From: Dave Hansen <dave.hansen@intel.com>
To: Borislav Petkov <bp@alien8.de>, Rik van Riel <riel@surriel.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
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,
jackmanb@google.com, jannh@google.com, mhklinux@outlook.com,
andrew.cooper3@citrix.com, Manali.Shukla@amd.com,
mingo@kernel.org
Subject: Re: [PATCH v14 03/13] x86/mm: add INVLPGB support code
Date: Mon, 3 Mar 2025 10:41:44 -0800 [thread overview]
Message-ID: <30c721e0-338d-4172-989c-5226d584bcbc@intel.com> (raw)
In-Reply-To: <20250228194734.GGZ8IS1iFVpPzmEyYl@fat_crate.local>
[-- Attachment #1: Type: text/plain, Size: 870 bytes --]
On 2/28/25 11:47, Borislav Petkov wrote:
> @@ -157,11 +140,14 @@ index 77f52bc1578a..91c9a4da3ace 100644
> +/* Flush all mappings for all PCIDs except globals. */
> +static inline void invlpgb_flush_all_nonglobals(void)
> +{
> ++ /*
> ++ * @addr=0 means both rax[1] (valid PCID) and rax[2] (valid ASID) are clear
> ++ * so flush *any* PCID and ASID.
> ++ */
> + __invlpgb(0, 0, 0, 1, 0, 0);
> + __tlbsync();
> +}
I had a bit of an allergic reaction to all of the magic numbers.
Could we do something like the attached where we give a _few_ of the
magic numbers some symbolic names?
For instance, instead of passing around a bool for pmd_stride, this uses
an enum. It also explicitly separates things that are setting
pmd_stride=0 but are really saying "this is a 4k stride" from things
that set pmd_stride=0 but are for operations that don't _have_ a stride.
[-- Attachment #2: supportcode.patch --]
[-- Type: text/x-patch, Size: 4430 bytes --]
--- c83449680170170f55a0ab2eb498b92ce97c0624.patch 2025-03-03 10:35:47.422277335 -0800
+++ 11ce4b22643be.patch 2025-03-03 10:38:05.692509993 -0800
@@ -1,8 +1,8 @@
-commit c83449680170170f55a0ab2eb498b92ce97c0624
+commit 11ce4b22643be54b2c70cf6b4743e6b73b461814
Author: Rik van Riel <riel@surriel.com>
Date: Fri Feb 28 20:32:30 2025 +0100
- x86/mm: Add INVLPGB support code
+ x86/mm: Add INVLPGB support code
Add helper functions and definitions needed to use broadcast TLB
invalidation on AMD CPUs.
@@ -17,7 +17,7 @@
Link: https://lore.kernel.org/r/20250226030129.530345-4-riel@surriel.com
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
-index 77f52bc1578a7..5375145eb9596 100644
+index 77f52bc1578a7..3bd617c204346 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,9 @@
@@ -30,10 +30,15 @@
static inline void tlb_flush(struct mmu_gather *tlb)
{
-@@ -25,4 +28,110 @@ static inline void invlpg(unsigned long addr)
+@@ -25,4 +28,119 @@ static inline void invlpg(unsigned long addr)
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
}
++enum invlpgb_stride {
++ NO_STRIDE = 0,
++ PTE_STRIDE = 0,
++ PMD_STRIDE = 1
++};
+
+/*
+ * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
@@ -54,10 +59,10 @@
+ */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+ unsigned long addr, u16 nr_pages,
-+ bool pmd_stride, u8 flags)
++ enum invlpgb_stride stride, u8 flags)
+{
+ u32 edx = (pcid << 16) | asid;
-+ u32 ecx = (pmd_stride << 31) | (nr_pages - 1);
++ u32 ecx = (stride << 31) | (nr_pages - 1);
+ u64 rax = addr | flags;
+
+ /* The low bits in rax are for flags. Verify addr is clean. */
@@ -84,33 +89,37 @@
+/*
+ * 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
++ * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
++ * - FLAG_PCID: invalidate all TLB entries matching the PCID
+ *
-+ * The first can be used to invalidate (kernel) mappings at a particular
++ * The first is 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)
++#define INVLPGB_FLAG_VA BIT(0)
++#define INVLPGB_FLAG_PCID BIT(1)
++#define INVLPGB_FLAG_ASID BIT(2)
++#define INVLPGB_FLAG_INCLUDE_GLOBAL BIT(3)
++#define INVLPGB_FLAG_FINAL_ONLY BIT(4)
++#define INVLPGB_FLAG_INCLUDE_NESTED BIT(5)
++
++/* The implied mode when all bits are clear: */
++#define INVLPGB_MODE_ALL_NONGLOBALS 0UL
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+ unsigned long addr,
+ u16 nr,
+ bool pmd_stride)
+{
-+ __invlpgb(0, pcid, addr, nr, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
++ __invlpgb(0, pcid, addr, nr, pmd_stride, INVLPGB_FLAG_PCID |
++ INVLPGB_FLAG_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, 1, 0, INVLPGB_PCID);
++ __invlpgb(0, pcid, 0, 1, NO_STRIDE, INVLPGB_FLAG_PCID);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
@@ -123,21 +132,21 @@
+ * as it is cheaper.
+ */
+ guard(preempt)();
-+ __invlpgb(0, 0, 0, 1, 0, INVLPGB_INCLUDE_GLOBAL);
++ __invlpgb(0, 0, 0, 1, NO_STRIDE, INVLPGB_FLAG_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, 0, INVLPGB_INCLUDE_GLOBAL);
++ __invlpgb(0, 0, addr, nr, PTE_STRIDE, INVLPGB_FLAG_INCLUDE_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invlpgb_flush_all_nonglobals(void)
+{
+ guard(preempt)();
-+ __invlpgb(0, 0, 0, 1, 0, 0);
++ __invlpgb(0, 0, 0, 1, NO_STRIDE, INVLPGB_MODE_ALL_NONGLOBALS);
+ __tlbsync();
+}
#endif /* _ASM_X86_TLB_H */
next prev parent reply other threads:[~2025-03-03 18:41 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-26 3:00 [PATCH v14 00/13] AMD broadcast TLB invalidation Rik van Riel
2025-02-26 3:00 ` [PATCH v14 01/13] x86/mm: consolidate full flush threshold decision Rik van Riel
2025-09-02 15:44 ` [BUG] x86/mm: regression after 4a02ed8e1cc3 Giovanni Cabiddu
2025-09-02 15:50 ` Dave Hansen
2025-09-02 16:08 ` Nadav Amit
2025-09-02 16:11 ` Dave Hansen
2025-09-03 14:00 ` Rik van Riel
2025-09-02 16:05 ` Jann Horn
2025-09-02 16:13 ` Jann Horn
2025-09-03 14:18 ` Nadav Amit
2025-09-03 14:42 ` Jann Horn
2025-09-02 16:31 ` Jann Horn
2025-09-02 16:57 ` Giovanni Cabiddu
2025-02-26 3:00 ` [PATCH v14 02/13] x86/mm: get INVLPGB count max from CPUID Rik van Riel
2025-02-28 16:21 ` Borislav Petkov
2025-02-28 19:27 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 03/13] x86/mm: add INVLPGB support code Rik van Riel
2025-02-28 18:46 ` Borislav Petkov
2025-02-28 18:51 ` Dave Hansen
2025-02-28 19:47 ` Borislav Petkov
2025-03-03 18:41 ` Dave Hansen [this message]
2025-03-03 19:23 ` Dave Hansen
2025-03-04 11:00 ` Borislav Petkov
2025-03-04 15:10 ` Dave Hansen
2025-03-04 16:19 ` Borislav Petkov
2025-03-04 16:57 ` Dave Hansen
2025-03-04 21:12 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 04/13] x86/mm: use INVLPGB for kernel TLB flushes Rik van Riel
2025-02-28 19:00 ` Dave Hansen
2025-02-28 21:43 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 05/13] x86/mm: use INVLPGB in flush_tlb_all Rik van Riel
2025-02-28 19:18 ` Dave Hansen
2025-03-01 12:20 ` Borislav Petkov
2025-03-01 15:54 ` Rik van Riel
2025-02-28 22:20 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 06/13] x86/mm: use broadcast TLB flushing for page reclaim TLB flushing Rik van Riel
2025-02-28 18:57 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 07/13] x86/mm: add global ASID allocation helper functions Rik van Riel
2025-03-02 7:06 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 08/13] x86/mm: global ASID context switch & TLB flush handling Rik van Riel
2025-03-02 7:58 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 09/13] x86/mm: global ASID process exit helpers Rik van Riel
2025-03-02 12:38 ` Borislav Petkov
2025-03-02 13:53 ` Rik van Riel
2025-03-03 10:16 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 10/13] x86/mm: enable broadcast TLB invalidation for multi-threaded processes Rik van Riel
2025-03-03 10:57 ` Borislav Petkov
2025-02-26 3:00 ` [PATCH v14 11/13] x86/mm: do targeted broadcast flushing from tlbbatch code Rik van Riel
2025-03-03 11:46 ` Borislav Petkov
2025-03-03 21:47 ` Dave Hansen
2025-03-04 11:52 ` Borislav Petkov
2025-03-04 15:24 ` Dave Hansen
2025-03-04 12:52 ` Brendan Jackman
2025-03-04 14:11 ` Borislav Petkov
2025-03-04 15:33 ` Brendan Jackman
2025-03-04 17:51 ` Dave Hansen
2025-02-26 3:00 ` [PATCH v14 12/13] x86/mm: enable AMD translation cache extensions Rik van Riel
2025-02-26 3:00 ` [PATCH v14 13/13] x86/mm: only invalidate final translations with INVLPGB Rik van Riel
2025-03-03 22:40 ` Dave Hansen
2025-03-04 11:53 ` Borislav Petkov
2025-03-03 12:42 ` [PATCH v14 00/13] AMD broadcast TLB invalidation Borislav Petkov
2025-03-03 13:29 ` Borislav Petkov
2025-03-04 12:04 ` [PATCH] x86/mm: Always set the ASID valid bit for the INVLPGB instruction Borislav Petkov
2025-03-04 12:43 ` Borislav Petkov
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=30c721e0-338d-4172-989c-5226d584bcbc@intel.com \
--to=dave.hansen@intel.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=jackmanb@google.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=mingo@kernel.org \
--cc=nadav.amit@gmail.com \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--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