[PATCH 04/11] x86/mm: add INVLPGB support code

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

Add invlpgb.h with the helper functions and definitions needed to use
broadcast TLB invalidation on AMD EPYC 3 and newer CPUs.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 arch/x86/include/asm/invlpgb.h  | 93 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/tlbflush.h |  1 +
 2 files changed, 94 insertions(+)
 create mode 100644 arch/x86/include/asm/invlpgb.h

diff --git a/arch/x86/include/asm/invlpgb.h b/arch/x86/include/asm/invlpgb.h
new file mode 100644
index 000000000000..862775897a54
--- /dev/null
+++ b/arch/x86/include/asm/invlpgb.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVLPGB
+#define _ASM_X86_INVLPGB
+
+#include <vdso/bits.h>
+
+/*
+ * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
+ *
+ * The INVLPGB instruction is weakly ordered, and a batch of invalidations can
+ * be done in a parallel fashion.
+ *
+ * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from
+ * this CPU have completed.
+ */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid, unsigned long addr,
+			    int extra_count, bool pmd_stride, unsigned long flags)
+{
+	u64 rax = addr | flags;
+	u32 ecx = (pmd_stride << 31) | extra_count;
+	u32 edx = (pcid << 16) | asid;
+
+	asm volatile("invlpgb" : : "a" (rax), "c" (ecx), "d" (edx));
+}
+
+/*
+ * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
+ * of the three. For example:
+ * - INVLPGB_VA | INVLPGB_INCLUDE_GLOBAL: invalidate all TLB entries at the address
+ * - INVLPGB_PCID:              	  invalidate all TLB entries matching the PCID
+ *
+ * The first can be used to invalidate (kernel) mappings at a particular
+ * address across all processes.
+ *
+ * The latter invalidates all TLB entries matching a PCID.
+ */
+#define INVLPGB_VA			BIT(0)
+#define INVLPGB_PCID			BIT(1)
+#define INVLPGB_ASID			BIT(2)
+#define INVLPGB_INCLUDE_GLOBAL		BIT(3)
+#define INVLPGB_FINAL_ONLY		BIT(4)
+#define INVLPGB_INCLUDE_NESTED		BIT(5)
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invlpgb_flush_user(unsigned long pcid,
+				      unsigned long addr)
+{
+	__invlpgb(0, pcid, addr, 0, 0, INVLPGB_PCID | INVLPGB_VA);
+}
+
+static inline void invlpgb_flush_user_nr(unsigned long pcid, unsigned long addr,
+					 int nr, bool pmd_stride)
+{
+	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
+}
+
+/* Flush all mappings for a given ASID, not including globals. */
+static inline void invlpgb_flush_single_asid(unsigned long asid)
+{
+	__invlpgb(asid, 0, 0, 0, 0, INVLPGB_ASID);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invlpgb_flush_single_pcid(unsigned long pcid)
+{
+	__invlpgb(0, pcid, 0, 0, 0, INVLPGB_PCID);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invlpgb_flush_all(void)
+{
+	__invlpgb(0, 0, 0, 0, 0, INVLPGB_INCLUDE_GLOBAL);
+}
+
+/* Flush addr, including globals, for all PCIDs. */
+static inline void invlpgb_flush_addr(unsigned long addr, int nr)
+{
+	__invlpgb(0, 0, addr, nr - 1, 0, INVLPGB_INCLUDE_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invlpgb_flush_all_nonglobals(void)
+{
+	__invlpgb(0, 0, 0, 0, 0, 0);
+}
+
+/* Wait for INVLPGB originated by this CPU to complete. */
+static inline void tlbsync(void)
+{
+	asm volatile("tlbsync");
+}
+
+#endif /* _ASM_X86_INVLPGB */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 7d1468a3967b..20074f17fbcd 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -10,6 +10,7 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invlpgb.h>
 #include <asm/invpcid.h>
 #include <asm/pti.h>
 #include <asm/processor-flags.h>
-- 
2.47.1