Merge branch 'linus' into x86/urgent, to pick up dependent commits

Prepare to fix aspects of the new BHI code.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

33 files changed, 463 insertions, 87 deletions

diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index cce768afec6bed..b70b1d8bd8e657 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically,
 the BHB might be shared across privilege levels even in the presence of
 Enhanced IBRS.
 
-Currently the only known real-world BHB attack vector is via
-unprivileged eBPF. Therefore, it's highly recommended to not enable
-unprivileged eBPF, especially when eIBRS is used (without retpolines).
-For a full mitigation against BHB attacks, it's recommended to use
-retpolines (or eIBRS combined with retpolines).
+Previously the only known real-world BHB attack vector was via unprivileged
+eBPF. Further research has found attacks that don't require unprivileged eBPF.
+For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or
+use the BHB clearing sequence.
 
 Attack scenarios
 ----------------
@@ -430,6 +429,23 @@ The possible values in this file are:
   'PBRSB-eIBRS: Not affected'  CPU is not affected by PBRSB
   ===========================  =======================================================
 
+  - Branch History Injection (BHI) protection status:
+
+.. list-table::
+
+ * - BHI: Not affected
+   - System is not affected
+ * - BHI: Retpoline
+   - System is protected by retpoline
+ * - BHI: BHI_DIS_S
+   - System is protected by BHI_DIS_S
+ * - BHI: SW loop; KVM SW loop
+   - System is protected by software clearing sequence
+ * - BHI: Syscall hardening
+   - Syscalls are hardened against BHI
+ * - BHI: Syscall hardening; KVM: SW loop
+   - System is protected from userspace attacks by syscall hardening; KVM is protected by software clearing sequence
+
 Full mitigation might require a microcode update from the CPU
 vendor. When the necessary microcode is not available, the kernel will
 report vulnerability.
@@ -484,7 +500,11 @@ Spectre variant 2
 
    Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
    boot, by setting the IBRS bit, and they're automatically protected against
-   Spectre v2 variant attacks.
+   some Spectre v2 variant attacks. The BHB can still influence the choice of
+   indirect branch predictor entry, and although branch predictor entries are
+   isolated between modes when eIBRS is enabled, the BHB itself is not isolated
+   between modes. Systems which support BHI_DIS_S will set it to protect against
+   BHI attacks.
 
    On Intel's enhanced IBRS systems, this includes cross-thread branch target
    injections on SMT systems (STIBP). In other words, Intel eIBRS enables
@@ -638,6 +658,22 @@ kernel command line.
 		spectre_v2=off. Spectre variant 1 mitigations
 		cannot be disabled.
 
+	spectre_bhi=
+
+		[X86] Control mitigation of Branch History Injection
+		(BHI) vulnerability. Syscalls are hardened against BHI
+		regardless of this setting. This setting affects the deployment
+		of the HW BHI control and the SW BHB clearing sequence.
+
+		on
+			unconditionally enable.
+		off
+			unconditionally disable.
+		auto
+			enable if hardware mitigation
+			control(BHI_DIS_S) is available, otherwise
+			enable alternate mitigation in KVM.
+
 For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt
 
 Mitigation selection guide
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 623fce7d5fcd0c..70046a019d42d8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6063,6 +6063,18 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/admin-guide/laptops/sonypi.rst
 
+	spectre_bhi=	[X86] Control mitigation of Branch History Injection
+			(BHI) vulnerability. Syscalls are hardened against BHI
+			reglardless of this setting. This setting affects the
+			deployment of the HW BHI control and the SW BHB
+			clearing sequence.
+
+			on   - unconditionally enable.
+			off  - unconditionally disable.
+			auto - (default) enable hardware mitigation
+			       (BHI_DIS_S) if available, otherwise enable
+			       alternate mitigation in KVM.
+
 	spectre_v2=	[X86,EARLY] Control mitigation of Spectre variant 2
 			(indirect branch speculation) vulnerability.
 			The default operation protects the kernel from
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4fff6ed46e902c..10a6251f58f3e0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2633,6 +2633,32 @@ config MITIGATION_RFDS
 	  stored in floating point, vector and integer registers.
 	  See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
 
+choice
+	prompt "Clear branch history"
+	depends on CPU_SUP_INTEL
+	default SPECTRE_BHI_ON
+	help
+	  Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
+	  where the branch history buffer is poisoned to speculatively steer
+	  indirect branches.
+	  See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
+
+config SPECTRE_BHI_ON
+	bool "on"
+	help
+	  Equivalent to setting spectre_bhi=on command line parameter.
+config SPECTRE_BHI_OFF
+	bool "off"
+	help
+	  Equivalent to setting spectre_bhi=off command line parameter.
+config SPECTRE_BHI_AUTO
+	bool "auto"
+	depends on BROKEN
+	help
+	  Equivalent to setting spectre_bhi=auto command line parameter.
+
+endchoice
+
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6356060caaf311..6de50b80702e61 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
 
 	if (likely(unr < NR_syscalls)) {
 		unr = array_index_nospec(unr, NR_syscalls);
-		regs->ax = sys_call_table[unr](regs);
+		regs->ax = x64_sys_call(regs, unr);
 		return true;
 	}
 	return false;
@@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
 
 	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
 		xnr = array_index_nospec(xnr, X32_NR_syscalls);
-		regs->ax = x32_sys_call_table[xnr](regs);
+		regs->ax = x32_sys_call(regs, xnr);
 		return true;
 	}
 	return false;
@@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 
 	if (likely(unr < IA32_NR_syscalls)) {
 		unr = array_index_nospec(unr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call_table[unr](regs);
+		regs->ax = ia32_sys_call(regs, unr);
 	} else if (nr != -1) {
 		regs->ax = __ia32_sys_ni_syscall(regs);
 	}
@@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void)
 }
 
 /**
- * int80_emulation - 32-bit legacy syscall entry
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in
@@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void)
  *   eax:				system call number
  *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
  */
-DEFINE_IDTENTRY_RAW(int80_emulation)
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
 {
 	int nr;
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8af2a26b24f6a9..1b5be07f86698a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	/* clobbers %rax, make sure it is after saving the syscall nr */
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	call	do_syscall_64		/* returns with IRQs disabled */
 
@@ -1491,3 +1492,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	call	make_task_dead
 SYM_CODE_END(rewind_stack_and_make_dead)
 .popsection
+
+/*
+ * This sequence executes branches in order to remove user branch information
+ * from the branch history tracker in the Branch Predictor, therefore removing
+ * user influence on subsequent BTB lookups.
+ *
+ * It should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ *
+ * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
+ * and not clearing the branch history. The call tree looks like:
+ *
+ * call 1
+ *    call 2
+ *      call 2
+ *        call 2
+ *          call 2
+ * 	      call 2
+ * 	      ret
+ * 	    ret
+ *        ret
+ *      ret
+ *    ret
+ * ret
+ *
+ * This means that the stack is non-constant and ORC can't unwind it with %rsp
+ * alone.  Therefore we unconditionally set up the frame pointer, which allows
+ * ORC to unwind properly.
+ *
+ * The alignment is for performance and not for safety, and may be safely
+ * refactored in the future if needed.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+	push	%rbp
+	mov	%rsp, %rbp
+	movl	$5, %ecx
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call	1f
+	jmp	5f
+	.align 64, 0xcc
+	ANNOTATE_INTRA_FUNCTION_CALL
+1:	call	2f
+	RET
+	.align 64, 0xcc
+2:	movl	$5, %eax
+3:	jmp	4f
+	nop
+4:	sub	$1, %eax
+	jnz	3b
+	sub	$1, %ecx
+	jnz	1b
+	RET
+5:	lfence
+	pop	%rbp
+	RET
+SYM_FUNC_END(clear_bhb_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_loop)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index eabf48c4d4b4c3..c779046cc3fe79 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT and AC
@@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
@@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	int3
 SYM_CODE_END(entry_SYSCALL_compat)
+
+/*
+ * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries
+ * point to C routines, however since this is a system call interface the branch
+ * history needs to be scrubbed to protect against BHI attacks, and that
+ * scrubbing needs to take place in assembly code prior to entering any C
+ * routines.
+ */
+SYM_CODE_START(int80_emulation)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	CLEAR_BRANCH_HISTORY
+	jmp do_int80_emulation
+SYM_CODE_END(int80_emulation)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cfc9bc73e7f8b..c2235bae17ef66 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
 #include <asm/syscalls_32.h>
 #undef __SYSCALL
 
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
 #define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_32.h>
 };
+#undef __SYSCALL
+#endif
+
+#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+
+long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_32.h>
+	default: return __ia32_sys_ni_syscall(regs);
+	}
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index be120eec1fc9f9..33b3f09e6f151e 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
 #include <asm/syscalls_64.h>
 #undef __SYSCALL
 
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
 #define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_64.h>
 };
+#undef __SYSCALL
+
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+
+long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_64.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
+};
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index bdd0e03a1265d2..03de4a93213182 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
 #include <asm/syscalls_x32.h>
 #undef __SYSCALL
 
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
 
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_x32.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
 };
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a38f8f9ba65729..3c7434329661c6 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -461,11 +461,15 @@
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
- * CPUID levels like 0x80000022, etc.
+ * CPUID levels like 0x80000022, etc and Linux defined features.
  *
  * Reuse free bits when adding new feature flags!
  */
 #define X86_FEATURE_AMD_LBR_PMC_FREEZE	(21*32+ 0) /* AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
 
 /*
  * BUG word(s)
@@ -515,4 +519,5 @@
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
 #define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
 #define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 05956bd8bacf50..e72c2b87295799 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,10 +61,13 @@
 #define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT	10	   /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S		BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
 
 /* A mask for bits which the kernel toggles when controlling mitigations */
 #define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
-							| SPEC_CTRL_RRSBA_DIS_S)
+							| SPEC_CTRL_RRSBA_DIS_S \
+							| SPEC_CTRL_BHI_DIS_S)
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
@@ -163,6 +166,10 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#define ARCH_CAP_BHI_NO			BIT(20)	/*
+						 * CPU is not affected by Branch
+						 * History Injection.
+						 */
 #define ARCH_CAP_PBRSB_NO		BIT(24)	/*
 						 * Not susceptible to Post-Barrier
 						 * Return Stack Buffer Predictions.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 170c89ed22fcd3..ff5f1ecc7d1e65 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -326,6 +326,19 @@
 	ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
 .endm
 
+#ifdef CONFIG_X86_64
+.macro CLEAR_BRANCH_HISTORY
+	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
+.endm
+
+.macro CLEAR_BRANCH_HISTORY_VMEXIT
+	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+.endm
+#else
+#define CLEAR_BRANCH_HISTORY
+#define CLEAR_BRANCH_HISTORY_VMEXIT
+#endif
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\
@@ -368,6 +381,10 @@ extern void srso_alias_return_thunk(void);
 extern void entry_untrain_ret(void);
 extern void entry_ibpb(void);
 
+#ifdef CONFIG_X86_64
+extern void clear_bhb_loop(void);
+#endif
+
 extern void (*x86_return_thunk)(void);
 
 extern void __warn_thunk(void);
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index f44e2f9ab65d77..2fc7bc3863ff6f 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,19 +16,17 @@
 #include <asm/thread_info.h>	/* for TS_COMPAT */
 #include <asm/unistd.h>
 
+/* This is used purely for kernel/trace/trace_syscalls.c */
 typedef long (*sys_call_ptr_t)(const struct pt_regs *);
 extern const sys_call_ptr_t sys_call_table[];
 
-#if defined(CONFIG_X86_32)
-#define ia32_sys_call_table sys_call_table
-#else
 /*
  * These may not exist, but still put the prototypes in so we
  * can use IS_ENABLED().
  */
-extern const sys_call_ptr_t ia32_sys_call_table[];
-extern const sys_call_ptr_t x32_sys_call_table[];
-#endif
+extern long ia32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x64_sys_call(const struct pt_regs *, unsigned int nr);
 
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
@@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 }
 
 bool do_syscall_64(struct pt_regs *regs, int nr);
+void do_int80_emulation(struct pt_regs *regs);
 
 #endif	/* CONFIG_X86_32 */
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e7ba936d798b81..295463707e6818 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1607,6 +1607,79 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_
 	dump_stack();
 }
 
+/*
+ * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by
+ * branch history in userspace. Not needed if BHI_NO is set.
+ */
+static bool __init spec_ctrl_bhi_dis(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_BHI_CTRL))
+		return false;
+
+	x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S;
+	update_spec_ctrl(x86_spec_ctrl_base);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW);
+
+	return true;
+}
+
+enum bhi_mitigations {
+	BHI_MITIGATION_OFF,
+	BHI_MITIGATION_ON,
+	BHI_MITIGATION_AUTO,
+};
+
+static enum bhi_mitigations bhi_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_SPECTRE_BHI_ON)  ? BHI_MITIGATION_ON  :
+	IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF :
+					     BHI_MITIGATION_AUTO;
+
+static int __init spectre_bhi_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		bhi_mitigation = BHI_MITIGATION_OFF;
+	else if (!strcmp(str, "on"))
+		bhi_mitigation = BHI_MITIGATION_ON;
+	else if (!strcmp(str, "auto"))
+		bhi_mitigation = BHI_MITIGATION_AUTO;
+	else
+		pr_err("Ignoring unknown spectre_bhi option (%s)", str);
+
+	return 0;
+}
+early_param("spectre_bhi", spectre_bhi_parse_cmdline);
+
+static void __init bhi_select_mitigation(void)
+{
+	if (bhi_mitigation == BHI_MITIGATION_OFF)
+		return;
+
+	/* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+	    !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+		return;
+
+	if (spec_ctrl_bhi_dis())
+		return;
+
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	/* Mitigate KVM by default */
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+	pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+
+	if (bhi_mitigation == BHI_MITIGATION_AUTO)
+		return;
+
+	/* Mitigate syscalls when the mitigation is forced =on */
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
+	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1718,6 +1791,9 @@ static void __init spectre_v2_select_mitigation(void)
 	    mode == SPECTRE_V2_RETPOLINE)
 		spec_ctrl_disable_kernel_rrsba();
 
+	if (boot_cpu_has(X86_BUG_BHI))
+		bhi_select_mitigation();
+
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
@@ -2695,15 +2771,15 @@ static char *stibp_state(void)
 
 	switch (spectre_v2_user_stibp) {
 	case SPECTRE_V2_USER_NONE:
-		return ", STIBP: disabled";
+		return "; STIBP: disabled";
 	case SPECTRE_V2_USER_STRICT:
-		return ", STIBP: forced";
+		return "; STIBP: forced";
 	case SPECTRE_V2_USER_STRICT_PREFERRED:
-		return ", STIBP: always-on";
+		return "; STIBP: always-on";
 	case SPECTRE_V2_USER_PRCTL:
 	case SPECTRE_V2_USER_SECCOMP:
 		if (static_key_enabled(&switch_to_cond_stibp))
-			return ", STIBP: conditional";
+			return "; STIBP: conditional";
 	}
 	return "";
 }
@@ -2712,10 +2788,10 @@ static char *ibpb_state(void)
 {
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		if (static_key_enabled(&switch_mm_always_ibpb))
-			return ", IBPB: always-on";
+			return "; IBPB: always-on";
 		if (static_key_enabled(&switch_mm_cond_ibpb))
-			return ", IBPB: conditional";
-		return ", IBPB: disabled";
+			return "; IBPB: conditional";
+		return "; IBPB: disabled";
 	}
 	return "";
 }
@@ -2725,14 +2801,31 @@ static char *pbrsb_eibrs_state(void)
 	if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
 		if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
 		    boot_cpu_has(X86_FEATURE_RSB_VMEXIT))
-			return ", PBRSB-eIBRS: SW sequence";
+			return "; PBRSB-eIBRS: SW sequence";
 		else
-			return ", PBRSB-eIBRS: Vulnerable";
+			return "; PBRSB-eIBRS: Vulnerable";
 	} else {
-		return ", PBRSB-eIBRS: Not affected";
+		return "; PBRSB-eIBRS: Not affected";
 	}
 }
 
+static const char * const spectre_bhi_state(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_BHI))
+		return "; BHI: Not affected";
+	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+		return "; BHI: BHI_DIS_S";
+	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+		return "; BHI: SW loop, KVM: SW loop";
+	else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+		 !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+		return "; BHI: Retpoline";
+	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+		return "; BHI: Syscall hardening, KVM: SW loop";
+
+	return "; BHI: Vulnerable (Syscall hardening enabled)";
+}
+
 static ssize_t spectre_v2_show_state(char *buf)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -2745,13 +2838,15 @@ static ssize_t spectre_v2_show_state(char *buf)
 	    spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
 		return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
 
-	return sysfs_emit(buf, "%s%s%s%s%s%s%s\n",
+	return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n",
 			  spectre_v2_strings[spectre_v2_enabled],
 			  ibpb_state(),
-			  boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+			  boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "",
 			  stibp_state(),
-			  boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+			  boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "",
 			  pbrsb_eibrs_state(),
+			  spectre_bhi_state(),
+			  /* this should always be at the end */
 			  spectre_v2_module_string());
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5c1e6d6be267af..754d91857d634a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1120,6 +1120,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_SPECTRE_V2		BIT(8)
 #define NO_MMIO			BIT(9)
 #define NO_EIBRS_PBRSB		BIT(10)
+#define NO_BHI			BIT(11)
 
 #define VULNWL(vendor, family, model, whitelist)	\
 	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1182,18 +1183,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
 
 	/* Zhaoxin Family 7 */
-	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
-	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
+	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
 	{}
 };
 
@@ -1435,6 +1436,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (vulnerable_to_rfds(ia32_cap))
 		setup_force_cpu_bug(X86_BUG_RFDS);
 
+	/* When virtualized, eIBRS could be hidden, assume vulnerable */
+	if (!(ia32_cap & ARCH_CAP_BHI_NO) &&
+	    !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+	    (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+	     boot_cpu_has(X86_FEATURE_HYPERVISOR)))
+		setup_force_cpu_bug(X86_BUG_BHI);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index a515328d9d7d88..af5aa2c754c222 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
 	{ X86_FEATURE_INTEL_PPIN,	CPUID_EBX,  0, 0x00000007, 1 },
 	{ X86_FEATURE_RRSBA_CTRL,	CPUID_EDX,  2, 0x00000007, 2 },
+	{ X86_FEATURE_BHI_CTRL,		CPUID_EDX,  4, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
 	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
 	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 58ac8d69c94bd1..2f4e155080badc 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_IPRED_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
 #define KVM_X86_FEATURE_RRSBA_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
 #define X86_FEATURE_DDPD_U		KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
-#define X86_FEATURE_BHI_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define KVM_X86_FEATURE_BHI_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
 #define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
 
 /* CPUID level 0x80000007 (EDX). */
@@ -128,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature)
 	KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
 	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
 	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+	KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
 	default:
 		return x86_feature;
 	}
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 2bfbf758d06110..f6986dee6f8c7c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
 
 	call vmx_spec_ctrl_restore_host
 
+	CLEAR_BRANCH_HISTORY_VMEXIT
+
 	/* Put return value in AX */
 	mov %_ASM_BX, %_ASM_AX
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47d9f03b777837..984ea2089efc31 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1621,7 +1621,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
 	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
-	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index 7bcbc4895ec221..271bfa038f5bc9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -25,6 +25,7 @@
 
 #include <subdev/bios.h>
 #include <subdev/bios/init.h>
+#include <subdev/gsp.h>
 
 void
 gm107_devinit_disable(struct nvkm_devinit *init)
@@ -33,10 +34,13 @@ gm107_devinit_disable(struct nvkm_devinit *init)
 	u32 r021c00 = nvkm_rd32(device, 0x021c00);
 	u32 r021c04 = nvkm_rd32(device, 0x021c04);
 
-	if (r021c00 & 0x00000001)
-		nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
-	if (r021c00 & 0x00000004)
-		nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+	/* gsp only wants to enable/disable display */
+	if (!nvkm_gsp_rm(device->gsp)) {
+		if (r021c00 & 0x00000001)
+			nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
+		if (r021c00 & 0x00000004)
+			nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+	}
 	if (r021c04 & 0x00000001)
 		nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
index 11b4c9c274a1a5..666eb93b1742ca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
@@ -41,6 +41,7 @@ r535_devinit_new(const struct nvkm_devinit_func *hw,
 
 	rm->dtor = r535_devinit_dtor;
 	rm->post = hw->post;
+	rm->disable = hw->disable;
 
 	ret = nv50_devinit_new_(rm, device, type, inst, pdevinit);
 	if (ret)
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index dd6f566a383f00..121ab890bd0557 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1133,6 +1133,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
+	ret = btrfs_record_root_in_trans(trans, node->root);
+	if (ret)
+		return ret;
 	ret = btrfs_update_delayed_inode(trans, node->root, path, node);
 	return ret;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 37701531eeb1ba..c65fe5de40220d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2533,7 +2533,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 		 */
 		if (bits & EXTENT_CLEAR_META_RESV &&
 		    root != fs_info->tree_root)
-			btrfs_delalloc_release_metadata(inode, len, false);
+			btrfs_delalloc_release_metadata(inode, len, true);
 
 		/* For sanity tests. */
 		if (btrfs_is_testing(fs_info))
@@ -4503,6 +4503,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_block_rsv block_rsv;
 	u64 root_flags;
+	u64 qgroup_reserved = 0;
 	int ret;
 
 	down_write(&fs_info->subvol_sem);
@@ -4547,12 +4548,20 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
 		goto out_undead;
+	qgroup_reserved = block_rsv.qgroup_rsv_reserved;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out_release;
 	}
+	ret = btrfs_record_root_in_trans(trans, root);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto out_end_trans;
+	}
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
@@ -4611,7 +4620,9 @@ out_end_trans:
 	ret = btrfs_end_transaction(trans);
 	inode->i_flags |= S_DEAD;
 out_release:
-	btrfs_subvolume_release_metadata(root, &block_rsv);
+	btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 294e31edec9d3b..55f3ba6a831ca1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -613,6 +613,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	int ret;
 	dev_t anon_dev;
 	u64 objectid;
+	u64 qgroup_reserved = 0;
 
 	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
 	if (!root_item)
@@ -650,13 +651,18 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 					       trans_num_items, false);
 	if (ret)
 		goto out_new_inode_args;
+	qgroup_reserved = block_rsv.qgroup_rsv_reserved;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_subvolume_release_metadata(root, &block_rsv);
-		goto out_new_inode_args;
+		goto out_release_rsv;
 	}
+	ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+	if (ret)
+		goto out;
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 	/* Tree log can't currently deal with an inode which is a new root. */
@@ -767,9 +773,11 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 out:
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
-	btrfs_subvolume_release_metadata(root, &block_rsv);
-
 	btrfs_end_transaction(trans);
+out_release_rsv:
+	btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 out_new_inode_args:
 	btrfs_new_inode_args_destroy(&new_inode_args);
 out_inode:
@@ -791,6 +799,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_pending_snapshot *pending_snapshot;
 	unsigned int trans_num_items;
 	struct btrfs_trans_handle *trans;
+	struct btrfs_block_rsv *block_rsv;
+	u64 qgroup_reserved = 0;
 	int ret;
 
 	/* We do not support snapshotting right now. */
@@ -827,19 +837,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		goto free_pending;
 	}
 
-	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
-			     BTRFS_BLOCK_RSV_TEMP);
+	block_rsv = &pending_snapshot->block_rsv;
+	btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
 	 * 1 to add dir item
 	 * 1 to add dir index
 	 * 1 to update parent inode item
 	 */
 	trans_num_items = create_subvol_num_items(inherit) + 3;
-	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
-					       &pending_snapshot->block_rsv,
+	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv,
 					       trans_num_items, false);
 	if (ret)
 		goto free_pending;
+	qgroup_reserved = block_rsv->qgroup_rsv_reserved;
 
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
@@ -852,6 +862,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		ret = PTR_ERR(trans);
 		goto fail;
 	}
+	ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+	if (ret) {
+		btrfs_end_transaction(trans);
+		goto fail;
+	}
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 
 	trans->pending_snapshot = pending_snapshot;
 
@@ -881,7 +898,9 @@ fail:
 	if (ret && pending_snapshot->snap)
 		pending_snapshot->snap->anon_dev = 0;
 	btrfs_put_root(pending_snapshot->snap);
-	btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv);
+	btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 free_pending:
 	if (pending_snapshot->anon_dev)
 		free_anon_bdev(pending_snapshot->anon_dev);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5f90f0605b12f7..cf8820ce7aa297 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -4495,6 +4495,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
 				      BTRFS_QGROUP_RSV_META_PREALLOC);
 	trace_qgroup_meta_convert(root, num_bytes);
 	qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
+	if (!sb_rdonly(fs_info->sb))
+		add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS);
 }
 
 /*
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 4bb538a372ce56..7007f9e0c97282 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -548,13 +548,3 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 	}
 	return ret;
 }
-
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
-				      struct btrfs_block_rsv *rsv)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 qgroup_to_release;
-
-	btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release);
-	btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release);
-}
diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h
index 6f929cf3bd4967..8f5739e732b9b6 100644
--- a/fs/btrfs/root-tree.h
+++ b/fs/btrfs/root-tree.h
@@ -18,8 +18,6 @@ struct btrfs_trans_handle;
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems, bool use_global_rsv);
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
-				      struct btrfs_block_rsv *rsv);
 int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 		       u64 ref_id, u64 dirid, u64 sequence,
 		       const struct fscrypt_str *name);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 46e8426adf4f15..85f359e0e0a7f2 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -745,14 +745,6 @@ again:
 		h->reloc_reserved = reloc_reserved;
 	}
 
-	/*
-	 * Now that we have found a transaction to be a part of, convert the
-	 * qgroup reservation from prealloc to pertrans. A different transaction
-	 * can't race in and free our pertrans out from under us.
-	 */
-	if (qgroup_reserved)
-		btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
-
 got_it:
 	if (!current->journal_info)
 		current->journal_info = h;
@@ -786,8 +778,15 @@ got_it:
 		 * not just freed.
 		 */
 		btrfs_end_transaction(h);
-		return ERR_PTR(ret);
+		goto reserve_fail;
 	}
+	/*
+	 * Now that we have found a transaction to be a part of, convert the
+	 * qgroup reservation from prealloc to pertrans. A different transaction
+	 * can't race in and free our pertrans out from under us.
+	 */
+	if (qgroup_reserved)
+		btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
 
 	return h;
 
@@ -1495,6 +1494,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 			radix_tree_tag_clear(&fs_info->fs_roots_radix,
 					(unsigned long)root->root_key.objectid,
 					BTRFS_ROOT_TRANS_TAG);
+			btrfs_qgroup_free_meta_all_pertrans(root);
 			spin_unlock(&fs_info->fs_roots_radix_lock);
 
 			btrfs_free_log(trans, root);
@@ -1519,7 +1519,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 			if (ret2)
 				return ret2;
 			spin_lock(&fs_info->fs_roots_radix_lock);
-			btrfs_qgroup_free_meta_all_pertrans(root);
 		}
 	}
 	spin_unlock(&fs_info->fs_roots_radix_lock);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c00cc6c0878a1e..8c252e073bd810 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -268,7 +268,7 @@ static inline void *offset_to_ptr(const int *off)
  *   - When one operand is a null pointer constant (i.e. when x is an integer
  *     constant expression) and the other is an object pointer (i.e. our
  *     third operand), the conditional operator returns the type of the
- *     object pointer operand (i.e. "int *). Here, within the sizeof(), we
+ *     object pointer operand (i.e. "int *"). Here, within the sizeof(), we
  *     would then get:
  *       sizeof(*((int *)(...))  == sizeof(int)  == 4
  *   - When one operand is a void pointer (i.e. when x is not an integer
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 868c8fb1bbc1c2..13becafe41df00 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -2,6 +2,8 @@
 #ifndef __LINUX_GFP_TYPES_H
 #define __LINUX_GFP_TYPES_H
 
+#include <linux/bits.h>
+
 /* The typedef is in types.h but we want the documentation here */
 #if 0
 /**
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 4b0673bf52c2e6..07cfad817d5390 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -8,6 +8,7 @@
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
 #include <linux/math.h>
+#include <linux/panic.h>
 #include <endian.h>
 #include <byteswap.h>
 
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
index f3c82ab5b14cd7..7d73da0980473f 100644
--- a/tools/include/linux/mm.h
+++ b/tools/include/linux/mm.h
@@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count)
 {
 }
 
+static inline int early_pfn_to_nid(unsigned long pfn)
+{
+	return 0;
+}
+
 #endif
diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h
new file mode 100644
index 00000000000000..9c8f17a41ce8ed
--- /dev/null
+++ b/tools/include/linux/panic.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PANIC_H
+#define _TOOLS_LINUX_PANIC_H
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+static inline void panic(const char *fmt, ...)
+{
+	va_list argp;
+
+	va_start(argp, fmt);
+	vfprintf(stderr, fmt, argp);
+	va_end(argp);
+	exit(-1);
+}
+
+#endif