From 735a6dd02222d8d070c7bb748f25895239ca8c92 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Feb 2020 15:16:15 -0800 Subject: x86/pkeys: Manually set X86_FEATURE_OSPKE to preserve existing changes Explicitly set X86_FEATURE_OSPKE via set_cpu_cap() instead of calling get_cpu_cap() to pull the feature bit from CPUID after enabling CR4.PKE. Invoking get_cpu_cap() effectively wipes out any {set,clear}_cpu_cap() changes that were made between this_cpu->c_init() and setup_pku(), as all non-synthetic feature words are reinitialized from the CPU's CPUID values. Blasting away capability updates manifests most visibility when running on a VMX capable CPU, but with VMX disabled by BIOS. To indicate that VMX is disabled, init_ia32_feat_ctl() clears X86_FEATURE_VMX, using clear_cpu_cap() instead of setup_clear_cpu_cap() so that KVM can report which CPU is misconfigured (KVM needs to probe every CPU anyways). Restoring X86_FEATURE_VMX from CPUID causes KVM to think VMX is enabled, ultimately leading to an unexpected #GP when KVM attempts to do VMXON. Arguably, init_ia32_feat_ctl() should use setup_clear_cpu_cap() and let KVM figure out a different way to report the misconfigured CPU, but VMX is not the only feature bit that is affected, i.e. there is precedent that tweaking feature bits via {set,clear}_cpu_cap() after ->c_init() is expected to work. Most notably, x86_init_rdrand()'s clearing of X86_FEATURE_RDRAND when RDRAND malfunctions is also overwritten. Fixes: 0697694564c8 ("x86/mm/pkeys: Actually enable Memory Protection Keys in the CPU") Reported-by: Jacob Keller Signed-off-by: Sean Christopherson Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Tested-by: Jacob Keller Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200226231615.13664-1-sean.j.christopherson@intel.com --- arch/x86/kernel/cpu/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 52c9bfbbdb2a..4cdb123ff66a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -445,7 +445,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS -- cgit v1.2.3-59-g8ed1b From 99bcd4a6e5b8ba201fdd252f1054689884899fee Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 18 Feb 2020 16:47:12 +0100 Subject: x86/ioperm: Add new paravirt function update_io_bitmap() Commit 111e7b15cf10f6 ("x86/ioperm: Extend IOPL config to control ioperm() as well") reworked the iopl syscall to use I/O bitmaps. Unfortunately this broke Xen PV domains using that syscall as there is currently no I/O bitmap support in PV domains. Add I/O bitmap support via a new paravirt function update_io_bitmap which Xen PV domains can use to update their I/O bitmaps via a hypercall. Fixes: 111e7b15cf10f6 ("x86/ioperm: Extend IOPL config to control ioperm() as well") Reported-by: Jan Beulich Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Tested-by: Jan Beulich Reviewed-by: Jan Beulich Cc: # 5.5 Link: https://lkml.kernel.org/r/20200218154712.25490-1-jgross@suse.com --- arch/x86/include/asm/io_bitmap.h | 9 ++++++++- arch/x86/include/asm/paravirt.h | 7 +++++++ arch/x86/include/asm/paravirt_types.h | 4 ++++ arch/x86/kernel/paravirt.c | 5 +++++ arch/x86/kernel/process.c | 2 +- arch/x86/xen/enlighten_pv.c | 25 +++++++++++++++++++++++++ 6 files changed, 50 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 02c6ef8f7667..07344d82e88e 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,7 +19,14 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(void); -void tss_update_io_bitmap(void); +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#endif + #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 86e7317eb31f..694d8daf4983 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -295,6 +295,13 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(cpu.update_io_bitmap); +} +#endif + static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 84812964d3dd..732f62e04ddb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -140,6 +140,10 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); +#ifdef CONFIG_X86_IOPL_IOPERM + void (*update_io_bitmap)(void); +#endif + void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89de..c131ba4e70ef 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7..3053c85e0e42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 79409120a603..507f4fb88fa7 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -72,6 +72,9 @@ #include #include #include +#ifdef CONFIG_X86_IOPL_IOPERM +#include +#endif #ifdef CONFIG_ACPI #include @@ -837,6 +840,25 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } +#ifdef CONFIG_X86_IOPL_IOPERM +static void xen_update_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap; + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + + native_tss_update_io_bitmap(); + + iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + + tss->x86_tss.io_bitmap_base; + if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) + iobitmap.nr_ports = 0; + else + iobitmap.nr_ports = IO_BITMAP_BITS; + + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} +#endif + static void xen_io_delay(void) { } @@ -1047,6 +1069,9 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, +#ifdef CONFIG_X86_IOPL_IOPERM + .update_io_bitmap = xen_update_io_bitmap, +#endif .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ -- cgit v1.2.3-59-g8ed1b