diff options
113 files changed, 1830 insertions, 425 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5d593ecadb90..5977c4d71356 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2523,6 +2523,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nojitter [IA-64] Disables jitter checking for ITC timers. + nopti [X86-64] Disable KAISER isolation of kernel from user. + no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page @@ -2555,6 +2557,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nopat [X86] Disable PAT (page attribute table extension of pagetables) support. + nopcid [X86-64] Disable the PCID cpu feature. + norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space @@ -3052,6 +3056,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. pt. [PARIDE] See Documentation/blockdev/paride.txt. + pti= [X86_64] + Control KAISER user/kernel address space isolation: + on - enable + off - disable + auto - default setting + pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in default number. @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 108 -EXTRAVERSION = +SUBLEVEL = 110 +EXTRAVERSION = -rc1 NAME = Blurry Fish Butt # *DOCUMENTATION* @@ -782,6 +782,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign) # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) +# Make sure -fstack-check isn't enabled (like gentoo apparently did) +KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,) + # conserve stack if available KBUILD_CFLAGS += $(call cc-option,-fconserve-stack) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index d1e65ce545b3..b2ab164a8094 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -401,8 +401,12 @@ static __u64 power_pmu_bhrb_to(u64 addr) int ret; __u64 target; - if (is_kernel_addr(addr)) - return branch_target((unsigned int *)addr); + if (is_kernel_addr(addr)) { + if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + return 0; + + return branch_target(&instr); + } /* Userspace: need copy instruction here then translate it */ pagefault_disable(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7e40905f6d4c..39d2dc66faa5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -42,7 +42,7 @@ config X86 select ARCH_USE_CMPXCHG_LOCKREF if X86_64 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS - select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_IPC_PARSE_VERSION if X86_32 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 3783dc3e10b3..4abb284a5b9c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -9,6 +9,7 @@ */ #undef CONFIG_PARAVIRT #undef CONFIG_PARAVIRT_SPINLOCKS +#undef CONFIG_PAGE_TABLE_ISOLATION #undef CONFIG_KASAN #include <linux/linkage.h> diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index cc0f2f5da19b..952b23b5d4e9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -35,6 +35,7 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/pgtable_types.h> +#include <asm/kaiser.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -135,6 +136,7 @@ ENTRY(entry_SYSCALL_64) * it is too small to ever cause noticeable irq latency. */ SWAPGS_UNSAFE_STACK + SWITCH_KERNEL_CR3_NO_STACK /* * A hypervisor implementation might want to use a label * after the swapgs, so that it can do the swapgs @@ -207,9 +209,17 @@ entry_SYSCALL_64_fastpath: testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ - RESTORE_C_REGS_EXCEPT_RCX_R11 movq RIP(%rsp), %rcx movq EFLAGS(%rsp), %r11 + RESTORE_C_REGS_EXCEPT_RCX_R11 + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ + SWITCH_USER_CR3 movq RSP(%rsp), %rsp /* * 64-bit SYSRET restores rip from rcx, @@ -347,10 +357,26 @@ GLOBAL(int_ret_from_sys_call) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ + SWITCH_USER_CR3 movq RSP(%rsp), %rsp USERGS_SYSRET64 opportunistic_sysret_failed: + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ + SWITCH_USER_CR3 SWAPGS jmp restore_c_regs_and_iret END(entry_SYSCALL_64) @@ -509,6 +535,7 @@ END(irq_entries_start) * tracking that we're in kernel mode. */ SWAPGS + SWITCH_KERNEL_CR3 /* * We need to tell lockdep that IRQs are off. We can't do this until @@ -568,6 +595,7 @@ GLOBAL(retint_user) mov %rsp,%rdi call prepare_exit_to_usermode TRACE_IRQS_IRETQ + SWITCH_USER_CR3 SWAPGS jmp restore_regs_and_iret @@ -625,6 +653,7 @@ native_irq_return_ldt: pushq %rax pushq %rdi SWAPGS + SWITCH_KERNEL_CR3 movq PER_CPU_VAR(espfix_waddr), %rdi movq %rax, (0*8)(%rdi) /* RAX */ movq (2*8)(%rsp), %rax /* RIP */ @@ -640,6 +669,7 @@ native_irq_return_ldt: andl $0xffff0000, %eax popq %rdi orq PER_CPU_VAR(espfix_stack), %rax + SWITCH_USER_CR3 SWAPGS movq %rax, %rsp popq %rax @@ -995,7 +1025,11 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vec /* * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + * + * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit + * ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit + * ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit */ ENTRY(paranoid_entry) cld @@ -1008,7 +1042,26 @@ ENTRY(paranoid_entry) js 1f /* negative -> in kernel */ SWAPGS xorl %ebx, %ebx -1: ret +1: +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * We might have come in between a swapgs and a SWITCH_KERNEL_CR3 + * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit. + * Do a conditional SWITCH_KERNEL_CR3: this could safely be done + * unconditionally, but we need to find out whether the reverse + * should be done on return (conveyed to paranoid_exit in %ebx). + */ + ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER + testl $KAISER_SHADOW_PGD_OFFSET, %eax + jz 2f + orl $2, %ebx + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + /* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */ + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID + movq %rax, %cr3 +2: +#endif + ret END(paranoid_entry) /* @@ -1021,19 +1074,26 @@ END(paranoid_entry) * be complicated. Fortunately, we there's no good reason * to try to handle preemption here. * - * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) + * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3 + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 + * ebx=2: needs both swapgs and SWITCH_USER_CR3 + * ebx=3: needs SWITCH_USER_CR3 but not swapgs */ ENTRY(paranoid_exit) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG - testl %ebx, %ebx /* swapgs needed? */ + TRACE_IRQS_IRETQ_DEBUG +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* No ALTERNATIVE for X86_FEATURE_KAISER: paranoid_entry sets %ebx */ + testl $2, %ebx /* SWITCH_USER_CR3 needed? */ + jz paranoid_exit_no_switch + SWITCH_USER_CR3 +paranoid_exit_no_switch: +#endif + testl $1, %ebx /* swapgs needed? */ jnz paranoid_exit_no_swapgs - TRACE_IRQS_IRETQ SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore paranoid_exit_no_swapgs: - TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: RESTORE_EXTRA_REGS RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 @@ -1048,6 +1108,13 @@ ENTRY(error_entry) cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 + /* + * error_entry() always returns with a kernel gsbase and + * CR3. We must also have a kernel CR3/gsbase before + * calling TRACE_IRQS_*. Just unconditionally switch to + * the kernel CR3 here. + */ + SWITCH_KERNEL_CR3 xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1210,6 +1277,10 @@ ENTRY(nmi) */ SWAPGS_UNSAFE_STACK + /* + * percpu variables are mapped with user CR3, so no need + * to switch CR3 here. + */ cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -1243,12 +1314,34 @@ ENTRY(nmi) movq %rsp, %rdi movq $-1, %rsi +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* Unconditionally use kernel CR3 for do_nmi() */ + /* %rax is saved above, so OK to clobber here */ + ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER + /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID + pushq %rax + /* mask off "user" bit of pgd address and 12 PCID bits: */ + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + movq %rax, %cr3 +2: +#endif call do_nmi +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * Unconditionally restore CR3. I know we return to + * kernel code that needs user CR3, but do we ever return + * to "user mode" where we need the kernel CR3? + */ + ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER +#endif + /* * Return back to user mode. We must *not* do the normal exit - * work, because we don't want to enable interrupts. Fortunately, - * do_nmi doesn't modify pt_regs. + * work, because we don't want to enable interrupts. Do not + * switch to user CR3: we might be going back to kernel code + * that had a user CR3 set. */ SWAPGS jmp restore_c_regs_and_iret @@ -1445,22 +1538,55 @@ end_repeat_nmi: ALLOC_PT_GPREGS_ON_STACK /* - * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit - * as we should not be calling schedule in NMI context. - * Even with normal interrupts enabled. An NMI should not be - * setting NEED_RESCHED or anything that normal interrupts and - * exceptions might do. + * Use the same approach as paranoid_entry to handle SWAPGS, but + * without CR3 handling since we do that differently in NMIs. No + * need to use paranoid_exit as we should not be calling schedule + * in NMI context. Even with normal interrupts enabled. An NMI + * should not be setting NEED_RESCHED or anything that normal + * interrupts and exceptions might do. */ - call paranoid_entry - - /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ + cld + SAVE_C_REGS + SAVE_EXTRA_REGS + movl $1, %ebx + movl $MSR_GS_BASE, %ecx + rdmsr + testl %edx, %edx + js 1f /* negative -> in kernel */ + SWAPGS + xorl %ebx, %ebx +1: movq %rsp, %rdi movq $-1, %rsi +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* Unconditionally use kernel CR3 for do_nmi() */ + /* %rax is saved above, so OK to clobber here */ + ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER + /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID + pushq %rax + /* mask off "user" bit of pgd address and 12 PCID bits: */ + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + movq %rax, %cr3 +2: +#endif + + /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ call do_nmi +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * Unconditionally restore CR3. We might be returning to + * kernel code that needs user CR3, like just just before + * a sysret. + */ + ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER +#endif + testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: + /* We fixed up CR3 above, so no need to switch it here */ SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_EXTRA_REGS diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 15cfebaa7688..d03bf0e28b8b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -13,6 +13,8 @@ #include <asm/irqflags.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> +#include <asm/kaiser.h> #include <linux/linkage.h> #include <linux/err.h> @@ -50,6 +52,7 @@ ENDPROC(native_usergs_sysret32) ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ SWAPGS_UNSAFE_STACK + SWITCH_KERNEL_CR3_NO_STACK movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -161,6 +164,7 @@ ENDPROC(entry_SYSENTER_compat) ENTRY(entry_SYSCALL_compat) /* Interrupts are off on entry. */ SWAPGS_UNSAFE_STACK + SWITCH_KERNEL_CR3_NO_STACK /* Stash user ESP and switch to the kernel stack. */ movl %esp, %r8d @@ -208,6 +212,7 @@ ENTRY(entry_SYSCALL_compat) /* Opportunistic SYSRET */ sysret32_from_system_call: TRACE_IRQS_ON /* User mode traces as IRQs on. */ + SWITCH_USER_CR3 movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -269,6 +274,7 @@ ENTRY(entry_INT80_compat) PARAVIRT_ADJUST_EXCEPTION_FRAME ASM_CLAC /* Do this early to minimize exposure */ SWAPGS + SWITCH_KERNEL_CR3_NO_STACK /* * User tracing code (ptrace or signal handlers) might assume that @@ -311,6 +317,7 @@ ENTRY(entry_INT80_compat) /* Go back to user mode. */ TRACE_IRQS_ON + SWITCH_USER_CR3 SWAPGS jmp restore_regs_and_iret END(entry_INT80_compat) diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h index e01f7f7ccb0c..84ae170bc3d0 100644 --- a/arch/x86/include/asm/cmdline.h +++ b/arch/x86/include/asm/cmdline.h @@ -2,5 +2,7 @@ #define _ASM_X86_CMDLINE_H int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); +int cmdline_find_option(const char *cmdline_ptr, const char *option, + char *buffer, int bufsize); #endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f7ba9fbf12ee..f6605712ca90 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -187,6 +187,7 @@ #define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ #define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ @@ -199,6 +200,9 @@ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ +#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4e10d73cf018..880db91d9457 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -43,7 +43,7 @@ struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); -DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); +DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index f226df064660..8b17c2ad1048 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ /* @@ -35,7 +37,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 59405a248fc2..9b76cd331990 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,8 +22,8 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - unsigned int irq_tlb_count; #endif + unsigned int irq_tlb_count; #ifdef CONFIG_X86_THERMAL_VECTOR unsigned int irq_thermal_count; #endif diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 59caa55fb9b5..ee52ff858699 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -187,7 +187,7 @@ extern char irq_entries_start[]; #define VECTOR_RETRIGGERED ((void *)~0UL) typedef struct irq_desc* vector_irq_t[NR_VECTORS]; -DECLARE_PER_CPU(vector_irq_t, vector_irq); +DECLARE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq); #endif /* !ASSEMBLY_ */ diff --git a/arch/x86/include/asm/kaiser.h b/arch/x86/include/asm/kaiser.h new file mode 100644 index 000000000000..802bbbdfe143 --- /dev/null +++ b/arch/x86/include/asm/kaiser.h @@ -0,0 +1,141 @@ +#ifndef _ASM_X86_KAISER_H +#define _ASM_X86_KAISER_H + +#include <uapi/asm/processor-flags.h> /* For PCID constants */ + +/* + * This file includes the definitions for the KAISER feature. + * KAISER is a counter measure against x86_64 side channel attacks on + * the kernel virtual memory. It has a shadow pgd for every process: the + * shadow pgd has a minimalistic kernel-set mapped, but includes the whole + * user memory. Within a kernel context switch, or when an interrupt is handled, + * the pgd is switched to the normal one. When the system switches to user mode, + * the shadow pgd is enabled. By this, the virtual memory caches are freed, + * and the user may not attack the whole kernel memory. + * + * A minimalistic kernel mapping holds the parts needed to be mapped in user + * mode, such as the entry/exit functions of the user space, or the stacks. + */ + +#define KAISER_SHADOW_PGD_OFFSET 0x1000 + +#ifdef __ASSEMBLY__ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + +.macro _SWITCH_TO_KERNEL_CR3 reg +movq %cr3, \reg +andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg +/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */ +ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID +movq \reg, %cr3 +.endm + +.macro _SWITCH_TO_USER_CR3 reg regb +/* + * regb must be the low byte portion of reg: because we have arranged + * for the low byte of the user PCID to serve as the high byte of NOFLUSH + * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are + * not enabled): so that the one register can update both memory and cr3. + */ +movq %cr3, \reg +orq PER_CPU_VAR(x86_cr3_pcid_user), \reg +js 9f +/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */ +movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7) +9: +movq \reg, %cr3 +.endm + +.macro SWITCH_KERNEL_CR3 +ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER +_SWITCH_TO_KERNEL_CR3 %rax +popq %rax +8: +.endm + +.macro SWITCH_USER_CR3 +ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER +_SWITCH_TO_USER_CR3 %rax %al +popq %rax +8: +.endm + +.macro SWITCH_KERNEL_CR3_NO_STACK +ALTERNATIVE "jmp 8f", \ + __stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \ + X86_FEATURE_KAISER +_SWITCH_TO_KERNEL_CR3 %rax +movq PER_CPU_VAR(unsafe_stack_register_backup), %rax +8: +.endm + +#else /* CONFIG_PAGE_TABLE_ISOLATION */ + +.macro SWITCH_KERNEL_CR3 +.endm +.macro SWITCH_USER_CR3 +.endm +.macro SWITCH_KERNEL_CR3_NO_STACK +.endm + +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Upon kernel/user mode switch, it may happen that the address + * space has to be switched before the registers have been + * stored. To change the address space, another register is + * needed. A register therefore has to be stored/restored. +*/ +DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); + +DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user); + +extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[]; + +extern int kaiser_enabled; +extern void __init kaiser_check_boottime_disable(void); +#else +#define kaiser_enabled 0 +static inline void __init kaiser_check_boottime_disable(void) {} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + +/* + * Kaiser function prototypes are needed even when CONFIG_PAGE_TABLE_ISOLATION is not set, + * so as to build with tests on kaiser_enabled instead of #ifdefs. + */ + +/** + * kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping + * @addr: the start address of the range + * @size: the size of the range + * @flags: The mapping flags of the pages + * + * The mapping is done on a global scope, so no bigger + * synchronization has to be done. the pages have to be + * manually unmapped again when they are not needed any longer. + */ +extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags); + +/** + * kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping + * @addr: the start address of the range + * @size: the size of the range + */ +extern void kaiser_remove_mapping(unsigned long start, unsigned long size); + +/** + * kaiser_init - Initialize the shadow mapping + * + * Most parts of the shadow mapping can be mapped upon boot + * time. Only per-process things like the thread stacks + * or a new LDT have to be mapped at runtime. These boot- + * time mappings are permanent and never unmapped. + */ +extern void kaiser_init(void); + +#endif /* __ASSEMBLY */ + +#endif /* _ASM_X86_KAISER_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 55234d5e7160..7680b76adafc 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -24,12 +24,6 @@ typedef struct { atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ } mm_context_t; -#ifdef CONFIG_SMP void leave_mm(int cpu); -#else -static inline void leave_mm(int cpu) -{ -} -#endif #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 44fc93987869..9bfc5fd77015 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -98,10 +98,8 @@ static inline void load_mm_ldt(struct mm_struct *mm) static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { -#ifdef CONFIG_SMP if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); -#endif } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6ec0c8b2e9df..84c62d950023 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -18,6 +18,12 @@ #ifndef __ASSEMBLY__ #include <asm/x86_init.h> +#ifdef CONFIG_PAGE_TABLE_ISOLATION +extern int kaiser_enabled; +#else +#define kaiser_enabled 0 +#endif + void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_checkwx(void); @@ -653,7 +659,17 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) static inline int pgd_bad(pgd_t pgd) { - return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE; + pgdval_t ignore_flags = _PAGE_USER; + /* + * We set NX on KAISER pgds that map userspace memory so + * that userspace can not meaningfully use the kernel + * page table by accident; it will fault on the first + * instruction it tries to run. See native_set_pgd(). + */ + if (kaiser_enabled) + ignore_flags |= _PAGE_NX; + + return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) @@ -855,7 +871,15 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { - memcpy(dst, src, count * sizeof(pgd_t)); + memcpy(dst, src, count * sizeof(pgd_t)); +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (kaiser_enabled) { + /* Clone the shadow pgd part as well */ + memcpy(native_get_shadow_pgd(dst), + native_get_shadow_pgd(src), + count * sizeof(pgd_t)); + } +#endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 2ee781114d34..c810226e741a 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -106,9 +106,32 @@ static inline void native_pud_clear(pud_t *pud) native_set_pud(pud, native_make_pud(0)); } +#ifdef CONFIG_PAGE_TABLE_ISOLATION +extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd); + +static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp) +{ +#ifdef CONFIG_DEBUG_VM + /* linux/mmdebug.h may not have been included at this point */ + BUG_ON(!kaiser_enabled); +#endif + return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE); +} +#else +static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp) +{ + BUILD_BUG_ON(1); + return NULL; +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pgd; + *pgdp = kaiser_set_shadow_pgd(pgdp, pgd); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 79c91853e50e..8dba273da25a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -89,7 +89,7 @@ #define _PAGE_NX (_AT(pteval_t, 0)) #endif -#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) +#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) @@ -102,6 +102,33 @@ _PAGE_SOFT_DIRTY) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) +/* The ASID is the lower 12 bits of CR3 */ +#define X86_CR3_PCID_ASID_MASK (_AC((1<<12)-1,UL)) + +/* Mask for all the PCID-related bits in CR3: */ +#define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK) +#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL)) + +#if defined(CONFIG_PAGE_TABLE_ISOLATION) && defined(CONFIG_X86_64) +/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */ +#define X86_CR3_PCID_ASID_USER (_AC(0x80,UL)) + +#define X86_CR3_PCID_KERN_FLUSH (X86_CR3_PCID_ASID_KERN) +#define X86_CR3_PCID_USER_FLUSH (X86_CR3_PCID_ASID_USER) +#define X86_CR3_PCID_KERN_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN) +#define X86_CR3_PCID_USER_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER) +#else +#define X86_CR3_PCID_ASID_USER (_AC(0x0,UL)) +/* + * PCIDs are unsupported on 32-bit and none of these bits can be + * set in CR3: + */ +#define X86_CR3_PCID_KERN_FLUSH (0) +#define X86_CR3_PCID_USER_FLUSH (0) +#define X86_CR3_PCID_KERN_NOFLUSH (0) +#define X86_CR3_PCID_USER_NOFLUSH (0) +#endif + /* * The cache modes defined here are used to translate between pure SW usage * and the HW defined cache mode bits and/or PAT entries. diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 2d5a50cb61a2..f3bdaed0188f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -305,7 +305,7 @@ struct tss_struct { } ____cacheline_aligned; -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4dc534175b5e..a691b66cc40a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -6,6 +6,7 @@ #include <asm/processor.h> #include <asm/special_insns.h> +#include <asm/smp.h> static inline void __invpcid(unsigned long pcid, unsigned long addr, unsigned long type) @@ -64,10 +65,8 @@ static inline void invpcid_flush_all_nonglobals(void) #endif struct tlb_state { -#ifdef CONFIG_SMP struct mm_struct *active_mm; int state; -#endif /* * Access to this CR4 shadow and to H/W CR4 is protected by @@ -132,6 +131,24 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) cr4_set_bits(mask); } +/* + * Declare a couple of kaiser interfaces here for convenience, + * to avoid the need for asm/kaiser.h in unexpected places. + */ +#ifdef CONFIG_PAGE_TABLE_ISOLATION +extern int kaiser_enabled; +extern void kaiser_setup_pcid(void); +extern void kaiser_flush_tlb_on_return_to_user(void); +#else +#define kaiser_enabled 0 +static inline void kaiser_setup_pcid(void) +{ +} +static inline void kaiser_flush_tlb_on_return_to_user(void) +{ +} +#endif + static inline void __native_flush_tlb(void) { /* @@ -140,6 +157,8 @@ static inline void __native_flush_tlb(void) * back: */ preempt_disable(); + if (kaiser_enabled) + kaiser_flush_tlb_on_return_to_user(); native_write_cr3(native_read_cr3()); preempt_enable(); } @@ -149,20 +168,27 @@ static inline void __native_flush_tlb_global_irq_disabled(void) unsigned long cr4; cr4 = this_cpu_read(cpu_tlbstate.cr4); - /* clear PGE */ - native_write_cr4(cr4 & ~X86_CR4_PGE); - /* write old PGE again and flush TLBs */ - native_write_cr4(cr4); + if (cr4 & X86_CR4_PGE) { + /* clear PGE and flush TLB of all entries */ + native_write_cr4(cr4 & ~X86_CR4_PGE); + /* restore PGE as it was before */ + native_write_cr4(cr4); + } else { + /* do it with cr3, letting kaiser flush user PCID */ + __native_flush_tlb(); + } } static inline void __native_flush_tlb_global(void) { unsigned long flags; - if (static_cpu_has(X86_FEATURE_INVPCID)) { + if (this_cpu_has(X86_FEATURE_INVPCID)) { /* * Using INVPCID is considerably faster than a pair of writes * to CR4 sandwiched inside an IRQ flag save/restore. + * + * Note, this works with CR4.PCIDE=0 or 1. */ invpcid_flush_all(); return; @@ -174,23 +200,52 @@ static inline void __native_flush_tlb_global(void) * be called from deep inside debugging code.) */ raw_local_irq_save(flags); - __native_flush_tlb_global_irq_disabled(); - raw_local_irq_restore(flags); } static inline void __native_flush_tlb_single(unsigned long addr) { - asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + /* + * SIMICS #GP's if you run INVPCID with type 2/3 + * and X86_CR4_PCIDE clear. Shame! + * + * The ASIDs used below are hard-coded. But, we must not + * call invpcid(type=1/2) before CR4.PCIDE=1. Just call + * invlpg in the case we are called early. + */ + + if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) { + if (kaiser_enabled) + kaiser_flush_tlb_on_return_to_user(); + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + return; + } + /* Flush the address out of both PCIDs. */ + /* + * An optimization here might be to determine addresses + * that are only kernel-mapped and only flush the kernel + * ASID. But, userspace flushes are probably much more + * important performance-wise. + * + * Make sure to do only a single invpcid when KAISER is + * disabled and we have only a single ASID. + */ + if (kaiser_enabled) + invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr); + invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr); } static inline void __flush_tlb_all(void) { - if (cpu_has_pge) - __flush_tlb_global(); - else - __flush_tlb(); + __flush_tlb_global(); + /* + * Note: if we somehow had PCID but not PGE, then this wouldn't work -- + * we'd end up flushing kernel translations for the current ASID but + * we might fail to flush kernel translations for other cached ASIDs. + * + * To avoid this issue, we force PCID off if PGE is off. + */ } static inline void __flush_tlb_one(unsigned long addr) @@ -204,7 +259,6 @@ static inline void __flush_tlb_one(unsigned long addr) /* * TLB flushing: * - * - flush_tlb() flushes the current mm struct TLBs * - flush_tlb_all() flushes all processes TLBs * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page @@ -216,84 +270,6 @@ static inline void __flush_tlb_one(unsigned long addr) * and page-granular flushes are available only on i486 and up. */ -#ifndef CONFIG_SMP - -/* "_up" is for UniProcessor. - * - * This is a helper for other header functions. *Not* intended to be called - * directly. All global TLB flushes need to either call this, or to bump the - * vm statistics themselves. - */ -static inline void __flush_tlb_up(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); -} - -static inline void flush_tlb_all(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb_all(); -} - -static inline void flush_tlb(void) -{ - __flush_tlb_up(); -} - -static inline void local_flush_tlb(void) -{ - __flush_tlb_up(); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_mm_range(struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned long vmflag) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ -} - -static inline void reset_lazy_tlbstate(void) -{ -} - -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - flush_tlb_all(); -} - -#else /* SMP */ - -#include <asm/smp.h> - #define local_flush_tlb() __flush_tlb() #define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL) @@ -302,13 +278,14 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_current_task(void); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -#define flush_tlb() flush_tlb_current_task() +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); +} void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, @@ -323,8 +300,6 @@ static inline void reset_lazy_tlbstate(void) this_cpu_write(cpu_tlbstate.active_mm, &init_mm); } -#endif /* SMP */ - #ifndef CONFIG_PARAVIRT #define flush_tlb_others(mask, mm, start, end) \ native_flush_tlb_others(mask, mm, start, end) diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 79887abcb5e1..1361779f44fe 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -77,7 +77,8 @@ #define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) #define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ #define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) -#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ +#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ +#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) /* * Intel CPU features in CR4 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bd17db15a2c1..0b6124315441 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -19,6 +19,14 @@ void __init check_bugs(void) { +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif + identify_boot_cpu(); #ifndef CONFIG_SMP pr_info("CPU: "); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c84b62956e8d..cc154ac64f00 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -92,7 +92,7 @@ static const struct cpu_dev default_cpu = { static const struct cpu_dev *this_cpu = &default_cpu; -DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 /* * We need valid kernel segments for data and code in long mode too @@ -162,6 +162,24 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +#ifdef CONFIG_X86_64 +static int __init x86_pcid_setup(char *s) +{ + /* require an exact match without trailing characters */ + if (strlen(s)) + return 0; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_PCID)) + return 1; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + pr_info("nopcid: PCID feature disabled\n"); + return 1; +} +__setup("nopcid", x86_pcid_setup); +#endif + static int __init x86_noinvpcid_setup(char *s) { /* noinvpcid doesn't accept parameters */ @@ -303,6 +321,39 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static void setup_pcid(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_PCID)) { + if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) { + cr4_set_bits(X86_CR4_PCIDE); + /* + * INVPCID has two "groups" of types: + * 1/2: Invalidate an individual address + * 3/4: Invalidate all contexts + * + * 1/2 take a PCID, but 3/4 do not. So, 3/4 + * ignore the PCID argument in the descriptor. + * But, we have to be careful not to call 1/2 + * with an actual non-zero PCID in them before + * we do the above cr4_set_bits(). + */ + if (cpu_has(c, X86_FEATURE_INVPCID)) + set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't + * work if PCID is on but PGE is not. Since that + * combination doesn't exist on real hardware, there's + * no reason to try to fully support it, but it's + * polite to avoid corrupting data if we're on + * an improperly configured VM. + */ + clear_cpu_cap(c, X86_FEATURE_PCID); + } + } + kaiser_setup_pcid(); +} + /* * Some CPU features depend on higher CPUID levels, which may not always * be available due to CPUID level capping or broken virtualization @@ -934,6 +985,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_smep(c); setup_smap(c); + /* Set up PCID */ + setup_pcid(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -1189,7 +1243,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { [DEBUG_STACK - 1] = DEBUG_STKSZ }; -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); /* May not be marked __init: used by software suspend */ @@ -1352,6 +1406,14 @@ void cpu_init(void) * try to read it. */ cr4_init_shadow(); + if (!kaiser_enabled) { + /* + * secondary_startup_64() deferred setting PGE in cr4: + * probe_page_size_mask() sets it on the boot cpu, + * but it needs to be set on each secondary cpu. + */ + cr4_set_bits(X86_CR4_PGE); + } /* * Load microcode on this cpu if a valid microcode is available. diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 1e7de3cefc9c..f01b3a12dce0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -2,11 +2,15 @@ #include <linux/types.h> #include <linux/slab.h> +#include <asm/kaiser.h> #include <asm/perf_event.h> #include <asm/insn.h> #include "perf_event.h" +static +DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu) static DEFINE_PER_CPU(void *, insn_buffer); +static void *dsalloc(size_t size, gfp_t flags, int node) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + unsigned int order = get_order(size); + struct page *page; + unsigned long addr; + + page = __alloc_pages_node(node, flags | __GFP_ZERO, order); + if (!page) + return NULL; + addr = (unsigned long)page_address(page); + if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) { + __free_pages(page, order); + addr = 0; + } + return (void *)addr; +#else + return kmalloc_node(size, flags | __GFP_ZERO, node); +#endif +} + +static void dsfree(const void *buffer, size_t size) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (!buffer) + return; + kaiser_remove_mapping((unsigned long)buffer, size); + free_pages((unsigned long)buffer, get_order(size)); +#else + kfree(buffer); +#endif +} + static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); + buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu) if (x86_pmu.intel_cap.pebs_format < 2) { ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); if (!ibuffer) { - kfree(buffer); + dsfree(buffer, x86_pmu.pebs_buffer_size); return -ENOMEM; } per_cpu(insn_buffer, cpu) = ibuffer; @@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu) kfree(per_cpu(insn_buffer, cpu)); per_cpu(insn_buffer, cpu) = NULL; - kfree((void *)(unsigned long)ds->pebs_buffer_base); + dsfree((void *)(unsigned long)ds->pebs_buffer_base, + x86_pmu.pebs_buffer_size); ds->pebs_buffer_base = 0; } @@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); if (unlikely(!buffer)) { WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; @@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu) if (!ds || !x86_pmu.bts) return; - kfree((void *)(unsigned long)ds->bts_buffer_base); + dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE); ds->bts_buffer_base = 0; } static int alloc_ds_buffer(int cpu) { - int node = cpu_to_node(cpu); - struct debug_store *ds; - - ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); - if (unlikely(!ds)) - return -ENOMEM; + struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu); + memset(ds, 0, sizeof(*ds)); per_cpu(cpu_hw_events, cpu).ds = ds; return 0; @@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu) return; per_cpu(cpu_hw_events, cpu).ds = NULL; - kfree(ds); } void release_ds_buffers(void) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 4d38416e2a7f..b02cb2ec6726 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -41,6 +41,7 @@ #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/espfix.h> +#include <asm/kaiser.h> /* * Note: we only need 6*8 = 48 bytes for the espfix stack, but round @@ -126,6 +127,15 @@ void __init init_espfix_bsp(void) /* Install the espfix pud into the kernel page directory */ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + /* + * Just copy the top-level PGD that is mapping the espfix + * area to ensure it is mapped into the shadow user page + * tables. + */ + if (kaiser_enabled) { + set_pgd(native_get_shadow_pgd(pgd_p), + __pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page))); + } /* Randomize the locations */ init_espfix_random(); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ffdc0e860390..4034e905741a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -183,8 +183,8 @@ ENTRY(secondary_startup_64) movq $(init_level4_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + /* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */ + movl $(X86_CR4_PAE | X86_CR4_PSE), %ecx movq %rcx, %cr4 /* Setup early boot stage 4 level pagetables. */ @@ -441,6 +441,27 @@ early_idt_ripmsg: .balign PAGE_SIZE; \ GLOBAL(name) +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Each PGD needs to be 8k long and 8k aligned. We do not + * ever go out to userspace with these, so we do not + * strictly *need* the second page, but this allows us to + * have a single set_pgd() implementation that does not + * need to worry about whether it has 4k or 8k to work + * with. + * + * This ensures PGDs are 8k long: + */ +#define KAISER_USER_PGD_FILL 512 +/* This ensures they are 8k-aligned: */ +#define NEXT_PGD_PAGE(name) \ + .balign 2 * PAGE_SIZE; \ +GLOBAL(name) +#else +#define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define KAISER_USER_PGD_FILL 0 +#endif + /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ @@ -450,9 +471,10 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PGD_PAGE(early_level4_pgt) .fill 511,8,0 .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -460,16 +482,18 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PGD_PAGE(init_level4_pgt) .fill 512,8,0 + .fill KAISER_USER_PGD_FILL,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PGD_PAGE(init_level4_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE .org init_level4_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE @@ -480,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt) */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 1423ab1b0312..f480b38a03c3 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -51,7 +51,7 @@ static struct irqaction irq2 = { .flags = IRQF_NO_THREAD, }; -DEFINE_PER_CPU(vector_irq_t, vector_irq) = { +DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d6279593bcdd..bc429365b72a 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <linux/kaiser.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm) set_ldt(pc->ldt->entries, pc->ldt->size); } +static void __free_ldt_struct(struct ldt_struct *ldt) +{ + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + free_page((unsigned long)ldt->entries); + kfree(ldt); +} + /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ static struct ldt_struct *alloc_ldt_struct(int size) { struct ldt_struct *new_ldt; int alloc_size; + int ret; if (size > LDT_ENTRIES) return NULL; @@ -66,7 +77,13 @@ static struct ldt_struct *alloc_ldt_struct(int size) return NULL; } + ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size, + __PAGE_KERNEL); new_ldt->size = size; + if (ret) { + __free_ldt_struct(new_ldt); + return NULL; + } return new_ldt; } @@ -92,12 +109,10 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; + kaiser_remove_mapping((unsigned long)ldt->entries, + ldt->size * LDT_ENTRY_SIZE); paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(ldt->entries); - else - free_page((unsigned long)ldt->entries); - kfree(ldt); + __free_ldt_struct(ldt); } /* diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..0677bf8d3a42 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -9,7 +9,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); @@ -62,7 +61,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9f7c21c22477..7c5c5dc90ffa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -39,7 +39,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss) = { .x86_tss = { .sp0 = TOP_OF_INIT_STACK, #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f660d63f40fe..9a16932c7258 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -93,6 +93,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e67b834279b2..bbaae4cf9e8e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,6 +112,7 @@ #include <asm/alternative.h> #include <asm/prom.h> #include <asm/microcode.h> +#include <asm/kaiser.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -1016,6 +1017,12 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); + /* + * This needs to happen right after XENPV is set on xen and + * kaiser_enabled is checked below in cleanup_highmap(). + */ + kaiser_check_boottime_disable(); + x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fbabe4fcc7fb..fe89f938e0f0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -104,14 +104,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) spin_lock_irqsave(&rtc_lock, flags); CMOS_WRITE(0xa, 0xf); spin_unlock_irqrestore(&rtc_lock, flags); - local_flush_tlb(); - pr_debug("1.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4; - pr_debug("2.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf; - pr_debug("3.\n"); } static inline void smpboot_restore_warm_reset_vector(void) @@ -119,11 +115,6 @@ static inline void smpboot_restore_warm_reset_vector(void) unsigned long flags; /* - * Install writable page 0 entry to set BIOS data area. - */ - local_flush_tlb(); - - /* * Paranoid: Set warm reset code and vector here back * to default values. */ diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 1c113db9ed57..2bb5ee464df3 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -9,10 +9,12 @@ #include <linux/atomic.h> atomic_t trace_idt_ctr = ATOMIC_INIT(0); +__aligned(PAGE_SIZE) struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) trace_idt_table }; /* No need to be aligned, but done to keep all IDTs defined the same way. */ +__aligned(PAGE_SIZE) gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; static int trace_irq_vector_refcount; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351961..510e80da7de4 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -187,7 +187,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_unmap_unlock(pte, ptl); out: up_write(&mm->mmap_sem); - flush_tlb(); + flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 684edebb4a0c..00045499f6c2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2383,9 +2383,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) } static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, - u64 cr0, u64 cr4) + u64 cr0, u64 cr3, u64 cr4) { int bad; + u64 pcid; + + /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ + pcid = 0; + if (cr4 & X86_CR4_PCIDE) { + pcid = cr3 & 0xfff; + cr3 &= ~0xfff; + } + + bad = ctxt->ops->set_cr(ctxt, 3, cr3); + if (bad) + return X86EMUL_UNHANDLEABLE; /* * First enable PAE, long mode needs it before CR0.PG = 1 is set. @@ -2404,6 +2416,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, bad = ctxt->ops->set_cr(ctxt, 4, cr4); if (bad) return X86EMUL_UNHANDLEABLE; + if (pcid) { + bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + } return X86EMUL_CONTINUE; @@ -2414,11 +2432,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) struct desc_struct desc; struct desc_ptr dt; u16 selector; - u32 val, cr0, cr4; + u32 val, cr0, cr3, cr4; int i; cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); - ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8)); + cr3 = GET_SMSTATE(u32, smbase, 0x7ff8); ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); @@ -2460,14 +2478,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); - return rsm_enter_protected_mode(ctxt, cr0, cr4); + return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); } static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) { struct desc_struct desc; struct desc_ptr dt; - u64 val, cr0, cr4; + u64 val, cr0, cr3, cr4; u32 base3; u16 selector; int i, r; @@ -2484,7 +2502,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); cr0 = GET_SMSTATE(u64, smbase, 0x7f58); - ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50)); + cr3 = GET_SMSTATE(u64, smbase, 0x7f50); cr4 = GET_SMSTATE(u64, smbase, 0x7f48); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); val = GET_SMSTATE(u64, smbase, 0x7ed0); @@ -2512,7 +2530,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); - r = rsm_enter_protected_mode(ctxt, cr0, cr4); + r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); if (r != X86EMUL_CONTINUE) return r; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e5f44f33de89..ccf17dbfea09 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -759,7 +759,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ - if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_ASID_MASK) || + !is_long_mode(vcpu)) return 1; } @@ -6941,7 +6942,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif kvm_rip_write(vcpu, regs->rip); - kvm_set_rflags(vcpu, regs->rflags); + kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 422db000d727..a744506856b1 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -82,3 +82,108 @@ int cmdline_find_option_bool(const char *cmdline, const char *option) return 0; /* Buffer overrun */ } + +/* + * Find a non-boolean option (i.e. option=argument). In accordance with + * standard Linux practice, if this option is repeated, this returns the + * last instance on the command line. + * + * @cmdline: the cmdline string + * @max_cmdline_size: the maximum size of cmdline + * @option: option string to look for + * @buffer: memory buffer to return the option argument + * @bufsize: size of the supplied memory buffer + * + * Returns the length of the argument (regardless of if it was + * truncated to fit in the buffer), or -1 on not found. + */ +static int +__cmdline_find_option(const char *cmdline, int max_cmdline_size, + const char *option, char *buffer, int bufsize) +{ + char c; + int pos = 0, len = -1; + const char *opptr = NULL; + char *bufptr = buffer; + enum { + st_wordstart = 0, /* Start of word/after whitespace */ + st_wordcmp, /* Comparing this word */ + st_wordskip, /* Miscompare, skip */ + st_bufcpy, /* Copying this to buffer */ + } state = st_wordstart; + + if (!cmdline) + return -1; /* No command line */ + + /* + * This 'pos' check ensures we do not overrun + * a non-NULL-terminated 'cmdline' + */ + while (pos++ < max_cmdline_size) { + c = *(char *)cmdline++; + if (!c) + break; + + switch (state) { + case st_wordstart: + if (myisspace(c)) + break; + + state = st_wordcmp; + opptr = option; + /* fall through */ + + case st_wordcmp: + if ((c == '=') && !*opptr) { + /* + * We matched all the way to the end of the + * option we were looking for, prepare to + * copy the argument. + */ + len = 0; + bufptr = buffer; + state = st_bufcpy; + break; + } else if (c == *opptr++) { + /* + * We are currently matching, so continue + * to the next character on the cmdline. + */ + break; + } + state = st_wordskip; + /* fall through */ + + case st_wordskip: + if (myisspace(c)) + state = st_wordstart; + break; + + case st_bufcpy: + if (myisspace(c)) { + state = st_wordstart; + } else { + /* + * Increment len, but don't overrun the + * supplied buffer and leave room for the + * NULL terminator. + */ + if (++len < bufsize) + *bufptr++ = c; + } + break; + } + } + + if (bufsize) + *bufptr = '\0'; + + return len; +} + +int cmdline_find_option(const char *cmdline, const char *option, char *buffer, + int bufsize) +{ + return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option, + buffer, bufsize); +} diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 1ae7c141f778..61e6cead9c4a 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -32,3 +32,4 @@ obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MPX) += mpx.o +obj-$(CONFIG_PAGE_TABLE_ISOLATION) += kaiser.o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 3aebbd6c6f5f..2bd45ae91eb3 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -165,7 +165,7 @@ static void __init probe_page_size_mask(void) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ - if (cpu_has_pge) { + if (cpu_has_pge && !kaiser_enabled) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } else @@ -753,10 +753,8 @@ void __init zone_sizes_init(void) } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { -#ifdef CONFIG_SMP .active_mm = &init_mm, .state = 0, -#endif .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec081fe0ce2c..d76ec9348cff 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -395,6 +395,16 @@ void __init cleanup_highmap(void) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); + else if (kaiser_enabled) { + /* + * level2_kernel_pgt is initialized with _PAGE_GLOBAL: + * clear that now. This is not important, so long as + * CR4.PGE remains clear, but it removes an anomaly. + * Physical mapping setup below avoids _PAGE_GLOBAL + * by use of massage_pgprot() inside pfn_pte() etc. + */ + set_pmd(pmd, pmd_clear_flags(*pmd, _PAGE_GLOBAL)); + } } } diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c new file mode 100644 index 000000000000..bf6a915f60e7 --- /dev/null +++ b/arch/x86/mm/kaiser.c @@ -0,0 +1,455 @@ +#include <linux/bug.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bug.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> + +#undef pr_fmt +#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt + +#include <asm/kaiser.h> +#include <asm/tlbflush.h> /* to verify its kaiser declarations */ +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/desc.h> +#include <asm/cmdline.h> + +int kaiser_enabled __read_mostly = 1; +EXPORT_SYMBOL(kaiser_enabled); /* for inlined TLB flush functions */ + +__visible +DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); + +/* + * These can have bit 63 set, so we can not just use a plain "or" + * instruction to get their value or'd into CR3. It would take + * another register. So, we use a memory reference to these instead. + * + * This is also handy because systems that do not support PCIDs + * just end up or'ing a 0 into their CR3, which does no harm. + */ +DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user); + +/* + * At runtime, the only things we map are some things for CPU + * hotplug, and stacks for new processes. No two CPUs will ever + * be populating the same addresses, so we only need to ensure + * that we protect between two CPUs trying to allocate and + * populate the same page table page. + * + * Only take this lock when doing a set_p[4um]d(), but it is not + * needed for doing a set_pte(). We assume that only the *owner* + * of a given allocation will be doing this for _their_ + * allocation. + * + * This ensures that once a system has been running for a while + * and there have been stacks all over and these page tables + * are fully populated, there will be no further acquisitions of + * this lock. + */ +static DEFINE_SPINLOCK(shadow_table_allocation_lock); + +/* + * Returns -1 on error. + */ +static inline unsigned long get_pa_from_mapping(unsigned long vaddr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(vaddr); + /* + * We made all the kernel PGDs present in kaiser_init(). + * We expect them to stay that way. + */ + BUG_ON(pgd_none(*pgd)); + /* + * PGDs are either 512GB or 128TB on all x86_64 + * configurations. We don't handle these. + */ + BUG_ON(pgd_large(*pgd)); + + pud = pud_offset(pgd, vaddr); + if (pud_none(*pud)) { + WARN_ON_ONCE(1); + return -1; + } + + if (pud_large(*pud)) + return (pud_pfn(*pud) << PAGE_SHIFT) | (vaddr & ~PUD_PAGE_MASK); + + pmd = pmd_offset(pud, vaddr); + if (pmd_none(*pmd)) { + WARN_ON_ONCE(1); + return -1; + } + + if (pmd_large(*pmd)) + return (pmd_pfn(*pmd) << PAGE_SHIFT) | (vaddr & ~PMD_PAGE_MASK); + + pte = pte_offset_kernel(pmd, vaddr); + if (pte_none(*pte)) { + WARN_ON_ONCE(1); + return -1; + } + + return (pte_pfn(*pte) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK); +} + +/* + * This is a relatively normal page table walk, except that it + * also tries to allocate page tables pages along the way. + * + * Returns a pointer to a PTE on success, or NULL on failure. + */ +static pte_t *kaiser_pagetable_walk(unsigned long address) +{ + pmd_t *pmd; + pud_t *pud; + pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address)); + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + + if (pgd_none(*pgd)) { + WARN_ONCE(1, "All shadow pgds should have been populated"); + return NULL; + } + BUILD_BUG_ON(pgd_large(*pgd) != 0); + + pud = pud_offset(pgd, address); + /* The shadow page tables do not use large mappings: */ + if (pud_large(*pud)) { + WARN_ON(1); + return NULL; + } + if (pud_none(*pud)) { + unsigned long new_pmd_page = __get_free_page(gfp); + if (!new_pmd_page) + return NULL; + spin_lock(&shadow_table_allocation_lock); + if (pud_none(*pud)) { + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); + __inc_zone_page_state(virt_to_page((void *) + new_pmd_page), NR_KAISERTABLE); + } else + free_page(new_pmd_page); + spin_unlock(&shadow_table_allocation_lock); + } + + pmd = pmd_offset(pud, address); + /* The shadow page tables do not use large mappings: */ + if (pmd_large(*pmd)) { + WARN_ON(1); + return NULL; + } + if (pmd_none(*pmd)) { + unsigned long new_pte_page = __get_free_page(gfp); + if (!new_pte_page) + return NULL; + spin_lock(&shadow_table_allocation_lock); + if (pmd_none(*pmd)) { + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); + __inc_zone_page_state(virt_to_page((void *) + new_pte_page), NR_KAISERTABLE); + } else + free_page(new_pte_page); + spin_unlock(&shadow_table_allocation_lock); + } + + return pte_offset_kernel(pmd, address); +} + +static int kaiser_add_user_map(const void *__start_addr, unsigned long size, + unsigned long flags) +{ + int ret = 0; + pte_t *pte; + unsigned long start_addr = (unsigned long )__start_addr; + unsigned long address = start_addr & PAGE_MASK; + unsigned long end_addr = PAGE_ALIGN(start_addr + size); + unsigned long target_address; + + /* + * It is convenient for callers to pass in __PAGE_KERNEL etc, + * and there is no actual harm from setting _PAGE_GLOBAL, so + * long as CR4.PGE is not set. But it is nonetheless troubling + * to see Kaiser itself setting _PAGE_GLOBAL (now that "nokaiser" + * requires that not to be #defined to 0): so mask it off here. + */ + flags &= ~_PAGE_GLOBAL; + + for (; address < end_addr; address += PAGE_SIZE) { + target_address = get_pa_from_mapping(address); + if (target_address == -1) { + ret = -EIO; + break; + } + pte = kaiser_pagetable_walk(address); + if (!pte) { + ret = -ENOMEM; + break; + } + if (pte_none(*pte)) { + set_pte(pte, __pte(flags | target_address)); + } else { + pte_t tmp; + set_pte(&tmp, __pte(flags | target_address)); + WARN_ON_ONCE(!pte_same(*pte, tmp)); + } + } + return ret; +} + +static int kaiser_add_user_map_ptrs(const void *start, const void *end, unsigned long flags) +{ + unsigned long size = end - start; + + return kaiser_add_user_map(start, size, flags); +} + +/* + * Ensure that the top level of the (shadow) page tables are + * entirely populated. This ensures that all processes that get + * forked have the same entries. This way, we do not have to + * ever go set up new entries in older processes. + * + * Note: we never free these, so there are no updates to them + * after this. + */ +static void __init kaiser_init_all_pgds(void) +{ + pgd_t *pgd; + int i = 0; + + pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0)); + for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) { + pgd_t new_pgd; + pud_t *pud = pud_alloc_one(&init_mm, + PAGE_OFFSET + i * PGDIR_SIZE); + if (!pud) { + WARN_ON(1); + break; + } + inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE); + new_pgd = __pgd(_KERNPG_TABLE |__pa(pud)); + /* + * Make sure not to stomp on some other pgd entry. + */ + if (!pgd_none(pgd[i])) { + WARN_ON(1); + continue; + } + set_pgd(pgd + i, new_pgd); + } +} + +#define kaiser_add_user_map_early(start, size, flags) do { \ + int __ret = kaiser_add_user_map(start, size, flags); \ + WARN_ON(__ret); \ +} while (0) + +#define kaiser_add_user_map_ptrs_early(start, end, flags) do { \ + int __ret = kaiser_add_user_map_ptrs(start, end, flags); \ + WARN_ON(__ret); \ +} while (0) + +void __init kaiser_check_boottime_disable(void) +{ + bool enable = true; + char arg[5]; + int ret; + + if (boot_cpu_has(X86_FEATURE_XENPV)) + goto silent_disable; + + ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg)); + if (ret > 0) { + if (!strncmp(arg, "on", 2)) + goto enable; + + if (!strncmp(arg, "off", 3)) + goto disable; + + if (!strncmp(arg, "auto", 4)) + goto skip; + } + + if (cmdline_find_option_bool(boot_command_line, "nopti")) + goto disable; + +skip: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + goto disable; + +enable: + if (enable) + setup_force_cpu_cap(X86_FEATURE_KAISER); + + return; + +disable: + pr_info("disabled\n"); + +silent_disable: + kaiser_enabled = 0; + setup_clear_cpu_cap(X86_FEATURE_KAISER); +} + +/* + * If anything in here fails, we will likely die on one of the + * first kernel->user transitions and init will die. But, we + * will have most of the kernel up by then and should be able to + * get a clean warning out of it. If we BUG_ON() here, we run + * the risk of being before we have good console output. + */ +void __init kaiser_init(void) +{ + int cpu; + + if (!kaiser_enabled) + return; + + kaiser_init_all_pgds(); + + for_each_possible_cpu(cpu) { + void *percpu_vaddr = __per_cpu_user_mapped_start + + per_cpu_offset(cpu); + unsigned long percpu_sz = __per_cpu_user_mapped_end - + __per_cpu_user_mapped_start; + kaiser_add_user_map_early(percpu_vaddr, percpu_sz, + __PAGE_KERNEL); + } + + /* + * Map the entry/exit text section, which is needed at + * switches from user to and from kernel. + */ + kaiser_add_user_map_ptrs_early(__entry_text_start, __entry_text_end, + __PAGE_KERNEL_RX); + +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) + kaiser_add_user_map_ptrs_early(__irqentry_text_start, + __irqentry_text_end, + __PAGE_KERNEL_RX); +#endif + kaiser_add_user_map_early((void *)idt_descr.address, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL_RO); +#ifdef CONFIG_TRACING + kaiser_add_user_map_early(&trace_idt_descr, + sizeof(trace_idt_descr), + __PAGE_KERNEL); + kaiser_add_user_map_early(&trace_idt_table, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL); +#endif + kaiser_add_user_map_early(&debug_idt_descr, sizeof(debug_idt_descr), + __PAGE_KERNEL); + kaiser_add_user_map_early(&debug_idt_table, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL); + + pr_info("enabled\n"); +} + +/* Add a mapping to the shadow mapping, and synchronize the mappings */ +int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +{ + if (!kaiser_enabled) + return 0; + return kaiser_add_user_map((const void *)addr, size, flags); +} + +void kaiser_remove_mapping(unsigned long start, unsigned long size) +{ + extern void unmap_pud_range_nofree(pgd_t *pgd, + unsigned long start, unsigned long end); + unsigned long end = start + size; + unsigned long addr, next; + pgd_t *pgd; + + if (!kaiser_enabled) + return; + pgd = native_get_shadow_pgd(pgd_offset_k(start)); + for (addr = start; addr < end; pgd++, addr = next) { + next = pgd_addr_end(addr, end); + unmap_pud_range_nofree(pgd, addr, next); + } +} + +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * This returns true for user pages that need to get copied into + * both the user and kernel copies of the page tables, and false + * for kernel pages that should only be in the kernel copy. + */ +static inline bool is_userspace_pgd(pgd_t *pgdp) +{ + return ((unsigned long)pgdp % PAGE_SIZE) < (PAGE_SIZE / 2); +} + +pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (!kaiser_enabled) + return pgd; + /* + * Do we need to also populate the shadow pgd? Check _PAGE_USER to + * skip cases like kexec and EFI which make temporary low mappings. + */ + if (pgd.pgd & _PAGE_USER) { + if (is_userspace_pgd(pgdp)) { + native_get_shadow_pgd(pgdp)->pgd = pgd.pgd; + /* + * Even if the entry is *mapping* userspace, ensure + * that userspace can not use it. This way, if we + * get out to userspace running on the kernel CR3, + * userspace will crash instead of running. + */ + pgd.pgd |= _PAGE_NX; + } + } else if (!pgd.pgd) { + /* + * pgd_clear() cannot check _PAGE_USER, and is even used to + * clear corrupted pgd entries: so just rely on cases like + * kexec and EFI never to be using pgd_clear(). + */ + if (!WARN_ON_ONCE((unsigned long)pgdp & PAGE_SIZE) && + is_userspace_pgd(pgdp)) + native_get_shadow_pgd(pgdp)->pgd = pgd.pgd; + } + return pgd; +} + +void kaiser_setup_pcid(void) +{ + unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET; + + if (this_cpu_has(X86_FEATURE_PCID)) + user_cr3 |= X86_CR3_PCID_USER_NOFLUSH; + /* + * These variables are used by the entry/exit + * code to change PCID and pgd and TLB flushing. + */ + this_cpu_write(x86_cr3_pcid_user, user_cr3); +} + +/* + * Make a note that this cpu will need to flush USER tlb on return to user. + * If cpu does not have PCID, then the NOFLUSH bit will never have been set. + */ +void kaiser_flush_tlb_on_return_to_user(void) +{ + if (this_cpu_has(X86_FEATURE_PCID)) + this_cpu_write(x86_cr3_pcid_user, + X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET); +} +EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index b599a780a5a9..79377e2a7bcd 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -52,6 +52,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 +#define CPA_FREE_PAGETABLES 8 #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; @@ -723,10 +724,13 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte, return 0; } -static bool try_to_free_pte_page(pte_t *pte) +static bool try_to_free_pte_page(struct cpa_data *cpa, pte_t *pte) { int i; + if (!(cpa->flags & CPA_FREE_PAGETABLES)) + return false; + for (i = 0; i < PTRS_PER_PTE; i++) if (!pte_none(pte[i])) return false; @@ -735,10 +739,13 @@ static bool try_to_free_pte_page(pte_t *pte) return true; } -static bool try_to_free_pmd_page(pmd_t *pmd) +static bool try_to_free_pmd_page(struct cpa_data *cpa, pmd_t *pmd) { int i; + if (!(cpa->flags & CPA_FREE_PAGETABLES)) + return false; + for (i = 0; i < PTRS_PER_PMD; i++) if (!pmd_none(pmd[i])) return false; @@ -759,7 +766,9 @@ static bool try_to_free_pud_page(pud_t *pud) return true; } -static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) +static bool unmap_pte_range(struct cpa_data *cpa, pmd_t *pmd, + unsigned long start, + unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); @@ -770,22 +779,23 @@ static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) pte++; } - if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { + if (try_to_free_pte_page(cpa, (pte_t *)pmd_page_vaddr(*pmd))) { pmd_clear(pmd); return true; } return false; } -static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, +static void __unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, pmd_t *pmd, unsigned long start, unsigned long end) { - if (unmap_pte_range(pmd, start, end)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (unmap_pte_range(cpa, pmd, start, end)) + if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud))) pud_clear(pud); } -static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) +static void unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, + unsigned long start, unsigned long end) { pmd_t *pmd = pmd_offset(pud, start); @@ -796,7 +806,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); - __unmap_pmd_range(pud, pmd, start, pre_end); + __unmap_pmd_range(cpa, pud, pmd, start, pre_end); start = pre_end; pmd++; @@ -809,7 +819,8 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) if (pmd_large(*pmd)) pmd_clear(pmd); else - __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); + __unmap_pmd_range(cpa, pud, pmd, + start, start + PMD_SIZE); start += PMD_SIZE; pmd++; @@ -819,17 +830,19 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) * 4K leftovers? */ if (start < end) - return __unmap_pmd_range(pud, pmd, start, end); + return __unmap_pmd_range(cpa, pud, pmd, start, end); /* * Try again to free the PMD page if haven't succeeded above. */ if (!pud_none(*pud)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud))) pud_clear(pud); } -static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +static void __unmap_pud_range(struct cpa_data *cpa, pgd_t *pgd, + unsigned long start, + unsigned long end) { pud_t *pud = pud_offset(pgd, start); @@ -840,7 +853,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); - unmap_pmd_range(pud, start, pre_end); + unmap_pmd_range(cpa, pud, start, pre_end); start = pre_end; pud++; @@ -854,7 +867,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) if (pud_large(*pud)) pud_clear(pud); else - unmap_pmd_range(pud, start, start + PUD_SIZE); + unmap_pmd_range(cpa, pud, start, start + PUD_SIZE); start += PUD_SIZE; pud++; @@ -864,7 +877,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) * 2M leftovers? */ if (start < end) - unmap_pmd_range(pud, start, end); + unmap_pmd_range(cpa, pud, start, end); /* * No need to try to free the PUD page because we'll free it in @@ -872,6 +885,24 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) */ } +static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +{ + struct cpa_data cpa = { + .flags = CPA_FREE_PAGETABLES, + }; + + __unmap_pud_range(&cpa, pgd, start, end); +} + +void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end) +{ + struct cpa_data cpa = { + .flags = 0, + }; + + __unmap_pud_range(&cpa, pgd, start, end); +} + static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) { pgd_t *pgd_entry = root + pgd_index(addr); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d6e4..dbc27a2b4ad5 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include <asm/fixmap.h> #include <asm/mtrr.h> -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM @@ -340,14 +340,24 @@ static inline void _pgd_free(pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } #else + +/* + * Instead of one pgd, Kaiser acquires two pgds. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ +#define PGD_ALLOCATION_ORDER kaiser_enabled + static inline pgd_t *_pgd_alloc(void) { - return (pgd_t *)__get_free_page(PGALLOC_GFP); + /* No __GFP_REPEAT: to avoid page allocation stalls in order-1 case */ + return (pgd_t *)__get_free_pages(PGALLOC_GFP & ~__GFP_REPEAT, + PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { - free_page((unsigned long)pgd); + free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 45ba87466e6a..7cad01af6dcd 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,16 +6,17 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> +#include <asm/kaiser.h> /* - * Smarter SMP flushing macros. + * TLB flushing, formerly SMP-only * c/o Linus Torvalds. * * These mean you can really definitely utterly forget about @@ -28,14 +29,42 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ -#ifdef CONFIG_SMP - struct flush_tlb_info { struct mm_struct *flush_mm; unsigned long flush_start; unsigned long flush_end; }; +static void load_new_mm_cr3(pgd_t *pgdir) +{ + unsigned long new_mm_cr3 = __pa(pgdir); + + if (kaiser_enabled) { + /* + * We reuse the same PCID for different tasks, so we must + * flush all the entries for the PCID out when we change tasks. + * Flush KERN below, flush USER when returning to userspace in + * kaiser's SWITCH_USER_CR3 (_SWITCH_TO_USER_CR3) macro. + * + * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could + * do it here, but can only be used if X86_FEATURE_INVPCID is + * available - and many machines support pcid without invpcid. + * + * If X86_CR3_PCID_KERN_FLUSH actually added something, then it + * would be needed in the write_cr3() below - if PCIDs enabled. + */ + BUILD_BUG_ON(X86_CR3_PCID_KERN_FLUSH); + kaiser_flush_tlb_on_return_to_user(); + } + + /* + * Caution: many callers of this function expect + * that load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask writes. + */ + write_cr3(new_mm_cr3); +} + /* * We cannot call mmdrop() because we are in interrupt context, * instead update mm->cpu_vm_mask. @@ -47,7 +76,7 @@ void leave_mm(int cpu) BUG(); if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); - load_cr3(swapper_pg_dir); + load_new_mm_cr3(swapper_pg_dir); /* * This gets called in the idle path where RCU * functions differently. Tracing normally @@ -59,8 +88,6 @@ void leave_mm(int cpu) } EXPORT_SYMBOL_GPL(leave_mm); -#endif /* CONFIG_SMP */ - void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -77,10 +104,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { -#ifdef CONFIG_SMP this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); this_cpu_write(cpu_tlbstate.active_mm, next); -#endif cpumask_set_cpu(cpu, mm_cpumask(next)); /* @@ -111,7 +136,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * ordering guarantee we need. * */ - load_cr3(next->pgd); + load_new_mm_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); @@ -137,9 +162,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (unlikely(prev->context.ldt != next->context.ldt)) load_mm_ldt(next); #endif - } -#ifdef CONFIG_SMP - else { + } else { this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); @@ -160,17 +183,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * As above, load_cr3() is serializing and orders TLB * fills with respect to the mm_cpumask write. */ - load_cr3(next->pgd); + load_new_mm_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); load_mm_ldt(next); } } -#endif } -#ifdef CONFIG_SMP - /* * The flush IPI assumes that a thread switch happens in this order: * [cpu0: the cpu that switches] @@ -272,23 +292,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, smp_call_function_many(cpumask, flush_tlb_func, &info, 1); } -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - - preempt_disable(); - - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - - /* This is an implicit full barrier that synchronizes with switch_mm. */ - local_flush_tlb(); - - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); - preempt_enable(); -} - /* * See Documentation/x86/tlb.txt for details. We choose 33 * because it is large enough to cover the vast majority (at @@ -309,6 +312,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); + + if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) + base_pages_to_flush = (end - start) >> PAGE_SHIFT; + if (base_pages_to_flush > tlb_single_page_flush_ceiling) + base_pages_to_flush = TLB_FLUSH_ALL; + if (current->active_mm != mm) { /* Synchronize with switch_mm. */ smp_mb(); @@ -325,15 +334,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, goto out; } - if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; - /* * Both branches below are implicit full barriers (MOV to CR or * INVLPG) that synchronize with switch_mm. */ - if (base_pages_to_flush > tlb_single_page_flush_ceiling) { - base_pages_to_flush = TLB_FLUSH_ALL; + if (base_pages_to_flush == TLB_FLUSH_ALL) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { @@ -354,33 +359,6 @@ out: preempt_enable(); } -void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) -{ - struct mm_struct *mm = vma->vm_mm; - - preempt_disable(); - - if (current->active_mm == mm) { - if (current->mm) { - /* - * Implicit full barrier (INVLPG) that synchronizes - * with switch_mm. - */ - __flush_tlb_one(start); - } else { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); - } - } - - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); - - preempt_enable(); -} - static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -465,5 +443,3 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); - -#endif /* CONFIG_SMP */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ffa41591bff9..cbef64b508e1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -433,6 +433,12 @@ static void __init xen_init_cpuid_mask(void) ~((1 << X86_FEATURE_MTRR) | /* disable MTRR */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + /* + * Xen PV would need some work to support PCID: CR3 handling as well + * as xen_flush_tlb_others() would need updating. + */ + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_PCID % 32)); /* disable PCID */ + if (!xen_initial_domain()) cpuid_leaf1_edx_mask &= ~((1 << X86_FEATURE_ACPI)); /* disable ACPI */ diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c index b4f3930266b1..f620fe09d20a 100644 --- a/crypto/mcryptd.c +++ b/crypto/mcryptd.c @@ -80,6 +80,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue, pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue); crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); INIT_WORK(&cpu_queue->work, mcryptd_queue_worker); + spin_lock_init(&cpu_queue->q_lock); } return 0; } @@ -103,15 +104,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue, int cpu, err; struct mcryptd_cpu_queue *cpu_queue; - cpu = get_cpu(); - cpu_queue = this_cpu_ptr(queue->cpu_queue); - rctx->tag.cpu = cpu; + cpu_queue = raw_cpu_ptr(queue->cpu_queue); + spin_lock(&cpu_queue->q_lock); + cpu = smp_processor_id(); + rctx->tag.cpu = smp_processor_id(); err = crypto_enqueue_request(&cpu_queue->queue, request); pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n", cpu, cpu_queue, request); + spin_unlock(&cpu_queue->q_lock); queue_work_on(cpu, kcrypto_wq, &cpu_queue->work); - put_cpu(); return err; } @@ -164,16 +166,11 @@ static void mcryptd_queue_worker(struct work_struct *work) cpu_queue = container_of(work, struct mcryptd_cpu_queue, work); i = 0; while (i < MCRYPTD_BATCH || single_task_running()) { - /* - * preempt_disable/enable is used to prevent - * being preempted by mcryptd_enqueue_request() - */ - local_bh_disable(); - preempt_disable(); + + spin_lock_bh(&cpu_queue->q_lock); backlog = crypto_get_backlog(&cpu_queue->queue); req = crypto_dequeue_request(&cpu_queue->queue); - preempt_enable(); - local_bh_enable(); + spin_unlock_bh(&cpu_queue->q_lock); if (!req) { mcryptd_opportunistic_flush(); @@ -188,7 +185,7 @@ static void mcryptd_queue_worker(struct work_struct *work) ++i; } if (cpu_queue->queue.qlen) - queue_work(kcrypto_wq, &cpu_queue->work); + queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work); } void mcryptd_flusher(struct work_struct *__work) diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 6682c5daf742..4c9be45ea328 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -1020,7 +1020,7 @@ skip: /* The record may be cleared by others, try read next record */ if (len == -ENOENT) goto skip; - else if (len < sizeof(*rcd)) { + else if (len < 0 || len < sizeof(*rcd)) { rc = -EIO; goto out; } diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index bc147582bed9..6d62b69c898e 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -579,10 +579,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, ret = -EAGAIN; goto skip_cqe; } - if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) { + if (unlikely(!CQE_STATUS(hw_cqe) && + CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) { t4_set_wq_in_error(wq); - hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN)); - goto proc_cqe; + hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN)); } goto proc_cqe; } diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c index 6a0f6ec67c6b..ee7847a1ca06 100644 --- a/drivers/mfd/cros_ec_spi.c +++ b/drivers/mfd/cros_ec_spi.c @@ -660,6 +660,7 @@ static int cros_ec_spi_probe(struct spi_device *spi) sizeof(struct ec_response_get_protocol_info); ec_dev->dout_size = sizeof(struct ec_host_request); + ec_spi->last_transfer_ns = ktime_get_ns(); err = cros_ec_register(ec_dev); if (err) { diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c index 0a1606480023..cc832d309599 100644 --- a/drivers/mfd/twl4030-audio.c +++ b/drivers/mfd/twl4030-audio.c @@ -159,13 +159,18 @@ unsigned int twl4030_audio_get_mclk(void) EXPORT_SYMBOL_GPL(twl4030_audio_get_mclk); static bool twl4030_audio_has_codec(struct twl4030_audio_data *pdata, - struct device_node *node) + struct device_node *parent) { + struct device_node *node; + if (pdata && pdata->codec) return true; - if (of_find_node_by_name(node, "codec")) + node = of_get_child_by_name(parent, "codec"); + if (node) { + of_node_put(node); return true; + } return false; } diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c index 08a693cd38cc..72aab60ae846 100644 --- a/drivers/mfd/twl6040.c +++ b/drivers/mfd/twl6040.c @@ -97,12 +97,16 @@ static struct reg_sequence twl6040_patch[] = { }; -static bool twl6040_has_vibra(struct device_node *node) +static bool twl6040_has_vibra(struct device_node *parent) { -#ifdef CONFIG_OF - if (of_find_node_by_name(node, "vibra")) + struct device_node *node; + + node = of_get_child_by_name(parent, "vibra"); + if (node) { + of_node_put(node); return true; -#endif + } + return false; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3613469dc5c6..ab53e0cfb4dc 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14228,7 +14228,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) /* Reset PHY, otherwise the read DMA engine will be in a mode that * breaks all requests to 256 bytes. */ - if (tg3_asic_rev(tp) == ASIC_REV_57766) + if (tg3_asic_rev(tp) == ASIC_REV_57766 || + tg3_asic_rev(tp) == ASIC_REV_5717 || + tg3_asic_rev(tp) == ASIC_REV_5719) reset_phy = true; err = tg3_restart_hw(tp, reset_phy); diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index fc2fb25343f4..c122b3b99cd8 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -241,7 +241,8 @@ static int orion_mdio_probe(struct platform_device *pdev) dev->regs + MVMDIO_ERR_INT_MASK); } else if (dev->err_interrupt == -EPROBE_DEFER) { - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out_mdio; } mutex_init(&dev->lock); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 15056f06754a..7430dd44019e 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -914,6 +914,10 @@ static void mvneta_port_disable(struct mvneta_port *pp) val &= ~MVNETA_GMAC0_PORT_ENABLE; mvreg_write(pp, MVNETA_GMAC_CTRL_0, val); + pp->link = 0; + pp->duplex = -1; + pp->speed = 0; + udelay(200); } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index c8b85f1069ff..920391165f18 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -541,6 +541,7 @@ static int ksz9031_read_status(struct phy_device *phydev) phydev->link = 0; if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) phydev->drv->config_intr(phydev); + return genphy_config_aneg(phydev); } return 0; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 2cbecbda1ae3..b0ea8dee5f06 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -737,6 +737,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index d0c2759076a2..312cb5b74dec 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -1654,3 +1654,36 @@ void lba_set_iregs(struct parisc_device *lba, u32 ibase, u32 imask) iounmap(base_addr); } + +/* + * The design of the Diva management card in rp34x0 machines (rp3410, rp3440) + * seems rushed, so that many built-in components simply don't work. + * The following quirks disable the serial AUX port and the built-in ATI RV100 + * Radeon 7000 graphics card which both don't have any external connectors and + * thus are useless, and even worse, e.g. the AUX port occupies ttyS0 and as + * such makes those machines the only PARISC machines on which we can't use + * ttyS0 as boot console. + */ +static void quirk_diva_ati_card(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1292) + return; + + dev_info(&dev->dev, "Hiding Diva built-in ATI card"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RADEON_QY, + quirk_diva_ati_card); + +static void quirk_diva_aux_disable(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1291) + return; + + dev_info(&dev->dev, "Hiding Diva built-in AUX serial device"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX, + quirk_diva_aux_disable); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index fca925543fae..32bd8ab79d53 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -944,7 +944,12 @@ static int pci_pm_thaw_noirq(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); - pci_update_current_state(pci_dev, PCI_D0); + /* + * pci_restore_state() requires the device to be in D0 (because of MSI + * restoration among other things), so force it into D0 in case the + * driver's "freeze" callbacks put it into a low-power state directly. + */ + pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); if (drv && drv->pm && drv->pm->thaw_noirq) diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c index 3009121173cd..3c6ea5c3ddd2 100644 --- a/drivers/spi/spi-xilinx.c +++ b/drivers/spi/spi-xilinx.c @@ -271,6 +271,7 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) while (remaining_words) { int n_words, tx_words, rx_words; u32 sr; + int stalled; n_words = min(remaining_words, xspi->buffer_size); @@ -299,7 +300,17 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) /* Read out all the data from the Rx FIFO */ rx_words = n_words; + stalled = 10; while (rx_words) { + if (rx_words == n_words && !(stalled--) && + !(sr & XSPI_SR_TX_EMPTY_MASK) && + (sr & XSPI_SR_RX_EMPTY_MASK)) { + dev_err(&spi->dev, + "Detected stall. Check C_SPI_MODE and C_SPI_MEMORY\n"); + xspi_init_hw(xspi); + return -EIO; + } + if ((sr & XSPI_SR_TX_EMPTY_MASK) && (rx_words > 1)) { xilinx_spi_rx(xspi); rx_words--; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 84e71bd19082..41dda25da049 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1801,7 +1801,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) { struct n_tty_data *ldata = tty->disc_data; - if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) { + if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) { bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE); ldata->line_start = ldata->read_tail; if (!L_ICANON(tty) || !read_cnt(ldata)) { @@ -2493,7 +2493,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file, return put_user(tty_chars_in_buffer(tty), (int __user *) arg); case TIOCINQ: down_write(&tty->termios_rwsem); - if (L_ICANON(tty)) + if (L_ICANON(tty) && !L_EXTPROC(tty)) retval = inq_canon(ldata); else retval = read_cnt(ldata); diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index f6fde903fcad..22dcccf2d286 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -973,7 +973,7 @@ int usb_get_bos_descriptor(struct usb_device *dev) case USB_SSP_CAP_TYPE: ssp_cap = (struct usb_ssp_cap_descriptor *)buffer; ssac = (le32_to_cpu(ssp_cap->bmAttributes) & - USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1; + USB_SSP_SUBLINK_SPEED_ATTRIBS); if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac)) dev->bos->ssp_cap = ssp_cap; break; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 50010282c010..c05c4f877750 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -57,10 +57,11 @@ static const struct usb_device_id usb_quirk_list[] = { /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, - /* Logitech HD Pro Webcams C920, C920-C and C930e */ + /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT }, /* Logitech ConferenceCam CC3000e */ { USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT }, @@ -154,6 +155,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */ { USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM }, + /* ELSA MicroLink 56K */ + { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */ { USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index e8f990642281..cbf3be66f89c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -185,6 +185,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_BROKEN_STREAMS; } if (pdev->vendor == PCI_VENDOR_ID_RENESAS && + pdev->device == 0x0014) + xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && pdev->device == 0x0015) xhci->quirks |= XHCI_RESET_ON_RESUME; if (pdev->vendor == PCI_VENDOR_ID_VIA) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 30344efc123f..64fe9dc25ed4 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1017,6 +1017,7 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, + { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index f9d15bd62785..543d2801632b 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -914,6 +914,12 @@ #define ICPDAS_I7563U_PID 0x0105 /* + * Airbus Defence and Space + */ +#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */ +#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */ + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index ffa8ec917ff5..a818c43a02ec 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -236,6 +236,8 @@ static void option_instat_callback(struct urb *urb); /* These Quectel products use Qualcomm's vendor ID */ #define QUECTEL_PRODUCT_UC20 0x9003 #define QUECTEL_PRODUCT_UC15 0x9090 +/* These Yuga products use Qualcomm's vendor ID */ +#define YUGA_PRODUCT_CLM920_NC5 0x9625 #define QUECTEL_VENDOR_ID 0x2c7c /* These Quectel products use Quectel's vendor ID */ @@ -283,6 +285,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_ME910 0x1100 +#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 @@ -648,6 +651,11 @@ static const struct option_blacklist_info telit_me910_blacklist = { .reserved = BIT(1) | BIT(3), }; +static const struct option_blacklist_info telit_me910_dual_modem_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(3), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -677,6 +685,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = { .reserved = BIT(4) | BIT(5), }; +static const struct option_blacklist_info yuga_clm920_nc5_blacklist = { + .reserved = BIT(1) | BIT(4), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1181,6 +1193,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)}, { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + /* Yuga products use Qualcomm vendor ID */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5), + .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist }, /* Quectel products using Quectel vendor ID */ { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, @@ -1247,6 +1262,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = (kernel_ulong_t)&telit_me910_blacklist }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), + .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 4516291df1b8..fb6dc16c754a 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */ {DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */ + {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ @@ -346,6 +348,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) break; case 2: dev_dbg(dev, "NMEA GPS interface found\n"); + sendsetup = true; break; case 3: dev_dbg(dev, "Modem port found\n"); diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c index af10f7b131a4..325b4c05acdd 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -252,11 +252,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev) struct stub_priv *priv; struct urb *urb; - dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev); + dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n"); while ((priv = stub_priv_pop(sdev))) { urb = priv->urb; - dev_dbg(&sdev->udev->dev, "free urb %p\n", urb); + dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n", + priv->seqnum); usb_kill_urb(urb); kmem_cache_free(stub_priv_cache, priv); diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 00e475c51a12..7de54a66044f 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -230,9 +230,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev, if (priv->seqnum != pdu->u.cmd_unlink.seqnum) continue; - dev_info(&priv->urb->dev->dev, "unlink urb %p\n", - priv->urb); - /* * This matched urb is not completed yet (i.e., be in * flight in usb hcd hardware/driver). Now we are @@ -271,8 +268,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev, ret = usb_unlink_urb(priv->urb); if (ret != -EINPROGRESS) dev_err(&priv->urb->dev->dev, - "failed to unlink a urb %p, ret %d\n", - priv->urb, ret); + "failed to unlink a urb # %lu, ret %d\n", + priv->seqnum, ret); return 0; } diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c index af858d52608a..f4dd30c56f36 100644 --- a/drivers/usb/usbip/stub_tx.c +++ b/drivers/usb/usbip/stub_tx.c @@ -201,8 +201,8 @@ static int stub_send_ret_submit(struct stub_device *sdev) /* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb); - usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n", - pdu_header.base.seqnum, urb); + usbip_dbg_stub_tx("setup txdata seqnum: %d\n", + pdu_header.base.seqnum); usbip_header_correct_endian(&pdu_header, 1); iov[iovnum].iov_base = &pdu_header; diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 81b2b9f808b5..f9af04d7f02f 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -467,9 +467,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, int ret = 0; struct vhci_device *vdev; - usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n", - hcd, urb, mem_flags); - /* patch to usb_sg_init() is in 2.5.60 */ BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length); @@ -627,8 +624,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) struct vhci_priv *priv; struct vhci_device *vdev; - pr_info("dequeue a urb %p\n", urb); - spin_lock(&the_controller->lock); priv = urb->hcpriv; @@ -656,7 +651,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) /* tcp connection is closed */ spin_lock(&vdev->priv_lock); - pr_info("device %p seems to be disconnected\n", vdev); list_del(&priv->list); kfree(priv); urb->hcpriv = NULL; @@ -668,8 +662,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) * vhci_rx will receive RET_UNLINK and give back the URB. * Otherwise, we give back it here. */ - pr_info("gives back urb %p\n", urb); - usb_hcd_unlink_urb_from_ep(hcd, urb); spin_unlock(&the_controller->lock); @@ -698,8 +690,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) unlink->unlink_seqnum = priv->seqnum; - pr_info("device %p seems to be still connected\n", vdev); - /* send cmd_unlink and try to cancel the pending URB in the * peer */ list_add_tail(&unlink->list, &vdev->unlink_tx); diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c index 00e4a54308e4..bc4eb0855314 100644 --- a/drivers/usb/usbip/vhci_rx.c +++ b/drivers/usb/usbip/vhci_rx.c @@ -37,24 +37,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum) urb = priv->urb; status = urb->status; - usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n", - urb, priv, seqnum); + usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum); switch (status) { case -ENOENT: /* fall through */ case -ECONNRESET: - dev_info(&urb->dev->dev, - "urb %p was unlinked %ssynchronuously.\n", urb, - status == -ENOENT ? "" : "a"); + dev_dbg(&urb->dev->dev, + "urb seq# %u was unlinked %ssynchronuously\n", + seqnum, status == -ENOENT ? "" : "a"); break; case -EINPROGRESS: /* no info output */ break; default: - dev_info(&urb->dev->dev, - "urb %p may be in a error, status %d\n", urb, - status); + dev_dbg(&urb->dev->dev, + "urb seq# %u may be in a error, status %d\n", + seqnum, status); } list_del(&priv->list); @@ -78,8 +77,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, spin_unlock(&vdev->priv_lock); if (!urb) { - pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum); - pr_info("max seqnum %d\n", + pr_err("cannot find a urb of seqnum %u max seqnum %d\n", + pdu->base.seqnum, atomic_read(&the_controller->seqnum)); usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); return; @@ -102,7 +101,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, if (usbip_dbg_flag_vhci_rx) usbip_dump_urb(urb); - usbip_dbg_vhci_rx("now giveback urb %p\n", urb); + usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum); spin_lock(&the_controller->lock); usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb); @@ -165,7 +164,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev, pr_info("the urb (seqnum %d) was already given back\n", pdu->base.seqnum); } else { - usbip_dbg_vhci_rx("now giveback urb %p\n", urb); + usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum); /* If unlink is successful, status is -ECONNRESET */ urb->status = pdu->u.ret_unlink.status; diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c index 409fd99f3257..3c5796c8633a 100644 --- a/drivers/usb/usbip/vhci_tx.c +++ b/drivers/usb/usbip/vhci_tx.c @@ -82,7 +82,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev) memset(&msg, 0, sizeof(msg)); memset(&iov, 0, sizeof(iov)); - usbip_dbg_vhci_tx("setup txdata urb %p\n", urb); + usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n", + priv->seqnum); /* 1. setup usbip_header */ setup_cmd_submit_pdu(&pdu_header, urb); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index ef2e8c97e183..a461b6604fd9 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -725,7 +725,14 @@ */ #define PERCPU_INPUT(cacheline) \ VMLINUX_SYMBOL(__per_cpu_start) = .; \ + VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \ *(.data..percpu..first) \ + . = ALIGN(cacheline); \ + *(.data..percpu..user_mapped) \ + *(.data..percpu..user_mapped..shared_aligned) \ + . = ALIGN(PAGE_SIZE); \ + *(.data..percpu..user_mapped..page_aligned) \ + VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h index c23ee1f7ee80..c2ff077168d3 100644 --- a/include/crypto/mcryptd.h +++ b/include/crypto/mcryptd.h @@ -26,6 +26,7 @@ static inline struct mcryptd_ahash *__mcryptd_ahash_cast( struct mcryptd_cpu_queue { struct crypto_queue queue; + spinlock_t q_lock; struct work_struct work; }; diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 402753bccafa..7b8e3afcc291 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -215,7 +215,8 @@ struct ipv6_pinfo { * 100: prefer care-of address */ dontfrag:1, - autoflowlabel:1; + autoflowlabel:1, + autoflowlabel_set:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h new file mode 100644 index 000000000000..58c55b1589d0 --- /dev/null +++ b/include/linux/kaiser.h @@ -0,0 +1,52 @@ +#ifndef _LINUX_KAISER_H +#define _LINUX_KAISER_H + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +#include <asm/kaiser.h> + +static inline int kaiser_map_thread_stack(void *stack) +{ + /* + * Map that page of kernel stack on which we enter from user context. + */ + return kaiser_add_mapping((unsigned long)stack + + THREAD_SIZE - PAGE_SIZE, PAGE_SIZE, __PAGE_KERNEL); +} + +static inline void kaiser_unmap_thread_stack(void *stack) +{ + /* + * Note: may be called even when kaiser_map_thread_stack() failed. + */ + kaiser_remove_mapping((unsigned long)stack + + THREAD_SIZE - PAGE_SIZE, PAGE_SIZE); +} +#else + +/* + * These stubs are used whenever CONFIG_PAGE_TABLE_ISOLATION is off, which + * includes architectures that support KAISER, but have it disabled. + */ + +static inline void kaiser_init(void) +{ +} +static inline int kaiser_add_mapping(unsigned long addr, + unsigned long size, unsigned long flags) +{ + return 0; +} +static inline void kaiser_remove_mapping(unsigned long start, + unsigned long size) +{ +} +static inline int kaiser_map_thread_stack(void *stack) +{ + return 0; +} +static inline void kaiser_unmap_thread_stack(void *stack) +{ +} + +#endif /* !CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* _LINUX_KAISER_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ff88d6189411..b93b578cfa42 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -131,8 +131,9 @@ enum zone_stat_item { NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ - NR_KERNEL_STACK, /* Second 128 byte cacheline */ + NR_KERNEL_STACK, + NR_KAISERTABLE, NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8f16299ca068..8902f23bb770 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -35,6 +35,12 @@ #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION +#define USER_MAPPED_SECTION "..user_mapped" +#else +#define USER_MAPPED_SECTION "" +#endif + /* * Base implementations of per-CPU variable declarations and definitions, where * the section in which the variable is to be placed is provided by the @@ -115,6 +121,12 @@ #define DEFINE_PER_CPU(type, name) \ DEFINE_PER_CPU_SECTION(type, name, "") +#define DECLARE_PER_CPU_USER_MAPPED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION) + +#define DEFINE_PER_CPU_USER_MAPPED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION) + /* * Declaration/definition used for per-CPU variables that must come first in * the set of variables. @@ -144,6 +156,14 @@ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \ ____cacheline_aligned_in_smp +#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \ + ____cacheline_aligned_in_smp + +#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \ + ____cacheline_aligned_in_smp + #define DECLARE_PER_CPU_ALIGNED(type, name) \ DECLARE_PER_CPU_SECTION(type, name, PER_CPU_ALIGNED_SECTION) \ ____cacheline_aligned @@ -162,11 +182,21 @@ #define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ DEFINE_PER_CPU_SECTION(type, name, "..page_aligned") \ __aligned(PAGE_SIZE) +/* + * Declaration/definition used for per-CPU variables that must be page aligned and need to be mapped in user mode. + */ +#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ + __aligned(PAGE_SIZE) + +#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ + __aligned(PAGE_SIZE) /* * Declaration/definition used for per-CPU variables that must be read mostly. */ -#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ +#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ DECLARE_PER_CPU_SECTION(type, name, "..read_mostly") #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e623d392db0c..8ef3a61fdc74 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -80,10 +80,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #endif #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/include/net/ip.h b/include/net/ip.h index 7476bb10ff37..639398af273b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,6 +33,8 @@ #include <net/flow.h> #include <net/flow_dissector.h> +#define IPV4_MIN_MTU 68 /* RFC 791 */ + struct sock; struct inet_skb_parm { diff --git a/init/main.c b/init/main.c index 9e64d7097f1a..49926d95442f 100644 --- a/init/main.c +++ b/init/main.c @@ -81,6 +81,7 @@ #include <linux/integrity.h> #include <linux/proc_ns.h> #include <linux/io.h> +#include <linux/kaiser.h> #include <asm/io.h> #include <asm/bugs.h> @@ -492,6 +493,7 @@ static void __init mm_init(void) pgtable_init(); vmalloc_init(); ioremap_huge_init(); + kaiser_init(); } asmlinkage __visible void __init start_kernel(void) diff --git a/kernel/fork.c b/kernel/fork.c index 68cfda1c1800..ac00f14208b7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -58,6 +58,7 @@ #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> +#include <linux/kaiser.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> @@ -169,6 +170,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static inline void free_thread_info(struct thread_info *ti) { + kaiser_unmap_thread_stack(ti); free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else @@ -352,6 +354,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) goto free_ti; tsk->stack = ti; + + err = kaiser_map_thread_stack(tsk->stack); + if (err) + goto free_ti; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 22c57e191a23..e5d228f7224c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -568,6 +568,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } +static inline bool local_timer_softirq_pending(void) +{ + return local_softirq_pending() & TIMER_SOFTIRQ; +} + static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ktime_t now, int cpu) { @@ -584,8 +589,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, } while (read_seqretry(&jiffies_lock, seq)); ts->last_jiffies = basejiff; - if (rcu_needs_cpu(basemono, &next_rcu) || - arch_needs_cpu() || irq_work_needs_cpu()) { + /* + * Keep the periodic tick, when RCU, architecture or irq_work + * requests it. + * Aside of that check whether the local timer softirq is + * pending. If so its a bad idea to call get_next_timer_interrupt() + * because there is an already expired timer, so it will request + * immeditate expiry, which rearms the hardware timer with a + * minimal delta which brings us back to this place + * immediately. Lather, rinse and repeat... + */ + if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || + irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1275175b0946..d9cd6191760b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) +#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED) + struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage) */ size_t ring_buffer_page_len(void *page) { - return local_read(&((struct buffer_data_page *)page)->commit) + struct buffer_data_page *bpage = page; + + return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS) + BUF_PAGE_HDR_SIZE; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 61d0960559c8..8aef4e63ac57 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5754,7 +5754,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; - int entries, size, i; + int entries, i; ssize_t ret = 0; #ifdef CONFIG_TRACER_MAX_TRACE @@ -5805,14 +5805,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - /* - * zero out any left over data, this is going to - * user land. - */ - size = ring_buffer_page_len(ref->page); - if (size < PAGE_SIZE) - memset(ref->page + size, 0, PAGE_SIZE - size); - page = virt_to_page(ref->page); spd.pages[i] = page; @@ -6539,6 +6531,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size buf->data = alloc_percpu(struct trace_array_cpu); if (!buf->data) { ring_buffer_free(buf->buffer); + buf->buffer = NULL; return -ENOMEM; } @@ -6562,7 +6555,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) allocate_snapshot ? size : 1); if (WARN_ON(ret)) { ring_buffer_free(tr->trace_buffer.buffer); + tr->trace_buffer.buffer = NULL; free_percpu(tr->trace_buffer.data); + tr->trace_buffer.data = NULL; return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; diff --git a/mm/vmstat.c b/mm/vmstat.c index c344e3609c53..324b7e90b4c5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -736,6 +736,7 @@ const char * const vmstat_text[] = { "nr_slab_unreclaimable", "nr_page_table_pages", "nr_kernel_stack", + "nr_overhead", "nr_unstable", "nr_bounce", "nr_vmscan_write", diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a1f697ec4fc2..0ce26a0f7913 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1067,19 +1067,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, struct net_bridge *br = netdev_priv(dev); int err; + err = register_netdevice(dev); + if (err) + return err; + if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } - err = register_netdevice(dev); - if (err) - return err; - err = br_changelink(dev, tb, data); if (err) - unregister_netdevice(dev); + br_dev_delete(dev, NULL); + return err; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2e9a1c2818c7..b5c351d2830b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -261,7 +261,7 @@ struct net *get_net_ns_by_id(struct net *net, int id) spin_lock_irqsave(&net->nsid_lock, flags); peer = idr_find(&net->netns_ids, id); if (peer) - get_net(peer); + peer = maybe_get_net(peer); spin_unlock_irqrestore(&net->nsid_lock, flags); rcu_read_unlock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d33609c2f276..86b619501350 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3676,7 +3676,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) - return; + goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. @@ -3685,7 +3685,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); sock_put(sk); + return; } + +err: + kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0212591b0077..63f99e9a821b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1358,7 +1358,7 @@ skip: static bool inetdev_valid_mtu(unsigned int mtu) { - return mtu >= 68; + return mtu >= IPV4_MIN_MTU; } static void inetdev_send_gratuitous_arp(struct net_device *dev, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0cb240c749bf..c9e68ff48a72 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1252,7 +1252,7 @@ fail: static void ip_fib_net_exit(struct net *net) { - unsigned int i; + int i; rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1260,7 +1260,12 @@ static void ip_fib_net_exit(struct net *net) RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif - for (i = 0; i < FIB_TABLE_HASHSZ; i++) { + /* Destroy the tables in reverse order to guarantee that the + * local table, ID 255, is destroyed before the main table, ID + * 254. This is necessary as the local table may contain + * references to data contained in the main table. + */ + for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3809d523d012..b60106d34346 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -89,6 +89,7 @@ #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> +#include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -327,6 +328,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } +/* source address selection per RFC 3376 section 4.2.13 */ +static __be32 igmpv3_get_srcaddr(struct net_device *dev, + const struct flowi4 *fl4) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return htonl(INADDR_ANY); + + for_ifa(in_dev) { + if (inet_ifa_match(fl4->saddr, ifa)) + return fl4->saddr; + } endfor_ifa(in_dev); + + return htonl(INADDR_ANY); +} + static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; @@ -374,7 +392,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; - pip->saddr = fl4.saddr; + pip->saddr = igmpv3_get_srcaddr(dev, &fl4); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); @@ -410,16 +428,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, - int type, struct igmpv3_grec **ppgr) + int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; - if (!skb) - skb = igmpv3_newpack(dev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = igmpv3_newpack(dev, mtu); + if (!skb) + return NULL; + } pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -441,12 +460,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV4_MIN_MTU) + return skb; + isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || @@ -467,7 +491,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); } } first = 1; @@ -494,12 +518,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -533,7 +557,7 @@ empty_source: igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 3310ac75e3f3..c18245e05d26 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -400,8 +400,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; mtu -= (dev->hard_header_len + t_hlen); - if (mtu < 68) - mtu = 68; + if (mtu < IPV4_MIN_MTU) + mtu = IPV4_MIN_MTU; return mtu; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8f2cd7d09720..4d3d4291c82f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -500,11 +500,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; + int hdrincl; err = -EMSGSIZE; if (len > 0xFFFF) goto out; + /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields + */ + hdrincl = inet->hdrincl; /* * Check the flags. */ @@ -579,7 +584,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Linux does not mangle headers on raw sockets, * so that IP options + IP_HDRINCL is non-sense. */ - if (inet->hdrincl) + if (hdrincl) goto done; if (ipc.opt->opt.srr) { if (!daddr) @@ -601,9 +606,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk) | - (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), + (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); if (!saddr && ipc.oif) { @@ -612,7 +617,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto done; } - if (!inet->hdrincl) { + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; @@ -637,7 +642,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto do_confirm; back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a5d790c13ef5..61c93a93f228 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -823,7 +823,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 83ec6639b04d..637a0e41b0aa 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -200,7 +200,6 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk)); sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 71624cf26832..1b4f5f2d2929 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -148,6 +148,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +{ + if (!np->autoflowlabel_set) + return ip6_default_np_autolabel(net); + else + return np->autoflowlabel; +} + /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified @@ -211,7 +219,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -1675,7 +1683,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a4a30d2ca66f..435e26210587 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -872,6 +872,7 @@ pref_skip_coa: break; case IPV6_AUTOFLOWLABEL: np->autoflowlabel = valbool; + np->autoflowlabel_set = 1; retv = 0; break; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d64ee7e83664..06640685ff43 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1668,16 +1668,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, - int type, struct mld2_grec **ppgr) + int type, struct mld2_grec **ppgr, unsigned int mtu) { - struct net_device *dev = pmc->idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr; - if (!skb) - skb = mld_newpack(pmc->idev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = mld_newpack(pmc->idev, mtu); + if (!skb) + return NULL; + } pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -1700,10 +1700,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV6_MIN_MTU) + return skb; + isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || @@ -1724,7 +1729,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); } } first = 1; @@ -1751,12 +1756,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -1790,7 +1795,7 @@ empty_source: mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 59c908ff251a..74cbcc4b399c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -949,7 +949,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr), 0, 0); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 5fabe68e20dd..48e1608414e6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -261,6 +261,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct sock *sk = skb->sk; int ret = -ENOMEM; + if (!net_eq(dev_net(dev), sock_net(sk))) + return 0; + dev_hold(dev); if (is_vmalloc_addr(skb->head)) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 61189c576963..a870d27ca778 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4153,7 +4153,7 @@ static int sctp_init_sock(struct sock *sk) SCTP_DBG_OBJCNT_INC(sock); local_bh_disable(); - percpu_counter_inc(&sctp_sockets_allocated); + sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); /* Nothing can fail after this block, otherwise @@ -4197,7 +4197,7 @@ static void sctp_destroy_sock(struct sock *sk) } sctp_endpoint_free(sp->ep); local_bh_disable(); - percpu_counter_dec(&sctp_sockets_allocated); + sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); } diff --git a/security/Kconfig b/security/Kconfig index e45237897b43..a3ebb6ee5bd5 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -31,6 +31,16 @@ config SECURITY If you are unsure how to answer this question, answer N. +config PAGE_TABLE_ISOLATION + bool "Remove the kernel mapping in user mode" + default y + depends on X86_64 && SMP + help + This enforces a strict kernel and user space isolation, in order + to close hardware side channels on kernel address information. + + If you are unsure how to answer this question, answer Y. + config SECURITYFS bool "Enable the securityfs filesystem" help diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index b450a27588c8..16f8124b1150 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -579,15 +579,14 @@ static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream, return 0; } -int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +static int __snd_rawmidi_info_select(struct snd_card *card, + struct snd_rawmidi_info *info) { struct snd_rawmidi *rmidi; struct snd_rawmidi_str *pstr; struct snd_rawmidi_substream *substream; - mutex_lock(®ister_mutex); rmidi = snd_rawmidi_search(card, info->device); - mutex_unlock(®ister_mutex); if (!rmidi) return -ENXIO; if (info->stream < 0 || info->stream > 1) @@ -603,6 +602,16 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info } return -ENXIO; } + +int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +{ + int ret; + + mutex_lock(®ister_mutex); + ret = __snd_rawmidi_info_select(card, info); + mutex_unlock(®ister_mutex); + return ret; +} EXPORT_SYMBOL(snd_rawmidi_info_select); static int snd_rawmidi_info_select_user(struct snd_card *card, diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index cce9ae5ec93b..bd7bcf428bcf 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -183,7 +183,7 @@ static int hdac_component_master_match(struct device *dev, void *data) */ int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops) { - if (WARN_ON(!hdac_acomp)) + if (!hdac_acomp) return -ENODEV; hdac_acomp->audio_ops = aops; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2159b18f76bf..5875a08d555e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5954,6 +5954,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1b, 0x01011020}, {0x21, 0x02211010}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x1b, 0x01011020}, + {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60160}, {0x14, 0x90170120}, {0x21, 0x02211030}), diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c index a5a4e9f75c57..a06395507225 100644 --- a/sound/soc/codecs/twl4030.c +++ b/sound/soc/codecs/twl4030.c @@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec) struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev); struct device_node *twl4030_codec_node = NULL; - twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node, + twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node, "codec"); if (!pdata && twl4030_codec_node) { @@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec) GFP_KERNEL); if (!pdata) { dev_err(codec->dev, "Can not allocate memory\n"); + of_node_put(twl4030_codec_node); return NULL; } twl4030_setup_pdata_of(pdata, twl4030_codec_node); + of_node_put(twl4030_codec_node); } return pdata; diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index 95d2392303eb..7ca67613e0d4 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -1408,12 +1408,6 @@ static int fsl_ssi_probe(struct platform_device *pdev) sizeof(fsl_ssi_ac97_dai)); fsl_ac97_data = ssi_private; - - ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev); - if (ret) { - dev_err(&pdev->dev, "could not set AC'97 ops\n"); - return ret; - } } else { /* Initialize this copy of the CPU DAI driver structure */ memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template, @@ -1473,6 +1467,14 @@ static int fsl_ssi_probe(struct platform_device *pdev) return ret; } + if (fsl_ssi_is_ac97(ssi_private)) { + ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev); + if (ret) { + dev_err(&pdev->dev, "could not set AC'97 ops\n"); + goto error_ac97_ops; + } + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component, &ssi_private->cpu_dai_drv, 1); if (ret) { @@ -1556,6 +1558,10 @@ error_sound_card: fsl_ssi_debugfs_remove(&ssi_private->dbg_stats); error_asoc_register: + if (fsl_ssi_is_ac97(ssi_private)) + snd_soc_set_ac97_ops(NULL); + +error_ac97_ops: if (ssi_private->soc->imx) fsl_ssi_imx_clean(pdev, ssi_private); diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 0ed9ae030ce1..c9ae29068c7c 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2101,20 +2101,25 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid, kctl->private_value = (unsigned long)namelist; kctl->private_free = usb_mixer_selector_elem_free; - nameid = uac_selector_unit_iSelector(desc); + /* check the static mapping table at first */ len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name)); - if (len) - ; - else if (nameid) - len = snd_usb_copy_string_desc(state, nameid, kctl->id.name, - sizeof(kctl->id.name)); - else - len = get_term_name(state, &state->oterm, - kctl->id.name, sizeof(kctl->id.name), 0); - if (!len) { - strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* no mapping ? */ + /* if iSelector is given, use it */ + nameid = uac_selector_unit_iSelector(desc); + if (nameid) + len = snd_usb_copy_string_desc(state, nameid, + kctl->id.name, + sizeof(kctl->id.name)); + /* ... or pick up the terminal name at next */ + if (!len) + len = get_term_name(state, &state->oterm, + kctl->id.name, sizeof(kctl->id.name), 0); + /* ... or use the fixed string "USB" as the last resort */ + if (!len) + strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* and add the proper suffix */ if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR) append_ctl_name(kctl, " Clock Source"); else if ((state->oterm.type & 0xff00) == 0x0100) diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c index 2b3d6d235015..3d7b42e77299 100644 --- a/tools/usb/usbip/src/utils.c +++ b/tools/usb/usbip/src/utils.c @@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add) char command[SYSFS_BUS_ID_SIZE + 4]; char match_busid_attr_path[SYSFS_PATH_MAX]; int rc; + int cmd_size; snprintf(match_busid_attr_path, sizeof(match_busid_attr_path), "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME, @@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add) attr_name); if (add) - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", + busid); else - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", + busid); rc = write_sysfs_attribute(match_busid_attr_path, command, - sizeof(command)); + cmd_size); if (rc < 0) { dbg("failed to write match_busid: %s", strerror(errno)); return -1; |