From 188fa82305e72b725473db9146e20cc9abf7bff3 Mon Sep 17 00:00:00 2001 From: Andrew Cooper Date: Fri, 15 Mar 2024 11:31:33 +0000 Subject: [PATCH] xen/vpci: Improve code generation in mask_write() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The use of __clear_bit() forces dmask to be spilled to the stack, and interferes with the compiler heuristcs for some upcoming improvements to the ffs() code generation. First, shrink dmask to just the active vectors by making out the upper bits. This replaces the "i < msi->vectors" part of the loop condition. Next, use a simple while() loop with "clear bottom bit" expressed in plane C, which affords the optimiser a far better understanding of what the loop is doing. Signed-off-by: Andrew Cooper Reviewed-by: Roger Pau Monné --- xen/drivers/vpci/msi.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/xen/drivers/vpci/msi.c b/xen/drivers/vpci/msi.c index d3aa5df089..30adcf7df0 100644 --- a/xen/drivers/vpci/msi.c +++ b/xen/drivers/vpci/msi.c @@ -169,13 +169,15 @@ static void cf_check mask_write( if ( msi->enabled ) { - unsigned int i; + /* Skip changes to vectors which aren't enabled. */ + dmask &= (~0U >> (32 - msi->vectors)); - for ( i = ffs(dmask) - 1; dmask && i < msi->vectors; - i = ffs(dmask) - 1 ) + while ( dmask ) { + unsigned int i = ffs(dmask) - 1; + vpci_msi_arch_mask(msi, pdev, i, (val >> i) & 1); - __clear_bit(i, &dmask); + dmask &= (dmask - 1); } }