TDX host: kexec/kdump support
Subsystems (5)
v7 cover TDX host: kexec/kdump support
This series is the latest attempt to support kexec on TDX host following Dave's suggestion to use a percpu boolean to control WBINVD during kexec. It allows the TDX host and the kexec/kdump to be turned on together in the Kconfig, and enables kexec/kdump on most of the TDX platforms (except SPR and EMR due to a TDX erratum).
Hi Dave,
Now the first two patches have Boris/Tom's Reviewed-by. TDX patches also received RBs from Rick and TDX developers. The last KVM patch also has Paolo's Acked-by. Since last version only the last KVM patch has minor updates (to address comments from Sean). Could you help to review this series, and if looks good to you, consider merging?
Btw, we also considered removing the last patch since previously we hadn't met the "kexec-ing time race" [*]. I did more tests on more TDX machines last week. I still didn't see any kexec failure but I saw the chance of meeting this race was getting higher on a GNR machine with 256 CPUs (I saw NMIs were needed to stop remote CPUs during kexec). So to be safe, we think we should keep the last patch.
[*] native_stop_other_cpus() firstly sends normal REBOOT vector IPIs to remote CPUs and waits for them to stop. When that times out, it sends NMIs to the still-alive CPUs and waits them to stop. The race _may_ happen when NMIs are needed albeit the chance is rare. While we haven't ever seen it in the real world, patch 7 should close any theoretical widening of the race by TDX.
v6 -> v7:
- Address comments from Sean/Paolo for last patch (see it for details).
- Collect Boris's Reviewed-by. (Thanks!)
- Regenerate this series based on tip/x86/tdx.
v6: https://lore.kernel.org/kvm/[email protected]/
v5 -> v6:
- Regenerate based on latest tip/master.
- Rename do_seamcall() to __seamcall_dirty_cache() - Rick.
- Collect Reviewed-by tags from Tom, Rick, Chao (thanks!).
v5: https://lore.kernel.org/kvm/[email protected]/
v4 -> v5:
- Address comments from Tom, Hpa and Chao (nothing major)
- RELOC_KERNEL_HOST_MEM_ACTIVE -> RELOC_KERNEL_HOST_MEM_ENC_ACTIVE in patch 1 (Tom)
- Add a comment to explain only RELOC_KERNEL_PRESERVE_CONTEXT is restored after jumping back from peer kernel for preserved_context kexec in patch 1.
- Use testb instead of testq to save 3 bytes in patch 1 (Hpa)
- Remove the unneeded 'ret' local variable in do_seamcall() (Chao)
v4: https://lore.kernel.org/kvm/[email protected]/
v3 -> v4:
- Rebase to latest tip/master.
- Add a cleanup patch to consolidate relocate_kernel()'s last two function parameters -- Boris.
- Address comments received -- please see individual patches.
- Collect tags (Tom, Rick, binbin).
v3: https://lore.kernel.org/kvm/[email protected]/
(For more history please see v3 coverletter.)
=== More information ===
TDX private memory is memory that is encrypted with private Host Key IDs (HKID). If the kernel has ever enabled TDX, part of system memory remains TDX private memory when kexec happens. E.g., the PAMT (Physical Address Metadata Table) pages used by the TDX module to track each TDX memory page's state are never freed once the TDX module is initialized. TDX guests also have guest private memory and secure-EPT pages.
After kexec, the new kernel will have no knowledge of which memory page was used as TDX private page and can use all memory as regular memory.
1) Cache flush
Per TDX 1.5 base spec "8.6.1.Platforms not Using ACT: Required Cache Flush and Initialization by the Host VMM", to support kexec for TDX, the kernel needs to flush cache to make sure there's no dirty cachelines of TDX private memory left over to the new kernel (when the TDX module reports TDX_FEATURES.CLFLUSH_BEFORE_ALLOC as 1 in the global metadata for the platform). The kernel also needs to make sure there's no more TDX activity (no SEAMCALL) after cache flush so that no new dirty cachelines of TDX private memory are generated.
SME has similar requirement. SME kexec support uses WBINVD to do the cache flush. WBINVD is able to flush cachelines associated with any HKID. Reuse the WBINVD introduced by SME to flush cache for TDX.
Currently the kernel explicitly checks whether the hardware supports SME and only does WBINVD if true. Instead of adding yet another TDX specific check, this series uses a percpu boolean to indicate whether WBINVD is needed on that CPU during kexec.
2) Reset TDX private memory using MOVDIR64B
The TDX spec (the aforementioned section) also suggests the kernel *should* use MOVDIR64B to clear TDX private page before the kernel reuses it as regular one.
However, in reality the situation can be more flexible. Per TDX 1.5 base spec ("Table 16.2: Non-ACT Platforms Checks on Memory Reads in Ci Mode" and "Table 16.3: Non-ACT Platforms Checks on Memory Reads in Li Mode"), the read/write to TDX private memory using shared KeyID without integrity check enabled will not poison the memory and cause machine check.
Note on the platforms with ACT (Access Control Table), there's no integrity check involved thus no machine check is possible to happen due to memory read/write using different KeyIDs.
KeyID 0 (TME key) doesn't support integrity check. This series chooses to NOT reset TDX private memory but leave TDX private memory as-is to the new kernel. As mentioned above, in practice it is safe to do so.
3) One limitation
If the kernel has ever enabled TDX, after kexec the new kernel won't be able to use TDX anymore. This is because when the new kernel tries to initialize TDX module it will fail on the first SEAMCALL due to the module has already been initialized by the old kernel.
More (non-trivial) work will be needed for the new kernel to use TDX, e.g., one solution is to just reload the TDX module from the location where BIOS loads the TDX module (/boot/efi/EFI/TDX/). This series doesn't cover this, but leave this as future work.
4) Kdump support
This series also enables kdump with TDX, but no special handling is needed for crash kexec (except turning on the Kconfig option):
- kdump kernel uses reserved memory from the old kernel as system ram, and the old kernel will never use the reserved memory as TDX memory.
- /proc/vmcore contains TDX private memory pages. It's meaningless to read them, but it doesn't do any harm either.
5) TDX "partial write machine check" erratum
On the platform with TDX erratum, a partial write (a write transaction of less than a cacheline lands at memory controller) to TDX private memory poisons that memory, and a subsequent read triggers machine check. On those platforms, the kernel needs to reset TDX private memory before jumping to the new kernel otherwise the new kernel may see unexpected machine check.
The kernel currently doesn't track which page is TDX private memory. It's not trivial to reset TDX private memory. For simplicity, this series simply disables kexec/kdump for such platforms. This can be enhanced in the future.
Kai Huang (7):
x86/kexec: Consolidate relocate_kernel() function parameters x86/sme: Use percpu boolean to control WBINVD during kexec x86/virt/tdx: Mark memory cache state incoherent when making SEAMCALL x86/kexec: Disable kexec/kdump on platforms with TDX partial write
erratum
x86/virt/tdx: Remove the !KEXEC_CORE dependency x86/virt/tdx: Update the kexec section in the TDX documentation
KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
Documentation/arch/x86/tdx.rst | 14 ++++----- arch/x86/Kconfig | 1 - arch/x86/include/asm/kexec.h | 12 ++++++-- arch/x86/include/asm/processor.h | 2 ++ arch/x86/include/asm/tdx.h | 26 +++++++++++++++- arch/x86/kernel/cpu/amd.c | 17 +++++++++++ arch/x86/kernel/machine_kexec_64.c | 44 ++++++++++++++++++++++------ arch/x86/kernel/process.c | 24 +++++++-------- arch/x86/kernel/relocate_kernel_64.S | 36 +++++++++++++++-------- arch/x86/kvm/vmx/tdx.c | 12 ++++++++ arch/x86/virt/vmx/tdx/tdx.c | 16 ++++++++-- 11 files changed, 157 insertions(+), 47 deletions(-)
base-commit: 01fb93a363e0583a3ce48098aca5ab9825a5b790
Signature · 1 line
2.50.1
PATCH v7 1/7 x86/kexec: Consolidate relocate_kernel() function parameters
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).
---
v6 -> v7:
- Add Boris's RB.
v5 -> v6:
- Add Tom's RB.
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(-)
arch/x86/include/asm/kexec.h +10 -2
@@ -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
arch/x86/kernel/machine_kexec_64.c +13 -9
@@ -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)
arch/x86/kernel/relocate_kernel_64.S +15 -10
@@ -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 */
Signature · 1 line
2.50.1
Re: [PATCH v7 1/7] x86/kexec: Consolidate relocate_kernel() function parameters
Quoted 13 lines · Kai Huang
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.
Quoted 7 lines
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 <[email protected]>Reviewed-by Tom Lendacky <[email protected]>Reviewed-by Borislav Petkov (AMD) <[email protected]>
PATCH v7 2/7 x86/sme: Use percpu boolean to control WBINVD during kexec
In reply to Kai HuangTL;DR:
Prepare to unify how TDX and SME do cache flushing during kexec by making a percpu boolean control whether to do the WBINVD.
-- Background --
On SME platforms, dirty cacheline aliases with and without encryption bit can coexist, and the CPU can flush them back to memory in random order. During kexec, the caches must be flushed before jumping to the new kernel otherwise the dirty cachelines could silently corrupt the memory used by the new kernel due to different encryption property.
TDX also needs a cache flush during kexec for the same reason. It would be good to have a generic way to flush the cache instead of scattering checks for each feature all around.
When SME is enabled, the kernel basically encrypts all memory including the kernel itself and a simple memory write from the kernel could dirty cachelines. Currently, the kernel uses WBINVD to flush the cache for SME during kexec in two places:
1) the one in stop_this_cpu() for all remote CPUs when the kexec-ing CPU stops them;
2) the one in the relocate_kernel() where the kexec-ing CPU jumps to the new kernel.
-- Solution --
Unlike SME, TDX can only dirty cachelines when it is used (i.e., when SEAMCALLs are performed). Since there are no more SEAMCALLs after the aforementioned WBINVDs, leverage this for TDX.
To unify the approach for SME and TDX, use a percpu boolean to indicate the cache may be in an incoherent state and needs flushing during kexec, and set the boolean for SME. TDX can then leverage it.
While SME could use a global flag (since it's enabled at early boot and enabled on all CPUs), the percpu flag fits TDX better:
The percpu flag can be set when a CPU makes a SEAMCALL, and cleared when another WBINVD on the CPU obviates the need for a kexec-time WBINVD. Saving kexec-time WBINVD is valuable, because there is an existing race[*] where kexec could proceed while another CPU is active. WBINVD could make this race worse, so it's worth skipping it when possible.
-- Side effect to SME --
Today the first WBINVD in the stop_this_cpu() is performed when SME is *supported* by the platform, and the second WBINVD is done in relocate_kernel() when SME is *activated* by the kernel. Make things simple by changing to do the second WBINVD when the platform supports SME. This allows the kernel to simply turn on this percpu boolean when bringing up a CPU by checking whether the platform supports SME.
No other functional change intended.
[*] The aforementioned race:
During kexec native_stop_other_cpus() is called to stop all remote CPUs before jumping to the new kernel. native_stop_other_cpus() firstly sends normal REBOOT vector IPIs to stop remote CPUs and waits them to stop. If that times out, it sends NMI to stop the CPUs that are still alive. The race may happen when native_stop_other_cpus() has to send NMIs and could potentially result in the system hang (see [1] for more information).
---
v6 -> v7:
- Add Boris's RB.
v5 -> v6:
- No change
v4 -> v5:
- Code rebase due to change RELOC_KERNEL_HOST_MEM_ACTIVE to RELOC_KERNEL_HOST_MEM_ENC_ACTIVE.
v3 -> v4:
- Simplify the changelog using AI -- Boris
- Call out "Test CPUID bit directly due to mem_encrypt=off" in the comment -- Boris
- Add a comment to explain the percpu boolean -- Boris
- s/wbinvd/WBINVD -- Boris
- Code update due to patch 1 being added
--- arch/x86/include/asm/kexec.h | 4 ++-- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/amd.c | 17 +++++++++++++++++ arch/x86/kernel/machine_kexec_64.c | 14 ++++++++++---- arch/x86/kernel/process.c | 24 +++++++++++------------- arch/x86/kernel/relocate_kernel_64.S | 13 ++++++++++--- 6 files changed, 52 insertions(+), 22 deletions(-)
arch/x86/include/asm/kexec.h +2 -2
@@ -17,8 +17,8 @@#include <linux/bits.h> -#define RELOC_KERNEL_PRESERVE_CONTEXT BIT(0) -#define RELOC_KERNEL_HOST_MEM_ENC_ACTIVE BIT(1) +#define RELOC_KERNEL_PRESERVE_CONTEXT BIT(0) +#define RELOC_KERNEL_CACHE_INCOHERENT BIT(1)#endif
arch/x86/include/asm/processor.h +2 -0
@@ -731,6 +731,8 @@ void __noreturn stop_this_cpu(void *dummy);void microcode_check (struct cpuinfo_x86 *prev_info);void store_cpu_caps (struct cpuinfo_x86 *info); +DECLARE_PER_CPU (bool, cache_state_incoherent); +enum l1tf_mitigations {L1TF_MITIGATION_OFF ,L1TF_MITIGATION_AUTO ,
arch/x86/kernel/cpu/amd.c +17 -0
@@ -545,6 +545,23 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) {u64 msr; +/* +* Mark using WBINVD is needed during kexec on processors that +* support SME. This provides support for performing a successful +* kexec when going from SME inactive to SME active (or vice-versa). +* +* The cache must be cleared so that if there are entries with the +* same physical address, both with and without the encryption bit, +* they don't race each other when flushed and potentially end up +* with the wrong entry being committed to memory. +* +* Test the CPUID bit directly because with mem_encrypt=off the +* BSP will clear the X86_FEATURE_SME bit and the APs will not +* see it set after that. +*/ +if (c->extended_cpuid_level >=0x8000001f && (cpuid_eax (0x8000001f ) &BIT (0 ))) +__this_cpu_write (cache_state_incoherent, true); +/* * BIOS support is required for SME and SEV. * For SME: If BIOS has enabled SME then adjust x86_phys_bits by
arch/x86/kernel/machine_kexec_64.c +10 -4
@@ -29,6 +29,7 @@#include <asm/set_memory.h> #include <asm/cpu.h> #include <asm/efi.h> +#include <asm/processor.h> #ifdef CONFIG_ACPI /*
@@ -426,11 +427,11 @@ void __nocfi machine_kexec(struct kimage *image) 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. +* This must be done before load_segments() since it resets +* GS to 0 and percpu data needs the correct GS to work. */ -if (cc_platform_has (CC_ATTR_HOST_MEM_ENCRYPT )) - relocate_kernel_flags |=RELOC_KERNEL_HOST_MEM_ENC_ACTIVE ; +if (this_cpu_read (cache_state_incoherent)) + relocate_kernel_flags |=RELOC_KERNEL_CACHE_INCOHERENT ;/* * The segment registers are funny things, they have both a
@@ -441,6 +442,11 @@ void __nocfi machine_kexec(struct kimage *image)* * Take advantage of this here by force loading the segments, * before the GDT is zapped with an invalid value. +* +* load_segments() resets GS to 0. Don't make any function call +* after here since call depth tracking uses percpu variables to +* operate (relocate_kernel() is explicitly ignored by call depth +* tracking). */ load_segments ();
arch/x86/kernel/process.c +11 -13
@@ -88,6 +88,16 @@ EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);DEFINE_PER_CPU (bool, __tss_limit_invalid);EXPORT_PER_CPU_SYMBOL_GPL (__tss_limit_invalid); +/* +* The cache may be in an incoherent state and needs flushing during kexec. +* E.g., on SME/TDX platforms, dirty cacheline aliases with and without +* encryption bit(s) can coexist and the cache needs to be flushed before +* booting to the new kernel to avoid the silent memory corruption due to +* dirty cachelines with different encryption property being written back +* to the memory. +*/ +DEFINE_PER_CPU (bool, cache_state_incoherent); +/* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread.
@@ -827,19 +837,7 @@ void __noreturn stop_this_cpu(void *dummy)disable_local_APIC ();mcheck_cpu_clear (c); -/* -* Use wbinvd on processors that support SME. This provides support -* for performing a successful kexec when going from SME inactive -* to SME active (or vice-versa). The cache must be cleared so that -* if there are entries with the same physical address, both with and -* without the encryption bit, they don't race each other when flushed -* and potentially end up with the wrong entry being committed to -* memory. -* -* Test the CPUID bit directly because the machine might've cleared -* X86_FEATURE_SME due to cmdline options. -*/ -if (c->extended_cpuid_level >=0x8000001f && (cpuid_eax (0x8000001f ) &BIT (0 ))) +if (this_cpu_read (cache_state_incoherent))wbinvd ();/*
arch/x86/kernel/relocate_kernel_64.S +10 -3
@@ -198,14 +198,21 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movq %r9, %cr3 /* + * If the memory cache is in incoherent state, e.g., due to + * memory encryption, do WBINVD to flush cache. + * * If SME is active, there could be old encrypted cache line * entries that will conflict with the now unencrypted memory * used by kexec. Flush the caches before copying the kernel. + * + * Note SME sets this flag to true when the platform supports + * SME, so the WBINVD is performed even SME is not activated + * by the kernel. But this has no harm. */ - testb $RELOC_KERNEL_HOST_MEM_ENC_ACTIVE, %r11b - jz .Lsme_off + testb $RELOC_KERNEL_CACHE_INCOHERENT, %r11b + jz .Lnowbinvd wbinvd -.Lsme_off: +.Lnowbinvd: call swap_pages
Signature · 1 line
2.50.1
PATCH v7 3/7 x86/virt/tdx: Mark memory cache state incoherent when making SEAMCALL
In reply to Kai HuangOn TDX platforms, dirty cacheline aliases with and without encryption bits can coexist, and the cpu can flush them back to memory in random order. During kexec, the caches must be flushed before jumping to the new kernel otherwise the dirty cachelines could silently corrupt the memory used by the new kernel due to different encryption property.
A percpu boolean is used to mark whether the cache of a given CPU may be in an incoherent state, and the kexec performs WBINVD on the CPUs with that boolean turned on.
For TDX, only the TDX module or the TDX guests can generate dirty cachelines of TDX private memory, i.e., they are only generated when the kernel does a SEAMCALL.
Set that boolean when the kernel does SEAMCALL so that kexec can flush the cache correctly.
The kernel provides both the __seamcall*() assembly functions and the seamcall*() wrapper ones which additionally handle running out of entropy error in a loop. Most of the SEAMCALLs are called using the seamcall*(), except TDH.VP.ENTER and TDH.PHYMEM.PAGE.RDMD which are called using __seamcall*() variant directly.
To cover the two special cases, add a new __seamcall_dirty_cache() helper which only sets the percpu boolean and calls the __seamcall*(), and change the special cases to use the new helper. To cover all other SEAMCALLs, change seamcall*() to call the new helper.
For the SEAMCALLs invoked via seamcall*(), they can be made from both task context and IRQ disabled context. Given SEAMCALL is just a lengthy instruction (e.g., thousands of cycles) from kernel's point of view and preempt_{disable|enable}() is cheap compared to it, just unconditionally disable preemption during setting the boolean and making SEAMCALL.
--- arch/x86/include/asm/tdx.h | 25 ++++++++++++++++++++++++- arch/x86/virt/vmx/tdx/tdx.c | 4 ++-- 2 files changed, 26 insertions(+), 3 deletions(-)
arch/x86/include/asm/tdx.h +24 -1
@@ -102,10 +102,31 @@ u64 __seamcall_ret(u64 fn, struct tdx_module_args *args);u64 __seamcall_saved_ret (u64 fn,struct tdx_module_args *args);void tdx_init (void ); +#include <linux/preempt.h> #include <asm/archrandom.h> +#include <asm/processor.h> typedef u64 (*sc_func_t )(u64 fn,struct tdx_module_args *args); +static __always_inline u64 __seamcall_dirty_cache(sc_func_t func, u64 fn, +struct tdx_module_args *args) +{ +lockdep_assert_preemption_disabled (); + +/* +* SEAMCALLs are made to the TDX module and can generate dirty +* cachelines of TDX private memory. Mark cache state incoherent +* so that the cache can be flushed during kexec. +* +* This needs to be done before actually making the SEAMCALL, +* because kexec-ing CPU could send NMI to stop remote CPUs, +* in which case even disabling IRQ won't help here. +*/ +this_cpu_write (cache_state_incoherent, true); + +return func (fn, args); +} + static __always_inline u64 sc_retry(sc_func_t func, u64 fn,struct tdx_module_args *args) {
@@ -113,7 +134,9 @@ static __always_inline u64 sc_retry(sc_func_t func, u64 fn,u64 ret;do { - ret =func (fn, args); +preempt_disable (); + ret =__seamcall_dirty_cache (func, fn, args); +preempt_enable (); }while (ret ==TDX_RND_NO_ENTROPY && --retry);return ret;
arch/x86/virt/vmx/tdx/tdx.c +2 -2
@@ -1268,7 +1268,7 @@ static bool paddr_is_tdx_private(unsigned long phys)return false;/* Get page type from the TDX module */ - sret =__seamcall_ret (TDH_PHYMEM_PAGE_RDMD , &args); + sret =__seamcall_dirty_cache (__seamcall_ret,TDH_PHYMEM_PAGE_RDMD , &args);/* * The SEAMCALL will not return success unless there is a
@@ -1524,7 +1524,7 @@ noinstr __flatten u64 tdh_vp_enter(struct tdx_vp *td, struct tdx_module_args *ar { args->rcx =tdx_tdvpr_pa (td); -return __seamcall_saved_ret (TDH_VP_ENTER , args); +return __seamcall_dirty_cache (__seamcall_saved_ret,TDH_VP_ENTER , args); }EXPORT_SYMBOL_GPL (tdh_vp_enter);
Signature · 1 line
2.50.1
PATCH v7 4/7 x86/kexec: Disable kexec/kdump on platforms with TDX partial write erratum
In reply to Kai HuangSome early TDX-capable platforms have an erratum: A kernel partial write (a write transaction of less than cacheline lands at memory controller) to TDX private memory poisons that memory, and a subsequent read triggers a machine check.
On those platforms, the old kernel must reset TDX private memory before jumping to the new kernel, otherwise the new kernel may see unexpected machine check. Currently the kernel doesn't track which page is a TDX private page. For simplicity just fail kexec/kdump for those platforms.
Leverage the existing machine_kexec_prepare() to fail kexec/kdump by adding the check of the presence of the TDX erratum (which is only checked for if the kernel is built with TDX host support). This rejects kexec/kdump when the kernel is loading the kexec/kdump kernel image.
The alternative is to reject kexec/kdump when the kernel is jumping to the new kernel. But for kexec this requires adding a new check (e.g., arch_kexec_allowed()) in the common code to fail kernel_kexec() at early stage. Kdump (crash_kexec()) needs similar check, but it's hard to justify because crash_kexec() is not supposed to abort.
It's feasible to further relax this limitation, i.e., only fail kexec when TDX is actually enabled by the kernel. But this is still a half measure compared to resetting TDX private memory so just do the simplest thing for now.
The impact to userspace is the users will get an error when loading the kexec/kdump kernel image:
kexec_load failed: Operation not supported
This might be confusing to the users, thus also print the reason in the dmesg:
[..] kexec: Not allowed on platform with tdx_pw_mce bug.
--- arch/x86/kernel/machine_kexec_64.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
arch/x86/kernel/machine_kexec_64.c +16 -0
@@ -347,6 +347,22 @@ int machine_kexec_prepare(struct kimage *image)unsigned long reloc_end = (unsigned long )__relocate_kernel_end;int result; +/* +* Some early TDX-capable platforms have an erratum. A kernel +* partial write (a write transaction of less than cacheline +* lands at memory controller) to TDX private memory poisons that +* memory, and a subsequent read triggers a machine check. +* +* On those platforms the old kernel must reset TDX private +* memory before jumping to the new kernel otherwise the new +* kernel may see unexpected machine check. For simplicity +* just fail kexec/kdump on those platforms. +*/ +if (boot_cpu_has_bug (X86_BUG_TDX_PW_MCE )) { +pr_info_once ("Not allowed on platform with tdx_pw_mce bug\n" ); +return -EOPNOTSUPP ; + } +/* Setup the identity mapped 64bit page table */ result =init_pgtable (image,__pa (control_page));if (result)
Signature · 1 line
2.50.1
PATCH v7 5/7 x86/virt/tdx: Remove the !KEXEC_CORE dependency
In reply to Kai HuangDuring kexec it is now guaranteed that all dirty cachelines of TDX private memory are flushed before jumping to the new kernel. The TDX private memory from the old kernel will remain as TDX private memory in the new kernel, but it is OK because kernel read/write to TDX private memory will never cause machine check, except on the platforms with the TDX partial write erratum, which has already been handled.
It is safe to allow kexec to work together with TDX now. Remove the !KEXEC_CORE dependency.
--- arch/x86/Kconfig | 1 - 1 file changed, 1 deletion(-)
arch/x86/Kconfig +0 -1
@@ -1896,7 +1896,6 @@ config INTEL_TDX_HOST depends on X86_X2APIC select ARCH_KEEP_MEMBLOCK depends on CONTIG_ALLOC - depends on !KEXEC_CORE depends on X86_MCE help Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
Signature · 1 line
2.50.1
PATCH v7 6/7 x86/virt/tdx: Update the kexec section in the TDX documentation
In reply to Kai HuangTDX host kernel now supports kexec/kdump. Update the documentation to reflect that.
Opportunistically, remove the parentheses in "Kexec()" and move this section under the "Erratum" section because the updated "Kexec" section now refers to that erratum.
--- Documentation/arch/x86/tdx.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
Documentation/arch/x86/tdx.rst +7 -7
@@ -142,13 +142,6 @@ but depends on the BIOS to behave correctly. Note TDX works with CPU logical online/offline, thus the kernel still allows to offline logical CPU and online it again. -Kexec() -~~~~~~~ - -TDX host support currently lacks the ability to handle kexec. For -simplicity only one of them can be enabled in the Kconfig. This will be -fixed in the future. - Erratum ~~~~~~~
@@ -171,6 +164,13 @@ If the platform has such erratum, the kernel prints additional message in machine check handler to tell user the machine check may be caused by kernel bug on TDX private memory. +Kexec +~~~~~~~ + +Currently kexec doesn't work on the TDX platforms with the aforementioned +erratum. It fails when loading the kexec kernel image. Otherwise it +works normally. + Interaction vs S3 and deeper states ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signature · 1 line
2.50.1
PATCH v7 7/7 KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
In reply to Kai HuangOn TDX platforms, during kexec, the kernel needs to make sure there are no dirty cachelines of TDX private memory before booting to the new kernel to avoid silent memory corruption to the new kernel.
During kexec, the kexec-ing CPU firstly invokes native_stop_other_cpus() to stop all remote CPUs before booting to the new kernel. The remote CPUs will then execute stop_this_cpu() to stop themselves.
The kernel has a percpu boolean to indicate whether the cache of a CPU may be in incoherent state. In stop_this_cpu(), the kernel does WBINVD if that percpu boolean is true.
TDX turns on that percpu boolean on a CPU when the kernel does SEAMCALL. This makes sure the caches will be flushed during kexec.
However, the native_stop_other_cpus() and stop_this_cpu() have a "race"[1] which is extremely rare to happen but could cause the system to hang. Doing WBINVD in stop_this_cpu() could increase the chance of the race happening.
Explicitly flush cache in tdx_disable_virtualization_cpu() after which no more TDX activity can happen on this cpu. This moves the WBINVD to an earlier stage than stop_this_cpus(), avoiding a possibly lengthy operation at a time where it could cause this race.
---
v6 -> v7:
- Remove the tdx_cpu_flush_cache() stub. -- Sean
- Rename tdx_cpu_flush_cache() to tdx_cpu_flush_cache_for_kexec(). -- Paolo
- Trim down changelog a little bit. -- Sean.
v5 -> v6:
- Add Chao's RB.
v4 -> v5:
- No change
v3 -> v4:
- Change doing wbinvd() from rebooting notifier to tdx_disable_virtualization_cpu() to cover the case where more SEAMCALL can be made after cache flush, i.e., doing kexec when there's TD alive. - Chao.
- Add check to skip wbinvd if the boolean is false. -- Chao
- Fix typo in the comment -- Binbin.
--- arch/x86/include/asm/tdx.h | 1 + arch/x86/kvm/vmx/tdx.c | 12 ++++++++++++ arch/x86/virt/vmx/tdx/tdx.c | 12 ++++++++++++ 3 files changed, 25 insertions(+)
arch/x86/include/asm/tdx.h +1 -0
@@ -219,6 +219,7 @@ u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u6u64 tdh_phymem_cache_wb (bool resume);u64 tdh_phymem_page_wbinvd_tdr (struct tdx_td *td);u64 tdh_phymem_page_wbinvd_hkid (u64 hkid,struct page *page); +void tdx_cpu_flush_cache_for_kexec (void );#else static inline void tdx_init (void ) { }static inline int tdx_cpu_enable (void ) {return -ENODEV ; }
arch/x86/kvm/vmx/tdx.c +12 -0
@@ -423,6 +423,18 @@ void tdx_disable_virtualization_cpu(void)tdx_flush_vp (&arg); }local_irq_restore (flags); + +/* +* No more TDX activity on this CPU from here. Flush cache to +* avoid having to do WBINVD in stop_this_cpu() during kexec. +* +* Kexec calls native_stop_other_cpus() to stop remote CPUs +* before booting to new kernel, but that code has a "race" +* when the normal REBOOT IPI times out and NMIs are sent to +* remote CPUs to stop them. Doing WBINVD in stop_this_cpu() +* could potentially increase the possibility of the "race". +*/ +tdx_cpu_flush_cache_for_kexec (); }#define TDX_SEAMCALL_RETRIES 10000
arch/x86/virt/vmx/tdx/tdx.c +12 -0
@@ -1872,3 +1872,15 @@ u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)return seamcall (TDH_PHYMEM_PAGE_WBINVD , &args); }EXPORT_SYMBOL_GPL (tdh_phymem_page_wbinvd_hkid); + +void tdx_cpu_flush_cache_for_kexec (void ) +{ +lockdep_assert_preemption_disabled (); + +if (!this_cpu_read (cache_state_incoherent)) +return ; + +wbinvd (); +this_cpu_write (cache_state_incoherent, false); +} +EXPORT_SYMBOL_GPL (tdx_cpu_flush_cache_for_kexec);
Signature · 1 line
2.50.1
Sean Christopherson
maintainerRe: [PATCH v7 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
Quoted 6 lines · Kai Huang
arch/x86/virt/vmx/tdx/tdx.c +0
-0@@ -1872,3 +1872,15 @@ u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)return seamcall (TDH_PHYMEM_PAGE_WBINVD , &args);
arch/x86/virt/vmx/tdx/tdx.c u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page) · line 1882
Quoted 10 lines
arch/x86/virt/vmx/tdx/tdx.c +8
-0}EXPORT_SYMBOL_GPL (tdh_phymem_page_wbinvd_hkid); + +void tdx_cpu_flush_cache_for_kexec (void ) +{ +lockdep_assert_preemption_disabled (); + +if (!this_cpu_read (cache_state_incoherent)) +return ; +
Can you add a comment here to explain why this is done even if the kernel doesn't support kexec? I've no objection to the superfluous flushing, but I've spent far too much time deciphering old commits where the changelog says one thing and the code does something else with no explanation. I don't want to be party to such crimes :-)
Quoted 7 lines
arch/x86/virt/vmx/tdx/tdx.c +4
-0+wbinvd (); +this_cpu_write (cache_state_incoherent, false); +} +EXPORT_SYMBOL_GPL (tdx_cpu_flush_cache_for_kexec);Signature · 1 line
2.50.1
Re: [PATCH v7 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
Quoted 4 lines · Sean Christopherson
Quoted 4 lines
arch/x86/virt/vmx/tdx/tdx.c +4
-0+void tdx_cpu_flush_cache_for_kexec (void ) +{ +lockdep_assert_preemption_disabled (); +
Quoted 8 lines
arch/x86/virt/vmx/tdx/tdx.c u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page) · line 1882
Quoted 3 lines
arch/x86/virt/vmx/tdx/tdx.c +3
-0+if (!this_cpu_read (cache_state_incoherent)) +return ; +Can you add a comment here to explain why this is done even if the kernel doesn't support kexec? I've no objection to the superfluous flushing, but I've spent far too much time deciphering old commits where the changelog says one thing and the code does something else with no explanation. I don't want to be party to such crimes 🙂
You mean as opposed to #ifdef'ing it out?
Looking at the code again, I completely agree in concept. The connection between TDX, kexec and 'cache_state_incoherent' is totally opaque.
Edgecombe, Rick P
maintainerRe: [PATCH v7 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
Quoted 10 lines · Dave Hansen
Quoted 5 lines
Can you add a comment here to explain why this is done even if the kernel doesn't support kexec? I've no objection to the superfluous flushing, but I've spent far too much time deciphering old commits where the changelog says one thing and the code does something else with no explanation. I don't want to be party to such crimes 🙂
You mean as opposed to #ifdef'ing it out?
Looking at the code again, I completely agree in concept. The connection between TDX, kexec and '
cache_state_incoherent' is totally opaque.
So what do we want to do here? Everyone agrees something must be done. We have two votes for compile out from the KVM maintainer side. Dave, not clear if this is ok with you or you prefer just a comment.
My 2 cents. Let's just compile it out with a stub (not an IS_ENABLED() check) because it also means we won't have a "kexec" symbol when kexec is not configured. For the comment, I think the one in the sole caller is enough. But if we want some, here is a suggestion to take or leave:
void tdx_cpu_flush_cache_for_kexec(void)
{
lockdep_assert_preemption_disabled();
/* Only flush if a SEAMCALL might have dirtied the cache */
if (!this_cpu_read(cache_state_incoherent))
return;
wbinvd();
/*
* Clear the tracking so racy shutdown logic doesn't
* need to flush later during kexec.
*/
this_cpu_write(cache_state_incoherent, false);
}EXPORT_SYMBOL_GPL(tdx_cpu_flush_cache_for_kexec);
Paolo, Kai and I are glad to take you up on your offer to take this over. Hopefully it only needs one more revision. The plan was to take it through tip with acks for the KVM patch. Do you want to reverse that and get acks for the arch/x86 parts?
Paolo Bonzini
maintainerRe: [PATCH v7 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
In reply to Sean ChristophersonQuoted 5 lines · Sean Christopherson
Can you add a comment here to explain why this is done even if the kernel doesn't support kexec? I've no objection to the superfluous flushing, but I've spent far too much time deciphering old commits where the changelog says one thing and the code does something else with no explanation. I don't want to be party to such crimes :-)
I asked on the review for v6 to make this conditional on CONFIG_KEXEC_CORE with a stub; Kai said he'd rather not and I acquiesced, but now it looks like we're going to need a v8 just for this comment or to follow that suggestion of mine, which I still prefer to a comment.
To be honest I've never felt so frustrated in ~10 years of participating to Linux, and this is not even *my* code. Not your fault though.
Kai, if you're also frustrated I can handle the v8. As you prefer.
Paolo
Paolo
Sean Christopherson
maintainerRe: [PATCH v7 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs
Quoted 11 lines · Paolo Bonzini
Quoted 5 lines · Sean Christopherson
Can you add a comment here to explain why this is done even if the kernel doesn't support kexec? I've no objection to the superfluous flushing, but I've spent far too much time deciphering old commits where the changelog says one thing and the code does something else with no explanation. I don't want to be party to such crimes :-)
I asked on the review for v6 to make this conditional on
CONFIG_KEXEC_COREwith a stub; Kai said he'd rather not and I acquiesced, but now it looks like we're going to need a v8 just for this comment or to follow that suggestion of mine, which I still prefer to a comment.
FWIW, I also prefer conditioning the flush with an #ifdef (we could even have both an #ifdef and a comment), but it's not a hill I'll die on.