c/pve-kernel-lowlatency-qoup
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update and drop applied patches for 6.2

Browse Source 
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
This commit is contained in:
Thomas Lamprecht 2023-03-08 12:29:55 +01:00
parent fd2107cc91
commit 24d804a086
16 changed files with 9 additions and 1490 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
patches/kernel/0001-Make-mkcompile_h-accept-an-alternate-timestamp-strin.patch
View File

@ -21,7 +21,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
1 file changed, 1 insertion(+), 1 deletion(-) 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/init/Makefile b/init/Makefile diff --git a/init/Makefile b/init/Makefile
index 8316c23bead2..e99b8de4a93a 100644 index 26de459006c4..3157d9c79901 100644
--- a/init/Makefile --- a/init/Makefile
+++ b/init/Makefile +++ b/init/Makefile
@@ -29,7 +29,7 @@ preempt-flag-$(CONFIG_PREEMPT_DYNAMIC) := PREEMPT_DYNAMIC @@ -29,7 +29,7 @@ preempt-flag-$(CONFIG_PREEMPT_DYNAMIC) := PREEMPT_DYNAMIC

4
patches/kernel/0004-pci-Enable-overrides-for-missing-ACS-capabilities-4..patch
View File

@ -55,10 +55,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
2 files changed, 111 insertions(+) 2 files changed, 111 insertions(+)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 7ab595b21b24..87caff8d4561 100644 index 2e77ecc12692..eae6fdc4c683 100644
--- a/Documentation/admin-guide/kernel-parameters.txt --- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4172,6 +4172,15 @@ @@ -4188,6 +4188,15 @@
Also, it enforces the PCI Local Bus spec Also, it enforces the PCI Local Bus spec
rule that those bits should be 0 in system reset rule that those bits should be 0 in system reset
events (useful for kexec/kdump cases). events (useful for kexec/kdump cases).

2
patches/kernel/0005-kvm-disable-default-dynamic-halt-polling-growth.patch
View File

@ -13,7 +13,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
1 file changed, 1 insertion(+), 1 deletion(-) 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fab4d3790578..adae153354c2 100644 index 9c60384b5ae0..725d08bf89de 100644
--- a/virt/kvm/kvm_main.c --- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c
@@ -79,7 +79,7 @@ module_param(halt_poll_ns, uint, 0644); @@ -79,7 +79,7 @@ module_param(halt_poll_ns, uint, 0644);

4
patches/kernel/0006-net-core-downgrade-unregister_netdevice-refcount-lea.patch
View File

@ -14,10 +14,10 @@ Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
1 file changed, 1 insertion(+), 1 deletion(-) 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/dev.c b/net/core/dev.c diff --git a/net/core/dev.c b/net/core/dev.c
index 7a2a4650a898..ee1ce573a63f 100644 index f23e287602b7..73566e165640 100644
--- a/net/core/dev.c --- a/net/core/dev.c
+++ b/net/core/dev.c +++ b/net/core/dev.c
@@ -10273,7 +10273,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) @@ -10255,7 +10255,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
if (time_after(jiffies, warning_time + if (time_after(jiffies, warning_time +
READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
list_for_each_entry(dev, list, todo_list) { list_for_each_entry(dev, list, todo_list) {

0
patches/kernel/0016-Revert-RDMA-irdma-Report-the-correct-link-speed.patch → patches/kernel/0007-Revert-RDMA-irdma-Report-the-correct-link-speed.patch
View File

57
patches/kernel/0007-bug-introduce-ASSERT_STRUCT_OFFSET.patch
View File

@ -1,57 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:49:59 +0300
Subject: [PATCH] bug: introduce ASSERT_STRUCT_OFFSET
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
ASSERT_STRUCT_OFFSET allows to assert during the build of
the kernel that a field in a struct have an expected offset.
KVM used to have such macro, but there is almost nothing KVM specific
in it so move it to build_bug.h, so that it can be used in other
places in KVM.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/vmx/vmcs12.h | 5 ++---
include/linux/build_bug.h | 9 +++++++++
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 746129ddd5ae..01936013428b 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -208,9 +208,8 @@ struct __packed vmcs12 {
/*
* For save/restore compatibility, the vmcs12 field offsets must not change.
*/
-#define CHECK_OFFSET(field, loc) \
- BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \
- "Offset of " #field " in struct vmcs12 has changed.")
+#define CHECK_OFFSET(field, loc) \
+ ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
static inline void vmx_check_vmcs12_offsets(void)
{
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index e3a0be2c90ad..3aa3640f8c18 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,4 +77,13 @@
#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
#endif /* _LINUX_BUILD_BUG_H */

38
patches/kernel/0008-KVM-x86-emulator-update-the-emulation-mode-after-rsm.patch
View File

@ -1,38 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:02 +0300
Subject: [PATCH] KVM: x86: emulator: update the emulation mode after rsm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This ensures that RIP will be correctly written back,
because the RSM instruction can switch the CPU mode from
32 bit (or less) to 64 bit.
This fixes a guest crash in case the #SMI is received
while the guest runs a code from an address > 32 bit.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/emulate.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4a43261d25a2..4f7f5117ec7a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2654,6 +2654,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
+
+ ret = emulator_recalc_and_set_mode(ctxt);
+ if (ret != X86EMUL_CONTINUE)
+ goto emulate_shutdown;
+
/*
* Note, the ctxt->ops callbacks are responsible for handling side
* effects when writing MSRs and CRs, e.g. MMU context resets, CPUID

2
patches/kernel/0017-Revert-fortify-Do-not-cast-to-unsigned-char.patch → patches/kernel/0008-Revert-fortify-Do-not-cast-to-unsigned-char.patch
View File

@ -15,7 +15,7 @@ Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
1 file changed, 1 insertion(+), 1 deletion(-) 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 5001a11258e4..1067a8450826 100644 index 7cad8bb031e9..acc24887db3e 100644
--- a/include/linux/fortify-string.h --- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h
@@ -18,7 +18,7 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" @@ -18,7 +18,7 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("

284
patches/kernel/0009-KVM-x86-emulator-smm-add-structs-for-KVM-s-smram-lay.patch
View File

@ -1,284 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:05 +0300
Subject: [PATCH] KVM: x86: emulator/smm: add structs for KVM's smram layout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Those structs will be used to read/write the smram state image.
Also document the differences between KVM's SMRAM layout and SMRAM
layout that is used by real Intel/AMD cpus.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/emulate.c | 6 +
arch/x86/kvm/kvm_emulate.h | 218 +++++++++++++++++++++++++++++++++++++
arch/x86/kvm/x86.c | 1 +
3 files changed, 225 insertions(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4f7f5117ec7a..470dd4453b01 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5856,3 +5856,9 @@ bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt)
return true;
}
+
+void __init kvm_emulator_init(void)
+{
+ __check_smram32_offsets();
+ __check_smram64_offsets();
+}
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 89246446d6aa..dd0ae61e44a1 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -13,6 +13,7 @@
#define _ASM_X86_KVM_X86_EMULATE_H
#include <asm/desc_defs.h>
+#include <linux/build_bug.h>
#include "fpu.h"
struct x86_emulate_ctxt;
@@ -503,6 +504,223 @@ enum x86_intercept {
nr_x86_intercepts
};
+
+/* 32 bit KVM's emulated SMM layout. Loosely based on Intel's layout */
+
+struct kvm_smm_seg_state_32 {
+ u32 flags;
+ u32 limit;
+ u32 base;
+} __packed;
+
+struct kvm_smram_state_32 {
+ u32 reserved1[62];
+ u32 smbase;
+ u32 smm_revision;
+ u32 reserved2[5];
+ u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
+ u32 reserved3[5];
+
+ /*
+ * Segment state is not present/documented in the Intel/AMD SMRAM image
+ * Instead this area on Intel/AMD contains IO/HLT restart flags.
+ */
+ struct kvm_smm_seg_state_32 ds;
+ struct kvm_smm_seg_state_32 fs;
+ struct kvm_smm_seg_state_32 gs;
+ struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */
+ struct kvm_smm_seg_state_32 tr;
+ u32 reserved;
+ struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */
+ struct kvm_smm_seg_state_32 ldtr;
+ struct kvm_smm_seg_state_32 es;
+ struct kvm_smm_seg_state_32 cs;
+ struct kvm_smm_seg_state_32 ss;
+
+ u32 es_sel;
+ u32 cs_sel;
+ u32 ss_sel;
+ u32 ds_sel;
+ u32 fs_sel;
+ u32 gs_sel;
+ u32 ldtr_sel;
+ u32 tr_sel;
+
+ u32 dr7;
+ u32 dr6;
+ u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */
+ u32 eip;
+ u32 eflags;
+ u32 cr3;
+ u32 cr0;
+} __packed;
+
+
+static inline void __check_smram32_offsets(void)
+{
+#define __CHECK_SMRAM32_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00)
+
+ __CHECK_SMRAM32_OFFSET(reserved1, 0xFE00);
+ __CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
+ __CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
+ __CHECK_SMRAM32_OFFSET(reserved2, 0xFF00);
+ __CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
+ __CHECK_SMRAM32_OFFSET(reserved3, 0xFF18);
+ __CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
+ __CHECK_SMRAM32_OFFSET(fs, 0xFF38);
+ __CHECK_SMRAM32_OFFSET(gs, 0xFF44);
+ __CHECK_SMRAM32_OFFSET(idtr, 0xFF50);
+ __CHECK_SMRAM32_OFFSET(tr, 0xFF5C);
+ __CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C);
+ __CHECK_SMRAM32_OFFSET(ldtr, 0xFF78);
+ __CHECK_SMRAM32_OFFSET(es, 0xFF84);
+ __CHECK_SMRAM32_OFFSET(cs, 0xFF90);
+ __CHECK_SMRAM32_OFFSET(ss, 0xFF9C);
+ __CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8);
+ __CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC);
+ __CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0);
+ __CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4);
+ __CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8);
+ __CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC);
+ __CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0);
+ __CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4);
+ __CHECK_SMRAM32_OFFSET(dr7, 0xFFC8);
+ __CHECK_SMRAM32_OFFSET(dr6, 0xFFCC);
+ __CHECK_SMRAM32_OFFSET(gprs, 0xFFD0);
+ __CHECK_SMRAM32_OFFSET(eip, 0xFFF0);
+ __CHECK_SMRAM32_OFFSET(eflags, 0xFFF4);
+ __CHECK_SMRAM32_OFFSET(cr3, 0xFFF8);
+ __CHECK_SMRAM32_OFFSET(cr0, 0xFFFC);
+#undef __CHECK_SMRAM32_OFFSET
+}
+
+
+/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */
+
+struct kvm_smm_seg_state_64 {
+ u16 selector;
+ u16 attributes;
+ u32 limit;
+ u64 base;
+};
+
+struct kvm_smram_state_64 {
+
+ struct kvm_smm_seg_state_64 es;
+ struct kvm_smm_seg_state_64 cs;
+ struct kvm_smm_seg_state_64 ss;
+ struct kvm_smm_seg_state_64 ds;
+ struct kvm_smm_seg_state_64 fs;
+ struct kvm_smm_seg_state_64 gs;
+ struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 ldtr;
+ struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 tr;
+
+ /* I/O restart and auto halt restart are not implemented by KVM */
+ u64 io_restart_rip;
+ u64 io_restart_rcx;
+ u64 io_restart_rsi;
+ u64 io_restart_rdi;
+ u32 io_restart_dword;
+ u32 reserved1;
+ u8 io_inst_restart;
+ u8 auto_hlt_restart;
+ u8 reserved2[6];
+
+ u64 efer;
+
+ /*
+ * Two fields below are implemented on AMD only, to store
+ * SVM guest vmcb address if the #SMI was received while in the guest mode.
+ */
+ u64 svm_guest_flag;
+ u64 svm_guest_vmcb_gpa;
+ u64 svm_guest_virtual_int; /* unknown purpose, not implemented */
+
+ u32 reserved3[3];
+ u32 smm_revison;
+ u32 smbase;
+ u32 reserved4[5];
+
+ /* ssp and svm_* fields below are not implemented by KVM */
+ u64 ssp;
+ u64 svm_guest_pat;
+ u64 svm_host_efer;
+ u64 svm_host_cr4;
+ u64 svm_host_cr3;
+ u64 svm_host_cr0;
+
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+};
+
+
+static inline void __check_smram64_offsets(void)
+{
+#define __CHECK_SMRAM64_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00)
+
+ __CHECK_SMRAM64_OFFSET(es, 0xFE00);
+ __CHECK_SMRAM64_OFFSET(cs, 0xFE10);
+ __CHECK_SMRAM64_OFFSET(ss, 0xFE20);
+ __CHECK_SMRAM64_OFFSET(ds, 0xFE30);
+ __CHECK_SMRAM64_OFFSET(fs, 0xFE40);
+ __CHECK_SMRAM64_OFFSET(gs, 0xFE50);
+ __CHECK_SMRAM64_OFFSET(gdtr, 0xFE60);
+ __CHECK_SMRAM64_OFFSET(ldtr, 0xFE70);
+ __CHECK_SMRAM64_OFFSET(idtr, 0xFE80);
+ __CHECK_SMRAM64_OFFSET(tr, 0xFE90);
+ __CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0);
+ __CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8);
+ __CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
+ __CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
+ __CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
+ __CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ __CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
+ __CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
+ __CHECK_SMRAM64_OFFSET(reserved2, 0xFECA);
+ __CHECK_SMRAM64_OFFSET(efer, 0xFED0);
+ __CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8);
+ __CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0);
+ __CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8);
+ __CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0);
+ __CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC);
+ __CHECK_SMRAM64_OFFSET(smbase, 0xFF00);
+ __CHECK_SMRAM64_OFFSET(reserved4, 0xFF04);
+ __CHECK_SMRAM64_OFFSET(ssp, 0xFF18);
+ __CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20);
+ __CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40);
+ __CHECK_SMRAM64_OFFSET(cr4, 0xFF48);
+ __CHECK_SMRAM64_OFFSET(cr3, 0xFF50);
+ __CHECK_SMRAM64_OFFSET(cr0, 0xFF58);
+ __CHECK_SMRAM64_OFFSET(dr7, 0xFF60);
+ __CHECK_SMRAM64_OFFSET(dr6, 0xFF68);
+ __CHECK_SMRAM64_OFFSET(rflags, 0xFF70);
+ __CHECK_SMRAM64_OFFSET(rip, 0xFF78);
+ __CHECK_SMRAM64_OFFSET(gprs, 0xFF80);
+#undef __CHECK_SMRAM64_OFFSET
+}
+
+union kvm_smram {
+ struct kvm_smram_state_64 smram64;
+ struct kvm_smram_state_32 smram32;
+ u8 bytes[512];
+};
+
+void __init kvm_emulator_init(void);
+
+
/* Host execution mode. */
#if defined(CONFIG_X86_32)
#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 393b1040f96e..8bdcba503f35 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13751,6 +13751,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
static int __init kvm_x86_init(void)
{
kvm_mmu_x86_module_init();
+ kvm_emulator_init();
mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible();
return 0;
}

3
patches/kernel/0018-block-don-t-allow-multiple-bios-for-IOCB_NOWAIT-issu.patch → patches/kernel/0009-block-don-t-allow-multiple-bios-for-IOCB_NOWAIT-issu.patch
View File

@ -24,12 +24,13 @@ Reported-and-tested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Jens Axboe <axboe@kernel.dk>
(commit 67d59247d4b52c917e373f05a807027756ab216f upstream) (commit 67d59247d4b52c917e373f05a807027756ab216f upstream)
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com> Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
--- ---
block/fops.c | 21 ++++++++++++++++++--- block/fops.c | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-) 1 file changed, 18 insertions(+), 3 deletions(-)
diff --git a/block/fops.c b/block/fops.c diff --git a/block/fops.c b/block/fops.c
index b90742595317..e406aa605327 100644 index 50d245e8c913..d2e6be4e3d1c 100644
--- a/block/fops.c --- a/block/fops.c
+++ b/block/fops.c +++ b/block/fops.c
@@ -221,6 +221,24 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, @@ -221,6 +221,24 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,

218
patches/kernel/0010-KVM-x86-emulator-smm-use-smram-structs-in-the-common.patch
View File

@ -1,218 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:06 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram structs in the common code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Switch from using a raw array to 'union kvm_smram'.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/include/asm/kvm_host.h | 5 +++--
arch/x86/kvm/emulate.c | 12 +++++++-----
arch/x86/kvm/kvm_emulate.h | 3 ++-
arch/x86/kvm/svm/svm.c | 8 ++++++--
arch/x86/kvm/vmx/vmx.c | 4 ++--
arch/x86/kvm/x86.c | 16 ++++++++--------
6 files changed, 28 insertions(+), 20 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f05ebaa26f0f..6885f3839e25 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -204,6 +204,7 @@ typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
+union kvm_smram;
enum x86_intercept;
enum x86_intercept_stage;
@@ -1613,8 +1614,8 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
- int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
+ int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+ int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 470dd4453b01..7294dffa794a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2582,16 +2582,18 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
- char buf[512];
+ const union kvm_smram smram;
u64 smbase;
int ret;
+ BUILD_BUG_ON(sizeof(smram) != 512);
+
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
smbase = ctxt->ops->get_smbase(ctxt);
- ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, (void *)&smram, sizeof(smram));
if (ret != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2641,15 +2643,15 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
* state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->leave_smm(ctxt, buf))
+ if (ctxt->ops->leave_smm(ctxt, &smram))
goto emulate_shutdown;
#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, buf);
+ ret = rsm_load_state_64(ctxt, (const char *)&smram);
else
#endif
- ret = rsm_load_state_32(ctxt, buf);
+ ret = rsm_load_state_32(ctxt, (const char *)&smram);
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index dd0ae61e44a1..76c0b8e7890b 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -19,6 +19,7 @@
struct x86_emulate_ctxt;
enum x86_intercept;
enum x86_intercept_stage;
+union kvm_smram;
struct x86_exception {
u8 vector;
@@ -236,7 +237,7 @@ struct x86_emulate_ops {
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
- int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate);
+ int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const union kvm_smram *smram);
void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
};
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0434bb7b456b..feb48828124e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4391,12 +4391,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return 1;
}
-static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map_save;
int ret;
+ char *smstate = (char *)smram;
+
if (!is_guest_mode(vcpu))
return 0;
@@ -4438,7 +4440,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
@@ -4446,6 +4448,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
struct vmcb *vmcb12;
int ret;
+ const char *smstate = (const char *)smram;
+
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 95ed874fbbcc..d12f341df52e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7913,7 +7913,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !is_smm(vcpu);
}
-static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7934,7 +7934,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8bdcba503f35..928b3c21b4cb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8205,9 +8205,9 @@ static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
}
static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const union kvm_smram *smram)
{
- return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+ return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smram);
}
static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
@@ -10267,25 +10267,25 @@ static void enter_smm(struct kvm_vcpu *vcpu)
struct kvm_segment cs, ds;
struct desc_ptr dt;
unsigned long cr0;
- char buf[512];
+ union kvm_smram smram;
- memset(buf, 0, 512);
+ memset(smram.bytes, 0, sizeof(smram.bytes));
#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, buf);
+ enter_smm_save_state_64(vcpu, (char *)&smram);
else
#endif
- enter_smm_save_state_32(vcpu, buf);
+ enter_smm_save_state_32(vcpu, (char *)&smram);
/*
* Give enter_smm() a chance to make ISA-specific changes to the vCPU
* state (e.g. leave guest mode) after we've saved the state into the
* SMM state-save area.
*/
- static_call(kvm_x86_enter_smm)(vcpu, buf);
+ static_call(kvm_x86_enter_smm)(vcpu, &smram);
kvm_smm_changed(vcpu, true);
- kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
+ kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram));
if (static_call(kvm_x86_get_nmi_mask)(vcpu))
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;

272
patches/kernel/0011-KVM-x86-emulator-smm-use-smram-struct-for-32-bit-smr.patch
View File

@ -1,272 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:07 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 32 bit smram
load/restore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Use kvm_smram_state_32 struct to save/restore 32 bit SMM state
(used when X86_FEATURE_LM is not present in the guest CPUID).
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/emulate.c | 81 +++++++++++++++---------------------------
arch/x86/kvm/x86.c | 75 +++++++++++++++++---------------------
2 files changed, 60 insertions(+), 96 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7294dffa794a..65d82292ccec 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2359,25 +2359,17 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smm_seg_state_32 *state,
+ u16 selector,
int n)
{
struct desc_struct desc;
- int offset;
- u16 selector;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
+ set_desc_base(&desc, state->base);
+ set_desc_limit(&desc, state->limit);
+ rsm_set_desc_flags(&desc, state->flags);
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
- return X86EMUL_CONTINUE;
}
#ifdef CONFIG_X86_64
@@ -2448,63 +2440,46 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
}
static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const struct kvm_smram_state_32 *smstate)
{
- struct desc_struct desc;
struct desc_ptr dt;
- u16 selector;
- u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
+ ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->eip;
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
-
- val = GET_SMSTATE(u32, smstate, 0x7fcc);
+ *reg_write(ctxt, i) = smstate->gprs[i];
- if (ctxt->ops->set_dr(ctxt, 6, val))
+ if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u32, smstate, 0x7fc8);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
+ if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
return X86EMUL_UNHANDLEABLE;
- selector = GET_SMSTATE(u32, smstate, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+ rsm_load_seg_32(ctxt, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR);
+ rsm_load_seg_32(ctxt, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR);
- selector = GET_SMSTATE(u32, smstate, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
+ dt.address = smstate->gdtr.base;
+ dt.size = smstate->gdtr.limit;
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
+ dt.address = smstate->idtr.base;
+ dt.size = smstate->idtr.limit;
ctxt->ops->set_idt(ctxt, &dt);
- for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
+ rsm_load_seg_32(ctxt, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
+ rsm_load_seg_32(ctxt, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
+ rsm_load_seg_32(ctxt, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS);
- cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
+ rsm_load_seg_32(ctxt, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS);
+ rsm_load_seg_32(ctxt, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS);
+ rsm_load_seg_32(ctxt, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, smstate->smbase);
- return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+ return rsm_enter_protected_mode(ctxt, smstate->cr0,
+ smstate->cr3, smstate->cr4);
}
#ifdef CONFIG_X86_64
@@ -2651,7 +2626,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
ret = rsm_load_state_64(ctxt, (const char *)&smram);
else
#endif
- ret = rsm_load_state_32(ctxt, (const char *)&smram);
+ ret = rsm_load_state_32(ctxt, &smram.smram32);
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 928b3c21b4cb..48a15a71c543 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10121,22 +10121,18 @@ static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
return flags;
}
-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_32 *state,
+ u32 *selector,
+ int n)
{
struct kvm_segment seg;
- int offset;
kvm_get_segment(vcpu, &seg, n);
- put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- put_smstate(u32, buf, offset + 8, seg.base);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
+ *selector = seg.selector;
+ state->base = seg.base;
+ state->limit = seg.limit;
+ state->flags = enter_smm_get_segment_flags(&seg);
}
#ifdef CONFIG_X86_64
@@ -10157,54 +10153,47 @@ static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
}
#endif
-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_state_32 *smram)
{
struct desc_ptr dt;
- struct kvm_segment seg;
unsigned long val;
int i;
- put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
- put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
- put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
- put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->eflags = kvm_get_rflags(vcpu);
+ smram->eip = kvm_rip_read(vcpu);
for (i = 0; i < 8; i++)
- put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
+ smram->gprs[i] = kvm_register_read_raw(vcpu, i);
kvm_get_dr(vcpu, 6, &val);
- put_smstate(u32, buf, 0x7fcc, (u32)val);
+ smram->dr6 = (u32)val;
kvm_get_dr(vcpu, 7, &val);
- put_smstate(u32, buf, 0x7fc8, (u32)val);
+ smram->dr7 = (u32)val;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u32, buf, 0x7fc4, seg.selector);
- put_smstate(u32, buf, 0x7f64, seg.base);
- put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u32, buf, 0x7fc0, seg.selector);
- put_smstate(u32, buf, 0x7f80, seg.base);
- put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
+ enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
+ enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f74, dt.address);
- put_smstate(u32, buf, 0x7f70, dt.size);
+ smram->gdtr.base = dt.address;
+ smram->gdtr.limit = dt.size;
static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f58, dt.address);
- put_smstate(u32, buf, 0x7f54, dt.size);
+ smram->idtr.base = dt.address;
+ smram->idtr.limit = dt.size;
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_32(vcpu, buf, i);
+ enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES);
+ enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS);
+ enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS);
- put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
+ enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS);
+ enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS);
+ enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS);
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020000);
- put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
+ smram->cr4 = kvm_read_cr4(vcpu);
+ smram->smm_revision = 0x00020000;
+ smram->smbase = vcpu->arch.smbase;
}
#ifdef CONFIG_X86_64
@@ -10275,7 +10264,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
enter_smm_save_state_64(vcpu, (char *)&smram);
else
#endif
- enter_smm_save_state_32(vcpu, (char *)&smram);
+ enter_smm_save_state_32(vcpu, &smram.smram32);
/*
* Give enter_smm() a chance to make ISA-specific changes to the vCPU

283
patches/kernel/0012-KVM-x86-emulator-smm-use-smram-struct-for-64-bit-smr.patch
View File

@ -1,283 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:08 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 64 bit smram
load/restore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Use kvm_smram_state_64 struct to save/restore the 64 bit SMM state
(used when X86_FEATURE_LM is present in the guest CPUID,
regardless of 32-bitness of the guest).
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/emulate.c | 88 ++++++++++++++----------------------------
arch/x86/kvm/x86.c | 75 ++++++++++++++++-------------------
2 files changed, 62 insertions(+), 101 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 65d82292ccec..03f9e5aa036e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2373,24 +2373,16 @@ static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
}
#ifdef CONFIG_X86_64
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
+static void rsm_load_seg_64(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smm_seg_state_64 *state,
+ int n)
{
struct desc_struct desc;
- int offset;
- u16 selector;
- u32 base3;
-
- offset = 0x7e00 + n * 16;
-
- selector = GET_SMSTATE(u16, smstate, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- base3 = GET_SMSTATE(u32, smstate, offset + 12);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
- return X86EMUL_CONTINUE;
+ rsm_set_desc_flags(&desc, state->attributes << 8);
+ set_desc_limit(&desc, state->limit);
+ set_desc_base(&desc, (u32)state->base);
+ ctxt->ops->set_segment(ctxt, state->selector, &desc, state->base >> 32, n);
}
#endif
@@ -2484,71 +2476,49 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
#ifdef CONFIG_X86_64
static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const struct kvm_smram_state_64 *smstate)
{
- struct desc_struct desc;
struct desc_ptr dt;
- u64 val, cr0, cr3, cr4;
- u32 base3;
- u16 selector;
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = smstate->gprs[15 - i];
- ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->rip;
+ ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u64, smstate, 0x7f68);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
+ if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u64, smstate, 0x7f60);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
+ if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
return X86EMUL_UNHANDLEABLE;
- cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
- cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
- cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
- val = GET_SMSTATE(u64, smstate, 0x7ed0);
+ ctxt->ops->set_smbase(ctxt, smstate->smbase);
- if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+ if (ctxt->ops->set_msr(ctxt, MSR_EFER, smstate->efer & ~EFER_LMA))
return X86EMUL_UNHANDLEABLE;
- selector = GET_SMSTATE(u32, smstate, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
- base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+ rsm_load_seg_64(ctxt, &smstate->tr, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
+ dt.size = smstate->idtr.limit;
+ dt.address = smstate->idtr.base;
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smstate, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
- base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+ rsm_load_seg_64(ctxt, &smstate->ldtr, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
+ dt.size = smstate->gdtr.limit;
+ dt.address = smstate->gdtr.base;
ctxt->ops->set_gdt(ctxt, &dt);
- r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+ r = rsm_enter_protected_mode(ctxt, smstate->cr0, smstate->cr3, smstate->cr4);
if (r != X86EMUL_CONTINUE)
return r;
- for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
+ rsm_load_seg_64(ctxt, &smstate->es, VCPU_SREG_ES);
+ rsm_load_seg_64(ctxt, &smstate->cs, VCPU_SREG_CS);
+ rsm_load_seg_64(ctxt, &smstate->ss, VCPU_SREG_SS);
+ rsm_load_seg_64(ctxt, &smstate->ds, VCPU_SREG_DS);
+ rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
+ rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
return X86EMUL_CONTINUE;
}
@@ -2623,7 +2593,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, (const char *)&smram);
+ ret = rsm_load_state_64(ctxt, &smram.smram64);
else
#endif
ret = rsm_load_state_32(ctxt, &smram.smram32);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 48a15a71c543..f5d3c0ff083d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10136,20 +10136,17 @@ static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
}
#ifdef CONFIG_X86_64
-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_64 *state,
+ int n)
{
struct kvm_segment seg;
- int offset;
- u16 flags;
kvm_get_segment(vcpu, &seg, n);
- offset = 0x7e00 + n * 16;
-
- flags = enter_smm_get_segment_flags(&seg) >> 8;
- put_smstate(u16, buf, offset, seg.selector);
- put_smstate(u16, buf, offset + 2, flags);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u64, buf, offset + 8, seg.base);
+ state->selector = seg.selector;
+ state->attributes = enter_smm_get_segment_flags(&seg) >> 8;
+ state->limit = seg.limit;
+ state->base = seg.base;
}
#endif
@@ -10197,57 +10194,51 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
}
#ifdef CONFIG_X86_64
-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_state_64 *smram)
{
struct desc_ptr dt;
- struct kvm_segment seg;
unsigned long val;
int i;
for (i = 0; i < 16; i++)
- put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
+ smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i);
+
+ smram->rip = kvm_rip_read(vcpu);
+ smram->rflags = kvm_get_rflags(vcpu);
- put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
- put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
kvm_get_dr(vcpu, 6, &val);
- put_smstate(u64, buf, 0x7f68, val);
+ smram->dr6 = val;
kvm_get_dr(vcpu, 7, &val);
- put_smstate(u64, buf, 0x7f60, val);
-
- put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
- put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
- put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
+ smram->dr7 = val;
- put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->cr4 = kvm_read_cr4(vcpu);
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020064);
+ smram->smbase = vcpu->arch.smbase;
+ smram->smm_revison = 0x00020064;
- put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
+ smram->efer = vcpu->arch.efer;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e94, seg.limit);
- put_smstate(u64, buf, 0x7e98, seg.base);
+ enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e84, dt.size);
- put_smstate(u64, buf, 0x7e88, dt.address);
+ smram->idtr.limit = dt.size;
+ smram->idtr.base = dt.address;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e74, seg.limit);
- put_smstate(u64, buf, 0x7e78, seg.base);
+ enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e64, dt.size);
- put_smstate(u64, buf, 0x7e68, dt.address);
+ smram->gdtr.limit = dt.size;
+ smram->gdtr.base = dt.address;
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_64(vcpu, buf, i);
+ enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES);
+ enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS);
+ enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS);
+ enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+ enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+ enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
}
#endif
@@ -10261,7 +10252,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
memset(smram.bytes, 0, sizeof(smram.bytes));
#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, (char *)&smram);
+ enter_smm_save_state_64(vcpu, &smram.smram64);
else
#endif
enter_smm_save_state_32(vcpu, &smram.smram32);

102
patches/kernel/0013-KVM-x86-SVM-use-smram-structs.patch
View File

@ -1,102 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:09 +0300
Subject: [PATCH] KVM: x86: SVM: use smram structs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This removes the last user of put_smstate/GET_SMSTATE so
remove these functions as well.
Also add a sanity check that we don't attempt to enter the SMM
on non long mode capable guest CPU with a running nested guest.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/include/asm/kvm_host.h | 6 ------
arch/x86/kvm/svm/svm.c | 21 ++++++---------------
2 files changed, 6 insertions(+), 21 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6885f3839e25..f5b82b6f4f84 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2090,12 +2090,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#endif
}
-#define put_smstate(type, buf, offset, val) \
- *(type *)((buf) + (offset) - 0x7e00) = val
-
-#define GET_SMSTATE(type, buf, offset) \
- (*(type *)((buf) + (offset) - 0x7e00))
-
int kvm_cpu_dirty_log_size(void);
int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index feb48828124e..023b6507a539 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4397,15 +4397,11 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
struct kvm_host_map map_save;
int ret;
- char *smstate = (char *)smram;
-
if (!is_guest_mode(vcpu))
return 0;
- /* FED8h - SVM Guest */
- put_smstate(u64, smstate, 0x7ed8, 1);
- /* FEE0h - SVM Guest VMCB Physical Address */
- put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+ smram->smram64.svm_guest_flag = 1;
+ smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
@@ -4444,28 +4440,23 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
- u64 saved_efer, vmcb12_gpa;
struct vmcb *vmcb12;
int ret;
- const char *smstate = (const char *)smram;
-
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
/* Non-zero if SMI arrived while vCPU was in guest mode. */
- if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+ if (!smram->smram64.svm_guest_flag)
return 0;
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return 1;
- saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
- if (!(saved_efer & EFER_SVME))
+ if (!(smram->smram64.efer & EFER_SVME))
return 1;
- vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram->smram64.svm_guest_vmcb_gpa), &map) == -EINVAL)
return 1;
ret = 1;
@@ -4491,7 +4482,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
vmcb12 = map.hva;
nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+ ret = enter_svm_guest_mode(vcpu, smram->smram64.svm_guest_vmcb_gpa, vmcb12, false);
if (ret)
goto unmap_save;

44
patches/kernel/0014-KVM-x86-SVM-don-t-save-SVM-state-to-SMRAM-when-VM-is.patch
View File

@ -1,44 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:10 +0300
Subject: [PATCH] KVM: x86: SVM: don't save SVM state to SMRAM when VM is not
long mode capable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When the guest CPUID doesn't have support for long mode, 32 bit SMRAM
layout is used and it has no support for preserving EFER and/or SVM
state.
Note that this isn't relevant to running 32 bit guests on VM which is
long mode capable - such VM can still run 32 bit guests in compatibility
mode.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/svm/svm.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 023b6507a539..a7acbe8246b6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4400,6 +4400,15 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
if (!is_guest_mode(vcpu))
return 0;
+ /*
+ * 32 bit SMRAM format doesn't preserve EFER and SVM state.
+ * SVM should not be enabled by the userspace without marking
+ * the CPU as at least long mode capable.
+ */
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return 1;
+
smram->smram64.svm_guest_flag = 1;
smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;

184
patches/kernel/0015-KVM-x86-emulator-smm-preserve-interrupt-shadow-in-SM.patch
View File

@ -1,184 +0,0 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:11 +0300
Subject: [PATCH] KVM: x86: emulator/smm: preserve interrupt shadow in SMRAM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When #SMI is asserted, the CPU can be in interrupt shadow
due to sti or mov ss.
It is not mandatory in Intel/AMD prm to have the #SMI
blocked during the shadow, and on top of
that, since neither SVM nor VMX has true support for SMI
window, waiting for one instruction would mean single stepping
the guest.
Instead, allow #SMI in this case, but both reset the interrupt
window and stash its value in SMRAM to restore it on exit
from SMM.
This fixes rare failures seen mostly on windows guests on VMX,
when #SMI falls on the sti instruction which mainfest in
VM entry failure due to EFLAGS.IF not being set, but STI interrupt
window still being set in the VMCS.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/x86/kvm/emulate.c | 17 ++++++++++++++---
arch/x86/kvm/kvm_emulate.h | 10 ++++++----
arch/x86/kvm/x86.c | 12 ++++++++++++
3 files changed, 32 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 03f9e5aa036e..bb008a5be539 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2435,7 +2435,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
const struct kvm_smram_state_32 *smstate)
{
struct desc_ptr dt;
- int i;
+ int i, r;
ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
ctxt->_eip = smstate->eip;
@@ -2470,8 +2470,16 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
ctxt->ops->set_smbase(ctxt, smstate->smbase);
- return rsm_enter_protected_mode(ctxt, smstate->cr0,
- smstate->cr3, smstate->cr4);
+ r = rsm_enter_protected_mode(ctxt, smstate->cr0,
+ smstate->cr3, smstate->cr4);
+
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ ctxt->ops->set_int_shadow(ctxt, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return X86EMUL_CONTINUE;
}
#ifdef CONFIG_X86_64
@@ -2520,6 +2528,9 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
+ ctxt->ops->set_int_shadow(ctxt, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
return X86EMUL_CONTINUE;
}
#endif
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 76c0b8e7890b..a7313add0f2a 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -234,6 +234,7 @@ struct x86_emulate_ops {
bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+ void (*set_int_shadow)(struct x86_emulate_ctxt *ctxt, u8 shadow);
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
@@ -518,7 +519,8 @@ struct kvm_smram_state_32 {
u32 reserved1[62];
u32 smbase;
u32 smm_revision;
- u32 reserved2[5];
+ u32 reserved2[4];
+ u32 int_shadow; /* KVM extension */
u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
u32 reserved3[5];
@@ -566,6 +568,7 @@ static inline void __check_smram32_offsets(void)
__CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
__CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
__CHECK_SMRAM32_OFFSET(reserved2, 0xFF00);
+ __CHECK_SMRAM32_OFFSET(int_shadow, 0xFF10);
__CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
__CHECK_SMRAM32_OFFSET(reserved3, 0xFF18);
__CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
@@ -625,7 +628,7 @@ struct kvm_smram_state_64 {
u64 io_restart_rsi;
u64 io_restart_rdi;
u32 io_restart_dword;
- u32 reserved1;
+ u32 int_shadow;
u8 io_inst_restart;
u8 auto_hlt_restart;
u8 reserved2[6];
@@ -663,7 +666,6 @@ struct kvm_smram_state_64 {
u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
};
-
static inline void __check_smram64_offsets(void)
{
#define __CHECK_SMRAM64_OFFSET(field, offset) \
@@ -684,7 +686,7 @@ static inline void __check_smram64_offsets(void)
__CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
__CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
__CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
- __CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ __CHECK_SMRAM64_OFFSET(int_shadow, 0xFEC4);
__CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
__CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
__CHECK_SMRAM64_OFFSET(reserved2, 0xFECA);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f5d3c0ff083d..e4573ac6ee94 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8192,6 +8192,11 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked);
}
+static void emulator_set_int_shadow(struct x86_emulate_ctxt *ctxt, u8 shadow)
+{
+ static_call(kvm_x86_set_interrupt_shadow)(emul_to_vcpu(ctxt), shadow);
+}
+
static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
{
return emul_to_vcpu(ctxt)->arch.hflags;
@@ -8272,6 +8277,7 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_fxsr = emulator_guest_has_fxsr,
.guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
+ .set_int_shadow = emulator_set_int_shadow,
.get_hflags = emulator_get_hflags,
.exiting_smm = emulator_exiting_smm,
.leave_smm = emulator_leave_smm,
@@ -10191,6 +10197,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
smram->cr4 = kvm_read_cr4(vcpu);
smram->smm_revision = 0x00020000;
smram->smbase = vcpu->arch.smbase;
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
}
#ifdef CONFIG_X86_64
@@ -10239,6 +10247,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_stat
enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
}
#endif
@@ -10275,6 +10285,8 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0x8000);
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
static_call(kvm_x86_set_cr0)(vcpu, cr0);
vcpu->arch.cr0 = cr0;