[PATCH 2/3] x86/efi: Replace efi_pgd with efi_mm.pgd

[PATCH 2/3] x86/efi: Replace efi_pgd with efi_mm.pgd

[Sai Praneeth Prakhya]

From: Sai Praneeth <sai.praneeth.prakhya@intel.com>

Since the previous patch added support for efi_mm, let's handle efi_pgd
through efi_mm and remove global variable efi_pgd.

Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Cc: Lee, Chun-Yi <jlee@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Bhupesh Sharma <bhsharma@redhat.com>
Cc: Ricardo Neri <ricardo.neri@intel.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ravi Shankar <ravi.v.shankar@intel.com>
Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
---
 arch/x86/platform/efi/efi_64.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ccf5239923e8..6b541bdbda5f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -189,8 +189,6 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	early_code_mapping_set_exec(0);
 }
 
-static pgd_t *efi_pgd;
-
 /*
  * We need our own copy of the higher levels of the page tables
  * because we want to avoid inserting EFI region mappings (EFI_VA_END
@@ -199,7 +197,7 @@ static pgd_t *efi_pgd;
  */
 int __init efi_alloc_page_tables(void)
 {
-	pgd_t *pgd;
+	pgd_t *pgd, *efi_pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	gfp_t gfp_mask;
@@ -227,6 +225,7 @@ int __init efi_alloc_page_tables(void)
 		return -ENOMEM;
 	}
 
+	efi_mm.pgd = efi_pgd;
 	mm_init_cpumask(&efi_mm);
 	init_new_context(NULL, &efi_mm);
 
@@ -242,6 +241,7 @@ void efi_sync_low_kernel_mappings(void)
 	pgd_t *pgd_k, *pgd_efi;
 	p4d_t *p4d_k, *p4d_efi;
 	pud_t *pud_k, *pud_efi;
+	pgd_t *efi_pgd = efi_mm.pgd;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
@@ -335,7 +335,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	unsigned long pfn, text, pf;
 	struct page *page;
 	unsigned npages;
-	pgd_t *pgd;
+	pgd_t *pgd = efi_mm.pgd;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
@@ -345,8 +345,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * this value is loaded into cr3 the PGD will be decrypted during
 	 * the pagetable walk.
 	 */
-	efi_scratch.efi_pgt = (pgd_t *)__sme_pa(efi_pgd);
-	pgd = efi_pgd;
+	efi_scratch.efi_pgt = (pgd_t *)__sme_pa(pgd);
 
 	/*
 	 * It can happen that the physical address of new_memmap lands in memory
@@ -416,7 +415,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
 	unsigned long flags = _PAGE_RW;
 	unsigned long pfn;
-	pgd_t *pgd = efi_pgd;
+	pgd_t *pgd = efi_mm.pgd;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
@@ -520,7 +519,7 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
 {
 	unsigned long pfn;
-	pgd_t *pgd = efi_pgd;
+	pgd_t *pgd = efi_mm.pgd;
 	int err1, err2;
 
 	/* Update the 1:1 mapping */
@@ -617,7 +616,7 @@ void __init efi_dump_pagetable(void)
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		ptdump_walk_pgd_level(NULL, swapper_pg_dir);
 	else
-		ptdump_walk_pgd_level(NULL, efi_pgd);
+		ptdump_walk_pgd_level(NULL, efi_mm.pgd);
 #endif
 }
 
-- 
2.1.4

[PATCH 0/3] Use mm_struct and switch_mm() instead of manually

[Sai Praneeth Prakhya]

From: Sai Praneeth <sai.praneeth.prakhya@intel.com>

Presently, in x86, to invoke any efi function like
efi_set_virtual_address_map() or any efi_runtime_service() the code path
typically involves read_cr3() (save previous pgd), write_cr3()
(write efi_pgd) and calling efi function. Likewise after returning from
efi function the code path typically involves read_cr3() (save efi_pgd),
write_cr3() (write previous pgd). We do this couple of times in efi
subsystem of Linux kernel, so we can use a function (efi_switch_mm())
to do this. This improves readability and maintainability. Also, instead
of maintaining a separate struct "efi_scratch" to store/restore efi_pgd,
we can use mm_struct to do this.

I have tested this patch set against LUV, so I think I didn't break
any existing configurations. I have tested this patch set for
1. x86_64,
2. x86_32,
3. Mixed mode
with efi=old_map and for kexec kernel. Please let me know if I have
missed any other configurations.

Special thanks to Matt for his initial review.

Matt,
I have implemented efi_switch_mm() in "arch/x86/platform/efi/efi_64.c"
because it's used only by x86_64. Please let me know if you think it
should be in "drivers/firmware/efi/efi.c"

Andy and Michael,
As I am twiddling with memory management for the first time and I think
you are mm experts, could you please review efi_switch_mm() function
in "x86/efi: Use efi_switch_mm() rather than manually twiddling with cr3"

Sai Praneeth (3):
  efi: Use efi_mm in x86 as well as ARM
  x86/efi: Replace efi_pgd with efi_mm.pgd
  x86/efi: Use efi_switch_mm() rather than manually twiddling with cr3

 arch/x86/include/asm/efi.h           | 30 +++++++++----------
 arch/x86/platform/efi/efi_64.c       | 57 ++++++++++++++++++++++--------------
 arch/x86/platform/efi/efi_thunk_64.S |  2 +-
 drivers/firmware/efi/arm-runtime.c   |  9 ------
 drivers/firmware/efi/efi.c           |  9 ++++++
 include/linux/efi.h                  |  2 ++
 6 files changed, 62 insertions(+), 47 deletions(-)

-- 
2.1.4

[PATCH 2/3] x86/efi: Replace efi_pgd with efi_mm.pgd

[Sai Praneeth Prakhya]

From: Sai Praneeth <sai.praneeth.prakhya@intel.com>

Since the previous patch added support for efi_mm, let's handle efi_pgd
through efi_mm and remove global variable efi_pgd.

Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Cc: Lee, Chun-Yi <jlee@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Ricardo Neri <ricardo.neri@intel.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ravi Shankar <ravi.v.shankar@intel.com>
---
 arch/x86/platform/efi/efi_64.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 8ff1f95627f9..0bb98c35e178 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -187,8 +187,6 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	early_code_mapping_set_exec(0);
 }
 
-static pgd_t *efi_pgd;
-
 /*
  * We need our own copy of the higher levels of the page tables
  * because we want to avoid inserting EFI region mappings (EFI_VA_END
@@ -197,7 +195,7 @@ static pgd_t *efi_pgd;
  */
 int __init efi_alloc_page_tables(void)
 {
-	pgd_t *pgd;
+	pgd_t *pgd, *efi_pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	gfp_t gfp_mask;
@@ -225,6 +223,8 @@ int __init efi_alloc_page_tables(void)
 		return -ENOMEM;
 	}
 
+	efi_mm.pgd = efi_pgd;
+
 	return 0;
 }
 
@@ -237,6 +237,7 @@ void efi_sync_low_kernel_mappings(void)
 	pgd_t *pgd_k, *pgd_efi;
 	p4d_t *p4d_k, *p4d_efi;
 	pud_t *pud_k, *pud_efi;
+	pgd_t *efi_pgd = efi_mm.pgd;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
@@ -330,13 +331,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	unsigned long pfn, text;
 	struct page *page;
 	unsigned npages;
-	pgd_t *pgd;
+	pgd_t *pgd = efi_mm.pgd;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd);
-	pgd = efi_pgd;
+	efi_scratch.efi_pgt = (pgd_t *)__pa(pgd);
 
 	/*
 	 * It can happen that the physical address of new_memmap lands in memory
@@ -400,7 +400,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
 	unsigned long flags = _PAGE_RW;
 	unsigned long pfn;
-	pgd_t *pgd = efi_pgd;
+	pgd_t *pgd = efi_mm.pgd;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
@@ -501,7 +501,7 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
 {
 	unsigned long pfn;
-	pgd_t *pgd = efi_pgd;
+	pgd_t *pgd = efi_mm.pgd;
 	int err1, err2;
 
 	/* Update the 1:1 mapping */
@@ -592,7 +592,7 @@ void __init efi_dump_pagetable(void)
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		ptdump_walk_pgd_level(NULL, swapper_pg_dir);
 	else
-		ptdump_walk_pgd_level(NULL, efi_pgd);
+		ptdump_walk_pgd_level(NULL, efi_mm.pgd);
 #endif
 }
 
-- 
2.1.4