for_each_online_pgdat(pgdat)
pgdat->min_slab_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
- sysctl_min_unmapped_ratio) / 100;
- return 0;
+ zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
+ sysctl_min_slab_ratio) / 100;
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
- for_each_online_pgdat(pgdat)
- pgdat->min_slab_pages = 0;
+ setup_min_slab_ratio();
- for_each_zone(zone)
- zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
- sysctl_min_slab_ratio) / 100;
return 0;
}
#endif
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
} else {
- if (PageTransCompound(page)) {
- VM_BUG_ON_PAGE(!PageLocked(page), page);
+ if (PageTransCompound(page) && page_mapping(page)) {
+ VM_WARN_ON_ONCE(!PageLocked(page));
+
SetPageDoubleMap(compound_head(page));
if (PageMlocked(page))
clear_page_mlock(compound_head(page));
{
int i, nr = 1;
- VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
+ VM_BUG_ON_PAGE(compound && !PageHead(page), page);
lock_page_memcg(page);
/* Hugepages are not counted in NR_FILE_MAPPED for now. */
struct kobj_attribute shmem_enabled_attr =
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
bool shmem_huge_enabled(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
return false;
}
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
#else /* !CONFIG_SHMEM */
module_init(slab_proc_init);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *cachep;
+ unsigned int objnr;
+ unsigned long offset;
+
+ /* Find and validate object. */
+ cachep = page->slab_cache;
+ objnr = obj_to_index(cachep, page, (void *)ptr);
+ BUG_ON(objnr >= cachep->num);
+
+ /* Find offset within object. */
+ offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= cachep->object_size && n <= cachep->object_size - offset)
+ return NULL;
+
+ return cachep->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
/**
* ksize - get the actual amount of memory allocated for a given object
* @objp: Pointer to the object
*/
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
+ LIST_HEAD(discard);
struct page *page, *h;
BUG_ON(irqs_disabled());
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
remove_partial(n, page);
- discard_slab(s, page);
+ list_add(&page->lru, &discard);
} else {
list_slab_objects(s, page,
"Objects remaining in %s on __kmem_cache_shutdown()");
}
}
spin_unlock_irq(&n->list_lock);
+
+ list_for_each_entry_safe(page, h, &discard, lru)
+ discard_slab(s, page);
}
/*
EXPORT_SYMBOL(__kmalloc_node);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *s;
+ unsigned long offset;
+ size_t object_size;
+
+ /* Find object and usable object size. */
+ s = page->slab_cache;
+ object_size = slab_ksize(s);
+
+ /* Reject impossible pointers. */
+ if (ptr < page_address(page))
+ return s->name;
+
+ /* Find offset within object. */
+ offset = (ptr - page_address(page)) % s->size;
+
+ /* Adjust for redzone and reject if within the redzone. */
+ if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) {
+ if (offset < s->red_left_pad)
+ return s->name;
+ offset -= s->red_left_pad;
+ }
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= object_size && n <= object_size - offset)
+ return NULL;
+
+ return s->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
static size_t __ksize(const void *object)
{
struct page *page;
--- /dev/null
+/*
+ * This implements the various checks for CONFIG_HARDENED_USERCOPY*,
+ * which are designed to protect kernel memory from needless exposure
+ * and overwrite under many unintended conditions. This code is based
+ * on PAX_USERCOPY, which is:
+ *
+ * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source
+ * Security Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/sections.h>
+
+enum {
+ BAD_STACK = -1,
+ NOT_STACK = 0,
+ GOOD_FRAME,
+ GOOD_STACK,
+};
+
+/*
+ * Checks if a given pointer and length is contained by the current
+ * stack frame (if possible).
+ *
+ * Returns:
+ * NOT_STACK: not at all on the stack
+ * GOOD_FRAME: fully within a valid stack frame
+ * GOOD_STACK: fully on the stack (when can't do frame-checking)
+ * BAD_STACK: error condition (invalid stack position or bad stack frame)
+ */
+static noinline int check_stack_object(const void *obj, unsigned long len)
+{
+ const void * const stack = task_stack_page(current);
+ const void * const stackend = stack + THREAD_SIZE;
+ int ret;
+
+ /* Object is not on the stack at all. */
+ if (obj + len <= stack || stackend <= obj)
+ return NOT_STACK;
+
+ /*
+ * Reject: object partially overlaps the stack (passing the
+ * the check above means at least one end is within the stack,
+ * so if this check fails, the other end is outside the stack).
+ */
+ if (obj < stack || stackend < obj + len)
+ return BAD_STACK;
+
+ /* Check if object is safely within a valid frame. */
+ ret = arch_within_stack_frames(stack, stackend, obj, len);
+ if (ret)
+ return ret;
+
+ return GOOD_STACK;
+}
+
+static void report_usercopy(const void *ptr, unsigned long len,
+ bool to_user, const char *type)
+{
+ pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n",
+ to_user ? "exposure" : "overwrite",
+ to_user ? "from" : "to", ptr, type ? : "unknown", len);
+ /*
+ * For greater effect, it would be nice to do do_group_exit(),
+ * but BUG() actually hooks all the lock-breaking and per-arch
+ * Oops code, so that is used here instead.
+ */
+ BUG();
+}
+
+/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */
+static bool overlaps(const void *ptr, unsigned long n, unsigned long low,
+ unsigned long high)
+{
+ unsigned long check_low = (uintptr_t)ptr;
+ unsigned long check_high = check_low + n;
+
+ /* Does not overlap if entirely above or entirely below. */
+ if (check_low >= high || check_high < low)
+ return false;
+
+ return true;
+}
+
+/* Is this address range in the kernel text area? */
+static inline const char *check_kernel_text_object(const void *ptr,
+ unsigned long n)
+{
+ unsigned long textlow = (unsigned long)_stext;
+ unsigned long texthigh = (unsigned long)_etext;
+ unsigned long textlow_linear, texthigh_linear;
+
+ if (overlaps(ptr, n, textlow, texthigh))
+ return "<kernel text>";
+
+ /*
+ * Some architectures have virtual memory mappings with a secondary
+ * mapping of the kernel text, i.e. there is more than one virtual
+ * kernel address that points to the kernel image. It is usually
+ * when there is a separate linear physical memory mapping, in that
+ * __pa() is not just the reverse of __va(). This can be detected
+ * and checked:
+ */
+ textlow_linear = (unsigned long)__va(__pa(textlow));
+ /* No different mapping: we're done. */
+ if (textlow_linear == textlow)
+ return NULL;
+
+ /* Check the secondary mapping... */
+ texthigh_linear = (unsigned long)__va(__pa(texthigh));
+ if (overlaps(ptr, n, textlow_linear, texthigh_linear))
+ return "<linear kernel text>";
+
+ return NULL;
+}
+
+static inline const char *check_bogus_address(const void *ptr, unsigned long n)
+{
+ /* Reject if object wraps past end of memory. */
+ if (ptr + n < ptr)
+ return "<wrapped address>";
+
+ /* Reject if NULL or ZERO-allocation. */
+ if (ZERO_OR_NULL_PTR(ptr))
+ return "<null>";
+
+ return NULL;
+}
+
+static inline const char *check_heap_object(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ struct page *page, *endpage;
+ const void *end = ptr + n - 1;
+ bool is_reserved, is_cma;
+
+ /*
+ * Some architectures (arm64) return true for virt_addr_valid() on
+ * vmalloced addresses. Work around this by checking for vmalloc
+ * first.
+ */
+ if (is_vmalloc_addr(ptr))
+ return NULL;
+
+ if (!virt_addr_valid(ptr))
+ return NULL;
+
+ page = virt_to_head_page(ptr);
+
+ /* Check slab allocator for flags and size. */
+ if (PageSlab(page))
+ return __check_heap_object(ptr, n, page);
+
+ /*
+ * Sometimes the kernel data regions are not marked Reserved (see
+ * check below). And sometimes [_sdata,_edata) does not cover
+ * rodata and/or bss, so check each range explicitly.
+ */
+
+ /* Allow reads of kernel rodata region (if not marked as Reserved). */
+ if (ptr >= (const void *)__start_rodata &&
+ end <= (const void *)__end_rodata) {
+ if (!to_user)
+ return "<rodata>";
+ return NULL;
+ }
+
+ /* Allow kernel data region (if not marked as Reserved). */
+ if (ptr >= (const void *)_sdata && end <= (const void *)_edata)
+ return NULL;
+
+ /* Allow kernel bss region (if not marked as Reserved). */
+ if (ptr >= (const void *)__bss_start &&
+ end <= (const void *)__bss_stop)
+ return NULL;
+
+ /* Is the object wholly within one base page? */
+ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) ==
+ ((unsigned long)end & (unsigned long)PAGE_MASK)))
+ return NULL;
+
+ /* Allow if start and end are inside the same compound page. */
+ endpage = virt_to_head_page(end);
+ if (likely(endpage == page))
+ return NULL;
+
+ /*
+ * Reject if range is entirely either Reserved (i.e. special or
+ * device memory), or CMA. Otherwise, reject since the object spans
+ * several independently allocated pages.
+ */
+ is_reserved = PageReserved(page);
+ is_cma = is_migrate_cma_page(page);
+ if (!is_reserved && !is_cma)
+ goto reject;
+
+ for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
+ page = virt_to_head_page(ptr);
+ if (is_reserved && !PageReserved(page))
+ goto reject;
+ if (is_cma && !is_migrate_cma_page(page))
+ goto reject;
+ }
+
+ return NULL;
+
+reject:
+ return "<spans multiple pages>";
+}
+
+/*
+ * Validates that the given object is:
+ * - not bogus address
+ * - known-safe heap or stack object
+ * - not in kernel text
+ */
+void __check_object_size(const void *ptr, unsigned long n, bool to_user)
+{
+ const char *err;
+
+ /* Skip all tests if size is zero. */
+ if (!n)
+ return;
+
+ /* Check for invalid addresses. */
+ err = check_bogus_address(ptr, n);
+ if (err)
+ goto report;
+
+ /* Check for bad heap object. */
+ err = check_heap_object(ptr, n, to_user);
+ if (err)
+ goto report;
+
+ /* Check for bad stack object. */
+ switch (check_stack_object(ptr, n)) {
+ case NOT_STACK:
+ /* Object is not touching the current process stack. */
+ break;
+ case GOOD_FRAME:
+ case GOOD_STACK:
+ /*
+ * Object is either in the correct frame (when it
+ * is possible to check) or just generally on the
+ * process stack (when frame checking not available).
+ */
+ return;
+ default:
+ err = "<process stack>";
+ goto report;
+ }
+
+ /* Check for object in kernel to avoid text exposure. */
+ err = check_kernel_text_object(ptr, n);
+ if (!err)
+ return;
+
+report:
+ report_usercopy(ptr, n, to_user, err);
+}
+EXPORT_SYMBOL(__check_object_size);
/* wakeup anybody waiting for slots to pin pages */
wake_up(&vp_wq);
}
- kfree(in_pages);
- kfree(out_pages);
+ kvfree(in_pages);
+ kvfree(out_pages);
return err;
}
put_generic_request(req);
}
-void cancel_generic_request(struct ceph_mon_generic_request *req)
+static void cancel_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
struct ceph_mon_generic_request *lookup_req;
pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
GFP_NOIO);
- if (!pages) {
+ if (IS_ERR(pages)) {
ceph_msg_put(m);
return NULL;
}
}
EXPORT_SYMBOL(ceph_find_or_create_string);
-static void ceph_free_string(struct rcu_head *head)
-{
- struct ceph_string *cs = container_of(head, struct ceph_string, rcu);
- kfree(cs);
-}
-
void ceph_release_string(struct kref *ref)
{
struct ceph_string *cs = container_of(ref, struct ceph_string, kref);
}
spin_unlock(&string_tree_lock);
- call_rcu(&cs->rcu, ceph_free_string);
+ kfree_rcu(cs, rcu);
}
EXPORT_SYMBOL(ceph_release_string);
}
static struct gss_upcall_msg *
-__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid)
+__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth)
{
struct gss_upcall_msg *pos;
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
+ if (auth && pos->auth->service != auth->service)
+ continue;
atomic_inc(&pos->count);
dprintk("RPC: %s found msg %p\n", __func__, pos);
return pos;
struct gss_upcall_msg *old;
spin_lock(&pipe->lock);
- old = __gss_find_upcall(pipe, gss_msg->uid);
+ old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth);
if (old == NULL) {
atomic_inc(&gss_msg->count);
list_add(&gss_msg->list, &pipe->in_downcall);
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid);
+ gss_msg = __gss_find_upcall(pipe, uid, NULL);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;
{
struct rpc_xprt_switch *xps;
struct rpc_xprt *xprt;
+ unsigned long reconnect_timeout;
unsigned char resvport;
int ret = 0;
return -EAGAIN;
}
resvport = xprt->resvport;
+ reconnect_timeout = xprt->max_reconnect_timeout;
rcu_read_unlock();
xprt = xprt_create_transport(xprtargs);
goto out_put_switch;
}
xprt->resvport = resvport;
+ xprt->max_reconnect_timeout = reconnect_timeout;
rpc_xprt_switch_set_roundrobin(xps);
if (setup) {
}
EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt);
+static int
+rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ void *data)
+{
+ unsigned long timeout = *((unsigned long *)data);
+
+ if (timeout < xprt->max_reconnect_timeout)
+ xprt->max_reconnect_timeout = timeout;
+ return 0;
+}
+
+void
+rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo)
+{
+ rpc_clnt_iterate_for_each_xprt(clnt,
+ rpc_xprt_cap_max_reconnect_timeout,
+ &timeo);
+}
+EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout);
+
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
static void rpc_show_header(void)
{
spin_unlock_bh(&xprt->transport_lock);
}
+static bool
+xprt_has_timer(const struct rpc_xprt *xprt)
+{
+ return xprt->idle_timeout != 0;
+}
+
+static void
+xprt_schedule_autodisconnect(struct rpc_xprt *xprt)
+ __must_hold(&xprt->transport_lock)
+{
+ if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
+ mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout);
+}
+
static void
xprt_init_autodisconnect(unsigned long data)
{
spin_lock(&xprt->transport_lock);
if (!list_empty(&xprt->recv))
goto out_abort;
+ /* Reset xprt->last_used to avoid connect/autodisconnect cycling */
+ xprt->last_used = jiffies;
if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
goto out_abort;
spin_unlock(&xprt->transport_lock);
goto out;
xprt->snd_task =NULL;
xprt->ops->release_xprt(xprt, NULL);
+ xprt_schedule_autodisconnect(xprt);
out:
spin_unlock_bh(&xprt->transport_lock);
wake_up_bit(&xprt->state, XPRT_LOCKED);
spin_unlock_bh(&xprt->transport_lock);
}
-static inline int xprt_has_timer(struct rpc_xprt *xprt)
-{
- return xprt->idle_timeout != 0;
-}
-
/**
* xprt_prepare_transmit - reserve the transport before sending a request
* @task: RPC task about to send a request
if (!list_empty(&req->rq_list))
list_del(&req->rq_list);
xprt->last_used = jiffies;
- if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
- mod_timer(&xprt->timer,
- xprt->last_used + xprt->idle_timeout);
+ xprt_schedule_autodisconnect(xprt);
spin_unlock_bh(&xprt->transport_lock);
if (req->rq_buffer)
xprt->ops->buf_free(req->rq_buffer);
* increase over time if the server is down or not responding.
*/
#define XS_TCP_INIT_REEST_TO (3U * HZ)
-#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ)
/*
* TCP idle timeout; client drops the transport socket if it is idle
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
+
+ xprt->stat.connect_start = jiffies;
}
static void xs_udp_setup_socket(struct work_struct *work)
unsigned int keepcnt = xprt->timeout->to_retries + 1;
unsigned int opt_on = 1;
unsigned int timeo;
+ unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC;
/* TCP Keepalive options */
kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
(char *)&keepcnt, sizeof(keepcnt));
+ /* Avoid temporary address, they are bad for long-lived
+ * connections such as NFS mounts.
+ * RFC4941, section 3.6 suggests that:
+ * Individual applications, which have specific
+ * knowledge about the normal duration of connections,
+ * MAY override this as appropriate.
+ */
+ kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES,
+ (char *)&addr_pref, sizeof(addr_pref));
+
/* TCP user timeout (see RFC5482) */
timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
(xprt->timeout->to_retries + 1);
/* SYN_SENT! */
if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+ break;
+ case -EADDRNOTAVAIL:
+ /* Source port number is unavailable. Try a new one! */
+ transport->srcport = 0;
}
out:
return ret;
xprt_wake_pending_tasks(xprt, status);
}
+static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt)
+{
+ unsigned long start, now = jiffies;
+
+ start = xprt->stat.connect_start + xprt->reestablish_timeout;
+ if (time_after(start, now))
+ return start - now;
+ return 0;
+}
+
+static void xs_reconnect_backoff(struct rpc_xprt *xprt)
+{
+ xprt->reestablish_timeout <<= 1;
+ if (xprt->reestablish_timeout > xprt->max_reconnect_timeout)
+ xprt->reestablish_timeout = xprt->max_reconnect_timeout;
+ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+ xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+}
+
/**
* xs_connect - connect a socket to a remote endpoint
* @xprt: pointer to transport structure
static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ unsigned long delay = 0;
WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport));
/* Start by resetting any existing state */
xs_reset_transport(transport);
- queue_delayed_work(xprtiod_workqueue,
- &transport->connect_worker,
- xprt->reestablish_timeout);
- xprt->reestablish_timeout <<= 1;
- if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
- xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
- if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO)
- xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
- } else {
+ delay = xs_reconnect_delay(xprt);
+ xs_reconnect_backoff(xprt);
+
+ } else
dprintk("RPC: xs_connect scheduled xprt %p\n", xprt);
- queue_delayed_work(xprtiod_workqueue,
- &transport->connect_worker, 0);
- }
+
+ queue_delayed_work(xprtiod_workqueue,
+ &transport->connect_worker,
+ delay);
}
/**
xprt->ops = &xs_tcp_ops;
xprt->timeout = &xs_tcp_default_timeout;
+ xprt->max_reconnect_timeout = xprt->timeout->to_maxval;
+
INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn);
INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket);
as-instr = $(call try-run,\
printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+# Do not attempt to build with gcc plugins during cc-option tests.
+# (And this uses delayed resolution so the flags will be up to date.)
+CC_OPTION_CFLAGS = $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS))
+
# cc-option
# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
cc-option = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
# cc-option-yn
# Usage: flag := $(call cc-option-yn,-march=winchip-c6)
cc-option-yn = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
# cc-option-align
# Prefix align with either -falign or -malign
# cc-disable-warning
# Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
cc-disable-warning = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
# cc-name
# Expands to either gcc or clang
endif
endif
- GCC_PLUGINS_CFLAGS := $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y))
+ GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y))
- export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN SANCOV_PLUGIN
+ export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR SANCOV_PLUGIN
+ ifneq ($(PLUGINCC),)
+ # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
+ GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS))
+ endif
+
+ KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
+ GCC_PLUGIN := $(gcc-plugin-y)
+ GCC_PLUGIN_SUBDIR := $(gcc-plugin-subdir-y)
+endif
+
+# If plugins aren't supported, abort the build before hard-to-read compiler
+# errors start getting spewed by the main build.
+PHONY += gcc-plugins-check
+gcc-plugins-check: FORCE
+ifdef CONFIG_GCC_PLUGINS
ifeq ($(PLUGINCC),)
ifneq ($(GCC_PLUGINS_CFLAGS),)
ifeq ($(call cc-ifversion, -ge, 0405, y), y)
- PLUGINCC := $(shell $(CONFIG_SHELL) -x $(srctree)/scripts/gcc-plugin.sh "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)")
- $(warning warning: your gcc installation does not support plugins, perhaps the necessary headers are missing?)
+ $(Q)$(srctree)/scripts/gcc-plugin.sh --show-error "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)" || true
+ @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc installation does not support plugins, perhaps the necessary headers are missing?" >&2 && exit 1
else
- $(warning warning: your gcc version does not support plugins, you should upgrade it to gcc 4.5 at least)
+ @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc version does not support plugins, you should upgrade it to at least gcc 4.5" >&2 && exit 1
endif
endif
- else
- # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
- GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS))
endif
+endif
+ @:
- KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
- GCC_PLUGIN := $(gcc-plugin-y)
-
+# Actually do the build, if requested.
+PHONY += gcc-plugins
+gcc-plugins: scripts_basic gcc-plugins-check
+ifdef CONFIG_GCC_PLUGINS
+ $(Q)$(MAKE) $(build)=scripts/gcc-plugins
endif
+ @:
#!/bin/sh
srctree=$(dirname "$0")
+
+SHOW_ERROR=
+if [ "$1" = "--show-error" ] ; then
+ SHOW_ERROR=1
+ shift || true
+fi
+
gccplugins_dir=$($3 -print-file-name=plugin)
plugincc=$($1 -E -x c++ - -o /dev/null -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF
#include "gcc-common.h"
if [ $? -ne 0 ]
then
+ if [ -n "$SHOW_ERROR" ] ; then
+ echo "${plugincc}" >&2
+ fi
exit 1
fi
echo "$2"
exit 0
fi
+
+if [ -n "$SHOW_ERROR" ] ; then
+ echo "${plugincc}" >&2
+fi
exit 1
export HOST_EXTRACXXFLAGS
endif
-export GCCPLUGINS_DIR HOSTLIBS
-
ifneq ($(CFLAGS_KCOV), $(SANCOV_PLUGIN))
GCC_PLUGIN := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGIN))
endif
-$(HOSTLIBS)-y := $(GCC_PLUGIN)
+export HOSTLIBS
+
+$(HOSTLIBS)-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p)))
always := $($(HOSTLIBS)-y)
-cyc_complexity_plugin-objs := cyc_complexity_plugin.o
-sancov_plugin-objs := sancov_plugin.o
+$(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o))
+
+subdir-y := $(GCC_PLUGIN_SUBDIR)
+subdir- += $(GCC_PLUGIN_SUBDIR)
clean-files += *.so
die "$P: file '${file}' not found\n";
}
}
- if ($from_filename || vcs_file_exists($file)) {
+ if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) {
$file =~ s/^\Q${cur_path}\E//; #strip any absolute path
$file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree
push(@files, $file);
this low address space will need the permission specific to the
systems running LSM.
+config HAVE_HARDENED_USERCOPY_ALLOCATOR
+ bool
+ help
+ The heap allocator implements __check_heap_object() for
+ validating memory ranges against heap object sizes in
+ support of CONFIG_HARDENED_USERCOPY.
+
+config HAVE_ARCH_HARDENED_USERCOPY
+ bool
+ help
+ The architecture supports CONFIG_HARDENED_USERCOPY by
+ calling check_object_size() just before performing the
+ userspace copies in the low level implementation of
+ copy_to_user() and copy_from_user().
+
+config HARDENED_USERCOPY
+ bool "Harden memory copies between kernel and userspace"
+ depends on HAVE_ARCH_HARDENED_USERCOPY
+ select BUG
+ help
+ This option checks for obviously wrong memory regions when
+ copying memory to/from the kernel (via copy_to_user() and
+ copy_from_user() functions) by rejecting memory ranges that
+ are larger than the specified heap object, span multiple
+ separately allocates pages, are not on the process stack,
+ or are part of the kernel text. This kills entire classes
+ of heap overflow exploits and similar kernel memory exposures.
+
source security/selinux/Kconfig
source security/smack/Kconfig
source security/tomoyo/Kconfig
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
struct hda_intel *hda;
+ struct hdac_bus *bus;
if (!card)
return 0;
chip = card->private_data;
hda = container_of(chip, struct hda_intel, chip);
+ bus = azx_bus(chip);
if (chip->disabled || hda->init_failed || !chip->running)
return 0;
- if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL
- && hda->need_i915_power) {
- snd_hdac_display_power(azx_bus(chip), true);
- snd_hdac_i915_set_bclk(azx_bus(chip));
+ if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+ snd_hdac_display_power(bus, true);
+ if (hda->need_i915_power)
+ snd_hdac_i915_set_bclk(bus);
}
+
if (chip->msi)
if (pci_enable_msi(pci) < 0)
chip->msi = 0;
hda_intel_init_chip(chip, true);
+ /* power down again for link-controlled chips */
+ if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+ !hda->need_i915_power)
+ snd_hdac_display_power(bus, false);
+
snd_power_change_state(card, SNDRV_CTL_POWER_D0);
trace_azx_resume(chip);
chip = card->private_data;
hda = container_of(chip, struct hda_intel, chip);
+ bus = azx_bus(chip);
if (chip->disabled || hda->init_failed)
return 0;
return 0;
if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
- bus = azx_bus(chip);
- if (hda->need_i915_power) {
- snd_hdac_display_power(bus, true);
+ snd_hdac_display_power(bus, true);
+ if (hda->need_i915_power)
snd_hdac_i915_set_bclk(bus);
- } else {
- /* toggle codec wakeup bit for STATESTS read */
- snd_hdac_set_codec_wakeup(bus, true);
- snd_hdac_set_codec_wakeup(bus, false);
- }
}
/* Read STATESTS before controller reset */
azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
~STATESTS_INT_MASK);
+ /* power down again for link-controlled chips */
+ if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+ !hda->need_i915_power)
+ snd_hdac_display_power(bus, false);
+
trace_azx_runtime_resume(chip);
return 0;
}
{
/* devices which do not support reading the sample rate. */
switch (chip->usb_id) {
+ case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */
case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */
case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */
case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
+ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */
case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
#ifdef CONFIG_X86_32
/*
* 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional
*/
#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
#endif
-
+#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#endif /* _ASM_X86_CPUFEATURES_H */
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
#define REQUIRED_MASK16 0
+#define REQUIRED_MASK17 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
#define EXIT_REASON_PML_FULL 62
#define EXIT_REASON_XSAVES 63
#define EXIT_REASON_XRSTORS 64
-#define EXIT_REASON_PCOMMIT 65
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
{ EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }, \
{ EXIT_REASON_XSAVES, "XSAVES" }, \
- { EXIT_REASON_XRSTORS, "XRSTORS" }, \
- { EXIT_REASON_PCOMMIT, "PCOMMIT" }
+ { EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
BPF_MAP_TYPE_PERCPU_HASH,
BPF_MAP_TYPE_PERCPU_ARRAY,
BPF_MAP_TYPE_STACK_TRACE,
+ BPF_MAP_TYPE_CGROUP_ARRAY,
};
enum bpf_prog_type {
BPF_PROG_TYPE_SCHED_CLS,
BPF_PROG_TYPE_SCHED_ACT,
BPF_PROG_TYPE_TRACEPOINT,
+ BPF_PROG_TYPE_XDP,
};
#define BPF_PSEUDO_MAP_FD 1
*/
BPF_FUNC_skb_get_tunnel_opt,
BPF_FUNC_skb_set_tunnel_opt,
+
+ /**
+ * bpf_skb_change_proto(skb, proto, flags)
+ * Change protocol of the skb. Currently supported is
+ * v4 -> v6, v6 -> v4 transitions. The helper will also
+ * resize the skb. eBPF program is expected to fill the
+ * new headers via skb_store_bytes and lX_csum_replace.
+ * @skb: pointer to skb
+ * @proto: new skb->protocol type
+ * @flags: reserved
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_proto,
+
+ /**
+ * bpf_skb_change_type(skb, type)
+ * Change packet type of skb.
+ * @skb: pointer to skb
+ * @type: new skb->pkt_type type
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_type,
+
+ /**
+ * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+ * @skb: pointer to skb
+ * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ * @index: index of the cgroup in the bpf_map
+ * Return:
+ * == 0 skb failed the cgroup2 descendant test
+ * == 1 skb succeeded the cgroup2 descendant test
+ * < 0 error
+ */
+ BPF_FUNC_skb_in_cgroup,
+
+ /**
+ * bpf_get_hash_recalc(skb)
+ * Retrieve and possibly recalculate skb->hash.
+ * @skb: pointer to skb
+ * Return: hash
+ */
+ BPF_FUNC_get_hash_recalc,
+
+ /**
+ * u64 bpf_get_current_task(void)
+ * Returns current task_struct
+ * Return: current
+ */
+ BPF_FUNC_get_current_task,
+
+ /**
+ * bpf_probe_write_user(void *dst, void *src, int len)
+ * safely attempt to write to a location
+ * @dst: destination address in userspace
+ * @src: source address on stack
+ * @len: number of bytes to copy
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_probe_write_user,
+
__BPF_FUNC_MAX_ID,
};
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
-/* BPF_FUNC_perf_event_output flags. */
+/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
#define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+#define BPF_F_CTXLEN_MASK (0xfffffULL << 32)
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
__u32 tunnel_label;
};
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will result
+ * in packet drop.
+ */
+enum xdp_action {
+ XDP_ABORTED = 0,
+ XDP_DROP,
+ XDP_PASS,
+ XDP_TX,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+ __u32 data;
+ __u32 data_end;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
-'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+TYPES
+-----
+Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe.
+String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
LINE SYNTAX
-----------
Line range is described by following syntax.
--fields::
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
- srcline, period, iregs, brstack, brstacksym, flags.
- Field list can be prepended with the type, trace, sw or hw,
+ srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+ callindent. Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
#endif
#if defined(_CALL_ELF) && _CALL_ELF == 2
-bool arch__prefers_symtab(void)
-{
- return true;
-}
#ifdef HAVE_LIBELF_SUPPORT
void arch__sym_update(struct symbol *s, GElf_Sym *sym)
tev->point.offset += lep_offset;
}
}
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+ int ntevs)
+{
+ struct probe_trace_event *tev;
+ struct map *map;
+ struct symbol *sym = NULL;
+ struct rb_node *tmp;
+ int i = 0;
+
+ map = get_target_map(pev->target, pev->uprobes);
+ if (!map || map__load(map, NULL) < 0)
+ return;
+
+ for (i = 0; i < ntevs; i++) {
+ tev = &pev->tevs[i];
+ map__for_each_symbol(map, sym, tmp) {
+ if (map->unmap_ip(map, sym->start) == tev->point.address)
+ arch__fix_tev_from_maps(pev, tev, map, sym);
+ }
+ }
+}
+
#endif
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,period,iregs,brstack,brstacksym,flags,"
- "callindent", parse_output_fields),
+ "bpf-output,callindent", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
return 0;
}
-static void read_counters(bool close_counters)
+static void read_counters(void)
{
struct perf_evsel *counter;
if (perf_stat_process_counter(&stat_config, counter))
pr_warning("failed to process counter %s\n", counter->name);
-
- if (close_counters) {
- perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
- thread_map__nr(evsel_list->threads));
- }
}
}
{
struct timespec ts, rs;
- read_counters(false);
+ read_counters();
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
perf_evlist__enable(evsel_list);
}
+static void disable_counters(void)
+{
+ /*
+ * If we don't have tracee (attaching to task or cpu), counters may
+ * still be running. To get accurate group ratios, we must stop groups
+ * from counting before reading their constituent counters.
+ */
+ if (!target__none(&target))
+ perf_evlist__disable(evsel_list);
+}
+
static volatile int workload_exec_errno;
/*
}
}
+ disable_counters();
+
t1 = rdclock();
update_stats(&walltime_nsecs_stats, t1 - t0);
- read_counters(true);
+ /*
+ * Closing a group leader splits the group, and as we only disable
+ * group leaders, results in remaining events becoming enabled. To
+ * avoid arbitrary skew, we must read all counters before closing any
+ * group leaders.
+ */
+ read_counters();
+ perf_evlist__close(evsel_list);
return WEXITSTATUS(status);
}
module = "kernel";
for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+ /* short_name is "[module]" */
if (strncmp(pos->dso->short_name + 1, module,
- pos->dso->short_name_len - 2) == 0) {
+ pos->dso->short_name_len - 2) == 0 &&
+ module[pos->dso->short_name_len - 2] == '\0') {
return pos;
}
}
return NULL;
}
-static struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, bool user)
{
/* Init maps of given executable or kernel */
if (user)
if (uprobes)
address = sym->start;
else
- address = map->unmap_ip(map, sym->start);
+ address = map->unmap_ip(map, sym->start) - map->reloc;
break;
}
if (!address) {
return ret;
}
-/* Post processing the probe events */
-static int post_process_probe_trace_events(struct probe_trace_event *tevs,
- int ntevs, const char *module,
- bool uprobe)
+static int
+post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
+ int ntevs)
{
struct ref_reloc_sym *reloc_sym;
char *tmp;
int i, skipped = 0;
- if (uprobe)
- return add_exec_to_probe_trace_events(tevs, ntevs, module);
-
- /* Note that currently ref_reloc_sym based probe is not for drivers */
- if (module)
- return add_module_to_probe_trace_events(tevs, ntevs, module);
-
reloc_sym = kernel_get_ref_reloc_sym();
if (!reloc_sym) {
pr_warning("Relocated base symbol is not found!\n");
return skipped;
}
+void __weak
+arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused,
+ int ntevs __maybe_unused)
+{
+}
+
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct perf_probe_event *pev,
+ struct probe_trace_event *tevs,
+ int ntevs, const char *module,
+ bool uprobe)
+{
+ int ret;
+
+ if (uprobe)
+ ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+ else if (module)
+ /* Currently ref_reloc_sym based probe is not for drivers */
+ ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+ else
+ ret = post_process_kernel_probe_trace_events(tevs, ntevs);
+
+ if (ret >= 0)
+ arch__post_process_probe_trace_events(pev, ntevs);
+
+ return ret;
+}
+
/* Try to find perf_probe_event with debuginfo */
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
struct probe_trace_event **tevs)
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("Found %d probe_trace_events.\n", ntevs);
- ret = post_process_probe_trace_events(*tevs, ntevs,
+ ret = post_process_probe_trace_events(pev, *tevs, ntevs,
pev->target, pev->uprobes);
if (ret < 0 || ret == ntevs) {
clear_probe_trace_events(*tevs, ntevs);
return err;
}
-bool __weak arch__prefers_symtab(void) { return false; }
-
/* Concatinate two arrays */
static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
{
if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */
return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
- if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
- ret = find_probe_trace_events_from_map(pev, tevs);
- if (ret > 0)
- return ret; /* Found in symbol table */
- }
-
/* Convert perf_probe_event with debuginfo */
ret = try_to_find_probe_trace_events(pev, tevs);
if (ret != 0)
int show_available_vars(struct perf_probe_event *pevs, int npevs,
struct strfilter *filter);
int show_available_funcs(const char *module, struct strfilter *filter, bool user);
-bool arch__prefers_symtab(void);
void arch__fix_tev_from_maps(struct perf_probe_event *pev,
struct probe_trace_event *tev, struct map *map,
struct symbol *sym);
int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
struct perf_probe_arg *pvar);
+struct map *get_target_map(const char *target, bool user);
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+ int ntevs);
+
#endif /*_PROBE_EVENT_H */
char sbuf[STRERR_BUFSIZE];
int bsize, boffs, total;
int ret;
+ char sign;
/* TODO: check all types */
- if (cast && strcmp(cast, "string") != 0) {
+ if (cast && strcmp(cast, "string") != 0 &&
+ strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
/* Non string type is OK */
+ /* and respect signedness cast */
tvar->type = strdup(cast);
return (tvar->type == NULL) ? -ENOMEM : 0;
}
return (tvar->type == NULL) ? -ENOMEM : 0;
}
+ if (cast && (strcmp(cast, "u") == 0))
+ sign = 'u';
+ else if (cast && (strcmp(cast, "s") == 0))
+ sign = 's';
+ else
+ sign = die_is_signed_type(&type) ? 's' : 'u';
+
ret = dwarf_bytesize(&type);
if (ret <= 0)
/* No size ... try to use default type */
dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
ret = MAX_BASIC_TYPE_BITS;
}
- ret = snprintf(buf, 16, "%c%d",
- die_is_signed_type(&type) ? 's' : 'u', ret);
+ ret = snprintf(buf, 16, "%c%d", sign, ret);
formatted:
if (ret < 0 || ret >= 16) {
} else {
pevent_event_info(&seq, evsel->tp_format, &rec);
}
- return seq.buffer;
+ /*
+ * Trim the buffer, it starts at 4KB and we're not going to
+ * add anything more to this buffer.
+ */
+ return realloc(seq.buffer, seq.len + 1);
}
static int64_t
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
#include <linux/libnvdimm.h>
#include <linux/vmalloc.h>
#include <linux/device.h>
if (nfit_test->setup != nfit_test0_setup)
return 0;
+ flush_work(&acpi_desc->work);
nfit_test->setup_hotplug = 1;
nfit_test->setup(nfit_test);
GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown")
-CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
+CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
export CFLAGS
int i, vcpu_lock_idx = -1, ret;
struct kvm_vcpu *vcpu;
- mutex_lock(&kvm->lock);
-
- if (irqchip_in_kernel(kvm)) {
- ret = -EEXIST;
- goto out;
- }
+ if (irqchip_in_kernel(kvm))
+ return -EEXIST;
/*
* This function is also called by the KVM_CREATE_IRQCHIP handler,
* the proper checks already.
*/
if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
- !kvm_vgic_global_state.can_emulate_gicv2) {
- ret = -ENODEV;
- goto out;
- }
+ !kvm_vgic_global_state.can_emulate_gicv2)
+ return -ENODEV;
/*
* Any time a vcpu is run, vcpu_load is called which tries to grab the
vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
mutex_unlock(&vcpu->mutex);
}
-
-out:
- mutex_unlock(&kvm->lock);
return ret;
}
{
struct kvm_device *dev, *tmp;
+ /*
+ * We do not need to take the kvm->lock here, because nobody else
+ * has a reference to the struct kvm at this point and therefore
+ * cannot access the devices list anyhow.
+ */
list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
list_del(&dev->vm_node);
dev->ops->destroy(dev);
dev->ops = ops;
dev->kvm = kvm;
+ mutex_lock(&kvm->lock);
ret = ops->create(dev, cd->type);
if (ret < 0) {
+ mutex_unlock(&kvm->lock);
kfree(dev);
return ret;
}
+ list_add(&dev->vm_node, &kvm->devices);
+ mutex_unlock(&kvm->lock);
+
+ if (ops->init)
+ ops->init(dev);
ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
if (ret < 0) {
ops->destroy(dev);
+ mutex_lock(&kvm->lock);
+ list_del(&dev->vm_node);
+ mutex_unlock(&kvm->lock);
return ret;
}
- list_add(&dev->vm_node, &kvm->devices);
kvm_get_kvm(kvm);
cd->fd = ret;
return 0;
projects / deliverable / linux.git / commitdiff
