From: Kai Huang <kai.huang@intel.com>
To: dave.hansen@intel.com, bp@alien8.de, tglx@linutronix.de,
peterz@infradead.org, mingo@redhat.com, hpa@zytor.com,
thomas.lendacky@amd.com
Cc: x86@kernel.org, kas@kernel.org, rick.p.edgecombe@intel.com,
dwmw@amazon.co.uk, linux-kernel@vger.kernel.org,
pbonzini@redhat.com, seanjc@google.com, kvm@vger.kernel.org,
reinette.chatre@intel.com, isaku.yamahata@intel.com,
dan.j.williams@intel.com, ashish.kalra@amd.com,
nik.borisov@suse.com, chao.gao@intel.com, sagis@google.com
Subject: [PATCH v5 1/7] x86/kexec: Consolidate relocate_kernel() function parameters
Date: Tue, 29 Jul 2025 00:28:35 +1200 [thread overview]
Message-ID: <48b3b8dc2ece4095d29f21a439664c0302f3c979.1753679792.git.kai.huang@intel.com> (raw)
In-Reply-To: <cover.1753679792.git.kai.huang@intel.com>
During kexec, the kernel jumps to the new kernel in relocate_kernel(),
which is implemented in assembly and both 32-bit and 64-bit have their
own version.
Currently, for both 32-bit and 64-bit, the last two parameters of the
relocate_kernel() are both 'unsigned int' but actually they only convey
a boolean, i.e., one bit information. The 'unsigned int' has enough
space to carry two bits information therefore there's no need to pass
the two booleans in two separate 'unsigned int'.
Consolidate the last two function parameters of relocate_kernel() into a
single 'unsigned int' and pass flags instead.
Only consolidate the 64-bit version albeit the similar optimization can
be done for the 32-bit version too. Don't bother changing the 32-bit
version while it is working (since assembly code change is required).
Signed-off-by: Kai Huang <kai.huang@intel.com>
---
v4 -> v5:
- RELOC_KERNEL_HOST_MEM_ACTIVE -> RELOC_KERNEL_HOST_MEM_ENC_ACTIVE
(Tom)
- Add a comment to explain only RELOC_KERNEL_PRESERVE_CONTEXT is
restored after jumping back from peer kernel for preserved_context
kexec (pointed out by Tom).
- Use testb instead of testq when comparing the flag with R11 to save
3 bytes (Hpa).
v4:
- new patch
---
arch/x86/include/asm/kexec.h | 12 ++++++++++--
arch/x86/kernel/machine_kexec_64.c | 22 +++++++++++++---------
arch/x86/kernel/relocate_kernel_64.S | 25 +++++++++++++++----------
3 files changed, 38 insertions(+), 21 deletions(-)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index f2ad77929d6e..12cebbcdb6c8 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -13,6 +13,15 @@
# define KEXEC_DEBUG_EXC_HANDLER_SIZE 6 /* PUSHI, PUSHI, 2-byte JMP */
#endif
+#ifdef CONFIG_X86_64
+
+#include <linux/bits.h>
+
+#define RELOC_KERNEL_PRESERVE_CONTEXT BIT(0)
+#define RELOC_KERNEL_HOST_MEM_ENC_ACTIVE BIT(1)
+
+#endif
+
# define KEXEC_CONTROL_PAGE_SIZE 4096
# define KEXEC_CONTROL_CODE_MAX_SIZE 2048
@@ -121,8 +130,7 @@ typedef unsigned long
relocate_kernel_fn(unsigned long indirection_page,
unsigned long pa_control_page,
unsigned long start_address,
- unsigned int preserve_context,
- unsigned int host_mem_enc_active);
+ unsigned int flags);
#endif
extern relocate_kernel_fn relocate_kernel;
#define ARCH_HAS_KIMAGE_ARCH
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 697fb99406e6..5cda8d8d8b13 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -384,16 +384,10 @@ void __nocfi machine_kexec(struct kimage *image)
{
unsigned long reloc_start = (unsigned long)__relocate_kernel_start;
relocate_kernel_fn *relocate_kernel_ptr;
- unsigned int host_mem_enc_active;
+ unsigned int relocate_kernel_flags;
int save_ftrace_enabled;
void *control_page;
- /*
- * This must be done before load_segments() since if call depth tracking
- * is used then GS must be valid to make any function calls.
- */
- host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT);
-
#ifdef CONFIG_KEXEC_JUMP
if (image->preserve_context)
save_processor_state();
@@ -427,6 +421,17 @@ void __nocfi machine_kexec(struct kimage *image)
*/
relocate_kernel_ptr = control_page + (unsigned long)relocate_kernel - reloc_start;
+ relocate_kernel_flags = 0;
+ if (image->preserve_context)
+ relocate_kernel_flags |= RELOC_KERNEL_PRESERVE_CONTEXT;
+
+ /*
+ * This must be done before load_segments() since if call depth tracking
+ * is used then GS must be valid to make any function calls.
+ */
+ if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+ relocate_kernel_flags |= RELOC_KERNEL_HOST_MEM_ENC_ACTIVE;
+
/*
* The segment registers are funny things, they have both a
* visible and an invisible part. Whenever the visible part is
@@ -443,8 +448,7 @@ void __nocfi machine_kexec(struct kimage *image)
image->start = relocate_kernel_ptr((unsigned long)image->head,
virt_to_phys(control_page),
image->start,
- image->preserve_context,
- host_mem_enc_active);
+ relocate_kernel_flags);
#ifdef CONFIG_KEXEC_JUMP
if (image->preserve_context)
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index ea604f4d0b52..26e945f85d19 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -66,8 +66,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
* %rdi indirection_page
* %rsi pa_control_page
* %rdx start address
- * %rcx preserve_context
- * %r8 host_mem_enc_active
+ * %rcx flags: RELOC_KERNEL_*
*/
/* Save the CPU context, used for jumping back */
@@ -111,7 +110,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
/* save indirection list for jumping back */
movq %rdi, pa_backup_pages_map(%rip)
- /* Save the preserve_context to %r11 as swap_pages clobbers %rcx. */
+ /* Save the flags to %r11 as swap_pages clobbers %rcx. */
movq %rcx, %r11
/* setup a new stack at the end of the physical control page */
@@ -129,9 +128,8 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
/*
* %rdi indirection page
* %rdx start address
- * %r8 host_mem_enc_active
* %r9 page table page
- * %r11 preserve_context
+ * %r11 flags: RELOC_KERNEL_*
* %r13 original CR4 when relocate_kernel() was invoked
*/
@@ -204,7 +202,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
* entries that will conflict with the now unencrypted memory
* used by kexec. Flush the caches before copying the kernel.
*/
- testq %r8, %r8
+ testb $RELOC_KERNEL_HOST_MEM_ENC_ACTIVE, %r11b
jz .Lsme_off
wbinvd
.Lsme_off:
@@ -220,7 +218,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
movq %cr3, %rax
movq %rax, %cr3
- testq %r11, %r11 /* preserve_context */
+ testb $RELOC_KERNEL_PRESERVE_CONTEXT, %r11b
jnz .Lrelocate
/*
@@ -273,7 +271,13 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
ANNOTATE_NOENDBR
andq $PAGE_MASK, %r8
lea PAGE_SIZE(%r8), %rsp
- movl $1, %r11d /* Ensure preserve_context flag is set */
+ /*
+ * Ensure RELOC_KERNEL_PRESERVE_CONTEXT flag is set so that
+ * swap_pages() can swap pages correctly. Note all other
+ * RELOC_KERNEL_* flags passed to relocate_kernel() are not
+ * restored.
+ */
+ movl $RELOC_KERNEL_PRESERVE_CONTEXT, %r11d
call swap_pages
movq kexec_va_control_page(%rip), %rax
0: addq $virtual_mapped - 0b, %rax
@@ -321,7 +325,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
UNWIND_HINT_END_OF_STACK
/*
* %rdi indirection page
- * %r11 preserve_context
+ * %r11 flags: RELOC_KERNEL_*
*/
movq %rdi, %rcx /* Put the indirection_page in %rcx */
xorl %edi, %edi
@@ -357,7 +361,8 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
movq %rdi, %rdx /* Save destination page to %rdx */
movq %rsi, %rax /* Save source page to %rax */
- testq %r11, %r11 /* Only actually swap for ::preserve_context */
+ /* Only actually swap for ::preserve_context */
+ testb $RELOC_KERNEL_PRESERVE_CONTEXT, %r11b
jz .Lnoswap
/* copy source page to swap page */
--
2.50.1
next prev parent reply other threads:[~2025-07-28 12:29 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-28 12:28 [PATCH v5 0/7] TDX host: kexec/kdump support Kai Huang
2025-07-28 12:28 ` Kai Huang [this message]
2025-08-06 6:53 ` [PATCH v5 1/7] x86/kexec: Consolidate relocate_kernel() function parameters Huang, Kai
2025-08-06 13:00 ` Tom Lendacky
2025-08-06 22:29 ` Huang, Kai
2025-07-28 12:28 ` [PATCH v5 2/7] x86/sme: Use percpu boolean to control WBINVD during kexec Kai Huang
2025-07-28 12:28 ` [PATCH v5 3/7] x86/virt/tdx: Mark memory cache state incoherent when making SEAMCALL Kai Huang
2025-08-01 8:23 ` Chao Gao
2025-08-04 12:47 ` Huang, Kai
2025-08-12 0:51 ` Edgecombe, Rick P
2025-08-12 1:32 ` Huang, Kai
2025-08-12 1:34 ` Edgecombe, Rick P
2025-08-12 2:03 ` Huang, Kai
2025-08-14 0:09 ` Huang, Kai
2025-07-28 12:28 ` [PATCH v5 4/7] x86/kexec: Disable kexec/kdump on platforms with TDX partial write erratum Kai Huang
2025-07-28 12:28 ` [PATCH v5 5/7] x86/virt/tdx: Remove the !KEXEC_CORE dependency Kai Huang
2025-07-28 12:28 ` [PATCH v5 6/7] x86/virt/tdx: Update the kexec section in the TDX documentation Kai Huang
2025-07-28 12:28 ` [PATCH v5 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs Kai Huang
2025-08-01 8:30 ` Chao Gao
2025-08-04 12:48 ` Huang, Kai
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=48b3b8dc2ece4095d29f21a439664c0302f3c979.1753679792.git.kai.huang@intel.com \
--to=kai.huang@intel.com \
--cc=ashish.kalra@amd.com \
--cc=bp@alien8.de \
--cc=chao.gao@intel.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=dwmw@amazon.co.uk \
--cc=hpa@zytor.com \
--cc=isaku.yamahata@intel.com \
--cc=kas@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nik.borisov@suse.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=reinette.chatre@intel.com \
--cc=rick.p.edgecombe@intel.com \
--cc=sagis@google.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=x86@kernel.org \
/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
all inboxes | Powered by JetHome®