- Introduce configfs-tsm as a shared ABI for confidential computing
attestation reports
- Convert sev-guest to additionally support configfs-tsm alongside its
vendor specific ioctl()
- Added signed attestation report retrieval to the tdx-guest driver
forgoing a new vendor specific ioctl()
- Misc. cleanups and a new __free() annotation for kvfree()
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQSbo+XnGs+rwLz9XGXfioYZHlFsZwUCZUQhiQAKCRDfioYZHlFs
Z2gMAQCJdtP0f2kH+pvf3oxAkA1OubKBqJqWOppeyrhTsNMpDQEA9ljXH9h7eRB/
2NQ6USrU6jqcdu3gB5Tzq8J/ZZabMQU=
=1Eiv
-----END PGP SIGNATURE-----
Merge tag 'tsm-for-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/linux
Pull unified attestation reporting from Dan Williams:
"In an ideal world there would be a cross-vendor standard attestation
report format for confidential guests along with a common device
definition to act as the transport.
In the real world the situation ended up with multiple platform
vendors inventing their own attestation report formats with the
SEV-SNP implementation being a first mover to define a custom
sev-guest character device and corresponding ioctl(). Later, this
configfs-tsm proposal intercepted an attempt to add a tdx-guest
character device and a corresponding new ioctl(). It also anticipated
ARM and RISC-V showing up with more chardevs and more ioctls().
The proposal takes for granted that Linux tolerates the vendor report
format differentiation until a standard arrives. From talking with
folks involved, it sounds like that standardization work is unlikely
to resolve anytime soon. It also takes the position that kernfs ABIs
are easier to maintain than ioctl(). The result is a shared configfs
mechanism to return per-vendor report-blobs with the option to later
support a standard when that arrives.
Part of the goal here also is to get the community into the
"uncomfortable, but beneficial to the long term maintainability of the
kernel" state of talking to each other about their differentiation and
opportunities to collaborate. Think of this like the device-driver
equivalent of the common memory-management infrastructure for
confidential-computing being built up in KVM.
As for establishing an "upstream path for cross-vendor
confidential-computing device driver infrastructure" this is something
I want to discuss at Plumbers. At present, the multiple vendor
proposals for assigning devices to confidential computing VMs likely
needs a new dedicated repository and maintainer team, but that is a
discussion for v6.8.
For now, Greg and Thomas have acked this approach and this is passing
is AMD, Intel, and Google tests.
Summary:
- Introduce configfs-tsm as a shared ABI for confidential computing
attestation reports
- Convert sev-guest to additionally support configfs-tsm alongside
its vendor specific ioctl()
- Added signed attestation report retrieval to the tdx-guest driver
forgoing a new vendor specific ioctl()
- Misc cleanups and a new __free() annotation for kvfree()"
* tag 'tsm-for-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/linux:
virt: tdx-guest: Add Quote generation support using TSM_REPORTS
virt: sevguest: Add TSM_REPORTS support for SNP_GET_EXT_REPORT
mm/slab: Add __free() support for kvfree
virt: sevguest: Prep for kernel internal get_ext_report()
configfs-tsm: Introduce a shared ABI for attestation reports
virt: coco: Add a coco/Makefile and coco/Kconfig
virt: sevguest: Fix passing a stack buffer as a scatterlist target
* Handle retrying/resuming page conversion hypercalls
* Make sure to use the (shockingly) reliable TSC in TDX guests
-----BEGIN PGP SIGNATURE-----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=FJ1Y
-----END PGP SIGNATURE-----
Merge tag 'x86_tdx_for_6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 TDX updates from Dave Hansen:
"The majority of this is a rework of the assembly and C wrappers that
are used to talk to the TDX module and VMM. This is a nice cleanup in
general but is also clearing the way for using this code when Linux is
the TDX VMM.
There are also some tidbits to make TDX guests play nicer with Hyper-V
and to take advantage the hardware TSC.
Summary:
- Refactor and clean up TDX hypercall/module call infrastructure
- Handle retrying/resuming page conversion hypercalls
- Make sure to use the (shockingly) reliable TSC in TDX guests"
[ TLA reminder: TDX is "Trust Domain Extensions", Intel's guest VM
confidentiality technology ]
* tag 'x86_tdx_for_6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/tdx: Mark TSC reliable
x86/tdx: Fix __noreturn build warning around __tdx_hypercall_failed()
x86/virt/tdx: Make TDX_MODULE_CALL handle SEAMCALL #UD and #GP
x86/virt/tdx: Wire up basic SEAMCALL functions
x86/tdx: Remove 'struct tdx_hypercall_args'
x86/tdx: Reimplement __tdx_hypercall() using TDX_MODULE_CALL asm
x86/tdx: Make TDX_HYPERCALL asm similar to TDX_MODULE_CALL
x86/tdx: Extend TDX_MODULE_CALL to support more TDCALL/SEAMCALL leafs
x86/tdx: Pass TDCALL/SEAMCALL input/output registers via a structure
x86/tdx: Rename __tdx_module_call() to __tdcall()
x86/tdx: Make macros of TDCALLs consistent with the spec
x86/tdx: Skip saving output regs when SEAMCALL fails with VMFailInvalid
x86/tdx: Zero out the missing RSI in TDX_HYPERCALL macro
x86/tdx: Retry partially-completed page conversion hypercalls
In TDX guest, the attestation process is used to verify the TDX guest
trustworthiness to other entities before provisioning secrets to the
guest. The first step in the attestation process is TDREPORT
generation, which involves getting the guest measurement data in the
format of TDREPORT, which is further used to validate the authenticity
of the TDX guest. TDREPORT by design is integrity-protected and can
only be verified on the local machine.
To support remote verification of the TDREPORT in a SGX-based
attestation, the TDREPORT needs to be sent to the SGX Quoting Enclave
(QE) to convert it to a remotely verifiable Quote. SGX QE by design can
only run outside of the TDX guest (i.e. in a host process or in a
normal VM) and guest can use communication channels like vsock or
TCP/IP to send the TDREPORT to the QE. But for security concerns, the
TDX guest may not support these communication channels. To handle such
cases, TDX defines a GetQuote hypercall which can be used by the guest
to request the host VMM to communicate with the SGX QE. More details
about GetQuote hypercall can be found in TDX Guest-Host Communication
Interface (GHCI) for Intel TDX 1.0, section titled
"TDG.VP.VMCALL<GetQuote>".
Trusted Security Module (TSM) [1] exposes a common ABI for Confidential
Computing Guest platforms to get the measurement data via ConfigFS.
Extend the TSM framework and add support to allow an attestation agent
to get the TDX Quote data (included usage example below).
report=/sys/kernel/config/tsm/report/report0
mkdir $report
dd if=/dev/urandom bs=64 count=1 > $report/inblob
hexdump -C $report/outblob
rmdir $report
GetQuote TDVMCALL requires TD guest pass a 4K aligned shared buffer
with TDREPORT data as input, which is further used by the VMM to copy
the TD Quote result after successful Quote generation. To create the
shared buffer, allocate a large enough memory and mark it shared using
set_memory_decrypted() in tdx_guest_init(). This buffer will be re-used
for GetQuote requests in the TDX TSM handler.
Although this method reserves a fixed chunk of memory for GetQuote
requests, such one time allocation can help avoid memory fragmentation
related allocation failures later in the uptime of the guest.
Since the Quote generation process is not time-critical or frequently
used, the current version uses a polling model for Quote requests and
it also does not support parallel GetQuote requests.
Link: https://lore.kernel.org/lkml/169342399185.3934343.3035845348326944519.stgit@dwillia2-xfh.jf.intel.com/ [1]
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Erdem Aktas <erdemaktas@google.com>
Tested-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Tested-by: Peter Gonda <pgonda@google.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In x86 virtualization environments, including TDX, RDTSC instruction is
handled without causing a VM exit, resulting in minimal overhead and
jitters. On the other hand, other clock sources (such as HPET, ACPI
timer, APIC, etc.) necessitate VM exits to implement, resulting in more
fluctuating measurements compared to TSC. Thus, those clock sources are
not effective for calibrating TSC.
As a foundation, the host TSC is guaranteed to be invariant on any
system which enumerates TDX support.
TDX guests and the TDX module build on that foundation by enforcing:
- Virtual TSC is monotonously incrementing for any single VCPU;
- Virtual TSC values are consistent among all the TD’s VCPUs at the
level supported by the CPU:
+ VMM is required to set the same TSC_ADJUST;
+ VMM must not modify from initial value of TSC_ADJUST before
SEAMCALL;
- The frequency is determined by TD configuration:
+ Virtual TSC frequency is specified by VMM on TDH.MNG.INIT;
+ Virtual TSC starts counting from 0 at TDH.MNG.INIT;
The result is that a reliable TSC is a TDX architectural guarantee.
Use the TSC as the only reliable clock source in TD guests, bypassing
unstable calibration.
This is similar to what the kernel already does in some VMWare and
HyperV environments.
[ dhansen: changelog tweaks ]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Erdem Aktas <erdemaktas@google.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20231006144549.2633-1-kirill.shutemov%40linux.intel.com
Now 'struct tdx_hypercall_args' is basically 'struct tdx_module_args'
minus RCX. Although from __tdx_hypercall()'s perspective RCX isn't
used as shared register thus not part of input/output registers, it's
not worth to have a separate structure just due to one register.
Remove the 'struct tdx_hypercall_args' and use 'struct tdx_module_args'
instead in __tdx_hypercall() related code. This also saves the memory
copy between the two structures within __tdx_hypercall().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/798dad5ce24e9d745cf0e16825b75ccc433ad065.1692096753.git.kai.huang%40intel.com
Now the TDX_HYPERCALL asm is basically identical to the TDX_MODULE_CALL
with both '\saved' and '\ret' enabled, with two minor things though:
1) The way to restore the structure pointer is different
The TDX_HYPERCALL uses RCX as spare to restore the structure pointer,
but the TDX_MODULE_CALL assumes no spare register can be used. In other
words, TDX_MODULE_CALL already covers what TDX_HYPERCALL does.
2) TDX_MODULE_CALL only clears shared registers for TDH.VP.ENTER
For this just need to make that code available for the non-host case.
Thus, remove the TDX_HYPERCALL and reimplement the __tdx_hypercall()
using the TDX_MODULE_CALL.
Extend the TDX_MODULE_CALL to cover "clear shared registers" for
TDG.VP.VMCALL. Introduce a new __tdcall_saved_ret() to replace the
temporary __tdcall_hypercall().
The __tdcall_saved_ret() can also be used for those new TDCALLs which
require more input/output registers than the basic TDCALLs do.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/e68a2473fb6f5bcd78b078cae7510e9d0753b3df.1692096753.git.kai.huang%40intel.com
Now the 'struct tdx_hypercall_args' and 'struct tdx_module_args' are
almost the same, and the TDX_HYPERCALL and TDX_MODULE_CALL asm macro
share similar code pattern too. The __tdx_hypercall() and __tdcall()
should be unified to use the same assembly code.
As a preparation to unify them, simplify the TDX_HYPERCALL to make it
more like the TDX_MODULE_CALL.
The TDX_HYPERCALL takes the pointer of 'struct tdx_hypercall_args' as
function call argument, and does below extra things comparing to the
TDX_MODULE_CALL:
1) It sets RAX to 0 (TDG.VP.VMCALL leaf) internally;
2) It sets RCX to the (fixed) bitmap of shared registers internally;
3) It calls __tdx_hypercall_failed() internally (and panics) when the
TDCALL instruction itself fails;
4) After TDCALL, it moves R10 to RAX to return the return code of the
VMCALL leaf, regardless the '\ret' asm macro argument;
Firstly, change the TDX_HYPERCALL to take the same function call
arguments as the TDX_MODULE_CALL does: TDCALL leaf ID, and the pointer
to 'struct tdx_module_args'. Then 1) and 2) can be moved to the
caller:
- TDG.VP.VMCALL leaf ID can be passed via the function call argument;
- 'struct tdx_module_args' is 'struct tdx_hypercall_args' + RCX, thus
the bitmap of shared registers can be passed via RCX in the
structure.
Secondly, to move 3) and 4) out of assembly, make the TDX_HYPERCALL
always save output registers to the structure. The caller then can:
- Call __tdx_hypercall_failed() when TDX_HYPERCALL returns error;
- Return R10 in the structure as the return code of the VMCALL leaf;
With above changes, change the asm function from __tdx_hypercall() to
__tdcall_hypercall(), and reimplement __tdx_hypercall() as the C wrapper
of it. This avoids having to add another wrapper of __tdx_hypercall()
(_tdx_hypercall() is already taken).
The __tdcall_hypercall() will be replaced with a __tdcall() variant
using TDX_MODULE_CALL in a later commit as the final goal is to have one
assembly to handle both TDCALL and TDVMCALL.
Currently, the __tdx_hypercall() asm is in '.noinstr.text'. To keep
this unchanged, annotate __tdx_hypercall(), which is a C function now,
as 'noinstr'.
Remove the __tdx_hypercall_ret() as __tdx_hypercall() already does so.
Implement __tdx_hypercall() in tdx-shared.c so it can be shared with the
compressed code.
Opportunistically fix a checkpatch error complaining using space around
parenthesis '(' and ')' while moving the bitmap of shared registers to
<asm/shared/tdx.h>.
[ dhansen: quash new calls of __tdx_hypercall_ret() that showed up ]
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/0cbf25e7aee3256288045023a31f65f0cef90af4.1692096753.git.kai.huang%40intel.com
The TDX guest live migration support (TDX 1.5) adds new TDCALL/SEAMCALL
leaf functions. Those new TDCALLs/SEAMCALLs take additional registers
for input (R10-R13) and output (R12-R13). TDG.SERVTD.RD is an example.
Also, the current TDX_MODULE_CALL doesn't aim to handle TDH.VP.ENTER
SEAMCALL, which monitors the TDG.VP.VMCALL in input/output registers
when it returns in case of VMCALL from TDX guest.
With those new TDCALLs/SEAMCALLs and the TDH.VP.ENTER covered, the
TDX_MODULE_CALL macro basically needs to handle the same input/output
registers as the TDX_HYPERCALL does. And as a result, they also share
similar logic in the assembly, thus should be unified to use one common
assembly.
Extend the TDX_MODULE_CALL asm to support the new TDCALLs/SEAMCALLs and
also the TDH.VP.ENTER SEAMCALL. Eventually it will be unified with the
TDX_HYPERCALL.
The new input/output registers fit with the "callee-saved" registers in
the x86 calling convention. Add a new "saved" parameter to support
those new TDCALLs/SEAMCALLs and TDH.VP.ENTER and keep the existing
TDCALLs/SEAMCALLs minimally impacted.
For TDH.VP.ENTER, after it returns the registers shared by the guest
contain guest's values. Explicitly clear them to prevent speculative
use of guest's values.
Note most TDX live migration related SEAMCALLs may also clobber AVX*
state ("AVX, AVX2 and AVX512 state: may be reset to the architectural
INIT state" -- see TDH.EXPORT.MEM for example). And TDH.VP.ENTER also
clobbers XMM0-XMM15 when the corresponding bit is set in RCX. Don't
handle them in the TDX_MODULE_CALL macro but let the caller save and
restore when needed.
This is basically based on Peter's code.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/d4785de7c392f7c5684407f6c24a73b92148ec49.1692096753.git.kai.huang%40intel.com
Currently, the TDX_MODULE_CALL asm macro, which handles both TDCALL and
SEAMCALL, takes one parameter for each input register and an optional
'struct tdx_module_output' (a collection of output registers) as output.
This is different from the TDX_HYPERCALL macro which uses a single
'struct tdx_hypercall_args' to carry all input/output registers.
The newer TDX versions introduce more TDCALLs/SEAMCALLs which use more
input/output registers. Also, the TDH.VP.ENTER (which isn't covered
by the current TDX_MODULE_CALL macro) basically can use all registers
that the TDX_HYPERCALL does. The current TDX_MODULE_CALL macro isn't
extendible to cover those cases.
Similar to the TDX_HYPERCALL macro, simplify the TDX_MODULE_CALL macro
to use a single structure 'struct tdx_module_args' to carry all the
input/output registers. Currently, R10/R11 are only used as output
register but not as input by any TDCALL/SEAMCALL. Change to also use
R10/R11 as input register to make input/output registers symmetric.
Currently, the TDX_MODULE_CALL macro depends on the caller to pass a
non-NULL 'struct tdx_module_output' to get additional output registers.
Similar to the TDX_HYPERCALL macro, change the TDX_MODULE_CALL macro to
take a new 'ret' macro argument to indicate whether to save the output
registers to the 'struct tdx_module_args'. Also introduce a new
__tdcall_ret() for that purpose, similar to the __tdx_hypercall_ret().
Note the tdcall(), which is a wrapper of __tdcall(), is called by three
callers: tdx_parse_tdinfo(), tdx_get_ve_info() and tdx_early_init().
The former two need the additional output but the last one doesn't. For
simplicity, make tdcall() always call __tdcall_ret() to avoid another
"_ret()" wrapper. The last caller tdx_early_init() isn't performance
critical anyway.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/483616c1762d85eb3a3c3035a7de061cfacf2f14.1692096753.git.kai.huang%40intel.com
__tdx_module_call() is only used by the TDX guest to issue TDCALL to the
TDX module. Rename it to __tdcall() to match its behaviour, e.g., it
cannot be used to make host-side SEAMCALL.
Also rename tdx_module_call() which is a wrapper of __tdx_module_call()
to tdcall().
No functional change intended.
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/785d20d99fbcd0db8262c94da6423375422d8c75.1692096753.git.kai.huang%40intel.com
The TDX spec names all TDCALLs with prefix "TDG". Currently, the kernel
doesn't follow such convention for the macros of those TDCALLs but uses
prefix "TDX_" for all of them. Although it's arguable whether the TDX
spec names those TDCALLs properly, it's better for the kernel to follow
the spec when naming those macros.
Change all macros of TDCALLs to make them consistent with the spec. As
a bonus, they get distinguished easily from the host-side SEAMCALLs,
which all have prefix "TDH".
No functional change intended.
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/516dccd0bd8fb9a0b6af30d25bb2d971aa03d598.1692096753.git.kai.huang%40intel.com
If SEAMCALL fails with VMFailInvalid, the SEAM software (e.g., the TDX
module) won't have chance to set any output register. Skip saving the
output registers to the structure in this case.
Also, as '.Lno_output_struct' is the very last symbol before RET, rename
it to '.Lout' to make it short.
Opportunistically make the asm directives unindented.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/704088f5b4d72c7e24084f7f15bd1ac5005b7213.1692096753.git.kai.huang%40intel.com
In the TDX_HYPERCALL asm, after the TDCALL instruction returns from the
untrusted VMM, the registers that the TDX guest shares to the VMM need
to be cleared to avoid speculative execution of VMM-provided values.
RSI is specified in the bitmap of those registers, but it is missing
when zeroing out those registers in the current TDX_HYPERCALL.
It was there when it was originally added in commit 752d13305c
("x86/tdx: Expand __tdx_hypercall() to handle more arguments"), but was
later removed in commit 1e70c68037 ("x86/tdx: Do not corrupt
frame-pointer in __tdx_hypercall()"), which was correct because %rsi is
later restored in the "pop %rsi". However a later commit 7a3a401874
("x86/tdx: Drop flags from __tdx_hypercall()") removed that "pop %rsi"
but forgot to add the "xor %rsi, %rsi" back.
Fix by adding it back.
Fixes: 7a3a401874 ("x86/tdx: Drop flags from __tdx_hypercall()")
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/e7d1157074a0b45d34564d5f17f3e0ffee8115e9.1692096753.git.kai.huang%40intel.com
TDX guest memory is private by default and the VMM may not access it.
However, in cases where the guest needs to share data with the VMM,
the guest and the VMM can coordinate to make memory shared between
them.
The guest side of this protocol includes the "MapGPA" hypercall. This
call takes a guest physical address range. The hypercall spec (aka.
the GHCI) says that the MapGPA call is allowed to return partial
progress in mapping this range and indicate that fact with a special
error code. A guest that sees such partial progress is expected to
retry the operation for the portion of the address range that was not
completed.
Hyper-V does this partial completion dance when set_memory_decrypted()
is called to "decrypt" swiotlb bounce buffers that can be up to 1GB
in size. It is evidently the only VMM that does this, which is why
nobody noticed this until now.
[ dhansen: rewrite changelog ]
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/all/20230811021246.821-2-decui%40microsoft.com
the usage patterns are becoming apparent
-----BEGIN PGP SIGNATURE-----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=Aj6p
-----END PGP SIGNATURE-----
Merge tag 'x86_sev_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 SEV updates from Borislav Petkov:
- Some SEV and CC platform helpers cleanup and simplifications now that
the usage patterns are becoming apparent
[ I'm sure I'm the only one that has gets confused by all the TLAs, but
in case there are others: here SEV is AMD's "Secure Encrypted
Virtualization" and CC is generic "Confidential Computing".
There's also Intel SGX (Software Guard Extensions) and TDX (Trust
Domain Extensions), along with all the vendor memory encryption
extensions (SME, TSME, TME, and WTF).
And then we have arm64 with RMA and CCA, and I probably forgot another
dozen or so related acronyms - Linus ]
* tag 'x86_sev_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/coco: Get rid of accessor functions
x86/sev: Get rid of special sev_es_enable_key
x86/coco: Mark cc_platform_has() and descendants noinstr
a fatal shutdown during TDX private<=>shared conversion
- Annotate sites where VM "exit reasons" are reused as hypercall
numbers.
-----BEGIN PGP SIGNATURE-----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=Hr3D
-----END PGP SIGNATURE-----
Merge tag 'x86_tdx_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 tdx updates from Dave Hansen:
- Fix a race window where load_unaligned_zeropad() could cause a fatal
shutdown during TDX private<=>shared conversion
The race has never been observed in practice but might allow
load_unaligned_zeropad() to catch a TDX page in the middle of its
conversion process which would lead to a fatal and unrecoverable
guest shutdown.
- Annotate sites where VM "exit reasons" are reused as hypercall
numbers.
* tag 'x86_tdx_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Fix enc_status_change_finish_noop()
x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()
x86/mm: Allow guest.enc_status_change_prepare() to fail
x86/tdx: Wrap exit reason with hcall_func()
The gist of it all is that Intel TDX and AMD SEV-SNP confidential
computing guests define the notion of accepting memory before using it
and thus preventing a whole set of attacks against such guests like
memory replay and the like.
There are a couple of strategies of how memory should be accepted
- the current implementation does an on-demand way of accepting.
-----BEGIN PGP SIGNATURE-----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=FS95
-----END PGP SIGNATURE-----
Merge tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 confidential computing update from Borislav Petkov:
- Add support for unaccepted memory as specified in the UEFI spec v2.9.
The gist of it all is that Intel TDX and AMD SEV-SNP confidential
computing guests define the notion of accepting memory before using
it and thus preventing a whole set of attacks against such guests
like memory replay and the like.
There are a couple of strategies of how memory should be accepted -
the current implementation does an on-demand way of accepting.
* tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
virt: sevguest: Add CONFIG_CRYPTO dependency
x86/efi: Safely enable unaccepted memory in UEFI
x86/sev: Add SNP-specific unaccepted memory support
x86/sev: Use large PSC requests if applicable
x86/sev: Allow for use of the early boot GHCB for PSC requests
x86/sev: Put PSC struct on the stack in prep for unaccepted memory support
x86/sev: Fix calculation of end address based on number of pages
x86/tdx: Add unaccepted memory support
x86/tdx: Refactor try_accept_one()
x86/tdx: Make _tdx_hypercall() and __tdx_module_call() available in boot stub
efi/unaccepted: Avoid load_unaligned_zeropad() stepping into unaccepted memory
efi: Add unaccepted memory support
x86/boot/compressed: Handle unaccepted memory
efi/libstub: Implement support for unaccepted memory
efi/x86: Get full memory map in allocate_e820()
mm: Add support for unaccepted memory
tl;dr: There is a race in the TDX private<=>shared conversion code
which could kill the TDX guest. Fix it by changing conversion
ordering to eliminate the window.
TDX hardware maintains metadata to track which pages are private and
shared. Additionally, TDX guests use the guest x86 page tables to
specify whether a given mapping is intended to be private or shared.
Bad things happen when the intent and metadata do not match.
So there are two thing in play:
1. "the page" -- the physical TDX page metadata
2. "the mapping" -- the guest-controlled x86 page table intent
For instance, an unrecoverable exit to VMM occurs if a guest touches a
private mapping that points to a shared physical page.
In summary:
* Private mapping => Private Page == OK (obviously)
* Shared mapping => Shared Page == OK (obviously)
* Private mapping => Shared Page == BIG BOOM!
* Shared mapping => Private Page == OK-ish
(It will read generate a recoverable #VE via handle_mmio())
Enter load_unaligned_zeropad(). It can touch memory that is adjacent but
otherwise unrelated to the memory it needs to touch. It will cause one
of those unrecoverable exits (aka. BIG BOOM) if it blunders into a
shared mapping pointing to a private page.
This is a problem when __set_memory_enc_pgtable() converts pages from
shared to private. It first changes the mapping and second modifies
the TDX page metadata. It's moving from:
* Shared mapping => Shared Page == OK
to:
* Private mapping => Shared Page == BIG BOOM!
This means that there is a window with a shared mapping pointing to a
private page where load_unaligned_zeropad() can strike.
Add a TDX handler for guest.enc_status_change_prepare(). This converts
the page from shared to private *before* the page becomes private. This
ensures that there is never a private mapping to a shared page.
Leave a guest.enc_status_change_finish() in place but only use it for
private=>shared conversions. This will delay updating the TDX metadata
marking the page private until *after* the mapping matches the metadata.
This also ensures that there is never a private mapping to a shared page.
[ dhansen: rewrite changelog ]
Fixes: 7dbde76316 ("x86/mm/cpa: Add support for TDX shared memory")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: https://lore.kernel.org/all/20230606095622.1939-3-kirill.shutemov%40linux.intel.com
Hookup TDX-specific code to accept memory.
Accepting the memory is done with ACCEPT_PAGE module call on every page
in the range. MAP_GPA hypercall is not required as the unaccepted memory
is considered private already.
Extract the part of tdx_enc_status_changed() that does memory acceptance
in a new helper. Move the helper tdx-shared.c. It is going to be used by
both main kernel and decompressor.
[ bp: Fix the INTEL_TDX_GUEST=y, KVM_GUEST=n build. ]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230606142637.5171-10-kirill.shutemov@linux.intel.com
Rework try_accept_one() to return accepted size instead of modifying
'start' inside the helper. It makes 'start' in-only argument and
streamlines code on the caller side.
Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20230606142637.5171-9-kirill.shutemov@linux.intel.com
Memory acceptance requires a hypercall and one or multiple module calls.
Make helpers for the calls available in boot stub. It has to accept
memory where kernel image and initrd are placed.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20230606142637.5171-8-kirill.shutemov@linux.intel.com
The decision to allow parallel bringup of secondary CPUs checks
CC_ATTR_GUEST_STATE_ENCRYPT to detect encrypted guests. Those cannot use
parallel bootup because accessing the local APIC is intercepted and raises
a #VC or #VE, which cannot be handled at that point.
The check works correctly, but only for AMD encrypted guests. TDX does not
set that flag.
As there is no real connection between CC attributes and the inability to
support parallel bringup, replace this with a generic control flag in
x86_cpuinit and let SEV-ES and TDX init code disable it.
Fixes: 0c7ffa32db ("x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it")
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/r/87ilc9gd2d.ffs@tglx
TDX reuses VMEXIT "reasons" in its guest->host hypercall ABI. This is
confusing because there might not be a VMEXIT involved at *all*.
These instances are supposed to document situation and reduce confusion
by wrapping VMEXIT reasons with hcall_func().
The decompression code does not follow this convention.
Unify the TDX decompression code with the other TDX use of VMEXIT reasons.
No functional changes.
Signed-off-by: Nikolay Borisov <nik.borisov@suse.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/all/20230505120332.1429957-1-nik.borisov%40suse.com
Those will be used in code regions where instrumentation is not allowed
so mark them as such.
No functional changes.
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20230328201712.25852-2-bp@alien8.de
assembly macro argument rather than a runtime register.
-----BEGIN PGP SIGNATURE-----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=hvDm
-----END PGP SIGNATURE-----
Merge tag 'x86_tdx_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 tdx update from Dave Hansen:
"The original tdx hypercall assembly code took two flags in %RSI to
tweak its behavior at runtime. PeterZ recently axed one flag in commit
e80a48bade ("x86/tdx: Remove TDX_HCALL_ISSUE_STI").
Kill the other flag too and tweak the 'output' mode with an assembly
macro instead. This results in elimination of one push/pop pair and
overall easier to read assembly.
- Do conditional __tdx_hypercall() 'output' processing via an
assembly macro argument rather than a runtime register"
* tag 'x86_tdx_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/tdx: Drop flags from __tdx_hypercall()
- Fix the incorrect handling of atomic offset updates in
reserve_eilvt_offset()
The check for the return value of atomic_cmpxchg() is not compared
against the old value, it is compared against the new value, which
makes it two round on success.
Convert it to atomic_try_cmpxchg() which does the right thing.
- Handle IO/APIC less systems correctly
When IO/APIC is not advertised by ACPI then the computation of the lower
bound for dynamically allocated interrupts like MSI goes wrong.
This lower bound is used to exclude the IO/APIC legacy GSI space as that
must stay reserved for the legacy interrupts.
In case that the system, e.g. VM, does not advertise an IO/APIC the
lower bound stays at 0.
0 is an invalid interrupt number except for the legacy timer interrupt
on x86. The return value is unchecked in the core code, so it ends up
to allocate interrupt number 0 which is subsequently considered to be
invalid by the caller, e.g. the MSI allocation code.
A similar problem was already cured for device tree based systems years
ago, but that missed - or did not envision - the zero IO/APIC case.
Consolidate the zero check and return the provided "from" argument to the
core code call site, which is guaranteed to be greater than 0.
- Simplify the X2APIC cluster CPU mask logic for CPU hotplug
Per cluster CPU masks are required for X2APIC in cluster mode to
determine the correct cluster for a target CPU when calculating the
destination for IPIs
These masks are established when CPUs are borught up. The first CPU in a
cluster must allocate a new cluster CPU mask. As this happens during the
early startup of a CPU, where memory allocations cannot be done, the
mask has to be allocated by the control CPU.
The current implementation allocates a clustermask just in case and if
the to be brought up CPU is the first in a cluster the CPU takes over
this allocation from a global pointer.
This works nicely in the fully serialized CPU bringup scenario which is
used today, but would fail completely for parallel bringup of CPUs.
The cluster association of a CPU can be computed from the APIC ID which
is enumerated by ACPI/MADT.
So the cluster CPU masks can be preallocated and associated upfront and
the upcoming CPUs just need to set their corresponding bit.
Aside of preparing for parallel bringup this is a valuable
simplification on its own.
- Remove global variables which control the early startup of secondary
CPUs on 64-bit
The only information which is needed by a starting CPU is the Linux CPU
number. The CPU number allows it to retrieve the rest of the required
data from already existing per CPU storage.
So instead of initial_stack, early_gdt_desciptor and initial_gs provide
a new variable smpboot_control which contains the Linux CPU number for
now. The starting CPU can retrieve and compute all required information
for startup from there.
Aside of being a cleanup, this is also preparing for parallel CPU
bringup, where starting CPUs will look up their Linux CPU number via the
APIC ID, when smpboot_control has the corresponding control bit set.
- Make cc_vendor globally accesible
Subsequent parallel bringup changes require access to cc_vendor because
confidental computing platforms need special treatment in the early
startup phase vs. CPUID and APCI ID readouts.
The change makes cc_vendor global and provides stub accessors in case
that CONFIG_ARCH_HAS_CC_PLATFORM is not set.
This was merged from the x86/cc branch in anticipation of further
parallel bringup commits which require access to cc_vendor. Due to late
discoveries of fundamental issue with those patches these commits never
happened.
The merge commit is unfortunately in the middle of the APIC commits so
unraveling it would have required a rebase or revert. As the parallel
bringup seems to be well on its way for 6.5 this would be just pointless
churn. As the commit does not contain any functional change it's not a
risk to keep it.
-----BEGIN PGP SIGNATURE-----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=IQWG
-----END PGP SIGNATURE-----
Merge tag 'x86-apic-2023-04-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 APIC updates from Thomas Gleixner:
- Fix the incorrect handling of atomic offset updates in
reserve_eilvt_offset()
The check for the return value of atomic_cmpxchg() is not compared
against the old value, it is compared against the new value, which
makes it two round on success.
Convert it to atomic_try_cmpxchg() which does the right thing.
- Handle IO/APIC less systems correctly
When IO/APIC is not advertised by ACPI then the computation of the
lower bound for dynamically allocated interrupts like MSI goes wrong.
This lower bound is used to exclude the IO/APIC legacy GSI space as
that must stay reserved for the legacy interrupts.
In case that the system, e.g. VM, does not advertise an IO/APIC the
lower bound stays at 0.
0 is an invalid interrupt number except for the legacy timer
interrupt on x86. The return value is unchecked in the core code, so
it ends up to allocate interrupt number 0 which is subsequently
considered to be invalid by the caller, e.g. the MSI allocation code.
A similar problem was already cured for device tree based systems
years ago, but that missed - or did not envision - the zero IO/APIC
case.
Consolidate the zero check and return the provided "from" argument to
the core code call site, which is guaranteed to be greater than 0.
- Simplify the X2APIC cluster CPU mask logic for CPU hotplug
Per cluster CPU masks are required for X2APIC in cluster mode to
determine the correct cluster for a target CPU when calculating the
destination for IPIs
These masks are established when CPUs are borught up. The first CPU
in a cluster must allocate a new cluster CPU mask. As this happens
during the early startup of a CPU, where memory allocations cannot be
done, the mask has to be allocated by the control CPU.
The current implementation allocates a clustermask just in case and
if the to be brought up CPU is the first in a cluster the CPU takes
over this allocation from a global pointer.
This works nicely in the fully serialized CPU bringup scenario which
is used today, but would fail completely for parallel bringup of
CPUs.
The cluster association of a CPU can be computed from the APIC ID
which is enumerated by ACPI/MADT.
So the cluster CPU masks can be preallocated and associated upfront
and the upcoming CPUs just need to set their corresponding bit.
Aside of preparing for parallel bringup this is a valuable
simplification on its own.
- Remove global variables which control the early startup of secondary
CPUs on 64-bit
The only information which is needed by a starting CPU is the Linux
CPU number. The CPU number allows it to retrieve the rest of the
required data from already existing per CPU storage.
So instead of initial_stack, early_gdt_desciptor and initial_gs
provide a new variable smpboot_control which contains the Linux CPU
number for now. The starting CPU can retrieve and compute all
required information for startup from there.
Aside of being a cleanup, this is also preparing for parallel CPU
bringup, where starting CPUs will look up their Linux CPU number via
the APIC ID, when smpboot_control has the corresponding control bit
set.
- Make cc_vendor globally accesible
Subsequent parallel bringup changes require access to cc_vendor
because confidental computing platforms need special treatment in the
early startup phase vs. CPUID and APCI ID readouts.
The change makes cc_vendor global and provides stub accessors in case
that CONFIG_ARCH_HAS_CC_PLATFORM is not set.
This was merged from the x86/cc branch in anticipation of further
parallel bringup commits which require access to cc_vendor. Due to
late discoveries of fundamental issue with those patches these
commits never happened.
The merge commit is unfortunately in the middle of the APIC commits
so unraveling it would have required a rebase or revert. As the
parallel bringup seems to be well on its way for 6.5 this would be
just pointless churn. As the commit does not contain any functional
change it's not a risk to keep it.
* tag 'x86-apic-2023-04-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/ioapic: Don't return 0 from arch_dynirq_lower_bound()
x86/apic: Fix atomic update of offset in reserve_eilvt_offset()
x86/coco: Export cc_vendor
x86/smpboot: Reference count on smpboot_setup_warm_reset_vector()
x86/smpboot: Remove initial_gs
x86/smpboot: Remove early_gdt_descr on 64-bit
x86/smpboot: Remove initial_stack on 64-bit
x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel
It will be used in different checks in future changes. Export it directly
and provide accessor functions and stubs so this can be used in general
code when CONFIG_ARCH_HAS_CC_PLATFORM is not set.
No functional changes.
[ tglx: Add accessor functions ]
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20230318115634.9392-2-bp@alien8.de
Hyper-V guests on AMD SEV-SNP hardware have the option of using the
"virtual Top Of Memory" (vTOM) feature specified by the SEV-SNP
architecture. With vTOM, shared vs. private memory accesses are
controlled by splitting the guest physical address space into two
halves.
vTOM is the dividing line where the uppermost bit of the physical
address space is set; e.g., with 47 bits of guest physical address
space, vTOM is 0x400000000000 (bit 46 is set). Guest physical memory is
accessible at two parallel physical addresses -- one below vTOM and one
above vTOM. Accesses below vTOM are private (encrypted) while accesses
above vTOM are shared (decrypted). In this sense, vTOM is like the
GPA.SHARED bit in Intel TDX.
Support for Hyper-V guests using vTOM was added to the Linux kernel in
two patch sets[1][2]. This support treats the vTOM bit as part of
the physical address. For accessing shared (decrypted) memory, these
patch sets create a second kernel virtual mapping that maps to physical
addresses above vTOM.
A better approach is to treat the vTOM bit as a protection flag, not
as part of the physical address. This new approach is like the approach
for the GPA.SHARED bit in Intel TDX. Rather than creating a second kernel
virtual mapping, the existing mapping is updated using recently added
coco mechanisms.
When memory is changed between private and shared using
set_memory_decrypted() and set_memory_encrypted(), the PTEs for the
existing kernel mapping are changed to add or remove the vTOM bit in the
guest physical address, just as with TDX. The hypercalls to change the
memory status on the host side are made using the existing callback
mechanism. Everything just works, with a minor tweak to map the IO-APIC
to use private accesses.
To accomplish the switch in approach, the following must be done:
* Update Hyper-V initialization to set the cc_mask based on vTOM
and do other coco initialization.
* Update physical_mask so the vTOM bit is no longer treated as part
of the physical address
* Remove CC_VENDOR_HYPERV and merge the associated vTOM functionality
under CC_VENDOR_AMD. Update cc_mkenc() and cc_mkdec() to set/clear
the vTOM bit as a protection flag.
* Code already exists to make hypercalls to inform Hyper-V about pages
changing between shared and private. Update this code to run as a
callback from __set_memory_enc_pgtable().
* Remove the Hyper-V special case from __set_memory_enc_dec()
* Remove the Hyper-V specific call to swiotlb_update_mem_attributes()
since mem_encrypt_init() will now do it.
* Add a Hyper-V specific implementation of the is_private_mmio()
callback that returns true for the IO-APIC and vTPM MMIO addresses
[1] https://lore.kernel.org/all/20211025122116.264793-1-ltykernel@gmail.com/
[2] https://lore.kernel.org/all/20211213071407.314309-1-ltykernel@gmail.com/
[ bp: Touchups. ]
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/1679838727-87310-7-git-send-email-mikelley@microsoft.com
After TDX_HCALL_ISSUE_STI got dropped, the only flag left is
TDX_HCALL_HAS_OUTPUT. The flag indicates if the caller wants to see
tdx_hypercall_args updated based on the hypercall output.
Drop the flags and provide __tdx_hypercall_ret() that matches
TDX_HCALL_HAS_OUTPUT semantics.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/20230321003511.9469-1-kirill.shutemov%40linux.intel.com
- Prevent unexpected #VE's from:
- Hosts removing perfectly good guest mappings (SEPT_VE_DISABLE
- Excessive #VE notifications (NOTIFY_ENABLES) which are
delivered via a #VE.
-----BEGIN PGP SIGNATURE-----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=UpyL
-----END PGP SIGNATURE-----
Merge tag 'x86_tdx_for_6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull Intel Trust Domain Extensions (TDX) updates from Dave Hansen:
"Other than a minor fixup, the content here is to ensure that TDX
guests never see virtualization exceptions (#VE's) that might be
induced by the untrusted VMM.
This is a highly desirable property. Without it, #VE exception
handling would fall somewhere between NMIs, machine checks and total
insanity. With it, #VE handling remains pretty mundane.
Summary:
- Fixup comment typo
- Prevent unexpected #VE's from:
- Hosts removing perfectly good guest mappings (SEPT_VE_DISABLE)
- Excessive #VE notifications (NOTIFY_ENABLES) which are delivered
via a #VE"
* tag 'x86_tdx_for_6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/tdx: Do not corrupt frame-pointer in __tdx_hypercall()
x86/tdx: Disable NOTIFY_ENABLES
x86/tdx: Relax SEPT_VE_DISABLE check for debug TD
x86/tdx: Use ReportFatalError to report missing SEPT_VE_DISABLE
x86/tdx: Expand __tdx_hypercall() to handle more arguments
x86/tdx: Refactor __tdx_hypercall() to allow pass down more arguments
x86/tdx: Add more registers to struct tdx_hypercall_args
x86/tdx: Fix typo in comment in __tdx_hypercall()
If compiled with CONFIG_FRAME_POINTER=y, objtool is not happy that
__tdx_hypercall() messes up RBP:
objtool: __tdx_hypercall+0x7f: return with modified stack frame
Rework the function to store TDX_HCALL_ flags on stack instead of RBP.
[ dhansen: minor changelog tweaks ]
Fixes: c30c4b2555 ("x86/tdx: Refactor __tdx_hypercall() to allow pass down more arguments")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/202301290255.buUBs99R-lkp@intel.com
Link: https://lore.kernel.org/all/20230130135354.27674-1-kirill.shutemov%40linux.intel.com
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmPW7E8eHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGf7MIAI0JnHN9WvtEukSZ
E6j6+cEGWxsvD6q0g3GPolaKOCw7hlv0pWcFJFcUAt0jebspMdxV2oUGJ8RYW7Lg
nCcHvEVswGKLAQtQSWw52qotW6fUfMPsNYYB5l31sm1sKH4Cgss0W7l2HxO/1LvG
TSeNHX53vNAZ8pVnFYEWCSXC9bzrmU/VALF2EV00cdICmfvjlgkELGXoLKJJWzUp
s63fBHYGGURSgwIWOKStoO6HNo0j/F/wcSMx8leY8qDUtVKHj4v24EvSgxUSDBER
ch3LiSQ6qf4sw/z7pqruKFthKOrlNmcc0phjiES0xwwGiNhLv0z3rAhc4OM2cgYh
SDc/Y/c=
=zpaD
-----END PGP SIGNATURE-----
Merge tag 'v6.2-rc6' into sched/core, to pick up fixes
Pick up fixes before merging another batch of cpuidle updates.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
== Background ==
There is a class of side-channel attacks against SGX enclaves called
"SGX Step"[1]. These attacks create lots of exceptions inside of
enclaves. Basically, run an in-enclave instruction, cause an exception.
Over and over.
There is a concern that a VMM could attack a TDX guest in the same way
by causing lots of #VE's. The TDX architecture includes new
countermeasures for these attacks. It basically counts the number of
exceptions and can send another *special* exception once the number of
VMM-induced #VE's hits a critical threshold[2].
== Problem ==
But, these special exceptions are independent of any action that the
guest takes. They can occur anywhere that the guest executes. This
includes sensitive areas like the entry code. The (non-paranoid) #VE
handler is incapable of handling exceptions in these areas.
== Solution ==
Fortunately, the special exceptions can be disabled by the guest via
write to NOTIFY_ENABLES TDCS field. NOTIFY_ENABLES is disabled by
default, but might be enabled by a bootloader, firmware or an earlier
kernel before the current kernel runs.
Disable NOTIFY_ENABLES feature explicitly and unconditionally. Any
NOTIFY_ENABLES-based #VE's that occur before this point will end up
in the early #VE exception handler and die due to unexpected exit
reason.
[1] https://github.com/jovanbulck/sgx-step
[2] https://intel.github.io/ccc-linux-guest-hardening-docs/security-spec.html#safety-against-ve-in-kernel-code
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-8-kirill.shutemov%40linux.intel.com
A "SEPT #VE" occurs when a TDX guest touches memory that is not properly
mapped into the "secure EPT". This can be the result of hypervisor
attacks or bugs, *OR* guest bugs. Most notably, buggy guests might
touch unaccepted memory for lots of different memory safety bugs like
buffer overflows.
TDX guests do not want to continue in the face of hypervisor attacks or
hypervisor bugs. They want to terminate as fast and safely as possible.
SEPT_VE_DISABLE ensures that TDX guests *can't* continue in the face of
these kinds of issues.
But, that causes a problem. TDX guests that can't continue can't spit
out oopses or other debugging info. In essence SEPT_VE_DISABLE=1 guests
are not debuggable.
Relax the SEPT_VE_DISABLE check to warning on debug TD and panic() in
the #VE handler on EPT-violation on private memory. It will produce
useful backtrace.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-7-kirill.shutemov%40linux.intel.com
Linux TDX guests require that the SEPT_VE_DISABLE "attribute" be set.
If it is not set, the kernel is theoretically required to handle
exceptions anywhere that kernel memory is accessed, including places
like NMI handlers and in the syscall entry gap.
Rather than even try to handle these exceptions, the kernel refuses to
run if SEPT_VE_DISABLE is unset.
However, the SEPT_VE_DISABLE detection and refusal code happens very
early in boot, even before earlyprintk runs. Calling panic() will
effectively just hang the system.
Instead, call a TDX-specific panic() function. This makes a very simple
TDVMCALL which gets a short error string out to the hypervisor without
any console infrastructure.
Use TDG.VP.VMCALL<ReportFatalError> to report the error. The hypercall
can encode message up to 64 bytes in eight registers.
[ dhansen: tweak comment and remove while loop brackets. ]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-6-kirill.shutemov%40linux.intel.com
So far __tdx_hypercall() only handles six arguments for VMCALL.
Expanding it to six more register would allow to cover more use-cases
like ReportFatalError() and Hyper-V hypercalls.
With all preparations in place, the expansion is pretty straight
forward.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-5-kirill.shutemov%40linux.intel.com
RDI is the first argument to __tdx_hypercall() that used to pass pointer
to struct tdx_hypercall_args. RSI is the second argument that contains
flags, such as TDX_HCALL_HAS_OUTPUT and TDX_HCALL_ISSUE_STI.
RDI and RSI can also be used as arguments to TDVMCALL leafs. Move RDI to
RAX and RSI to RBP to free up them for the hypercall arguments.
RAX saved on stack during TDCALL as it returns status code in the
register.
RBP value has to be restored before returning from __tdx_hypercall() as
it is callee-saved register.
This is preparatory patch. No functional change.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-4-kirill.shutemov%40linux.intel.com
Comment in __tdx_hypercall() points that RAX==0 indicates TDVMCALL
failure which is opposite of the truth: RAX==0 is success.
Fix the comment. No functional changes.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20230126221159.8635-2-kirill.shutemov%40linux.intel.com
objtool found a few cases where this code called out into instrumented
code:
vmlinux.o: warning: objtool: __halt+0x2c: call to hcall_func.constprop.0() leaves .noinstr.text section
vmlinux.o: warning: objtool: __halt+0x3f: call to __tdx_hypercall() leaves .noinstr.text section
vmlinux.o: warning: objtool: __tdx_hypercall+0x66: call to __tdx_hypercall_failed() leaves .noinstr.text section
Fix it by:
- moving TDX tdcall assembly methods into .noinstr.text (they are already noistr-clean)
- marking __tdx_hypercall_failed() as 'noinstr'
- annotating hcall_func() as __always_inline
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195541.111485720@infradead.org
Now that arch_cpu_idle() is expected to return with IRQs disabled,
avoid the useless STI/CLI dance.
Per the specs this is supposed to work, but nobody has yet relied up
this behaviour so broken implementations are possible.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195540.682137572@infradead.org
Current arch_cpu_idle() is called with IRQs disabled, but will return
with IRQs enabled.
However, the very first thing the generic code does after calling
arch_cpu_idle() is raw_local_irq_disable(). This means that
architectures that can idle with IRQs disabled end up doing a
pointless 'enable-disable' dance.
Therefore, push this IRQ disabling into the idle function, meaning
that those architectures can avoid the pointless IRQ state flipping.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Acked-by: Mark Rutland <mark.rutland@arm.com> [arm64]
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195540.618076436@infradead.org
Both <linux/mmiotrace.h> and <asm/insn-eval.h> define various MMIO_ enum constants,
whose namespace overlaps.
Rename the <asm/insn-eval.h> ones to have a INSN_ prefix, so that the headers can be
used from the same source file.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230101162910.710293-2-Jason@zx2c4.com
To support TDX attestation, the TDX guest driver exposes an IOCTL
interface to allow userspace to get the TDREPORT0 (a.k.a. TDREPORT
subtype 0) from the TDX module via TDG.MR.TDREPORT TDCALL.
In order to get the TDREPORT0 in the TDX guest driver, instead of using
a low level function like __tdx_module_call(), add a
tdx_mcall_get_report0() wrapper function to handle it.
This is a preparatory patch for adding attestation support.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Wander Lairson Costa <wander@redhat.com>
Link: https://lore.kernel.org/all/20221116223820.819090-2-sathyanarayanan.kuppuswamy%40linux.intel.com
All normal kernel memory is "TDX private memory". This includes
everything from kernel stacks to kernel text. Handling
exceptions on arbitrary accesses to kernel memory is essentially
impossible because they can happen in horribly nasty places like
kernel entry/exit. But, TDX hardware can theoretically _deliver_
a virtualization exception (#VE) on any access to private memory.
But, it's not as bad as it sounds. TDX can be configured to never
deliver these exceptions on private memory with a "TD attribute"
called ATTR_SEPT_VE_DISABLE. The guest has no way to *set* this
attribute, but it can check it.
Ensure ATTR_SEPT_VE_DISABLE is set in early boot. panic() if it
is unset. There is no sane way for Linux to run with this
attribute clear so a panic() is appropriate.
There's small window during boot before the check where kernel
has an early #VE handler. But the handler is only for port I/O
and will also panic() as soon as it sees any other #VE, such as
a one generated by a private memory access.
[ dhansen: Rewrite changelog and rebase on new tdx_parse_tdinfo().
Add Kirill's tested-by because I made changes since
he wrote this. ]
Fixes: 9a22bf6deb ("x86/traps: Add #VE support for TDX guest")
Reported-by: ruogui.ygr@alibaba-inc.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20221028141220.29217-3-kirill.shutemov%40linux.intel.com
The TDG.VP.INFO TDCALL provides the guest with various details about
the TDX system that the guest needs to run. Only one field is currently
used: 'gpa_width' which tells the guest which PTE bits mark pages shared
or private.
A second field is now needed: the guest "TD attributes" to tell if
virtualization exceptions are configured in a way that can harm the guest.
Make the naming and calling convention more generic and discrete from the
mask-centric one.
Thanks to Sathya for the inspiration here, but there's no code, comments
or changelogs left from where he started.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: stable@vger.kernel.org
load_unaligned_zeropad() can lead to unwanted loads across page boundaries.
The unwanted loads are typically harmless. But, they might be made to
totally unrelated or even unmapped memory. load_unaligned_zeropad()
relies on exception fixup (#PF, #GP and now #VE) to recover from these
unwanted loads.
In TDX guests, the second page can be shared page and a VMM may configure
it to trigger #VE.
The kernel assumes that #VE on a shared page is an MMIO access and tries to
decode instruction to handle it. In case of load_unaligned_zeropad() it
may result in confusion as it is not MMIO access.
Fix it by detecting split page MMIO accesses and failing them.
load_unaligned_zeropad() will recover using exception fixups.
The issue was discovered by analysis and reproduced artificially. It was
not triggered during testing.
[ dhansen: fix up changelogs and comments for grammar and clarity,
plus incorporate Kirill's off-by-one fix]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220614120135.14812-4-kirill.shutemov@linux.intel.com
After successful #VE handling, tdx_handle_virt_exception() has to move
RIP to the next instruction. The handler needs to know the length of the
instruction.
If the #VE happened due to instruction execution, the GET_VEINFO TDX
module call provides info on the instruction in R10, including its length.
For #VE due to EPT violation, the info in R10 is not populand and the
kernel must decode the instruction manually to find out its length.
Restructure the code to make it explicit that the instruction length
depends on the type of #VE. Make individual #VE handlers return
the instruction length on success or -errno on failure.
[ dhansen: fix up changelog and comments ]
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220614120135.14812-3-kirill.shutemov@linux.intel.com
tdx_early_handle_ve() does not increment RIP after successfully
handling the exception. That leads to infinite loop of exceptions.
Move RIP when exceptions are successfully handled.
[ dhansen: make problem statement more clear ]
Fixes: 32e72854fa ("x86/tdx: Port I/O: Add early boot support")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: https://lkml.kernel.org/r/20220614120135.14812-2-kirill.shutemov@linux.intel.com
Linus Torvalds