[GIT pull] x86/urgent for v5.16-rc1

From: Thomas Gleixner
Date: Sun Nov 21 2021 - 10:09:36 EST


Linus,

please pull the latest x86/urgent branch from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-2021-11-21

up to: ac5d272a0ad0: x86/sgx: Fix free page accounting

Two X86 fixes:

- Move the command line preparation and the early command line parsing
earlier so that the command line parameters which affect
early_reserve_memory(), e.g. efi=nosftreserve, are taken into
account. This was broken when the invocation of early_reserve_memory()
was moved recently.

- Use an atomic type for the SGX page accounting, which is read and
written lockless, to plug various race conditions related to it.

Thanks,

tglx

------------------>
Borislav Petkov (1):
x86/boot: Pull up cmdline preparation and early param parsing

Reinette Chatre (1):
x86/sgx: Fix free page accounting


arch/x86/kernel/cpu/sgx/main.c | 12 ++++----
arch/x86/kernel/setup.c | 66 +++++++++++++++++++++++++-----------------
2 files changed, 45 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 63d3de02bbcc..8471a8b9b48e 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -28,8 +28,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq);
static LIST_HEAD(sgx_active_page_list);
static DEFINE_SPINLOCK(sgx_reclaimer_lock);

-/* The free page list lock protected variables prepend the lock. */
-static unsigned long sgx_nr_free_pages;
+static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0);

/* Nodes with one or more EPC sections. */
static nodemask_t sgx_numa_mask;
@@ -403,14 +402,15 @@ static void sgx_reclaim_pages(void)

spin_lock(&node->lock);
list_add_tail(&epc_page->list, &node->free_page_list);
- sgx_nr_free_pages++;
spin_unlock(&node->lock);
+ atomic_long_inc(&sgx_nr_free_pages);
}
}

static bool sgx_should_reclaim(unsigned long watermark)
{
- return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list);
+ return atomic_long_read(&sgx_nr_free_pages) < watermark &&
+ !list_empty(&sgx_active_page_list);
}

static int ksgxd(void *p)
@@ -471,9 +471,9 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)

page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
list_del_init(&page->list);
- sgx_nr_free_pages--;

spin_unlock(&node->lock);
+ atomic_long_dec(&sgx_nr_free_pages);

return page;
}
@@ -625,9 +625,9 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
spin_lock(&node->lock);

list_add_tail(&page->list, &node->free_page_list);
- sgx_nr_free_pages++;

spin_unlock(&node->lock);
+ atomic_long_inc(&sgx_nr_free_pages);
}

static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 49b596db5631..c410be738ae7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -742,6 +742,28 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
return 0;
}

+static char *prepare_command_line(void)
+{
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0]) {
+ /* append boot loader cmdline to builtin */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif
+#endif
+
+ strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+
+ parse_early_param();
+
+ return command_line;
+}
+
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -830,6 +852,23 @@ void __init setup_arch(char **cmdline_p)

x86_init.oem.arch_setup();

+ /*
+ * x86_configure_nx() is called before parse_early_param() (called by
+ * prepare_command_line()) to detect whether hardware doesn't support
+ * NX (so that the early EHCI debug console setup can safely call
+ * set_fixmap()). It may then be called again from within noexec_setup()
+ * during parsing early parameters to honor the respective command line
+ * option.
+ */
+ x86_configure_nx();
+
+ /*
+ * This parses early params and it needs to run before
+ * early_reserve_memory() because latter relies on such settings
+ * supplied as early params.
+ */
+ *cmdline_p = prepare_command_line();
+
/*
* Do some memory reservations *before* memory is added to memblock, so
* memblock allocations won't overwrite it.
@@ -863,33 +902,6 @@ void __init setup_arch(char **cmdline_p)
bss_resource.start = __pa_symbol(__bss_start);
bss_resource.end = __pa_symbol(__bss_stop)-1;

-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
- strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
- if (builtin_cmdline[0]) {
- /* append boot loader cmdline to builtin */
- strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
- strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
- strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
- }
-#endif
-#endif
-
- strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
- *cmdline_p = command_line;
-
- /*
- * x86_configure_nx() is called before parse_early_param() to detect
- * whether hardware doesn't support NX (so that the early EHCI debug
- * console setup can safely call set_fixmap()). It may then be called
- * again from within noexec_setup() during parsing early parameters
- * to honor the respective command line option.
- */
- x86_configure_nx();
-
- parse_early_param();
-
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux