[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <efe7eb41-e23d-bf22-50f7-73f47bab4d5e@oracle.com>
Date: Thu, 27 Feb 2020 09:51:29 +0100
From: Alexandre Chartre <alexandre.chartre@...cle.com>
To: Ira Weiny <ira.weiny@...el.com>
Cc: rkrcmar@...hat.com, tglx@...utronix.de, mingo@...hat.com,
bp@...en8.de, hpa@...or.com, dave.hansen@...ux.intel.com,
luto@...nel.org, peterz@...radead.org, x86@...nel.org,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
pbonzini@...hat.com, konrad.wilk@...cle.com,
jan.setjeeilers@...cle.com, liran.alon@...cle.com,
junaids@...gle.com, graf@...zon.de, rppt@...ux.vnet.ibm.com,
kuzuno@...il.com, mgross@...ux.intel.com
Subject: Re: [RFC PATCH v3 2/7] mm/asi: ASI entry/exit interface
On 2/26/20 11:02 PM, Ira Weiny wrote:
> On Wed, Feb 26, 2020 at 05:21:55PM +0100, Alexandre Chartre wrote:
>> Address Space Isolation (ASI) is entered by calling asi_enter() which
>> switches the kernel page-table to the ASI page-table. Isolation is then
>> exited by calling asi_exit() which switches the page-table back to the
>> original kernel page-table.
>>
>> The ASI being used and its state is tracked in a per-cpu ASI session
>> structure (struct asi_session).
>>
>> Signed-off-by: Alexandre Chartre <alexandre.chartre@...cle.com>
>> ---
>> arch/x86/include/asm/asi.h | 4 ++
>> arch/x86/include/asm/asi_session.h | 17 +++++++
>> arch/x86/include/asm/mmu_context.h | 19 +++++++-
>> arch/x86/include/asm/tlbflush.h | 12 +++++
>> arch/x86/mm/asi.c | 90 ++++++++++++++++++++++++++++++++++++
>> 5 files changed, 140 insertions(+), 2 deletions(-)
>> create mode 100644 arch/x86/include/asm/asi_session.h
>>
>> diff --git a/arch/x86/include/asm/asi.h b/arch/x86/include/asm/asi.h
>> index 844a81f..29b745a 100644
>> --- a/arch/x86/include/asm/asi.h
>> +++ b/arch/x86/include/asm/asi.h
>> @@ -44,6 +44,8 @@
>>
>> #include <linux/export.h>
>>
>> +#include <asm/asi_session.h>
>> +
>> struct asi_type {
>> int pcid_prefix; /* PCID prefix */
>> };
>> @@ -80,6 +82,8 @@ struct asi {
>> extern struct asi *asi_create(struct asi_type *type);
>> extern void asi_destroy(struct asi *asi);
>> extern void asi_set_pagetable(struct asi *asi, pgd_t *pagetable);
>> +extern int asi_enter(struct asi *asi);
>> +extern void asi_exit(struct asi *asi);
>>
>> #endif /* __ASSEMBLY__ */
>>
>> diff --git a/arch/x86/include/asm/asi_session.h b/arch/x86/include/asm/asi_session.h
>> new file mode 100644
>> index 0000000..9d39c93
>> --- /dev/null
>> +++ b/arch/x86/include/asm/asi_session.h
>> @@ -0,0 +1,17 @@
>> +/* SPDX-License-Identifier: GPL-2.0 */
>> +#ifndef ARCH_X86_MM_ASI_SESSION_H
>> +#define ARCH_X86_MM_ASI_SESSION_H
>> +
>> +#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
>> +
>> +struct asi;
>> +
>> +struct asi_session {
>> + struct asi *asi; /* ASI for this session */
>> + unsigned long isolation_cr3; /* cr3 when ASI is active */
>> + unsigned long original_cr3; /* cr3 before entering ASI */
>> +};
>> +
>> +#endif /* CONFIG_ADDRESS_SPACE_ISOLATION */
>> +
>> +#endif
>> diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
>> index 5f33924..2d65443 100644
>> --- a/arch/x86/include/asm/mmu_context.h
>> +++ b/arch/x86/include/asm/mmu_context.h
>> @@ -14,6 +14,7 @@
>> #include <asm/paravirt.h>
>> #include <asm/mpx.h>
>> #include <asm/debugreg.h>
>> +#include <asm/asi.h>
>>
>> extern atomic64_t last_mm_ctx_id;
>>
>> @@ -349,8 +350,22 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
>> */
>> static inline unsigned long __get_current_cr3_fast(void)
>> {
>> - unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
>> - this_cpu_read(cpu_tlbstate.loaded_mm_asid));
>> + unsigned long cr3;
>> +
>> + /*
>> + * If isolation is active then we need to return the CR3 for the
>> + * currently active ASI. This value is stored in the isolation_cr3
>> + * field of the ASI session.
>> + */
>> + if (IS_ENABLED(CONFIG_ADDRESS_SPACE_ISOLATION) &&
>> + this_cpu_read(cpu_asi_session.asi)) {
>> + cr3 = this_cpu_read(cpu_asi_session.isolation_cr3);
>> + /* CR3 read never returns with the NOFLUSH bit */
>> + cr3 &= ~X86_CR3_PCID_NOFLUSH;
>> + } else {
>> + cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
>> + this_cpu_read(cpu_tlbstate.loaded_mm_asid));
>> + }
>>
>> /* For now, be very restrictive about when this can be called. */
>> VM_WARN_ON(in_nmi() || preemptible());
>> diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
>> index 6f66d84..241058f 100644
>> --- a/arch/x86/include/asm/tlbflush.h
>> +++ b/arch/x86/include/asm/tlbflush.h
>> @@ -12,6 +12,7 @@
>> #include <asm/invpcid.h>
>> #include <asm/pti.h>
>> #include <asm/processor-flags.h>
>> +#include <asm/asi.h>
>>
>> /*
>> * The x86 feature is called PCID (Process Context IDentifier). It is similar
>> @@ -239,9 +240,20 @@ struct tlb_state {
>> * context 0.
>> */
>> struct tlb_context ctxs[TLB_NR_DYN_ASIDS];
>> +
>> +#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
>> + /*
>> + * The ASI session tracks the ASI being used and its state.
>> + */
>> + struct asi_session asi_session;
>> +#endif
>> };
>> DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
>>
>> +#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
>> +#define cpu_asi_session (cpu_tlbstate.asi_session)
>> +#endif
>> +
>> /*
>> * Blindly accessing user memory from NMI context can be dangerous
>> * if we're in the middle of switching the current user task or
>> diff --git a/arch/x86/mm/asi.c b/arch/x86/mm/asi.c
>> index 0a0ac9d..9fbc921 100644
>> --- a/arch/x86/mm/asi.c
>> +++ b/arch/x86/mm/asi.c
>> @@ -10,6 +10,8 @@
>>
>> #include <asm/asi.h>
>> #include <asm/bug.h>
>> +#include <asm/mmu_context.h>
>> +#include <asm/tlbflush.h>
>>
>> struct asi *asi_create(struct asi_type *type)
>> {
>> @@ -58,3 +60,91 @@ void asi_set_pagetable(struct asi *asi, pgd_t *pagetable)
>>
>> }
>> EXPORT_SYMBOL(asi_set_pagetable);
>> +
>> +static void asi_switch_to_asi_cr3(struct asi *asi)
>> +{
>> + unsigned long original_cr3, asi_cr3;
>> + struct asi_session *asi_session;
>> + u16 pcid;
>> +
>> + WARN_ON(!irqs_disabled());
>> +
>> + original_cr3 = __get_current_cr3_fast();
>> +
>> + /* build the ASI cr3 value */
>> + asi_cr3 = asi->base_cr3;
>> + if (boot_cpu_has(X86_FEATURE_PCID)) {
>> + pcid = original_cr3 & ASI_KERNEL_PCID_MASK;
>> + asi_cr3 |= pcid;
>> + }
>> +
>> + /* get the ASI session ready for entering ASI */
>> + asi_session = &get_cpu_var(cpu_asi_session);
>> + asi_session->asi = asi;
>> + asi_session->original_cr3 = original_cr3;
>> + asi_session->isolation_cr3 = asi_cr3;
>> +
>> + /* Update CR3 to immediately enter ASI */
>> + native_write_cr3(asi_cr3);
>> +}
>> +
>> +static void asi_switch_to_kernel_cr3(struct asi *asi)
>
> asi is not used in this function?
>
You are right, I was probably using it in a previous version of the code
and forgot to remote it. I will remove it.
>> +{
>> + struct asi_session *asi_session;
>> + unsigned long original_cr3;
>> +
>> + WARN_ON(!irqs_disabled());
>> +
>> + original_cr3 = this_cpu_read(cpu_asi_session.original_cr3);
>> + if (boot_cpu_has(X86_FEATURE_PCID))
>> + original_cr3 |= X86_CR3_PCID_NOFLUSH;
>> + native_write_cr3(original_cr3);
>> +
>> + asi_session = &get_cpu_var(cpu_asi_session);
>> + asi_session->asi = NULL;
>> +}
>> +
>> +int asi_enter(struct asi *asi)
>> +{
>> + struct asi *current_asi;
>> + unsigned long flags;
>> +
>> + /*
>> + * We can re-enter isolation, but only with the same ASI (we don't
>> + * support nesting isolation).
>> + */
>> + current_asi = this_cpu_read(cpu_asi_session.asi);
>> + if (current_asi) {
>> + if (current_asi != asi) {
>> + WARN_ON(1);
>> + return -EBUSY;
>> + }
>
> if (WARN_ON(current_asi != asi)) {
> return -EBUSY;
>
Yes, much better, will change.
Thanks,
alex.
>
>> + return 0;
>> + }
>> +
>> + local_irq_save(flags);
>> + asi_switch_to_asi_cr3(asi);
>> + local_irq_restore(flags);
>> +
>> + return 0;
>> +}
>> +EXPORT_SYMBOL(asi_enter);
>> +
>> +void asi_exit(struct asi *asi)
>> +{
>> + struct asi *current_asi;
>> + unsigned long flags;
>> +
>> + current_asi = this_cpu_read(cpu_asi_session.asi);
>> + if (!current_asi) {
>> + /* already exited */
>> + return;
>> + }
>> +
>> + WARN_ON(current_asi != asi);
>> +
>> + local_irq_save(flags);
>> + asi_switch_to_kernel_cr3(asi);
>> + local_irq_restore(flags);
>> +}
>> +EXPORT_SYMBOL(asi_exit);
>> --
>> 1.7.1
>>
>>
>
Powered by blists - more mailing lists