From: Rik van Riel <riel@surriel.com>
To: x86@kernel.org
Cc: linux-kernel@vger.kernel.org, bp@alien8.de, peterz@infradead.org,
dave.hansen@linux.intel.com, zhengqi.arch@bytedance.com,
nadav.amit@gmail.com, thomas.lendacky@amd.com,
kernel-team@meta.com, linux-mm@kvack.org,
akpm@linux-foundation.org, jannh@google.com,
mhklinux@outlook.com, andrew.cooper3@citrix.com,
Rik van Riel <riel@surriel.com>,
Manali Shukla <Manali.Shukla@amd.com>
Subject: [PATCH v8 05/12] x86/mm: add INVLPGB support code
Date: Tue, 4 Feb 2025 20:39:54 -0500 [thread overview]
Message-ID: <20250205014033.3626204-6-riel@surriel.com> (raw)
In-Reply-To: <20250205014033.3626204-1-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>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
---
arch/x86/include/asm/invlpgb.h | 101 ++++++++++++++++++++++++++++++++
arch/x86/include/asm/tlbflush.h | 1 +
2 files changed, 102 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..a1d5dedd5217
--- /dev/null
+++ b/arch/x86/include/asm/invlpgb.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVLPGB
+#define _ASM_X86_INVLPGB
+
+#include <linux/kernel.h>
+#include <vdso/bits.h>
+#include <vdso/page.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, u16 extra_count,
+ bool pmd_stride, u8 flags)
+{
+ u32 edx = (pcid << 16) | asid;
+ u32 ecx = (pmd_stride << 31) | extra_count;
+ u64 rax = addr | flags;
+
+ /* The low bits in rax are for flags. Verify addr is clean. */
+ VM_WARN_ON_ONCE(addr & ~PAGE_MASK);
+
+ /* INVLPGB; supported in binutils >= 2.36. */
+ asm volatile(".byte 0x0f, 0x01, 0xfe" : : "a" (rax), "c" (ecx), "d" (edx));
+}
+
+/* Wait for INVLPGB originated by this CPU to complete. */
+static inline void tlbsync(void)
+{
+ cant_migrate();
+ /* TLBSYNC: supported in binutils >= 0.36. */
+ asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
+}
+
+/*
+ * 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);
+ tlbsync();
+}
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+ unsigned long addr,
+ u16 nr,
+ bool pmd_stride)
+{
+ __invlpgb(0, pcid, addr, nr - 1, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invlpgb_flush_single_pcid_nosync(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);
+ tlbsync();
+}
+
+/* Flush addr, including globals, for all PCIDs. */
+static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 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);
+ tlbsync();
+}
+
+#endif /* _ASM_X86_INVLPGB */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 8fe3b2dda507..dba5caa4a9f4 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
next prev parent reply other threads:[~2025-02-05 1:42 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-05 1:39 [PATCH v8 00/12] AMD broadcast TLB invalidation Rik van Riel
2025-02-05 1:39 ` [PATCH v8 01/12] x86/mm: make MMU_GATHER_RCU_TABLE_FREE unconditional Rik van Riel
2025-02-05 1:39 ` [PATCH v8 02/12] x86/mm: remove pv_ops.mmu.tlb_remove_table call Rik van Riel
2025-02-05 1:39 ` [PATCH v8 03/12] x86/mm: consolidate full flush threshold decision Rik van Riel
2025-02-05 12:20 ` Peter Zijlstra
2025-02-05 13:00 ` Peter Zijlstra
2025-02-05 13:52 ` Rik van Riel
2025-02-05 1:39 ` [PATCH v8 04/12] x86/mm: get INVLPGB count max from CPUID Rik van Riel
2025-02-05 1:39 ` Rik van Riel [this message]
2025-02-05 1:39 ` [PATCH v8 06/12] x86/mm: use INVLPGB for kernel TLB flushes Rik van Riel
2025-02-05 1:39 ` [PATCH v8 07/12] x86/mm: use INVLPGB in flush_tlb_all Rik van Riel
2025-02-05 1:39 ` [PATCH v8 08/12] x86/mm: use broadcast TLB flushing for page reclaim TLB flushing Rik van Riel
2025-02-05 1:39 ` [PATCH v8 09/12] x86/mm: enable broadcast TLB invalidation for multi-threaded processes Rik van Riel
2025-02-05 1:39 ` [PATCH v8 10/12] x86/mm: do targeted broadcast flushing from tlbbatch code Rik van Riel
2025-02-05 13:51 ` Peter Zijlstra
2025-02-05 14:52 ` Rik van Riel
2025-02-05 1:40 ` [PATCH v8 11/12] x86/mm: enable AMD translation cache extensions Rik van Riel
2025-02-05 1:40 ` [PATCH v8 12/12] x86/mm: only invalidate final translations with INVLPGB Rik van Riel
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=20250205014033.3626204-6-riel@surriel.com \
--to=riel@surriel.com \
--cc=Manali.Shukla@amd.com \
--cc=akpm@linux-foundation.org \
--cc=andrew.cooper3@citrix.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=jannh@google.com \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhklinux@outlook.com \
--cc=nadav.amit@gmail.com \
--cc=peterz@infradead.org \
--cc=thomas.lendacky@amd.com \
--cc=x86@kernel.org \
--cc=zhengqi.arch@bytedance.com \
/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