[PATCH 10/11] x86/mm: enable AMD translation cache extensions

[Rik van Riel <riel@surriel.com>]

With AMD TCE (translation cache extensions) only the intermediate mappings
that cover the address range zapped by INVLPG / INVLPGB get invalidated,
rather than all intermediate mappings getting zapped at every TLB invalidation.

This can help reduce the TLB miss rate, by keeping more intermediate
mappings in the cache.

From the AMD manual:

Translation Cache Extension (TCE) Bit. Bit 15, read/write. Setting this bit
to 1 changes how the INVLPG, INVLPGB, and INVPCID instructions operate on
TLB entries. When this bit is 0, these instructions remove the target PTE
from the TLB as well as all upper-level table entries that are cached
in the TLB, whether or not they are associated with the target PTE.
When this bit is set, these instructions will remove the target PTE and
only those upper-level entries that lead to the target PTE in
the page table hierarchy, leaving unrelated upper-level entries intact.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 arch/x86/kernel/cpu/amd.c |  8 ++++++++
 arch/x86/mm/tlb.c         | 10 +++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 226b8fc64bfc..4dc42705aaca 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1143,6 +1143,14 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	/* Max number of pages INVLPGB can invalidate in one shot */
 	invlpgb_count_max = (edx & 0xffff) + 1;
+
+	/* If supported, enable translation cache extensions (TCE) */
+	cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+	if (ecx & BIT(17)) {
+		u64 msr = native_read_msr(MSR_EFER);;
+		msr |= BIT(15);
+		wrmsrl(MSR_EFER, msr);
+	}
 }
 
 static const struct cpu_dev amd_cpu_dev = {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c5459516a72e..f1e2358616e5 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -480,7 +480,7 @@ static void broadcast_tlb_flush(struct flush_tlb_info *info)
 	if (info->stride_shift > PMD_SHIFT)
 		maxnr = 1;
 
-	if (info->end == TLB_FLUSH_ALL) {
+	if (info->end == TLB_FLUSH_ALL || info->freed_tables) {
 		invlpgb_flush_single_pcid(kern_pcid(asid));
 		/* Do any CPUs supporting INVLPGB need PTI? */
 		if (static_cpu_has(X86_FEATURE_PTI))
@@ -1113,7 +1113,7 @@ static void flush_tlb_func(void *info)
 	 *
 	 * The only question is whether to do a full or partial flush.
 	 *
-	 * We do a partial flush if requested and two extra conditions
+	 * We do a partial flush if requested and three extra conditions
 	 * are met:
 	 *
 	 * 1. f->new_tlb_gen == local_tlb_gen + 1.  We have an invariant that
@@ -1140,10 +1140,14 @@ static void flush_tlb_func(void *info)
 	 *    date.  By doing a full flush instead, we can increase
 	 *    local_tlb_gen all the way to mm_tlb_gen and we can probably
 	 *    avoid another flush in the very near future.
+	 *
+	 * 3. No page tables were freed. If page tables were freed, a full
+	 *    flush ensures intermediate translations in the TLB get flushed.
 	 */
 	if (f->end != TLB_FLUSH_ALL &&
 	    f->new_tlb_gen == local_tlb_gen + 1 &&
-	    f->new_tlb_gen == mm_tlb_gen) {
+	    f->new_tlb_gen == mm_tlb_gen &&
+	    !f->freed_tables) {
 		/* Partial flush */
 		unsigned long addr = f->start;
 
-- 
2.47.1