[PATCH v6 8/8] dma: swiotlb: Remove SWIOTLB_ANY

["Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>]

swiotlb pools are currently allocated below the architecture's low
address limit by default. SWIOTLB_ANY overrides this and permits
allocation anywhere in directly mapped memory.

SWIOTLB_INIT_ADDRESSING_LIMIT now explicitly identifies callers which
need a pool that is reachable by devices with limited DMA addressing.
Use it as the placement constraint and remove SWIOTLB_ANY.

This changes the default behavior for callers which do not set either
flag. Previously, omitting SWIOTLB_ANY placed the default pool below the
architecture's low address limit and also constrained dynamically
allocated pools to the same range. After this change, omitting
SWIOTLB_INIT_ADDRESSING_LIMIT permits both static and dynamic pools to
use any directly mapped memory.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: "Christophe Leroy (CS GROUP)" <chleroy@kernel.org>
Cc: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
 Documentation/core-api/swiotlb.rst |  8 ++++----
 arch/powerpc/mm/mem.c              |  6 ++++--
 arch/riscv/mm/init.c               | 16 ----------------
 arch/s390/mm/init.c                |  2 +-
 arch/x86/kernel/pci-dma.c          |  2 +-
 include/linux/swiotlb.h            |  7 +++----
 kernel/dma/swiotlb.c               | 17 ++++++-----------
 7 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/Documentation/core-api/swiotlb.rst b/Documentation/core-api/swiotlb.rst
index 71b4e4c27eb5..06d9f88fdf7b 100644
--- a/Documentation/core-api/swiotlb.rst
+++ b/Documentation/core-api/swiotlb.rst
@@ -148,10 +148,10 @@ may also be adjusted
 due to other conditions, such as running in a CoCo VM, as described above. If
 CONFIG_SWIOTLB_DYNAMIC is enabled, additional pools may be allocated later in
 the life of the system. Each pool must be a contiguous range of physical
-memory. The default pool is allocated below the 4 GiB physical address line so
-it works for devices that can only address 32-bits of physical memory (unless
-architecture-specific code provides the SWIOTLB_ANY flag). In a CoCo VM, the
-pool memory must be decrypted before swiotlb is used.
+memory. The default pool is allocated below the architecture's low address
+limit when it is needed for devices with limited DMA addressing. Otherwise,
+it may be allocated anywhere in directly mapped memory. In a CoCo VM, the pool
+memory must be decrypted before swiotlb is used.
 
 Each pool is divided into "slots" of size IO_TLB_SIZE, which is 2 KiB with
 current definitions. IO_TLB_SEGSIZE contiguous slots (128 slots) constitute
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 006ed41097e9..1bdea6c03848 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -295,9 +295,11 @@ void __init arch_mm_preinit(void)
 		/*
 		 * Since the guest memory is inaccessible to the host,
 		 * devices always need to use the SWIOTLB buffer for DMA
-		 * even if dma_capable() says otherwise.
+		 * even if dma_capable() says otherwise. The hypervisor has
+		 * no addressing limitation, so the buffer may be allocated
+		 * anywhere.
 		 */
-		ppc_swiotlb_flags |= SWIOTLB_ANY;
+		ppc_swiotlb_flags &= ~SWIOTLB_INIT_ADDRESSING_LIMIT;
 	}
 
 	/*
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 96856114b387..734712230f35 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -165,27 +165,11 @@ static void print_vm_layout(void) { }
 
 void __init arch_mm_preinit(void)
 {
-	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit) &&
-		       memblock_start_of_DRAM() < dma32_phys_limit;
 	unsigned int swiotlb_flags = SWIOTLB_VERBOSE;
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
-	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
-	    dma_cache_alignment != 1) {
-		/*
-		 * No 32-bit DMA bouncing needed (either all DRAM is within
-		 * the 32-bit limit, or it all starts above it), but
-		 * kmalloc() buffers whose sizes are not cache-line-aligned
-		 * still require bouncing for non-coherent DMA.  Use
-		 * SWIOTLB_ANY so that the buffer can be allocated from high
-		 * memory when DRAM starts above dma32_phys_limit.  Allocate
-		 * ~1 MB per 1 GB of RAM.
-		 */
-		swiotlb_flags |= SWIOTLB_ANY;
-	}
-
 	if ((max_pfn > PFN_DOWN(dma32_phys_limit)) &&
 	     (memblock_start_of_DRAM() < dma32_phys_limit))
 		swiotlb_flags |= SWIOTLB_INIT_ADDRESSING_LIMIT;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 78f507e24ceb..ce10292447f1 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -166,7 +166,7 @@ static void __init pv_init(void)
 	virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
 
 	/* make sure bounce buffers are shared */
-	swiotlb_init(SWIOTLB_VERBOSE | SWIOTLB_ANY);
+	swiotlb_init(SWIOTLB_VERBOSE);
 	swiotlb_update_mem_attributes();
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index ce257b20ea9c..74e92b457758 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -90,7 +90,7 @@ static void __init pci_xen_swiotlb_init(void)
 	/* Xen can use a SWIOTLB pool anywhere in directly mapped memory. */
 	x86_swiotlb_flags &= ~(SWIOTLB_INIT_ADDRESSING_LIMIT |
 			       SWIOTLB_INIT_DEFAULT_OFF);
-	x86_swiotlb_flags |= SWIOTLB_INIT_REMAP | SWIOTLB_ANY;
+	x86_swiotlb_flags |= SWIOTLB_INIT_REMAP;
 	swiotlb_init_remap(x86_swiotlb_flags, xen_swiotlb_fixup);
 	dma_ops = &xen_swiotlb_dma_ops;
 	if (IS_ENABLED(CONFIG_PCI))
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index f5ce45f2994b..3c3f9d93d400 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -15,13 +15,12 @@ struct page;
 struct scatterlist;
 
 #define SWIOTLB_VERBOSE	(1 << 0) /* verbose initialization */
-#define SWIOTLB_ANY	(1 << 1) /* allow any memory for the buffer */
 /* Initialize a default-sized pool for devices with limited DMA addressing. */
-#define SWIOTLB_INIT_ADDRESSING_LIMIT	(1 << 2)
+#define SWIOTLB_INIT_ADDRESSING_LIMIT	(1 << 1)
 /* Initialize a default-sized pool that requires architecture remapping. */
-#define SWIOTLB_INIT_REMAP		(1 << 3)
+#define SWIOTLB_INIT_REMAP		(1 << 2)
 /* Do not initialize a pool unless SWIOTLB is explicitly required. */
-#define SWIOTLB_INIT_DEFAULT_OFF		(1 << 4)
+#define SWIOTLB_INIT_DEFAULT_OFF	(1 << 3)
 
 /*
  * Maximum allowable number of contiguous slabs to map,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 130a13eb85b0..4d13421c3901 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -437,15 +437,10 @@ static void __init *swiotlb_memblock_alloc(unsigned long nslabs,
 	size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT);
 	void *tlb;
 
-	/*
-	 * By default allocate the bounce buffer memory from low memory, but
-	 * allow to pick a location everywhere for hypervisors with guest
-	 * memory encryption.
-	 */
-	if (flags & SWIOTLB_ANY)
-		tlb = memblock_alloc(bytes, PAGE_SIZE);
-	else
+	if (flags & SWIOTLB_INIT_ADDRESSING_LIMIT)
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+	else
+		tlb = memblock_alloc(bytes, PAGE_SIZE);
 
 	if (!tlb) {
 		pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
@@ -567,10 +562,10 @@ void __init swiotlb_init_remap(unsigned int flags,
 #ifdef CONFIG_SWIOTLB_DYNAMIC
 	if (!remap)
 		io_tlb_default_mem.can_grow = true;
-	if (flags & SWIOTLB_ANY)
-		io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
-	else
+	if (flags & SWIOTLB_INIT_ADDRESSING_LIMIT)
 		io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT;
+	else
+		io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
 #endif
 
 	/* if we have host or guest memory encryption */
-- 
2.43.0