linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>
Cc: x86@kernel.org, Kostya Serebryany <kcc@google.com>,
	Andrey Ryabinin <ryabinin.a.a@gmail.com>,
	Andrey Konovalov <andreyknvl@gmail.com>,
	Alexander Potapenko <glider@google.com>,
	Taras Madan <tarasmadan@google.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	"H . J . Lu" <hjl.tools@gmail.com>,
	Andi Kleen <ak@linux.intel.com>,
	Rick Edgecombe <rick.p.edgecombe@intel.com>,
	Bharata B Rao <bharata@amd.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Ashok Raj <ashok.raj@intel.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv9 04/14] x86/mm: Handle LAM on context switch
Date: Fri, 30 Sep 2022 17:47:48 +0300	[thread overview]
Message-ID: <20220930144758.30232-5-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20220930144758.30232-1-kirill.shutemov@linux.intel.com>

Linear Address Masking mode for userspace pointers encoded in CR3 bits.
The mode is selected per-process and stored in mm_context_t.

switch_mm_irqs_off() now respects selected LAM mode and constructs CR3
accordingly.

The active LAM mode gets recorded in the tlb_state.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alexander Potapenko <glider@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/mmu.h         |  3 ++
 arch/x86/include/asm/mmu_context.h | 24 +++++++++++++++
 arch/x86/include/asm/tlbflush.h    | 35 ++++++++++++++++++++++
 arch/x86/mm/tlb.c                  | 48 ++++++++++++++++++++----------
 4 files changed, 94 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5d7494631ea9..002889ca8978 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -40,6 +40,9 @@ typedef struct {
 
 #ifdef CONFIG_X86_64
 	unsigned short flags;
+
+	/* Active LAM mode:  X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
+	unsigned long lam_cr3_mask;
 #endif
 
 	struct mutex lock;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index b8d40ddeab00..69c943b2ae90 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -91,6 +91,29 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 }
 #endif
 
+#ifdef CONFIG_X86_64
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+	return mm->context.lam_cr3_mask;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask;
+}
+
+#else
+
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+}
+#endif
+
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
@@ -168,6 +191,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	arch_dup_pkeys(oldmm, mm);
 	paravirt_arch_dup_mmap(oldmm, mm);
+	dup_lam(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cda3118f3b27..1ad080163363 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -101,6 +101,16 @@ struct tlb_state {
 	 */
 	bool invalidate_other;
 
+#ifdef CONFIG_X86_64
+	/*
+	 * Active LAM mode.
+	 *
+	 * X86_CR3_LAM_U57/U48 shifted right by X86_CR3_LAM_U57_BIT or 0 if LAM
+	 * disabled.
+	 */
+	u8 lam;
+#endif
+
 	/*
 	 * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
 	 * the corresponding user PCID needs a flush next time we
@@ -357,6 +367,30 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
 }
 #define huge_pmd_needs_flush huge_pmd_needs_flush
 
+#ifdef CONFIG_X86_64
+static inline unsigned long tlbstate_lam_cr3_mask(void)
+{
+	unsigned long lam = this_cpu_read(cpu_tlbstate.lam);
+
+	return lam << X86_CR3_LAM_U57_BIT;
+}
+
+static inline void set_tlbstate_cr3_lam_mask(unsigned long mask)
+{
+	this_cpu_write(cpu_tlbstate.lam, mask >> X86_CR3_LAM_U57_BIT);
+}
+
+#else
+
+static inline unsigned long tlbstate_lam_cr3_mask(void)
+{
+	return 0;
+}
+
+static inline void set_tlbstate_cr3_lam_mask(u64 mask)
+{
+}
+#endif
 #endif /* !MODULE */
 
 static inline void __native_tlb_flush_global(unsigned long cr4)
@@ -364,4 +398,5 @@ static inline void __native_tlb_flush_global(unsigned long cr4)
 	native_write_cr4(cr4 ^ X86_CR4_PGE);
 	native_write_cr4(cr4);
 }
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c1e31e9a85d7..d6c9c15d2ad2 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -154,26 +154,30 @@ static inline u16 user_pcid(u16 asid)
 	return ret;
 }
 
-static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid, unsigned long lam)
 {
+	unsigned long cr3 = __sme_pa(pgd) | lam;
+
 	if (static_cpu_has(X86_FEATURE_PCID)) {
-		return __sme_pa(pgd) | kern_pcid(asid);
+		VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+		cr3 |= kern_pcid(asid);
 	} else {
 		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(pgd);
 	}
+
+	return cr3;
 }
 
-static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid,
+					      unsigned long lam)
 {
-	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
 	/*
 	 * Use boot_cpu_has() instead of this_cpu_has() as this function
 	 * might be called during early boot. This should work even after
 	 * boot because all CPU's the have same capabilities:
 	 */
 	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
-	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
+	return build_cr3(pgd, asid, lam) | CR3_NOFLUSH;
 }
 
 /*
@@ -274,15 +278,16 @@ static inline void invalidate_user_asid(u16 asid)
 		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
 }
 
-static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam,
+			    bool need_flush)
 {
 	unsigned long new_mm_cr3;
 
 	if (need_flush) {
 		invalidate_user_asid(new_asid);
-		new_mm_cr3 = build_cr3(pgdir, new_asid);
+		new_mm_cr3 = build_cr3(pgdir, new_asid, lam);
 	} else {
-		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid, lam);
 	}
 
 	/*
@@ -491,6 +496,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	unsigned long prev_lam = tlbstate_lam_cr3_mask();
+	unsigned long new_lam = mm_lam_cr3_mask(next);
 	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
@@ -520,7 +527,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * isn't free.
 	 */
 #ifdef CONFIG_DEBUG_VM
-	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid, prev_lam))) {
 		/*
 		 * If we were to BUG here, we'd be very likely to kill
 		 * the system so hard that we don't see the call trace.
@@ -554,6 +561,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	if (real_prev == next) {
 		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
+		VM_WARN_ON(prev_lam != new_lam);
 
 		/*
 		 * Even in lazy TLB mode, the CPU should stay set in the
@@ -622,15 +630,16 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		barrier();
 	}
 
+	set_tlbstate_cr3_lam_mask(new_lam);
 	if (need_flush) {
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-		load_new_mm_cr3(next->pgd, new_asid, true);
+		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
-		load_new_mm_cr3(next->pgd, new_asid, false);
+		load_new_mm_cr3(next->pgd, new_asid, new_lam, false);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
@@ -691,6 +700,10 @@ void initialize_tlbstate_and_flush(void)
 	/* Assert that CR3 already references the right mm. */
 	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
 
+	/* LAM expected to be disabled in CR3 and init_mm */
+	WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
+	WARN_ON(mm_lam_cr3_mask(&init_mm));
+
 	/*
 	 * Assert that CR4.PCIDE is set if needed.  (CR4.PCIDE initialization
 	 * doesn't work like other CR4 bits because it can only be set from
@@ -699,8 +712,8 @@ void initialize_tlbstate_and_flush(void)
 	WARN_ON(boot_cpu_has(X86_FEATURE_PCID) &&
 		!(cr4_read_shadow() & X86_CR4_PCIDE));
 
-	/* Force ASID 0 and force a TLB flush. */
-	write_cr3(build_cr3(mm->pgd, 0));
+	/* Disable LAM, force ASID 0 and force a TLB flush. */
+	write_cr3(build_cr3(mm->pgd, 0, 0));
 
 	/* Reinitialize tlbstate. */
 	this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
@@ -708,6 +721,7 @@ void initialize_tlbstate_and_flush(void)
 	this_cpu_write(cpu_tlbstate.next_asid, 1);
 	this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);
 	this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen);
+	set_tlbstate_cr3_lam_mask(0);
 
 	for (i = 1; i < TLB_NR_DYN_ASIDS; i++)
 		this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0);
@@ -1071,8 +1085,10 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
  */
 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 =
+		build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
+			  this_cpu_read(cpu_tlbstate.loaded_mm_asid),
+			  tlbstate_lam_cr3_mask());
 
 	/* For now, be very restrictive about when this can be called. */
 	VM_WARN_ON(in_nmi() || preemptible());
-- 
2.35.1



  parent reply	other threads:[~2022-09-30 14:48 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-30 14:47 [PATCHv9 00/14] Linear Address Masking enabling Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 01/14] x86/mm: Fix CR3_ADDR_MASK Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 02/14] x86: CPUID and CR3/CR4 flags for Linear Address Masking Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 03/14] mm: Pass down mm_struct to untagged_addr() Kirill A. Shutemov
2022-09-30 14:47 ` Kirill A. Shutemov [this message]
2022-09-30 14:47 ` [PATCHv9 05/14] x86/uaccess: Provide untagged_addr() and remove tags before address check Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 06/14] KVM: Serialize tagged address check against tagging enabling Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 07/14] x86/mm: Provide arch_prctl() interface for LAM Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 08/14] x86/mm: Reduce untagged_addr() overhead until the first LAM user Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 09/14] x86: Expose untagging mask in /proc/$PID/arch_status Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 10/14] x86/mm, iommu/sva: Make LAM and SVM mutually exclusive Kirill A. Shutemov
2022-10-10 21:24   ` Jacob Pan
2022-09-30 14:47 ` [PATCHv9 11/14] selftests/x86/lam: Add malloc and tag-bits test cases for linear-address masking Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 12/14] selftests/x86/lam: Add mmap and SYSCALL " Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 13/14] selftests/x86/lam: Add io_uring " Kirill A. Shutemov
2022-09-30 14:47 ` [PATCHv9 14/14] selftests/x86/lam: Add inherit " Kirill A. Shutemov
2022-10-06 13:58 ` [PATCHv9 00/14] Linear Address Masking enabling Alexander Potapenko
2022-10-06 16:41   ` Kirill A. Shutemov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220930144758.30232-5-kirill.shutemov@linux.intel.com \
    --to=kirill.shutemov@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=andreyknvl@gmail.com \
    --cc=ashok.raj@intel.com \
    --cc=bharata@amd.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dvyukov@google.com \
    --cc=glider@google.com \
    --cc=hjl.tools@gmail.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=kcc@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=ryabinin.a.a@gmail.com \
    --cc=tarasmadan@google.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).