| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 14 May 2024 17:56:21 +0300
From: Nikolay Borisov <nik.borisov@...e.com>
To: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
Borislav Petkov <bp@...en8.de>, x86@...nel.org,
"H. Peter Anvin" <hpa@...or.com>
Cc: linux-coco@...ts.linux.dev, linux-kernel@...r.kernel.org,
stable@...r.kernel.org
Subject: Re: [PATCHv4 3/4] x86/tdx: Dynamically disable SEPT violations from
causing #VEs
On 12.05.24 г. 15:21 ч., Kirill A. Shutemov wrote:
> Memory access #VE's are hard for Linux to handle in contexts like the
> entry code or NMIs. But other OSes need them for functionality.
> There's a static (pre-guest-boot) way for a VMM to choose one or the
> other. But VMMs don't always know which OS they are booting, so they
> choose to deliver those #VE's so the "other" OSes will work. That,
> unfortunately has left us in the lurch and exposed to these
> hard-to-handle #VEs.
>
> The TDX module has introduced a new feature. Even if the static
> configuration is "send nasty #VE's", the kernel can dynamically request
> that they be disabled.
>
> Check if the feature is available and disable SEPT #VE if possible.
>
> If the TD allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE
> attribute is no longer reliable. It reflects the initial state of the
> control for the TD, but it will not be updated if someone (e.g. bootloader)
> changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to
> determine if SEPT #VEs are enabled or disabled.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
> Fixes: 373e715e31bf ("x86/tdx: Panic on bad configs that #VE on "private" memory access")
> Cc: stable@...r.kernel.org
Reviewed-by: Nikolay Borisov <nik.borisov@...e.com> though one nit below.
> ---
> arch/x86/coco/tdx/tdx.c | 88 +++++++++++++++++++++++++------
> arch/x86/include/asm/shared/tdx.h | 11 +++-
> 2 files changed, 83 insertions(+), 16 deletions(-)
>
> diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
> index 1ff571cb9177..ba37f4306f4e 100644
> --- a/arch/x86/coco/tdx/tdx.c
> +++ b/arch/x86/coco/tdx/tdx.c
> @@ -77,6 +77,20 @@ static inline void tdcall(u64 fn, struct tdx_module_args *args)
> panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
> }
>
> +/* Read TD-scoped metadata */
> +static inline u64 tdg_vm_rd(u64 field, u64 *value)
> +{
> + struct tdx_module_args args = {
> + .rdx = field,
> + };
> + u64 ret;
> +
> + ret = __tdcall_ret(TDG_VM_RD, &args);
> + *value = args.r8;
> +
> + return ret;
> +}
nit: Perhaps this function can be put in the first patch and the
description there be made more generic, something along the lines of
"introduce functions for tdg_rd/tdg_wr" ?
> +
> /* Write TD-scoped metadata */
> static inline u64 tdg_vm_wr(u64 field, u64 value, u64 mask)
> {
> @@ -179,6 +193,62 @@ static void __noreturn tdx_panic(const char *msg)
> __tdx_hypercall(&args);
> }
>
> +/*
> + * The kernel cannot handle #VEs when accessing normal kernel memory. Ensure
> + * that no #VE will be delivered for accesses to TD-private memory.
> + *
> + * TDX 1.0 does not allow the guest to disable SEPT #VE on its own. The VMM
> + * controls if the guest will receive such #VE with TD attribute
> + * ATTR_SEPT_VE_DISABLE.
> + *
> + * Newer TDX module allows the guest to control if it wants to receive SEPT
> + * violation #VEs.
> + *
> + * Check if the feature is available and disable SEPT #VE if possible.
> + *
> + * If the TD allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE
> + * attribute is no longer reliable. It reflects the initial state of the
> + * control for the TD, but it will not be updated if someone (e.g. bootloader)
> + * changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to
> + * determine if SEPT #VEs are enabled or disabled.
> + */
> +static void disable_sept_ve(u64 td_attr)
> +{
> + const char *msg = "TD misconfiguration: SEPT #VE has to be disabled";
> + bool debug = td_attr & ATTR_DEBUG;
> + u64 config, controls;
> +
> + /* Is this TD allowed to disable SEPT #VE */
> + tdg_vm_rd(TDCS_CONFIG_FLAGS, &config);
> + if (!(config & TDCS_CONFIG_FLEXIBLE_PENDING_VE)) {
> + /* No SEPT #VE controls for the guest: check the attribute */
> + if (td_attr & ATTR_SEPT_VE_DISABLE)
> + return;
> +
> + /* Relax SEPT_VE_DISABLE check for debug TD for backtraces */
> + if (debug)
> + pr_warn("%s\n", msg);
> + else
> + tdx_panic(msg);
> + return;
> + }
> +
> + /* Check if SEPT #VE has been disabled before us */
> + tdg_vm_rd(TDCS_TD_CTLS, &controls);
> + if (controls & TD_CTLS_PENDING_VE_DISABLE)
> + return;
> +
> + /* Keep #VEs enabled for splats in debugging environments */
> + if (debug)
> + return;
> +
> + /* Disable SEPT #VEs */
> + tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_PENDING_VE_DISABLE,
> + TD_CTLS_PENDING_VE_DISABLE);
> +
> + return;
> +}
> +
> static void tdx_setup(u64 *cc_mask)
> {
> struct tdx_module_args args = {};
> @@ -204,24 +274,12 @@ static void tdx_setup(u64 *cc_mask)
> gpa_width = args.rcx & GENMASK(5, 0);
> *cc_mask = BIT_ULL(gpa_width - 1);
>
> + td_attr = args.rdx;
> +
> /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */
> tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL);
>
> - /*
> - * The kernel can not handle #VE's when accessing normal kernel
> - * memory. Ensure that no #VE will be delivered for accesses to
> - * TD-private memory. Only VMM-shared memory (MMIO) will #VE.
> - */
> - td_attr = args.rdx;
> - if (!(td_attr & ATTR_SEPT_VE_DISABLE)) {
> - const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set.";
> -
> - /* Relax SEPT_VE_DISABLE check for debug TD. */
> - if (td_attr & ATTR_DEBUG)
> - pr_warn("%s\n", msg);
> - else
> - tdx_panic(msg);
> - }
> + disable_sept_ve(td_attr);
> }
>
> /*
> diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
> index fdfd41511b02..fecb2a6e864b 100644
> --- a/arch/x86/include/asm/shared/tdx.h
> +++ b/arch/x86/include/asm/shared/tdx.h
> @@ -16,11 +16,20 @@
> #define TDG_VP_VEINFO_GET 3
> #define TDG_MR_REPORT 4
> #define TDG_MEM_PAGE_ACCEPT 6
> +#define TDG_VM_RD 7
> #define TDG_VM_WR 8
>
> -/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */
> +/* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */
> +#define TDCS_CONFIG_FLAGS 0x1110000300000016
> +#define TDCS_TD_CTLS 0x1110000300000017
> #define TDCS_NOTIFY_ENABLES 0x9100000000000010
>
> +/* TDCS_CONFIG_FLAGS bits */
> +#define TDCS_CONFIG_FLEXIBLE_PENDING_VE BIT_ULL(1)
> +
> +/* TDCS_TD_CTLS bits */
> +#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(0)
> +
> /* TDX hypercall Leaf IDs */
> #define TDVMCALL_MAP_GPA 0x10001
> #define TDVMCALL_GET_QUOTE 0x10002
Powered by blists - more mailing lists