diff mbox series

[v9,12/12] x86/mm: only invalidate final translations with INVLPGB

Message ID 20250206044346.3810242-13-riel@surriel.com (mailing list archive)
State New
Headers show
Series AMD broadcast TLB invalidation | expand

Commit Message

Rik van Riel Feb. 6, 2025, 4:43 a.m. UTC 
Use the INVLPGB_FINAL_ONLY flag when invalidating mappings with INVPLGB.
This way only leaf mappings get removed from the TLB, leaving intermediate
translations cached.

On the (rare) occasions where we free page tables we do a full flush,
ensuring intermediate translations get flushed from the TLB.

Signed-off-by: Rik van Riel <riel@surriel.com>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
---
 arch/x86/include/asm/invlpgb.h | 10 ++++++++--
 arch/x86/mm/tlb.c              | 13 +++++++------
 2 files changed, 15 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/include/asm/invlpgb.h b/arch/x86/include/asm/invlpgb.h
index 357e3cc417e4..9df559974f78 100644
--- a/arch/x86/include/asm/invlpgb.h
+++ b/arch/x86/include/asm/invlpgb.h
@@ -66,9 +66,15 @@  static inline void invlpgb_flush_user(unsigned long pcid,
 static inline void __invlpgb_flush_user_nr_nosync(unsigned long pcid,
 						  unsigned long addr,
 						  u16 nr,
-						  bool pmd_stride)
+						  bool pmd_stride,
+						  bool freed_tables)
 {
-	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
+	u8 flags = INVLPGB_PCID | INVLPGB_VA;
+
+	if (!freed_tables)
+		flags |= INVLPGB_FINAL_ONLY;
+
+	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, flags);
 }
 
 /* Flush all mappings for a given PCID, not including globals. */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4253c3efd7e4..b9aa5ab1b1af 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -498,9 +498,10 @@  static inline void tlbsync(void)
 
 static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
 						unsigned long addr,
-						u16 nr, bool pmd_stride)
+						u16 nr, bool pmd_stride,
+						bool freed_tables)
 {
-	__invlpgb_flush_user_nr_nosync(pcid, addr, nr, pmd_stride);
+	__invlpgb_flush_user_nr_nosync(pcid, addr, nr, pmd_stride, freed_tables);
 	if (!this_cpu_read(cpu_tlbstate.need_tlbsync))
 		this_cpu_write(cpu_tlbstate.need_tlbsync, true);
 }
@@ -549,10 +550,10 @@  static void broadcast_tlb_flush(struct flush_tlb_info *info)
 		nr = min(maxnr, (info->end - addr) >> info->stride_shift);
 		nr = max(nr, 1);
 
-		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd, info->freed_tables);
 		/* Do any CPUs supporting INVLPGB need PTI? */
 		if (static_cpu_has(X86_FEATURE_PTI))
-			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd, info->freed_tables);
 
 		addr += nr << info->stride_shift;
 	} while (addr < info->end);
@@ -1715,10 +1716,10 @@  void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
 	u16 asid = mm_global_asid(mm);
 
 	if (asid) {
-		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false);
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false, false);
 		/* Do any CPUs supporting INVLPGB need PTI? */
 		if (static_cpu_has(X86_FEATURE_PTI))
-			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false);
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false, false);
 
 		/*
 		 * Some CPUs might still be using a local ASID for this