Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Ankur Arora <ankur.a.arora@oracle.com>
To:     linux-kernel@vger.kernel.org, x86@kernel.org
Cc:     peterz@infradead.org, hpa@zytor.com, jpoimboe@redhat.com,
        namit@vmware.com, mhiramat@kernel.org, jgross@suse.com,
        bp@alien8.de, vkuznets@redhat.com, pbonzini@redhat.com,
        boris.ostrovsky@oracle.com, mihai.carabas@oracle.com,
        kvm@vger.kernel.org, xen-devel@lists.xenproject.org,
        virtualization@lists.linux-foundation.org,
        Ankur Arora <ankur.a.arora@oracle.com>
Subject: [RFC PATCH 02/26] x86/paravirt: Allow paravirt patching post-init
Date:   Tue,  7 Apr 2020 22:02:59 -0700
Message-Id: <20200408050323.4237-3-ankur.a.arora@oracle.com>
In-Reply-To: <20200408050323.4237-1-ankur.a.arora@oracle.com>
References: <20200408050323.4237-1-ankur.a.arora@oracle.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Paravirt-ops are patched at init to convert indirect calls into
direct calls and in some cases, to inline the target at the call-site.
This is done by way of PVOP* macros which save the call-site
information via compile time annotations.

Pull this state out in .parainstructions.runtime for some pv-ops such
that they can be used for runtime patching.

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 arch/x86/Kconfig                      | 12 ++++++++++++
 arch/x86/include/asm/paravirt_types.h |  5 +++++
 arch/x86/include/asm/text-patching.h  |  5 +++++
 arch/x86/kernel/alternative.c         |  2 ++
 arch/x86/kernel/module.c              | 10 +++++++++-
 arch/x86/kernel/vmlinux.lds.S         | 16 ++++++++++++++++
 include/asm-generic/vmlinux.lds.h     |  8 ++++++++
 7 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1edf788d301c..605619938f08 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -764,6 +764,18 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_RUNTIME
+	bool "Enable paravirtualized ops to be patched at runtime"
+	depends on PARAVIRT
+	help
+	  Enable the paravirtualized guest kernel to switch pv-ops based on
+	  changed host conditions, potentially improving performance
+	  significantly.
+
+	  This would increase the memory footprint of the running kernel
+	  slightly (depending mostly on whether lock and unlock are inlined
+	  or not.)
+
 config PARAVIRT_XXL
 	bool
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 37e8f27a3b9d..00e4a062ca10 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -723,6 +723,11 @@ struct paravirt_patch_site {
 extern struct paravirt_patch_site __parainstructions[],
 	__parainstructions_end[];
 
+#ifdef CONFIG_PARAVIRT_RUNTIME
+extern struct paravirt_patch_site __parainstructions_runtime[],
+	__parainstructions_runtime_end[];
+#endif
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 67315fa3956a..e2ef241c261e 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -18,6 +18,11 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
+#ifndef CONFIG_PARAVIRT_RUNTIME
+#define __parainstructions_runtime	NULL
+#define __parainstructions_runtime_end	NULL
+#endif
+
 /*
  * Currently, the max observed size in the kernel code is
  * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7867dfb3963e..fdfda1375f82 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -740,6 +740,8 @@ void __init alternative_instructions(void)
 #endif
 
 	apply_paravirt(__parainstructions, __parainstructions_end);
+	apply_paravirt(__parainstructions_runtime,
+		       __parainstructions_runtime_end);
 
 	restart_nmi();
 	alternatives_patched = 1;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d5c72cb877b3..658ea60ce324 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -222,7 +222,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
-		*para = NULL, *orc = NULL, *orc_ip = NULL;
+		*para = NULL, *para_run = NULL, *orc = NULL, *orc_ip = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -234,6 +234,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 			locks = s;
 		if (!strcmp(".parainstructions", secstrings + s->sh_name))
 			para = s;
+		if (!strcmp(".parainstructions.runtime",
+			    secstrings + s->sh_name))
+			para_run = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -257,6 +260,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *pseg = (void *)para->sh_addr;
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
+	if (para_run) {
+		void *pseg = (void *)para_run->sh_addr;
+
+		apply_paravirt(pseg, pseg + para_run->sh_size);
+	}
 
 	/* make jump label nops */
 	jump_label_apply_nops(me);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 1bf7e312361f..7f5b8f6ab96e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -269,6 +269,7 @@ SECTIONS
 	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
 		__parainstructions = .;
 		*(.parainstructions)
+		PARAVIRT_DISCARD(.parainstructions.runtime)
 		__parainstructions_end = .;
 	}
 
@@ -348,6 +349,21 @@ SECTIONS
 		__smp_locks_end = .;
 	}
 
+#ifdef CONFIG_PARAVIRT_RUNTIME
+	/*
+	 * .parainstructions.runtime sticks around in memory after
+	 * init so it doesn't need to be page-aligned but everything
+	 * around us is so we will be too.
+	 */
+	. = ALIGN(8);
+	.parainstructions.runtime : AT(ADDR(.parainstructions.runtime) - \
+								LOAD_OFFSET) {
+		__parainstructions_runtime = .;
+		PARAVIRT_KEEP(.parainstructions.runtime)
+		__parainstructions_runtime_end = .;
+	}
+#endif
+
 #ifdef CONFIG_X86_64
 	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
 		NOSAVE_DATA
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 71e387a5fe90..6b009d5ce51f 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -135,6 +135,14 @@
 #define MEM_DISCARD(sec) *(.mem##sec)
 #endif
 
+#if defined(CONFIG_PARAVIRT_RUNTIME)
+#define PARAVIRT_KEEP(sec)	*(sec)
+#define PARAVIRT_DISCARD(sec)
+#else
+#define PARAVIRT_KEEP(sec)
+#define PARAVIRT_DISCARD(sec)	*(sec)
+#endif
+
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 /*
  * The ftrace call sites are logged to a section whose name depends on the
-- 
2.20.1