All of lore.kernel.org
 help / color / mirror / Atom feed
From: Suleiman Souhlal <suleiman@google.com>
To: stable@vger.kernel.org
Cc: x86@kernel.org, kvm@vger.kernel.org, bp@alien8.de,
	pbonzini@redhat.com, peterz@infradead.org, jpoimboe@kernel.org,
	cascardo@canonical.com, surajjs@amazon.com, ssouhlal@FreeBSD.org,
	suleiman@google.com
Subject: [PATCH 4.19 33/34] x86/bugs: Warn when "ibrs" mitigation is selected on Enhanced IBRS parts
Date: Thu, 17 Nov 2022 18:19:51 +0900	[thread overview]
Message-ID: <20221117091952.1940850-34-suleiman@google.com> (raw)
In-Reply-To: <20221117091952.1940850-1-suleiman@google.com>

From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>

commit eb23b5ef9131e6d65011de349a4d25ef1b3d4314 upstream.

IBRS mitigation for spectre_v2 forces write to MSR_IA32_SPEC_CTRL at
every kernel entry/exit. On Enhanced IBRS parts setting
MSR_IA32_SPEC_CTRL[IBRS] only once at boot is sufficient. MSR writes at
every kernel entry/exit incur unnecessary performance loss.

When Enhanced IBRS feature is present, print a warning about this
unnecessary performance loss.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/2a5eaf54583c2bfe0edc4fea64006656256cca17.1657814857.git.pawan.kumar.gupta@linux.intel.com
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Suleiman Souhlal <suleiman@google.com>
---
 arch/x86/kernel/cpu/bugs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a4684b224b59..351551fdd198 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -851,6 +851,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; }
 #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n"
 #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n"
 #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n"
+#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n"
 
 #ifdef CONFIG_BPF_SYSCALL
 void unpriv_ebpf_notify(int new_state)
@@ -1277,6 +1278,8 @@ static void __init spectre_v2_select_mitigation(void)
 
 	case SPECTRE_V2_IBRS:
 		setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS);
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED))
+			pr_warn(SPECTRE_V2_IBRS_PERF_MSG);
 		break;
 
 	case SPECTRE_V2_LFENCE:
-- 
2.38.1.431.g37b22c650d-goog


  parent reply	other threads:[~2022-11-17  9:23 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-17  9:19 [PATCH 4.19 00/34] Intel RETBleed mitigations for 4.19 Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 01/34] Revert "x86/speculation: Add RSB VM Exit protections" Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 02/34] Revert "x86/cpu: Add a steppings field to struct x86_cpu_id" Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 03/34] x86/cpufeature: Add facility to check for min microcode revisions Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 04/34] x86/cpufeature: Fix various quality problems in the <asm/cpu_device_hd.h> header Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 05/34] x86/devicetable: Move x86 specific macro out of generic code Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 06/34] x86/cpu: Add consistent CPU match macros Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 07/34] x86/cpu: Add a steppings field to struct x86_cpu_id Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 08/34] x86/cpufeatures: Move RETPOLINE flags to word 11 Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 09/34] x86/bugs: Report AMD retbleed vulnerability Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 10/34] x86/bugs: Add AMD retbleed= boot parameter Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 11/34] x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 12/34] x86/entry: Remove skip_r11rcx Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 13/34] x86/entry: Add kernel IBRS implementation Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 14/34] x86/bugs: Optimize SPEC_CTRL MSR writes Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 15/34] x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 16/34] x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 17/34] x86/bugs: Report Intel retbleed vulnerability Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 18/34] intel_idle: Disable IBRS during long idle Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 19/34] x86/speculation: Change FILL_RETURN_BUFFER to work with objtool Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 20/34] x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 21/34] x86/speculation: Fix firmware entry SPEC_CTRL handling Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 22/34] x86/speculation: Fix SPEC_CTRL write on SMT state change Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 23/34] x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 24/34] x86/speculation: Remove x86_spec_ctrl_mask Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 25/34] KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 26/34] KVM: VMX: Fix IBRS handling after vmexit Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 27/34] x86/speculation: Fill RSB on vmexit for IBRS Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 28/34] x86/common: Stamp out the stepping madness Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 29/34] x86/cpu/amd: Enumerate BTC_NO Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 30/34] x86/bugs: Add Cannon lake to RETBleed affected CPU list Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 31/34] x86/speculation: Disable RRSBA behavior Suleiman Souhlal
2022-11-17  9:19 ` [PATCH 4.19 32/34] x86/speculation: Use DECLARE_PER_CPU for x86_spec_ctrl_current Suleiman Souhlal
2022-11-17  9:19 ` Suleiman Souhlal [this message]
2022-11-17  9:19 ` [PATCH 4.19 34/34] x86/speculation: Add RSB VM Exit protections Suleiman Souhlal
2022-11-21 12:26 ` [PATCH 4.19 00/34] Intel RETBleed mitigations for 4.19 Greg KH
2022-11-21 12:43 [PATCH 4.19 00/34] 4.19.266-rc1 review Greg Kroah-Hartman
2022-11-21 12:43 ` [PATCH 4.19 33/34] x86/bugs: Warn when "ibrs" mitigation is selected on Enhanced IBRS parts Greg Kroah-Hartman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221117091952.1940850-34-suleiman@google.com \
    --to=suleiman@google.com \
    --cc=bp@alien8.de \
    --cc=cascardo@canonical.com \
    --cc=jpoimboe@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ssouhlal@FreeBSD.org \
    --cc=stable@vger.kernel.org \
    --cc=surajjs@amazon.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.